JP7724456B2 - Control device, display device control method and program - Google Patents

Description

This disclosure relates to a control device, a control method for a display device, and a program.

Patent Document 1 discloses a shape inspection device that projects a slit light onto a weld bead, captures images of shape lines sequentially formed on the weld bead by scanning the slit light, and acquires the three-dimensional shape of the weld bead as point cloud data based on the image data of each sequentially formed shape line. This shape inspection device sets an arbitrary cutting line, different from the shape line formed by scanning the slit light, on the weld bead displayed based on the point cloud data in response to input, and calculates the cross-sectional shape of the weld bead at the cutting line using the point cloud data corresponding to the cutting line. The shape inspection device also compares various feature values calculated in accordance with the calculated cross-sectional shape with pre-registered tolerance ranges for various feature values to determine whether the feature values are acceptable.

JP 2012-37487 A

This disclosure provides a control device, a control method for a display device, and a program that can visualize the visual inspection of weld beads and the validity of repair welding.

The present disclosure provides a control device that includes a processor that acquires visual inspection information of a weld bead before repair welding, repair welding information of the weld bead, and visual inspection information of the weld bead after repair welding, and displays the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding on a display device by superimposing the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding on the visual inspection information of the weld bead before repair welding, and each of the visual inspection information of the weld bead before repair welding, the repair welding information, and the visual inspection information of the weld bead after repair welding is displayed on the display device not as text information but in an aligned position .

The present disclosure also provides a control method for a display device executed by a control device, the control method comprising the steps of: acquiring visual inspection information of a weld bead before repair welding; acquiring repair welding information of the weld bead; acquiring visual inspection information of the weld bead after repair welding; and displaying the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding on the display device, superimposing the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding on the visual inspection information of the weld bead before repair welding; wherein the visual inspection information of the weld bead before repair welding, the repair welding information, and the visual inspection information of the weld bead after repair welding are each displayed on the display device not as text information, but in an aligned position .

The present disclosure also provides a program that causes a control device, which is a computer, to execute the steps of acquiring visual inspection information of a weld bead before repair welding, acquiring repair welding information of the weld bead, acquiring visual inspection information of the weld bead after repair welding, and displaying the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding superimposed on the visual inspection information of the weld bead before repair welding on a display device, wherein each of the visual inspection information of the weld bead before repair welding, the repair welding information, and the visual inspection information of the weld bead after repair welding is displayed on the display device not as text information but in an aligned position .

This disclosure makes it possible to visualize the visual inspection of weld beads and the validity of repair welding.

Schematic diagram showing an example of the system configuration of a welding system FIG. 1 is a diagram showing an example of the internal configuration of an inspection control device, a robot control device, and a higher-level device according to a first embodiment. FIG. 1 is a sequence diagram illustrating an example of a series of processing steps including main welding, bead appearance inspection, and repair welding by the welding system according to the first embodiment. 1 is a flowchart showing an example of a processing procedure illustrating details of the first inspection judgment (point cloud comparison) and the second to Nth inspection judgments (AI judgments). A table showing examples of appropriateness of first inspection judgments and second inspection judgments for each of a plurality of inspection items. FIG. 10 is a diagram showing an example of the internal configuration of an inspection control device, a robot control device, and a higher-level device according to a second embodiment. FIG. 10 is a sequence diagram showing an example of a series of processing procedures including main welding, bead appearance inspection, and repair welding by the welding system according to the second embodiment. Display example of weld bead appearance inspection information before repair welding displayed on monitor DISP Display example of repair welding information displayed on monitor DISP Display example of visual inspection information of weld bead after repair welding displayed on monitor DISP 10 is a display example in which the visual inspection information of the weld bead before repair welding, the repair welding information, and the visual inspection information of the weld bead after repair welding are superimposed on the monitor DISP. Display example of weld bead appearance inspection information before repair welding and weld bead appearance inspection information after repair welding displayed side by side on the monitor DISP. Illustrative examples of graphs showing changes in welding parameters over time that can be additionally displayed on the monitor DISP. Example of a waveform graph showing command values and measured values superimposed on each other

(Background to this disclosure)
As in Patent Document 1, there have been known apparatus configurations that automatically inspect the external shape of weld beads, such as determining that a workpiece produced by main welding is non-defective when calculated values of feature quantities (e.g., bead width, bead height, etc.) related to the shape of the weld bead are within an allowable range. However, at actual welding sites, workers often visually inspect the external shape of the weld bead to determine whether the main welding of the workpiece was successful.

In visual inspection of weld beads, in addition to the above-mentioned feature quantities related to the shape of the weld bead, a wide range of inspection items can be inspected, such as misalignment of the weld bead, the presence or absence of holes, and the presence or absence of welding defects such as spatter. Furthermore, users often have different criteria for determining whether a product is good or bad. For this reason, in visual inspection of weld beads, not only do the inspection items differ from user to user, but the quality of the finished workpiece also differs from user to user. Given this, it is believed that there is room for improvement over conventional technology in that greater usability of visual inspection is required, along with the ability to customize the inspection items as desired.

The following embodiments describe examples of a bead appearance inspection device, bead appearance inspection method, program, and bead appearance inspection system that more efficiently perform bead appearance inspection of workpieces produced by actual welding.

In addition, when repair welding is automated, a method may be used in which visual inspection of the welded bead and repair welding based on the results of the visual inspection are repeatedly performed to achieve a weld appearance closer to that of a good product.

Here, the shape and position of defects detected during visual inspection, the welding conditions and weld line trajectory during repair welding, and data on the appearance of the bead before and after repair welding are important for quality control of welded products. If this information could be saved and displayed for comparison as needed, it would be ideal, as it would allow for the visual inspection of the weld bead and the appropriateness of the repair welding to be visualized.

The following embodiments therefore describe examples of a control device, a control method for a display device, and a program that visualize the visual inspection of weld beads and the validity of repair welding.

Hereinafter, with reference to the drawings as appropriate, detailed descriptions will be given of specific embodiments of the bead appearance inspection device, bead appearance inspection method, program, and bead appearance inspection system according to the present disclosure. Then, detailed descriptions will be given of specific embodiments of the control device, display device control method, and program according to the present disclosure. However, more detailed descriptions than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art. Note that the accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter recited in the claims.

(Embodiment 1)
The bead visual inspection device according to the first embodiment receives input data relating to the weld bead of a workpiece produced by actual welding, and performs a first inspection and judgment on the shape of the weld bead based on a comparison of the input data with master data of a non-defective workpiece. The bead visual inspection device is equipped with k (k: an integer greater than or equal to 1) types of artificial intelligence and performs a second inspection and judgment on welding defects of the weld bead based on processing of the k types of artificial intelligence on the input data. Examples of welding defects in the weld bead include holes, pits, undercuts, spatter, and protrusions. Note that welding defects are not limited to those described above. The bead visual inspection device outputs the results of the weld bead visual inspection to an output device based on the results of the first visual inspection and each of the k second inspection and judgments.

Hereinafter, the object to be welded (e.g., metal) will be defined as the "original workpiece," the object produced (manufactured) by this welding will be defined as the "workpiece," and the object in which a defective weld detected during a visual inspection of the "workpiece" has been repair-welded will be defined as the "repair workpiece."

The process of producing a workpiece by joining an original workpiece with another original workpiece using a welding robot is defined as "main welding," while the process of repairing or correcting defective parts of the workpiece using a welding robot is defined as "repair welding."

Note that "work" or "repair work" is not limited to work produced by a single main welding operation, but may also refer to a composite work produced by two or more main welding operations.

(Welding system configuration)
FIG. 1 is a schematic diagram illustrating an example system configuration of a welding system 100. The welding system 100 includes a host device 1 connected to an external storage device ST, an input interface UI1, and a monitor MN1, a robot control device 2, an inspection control device 3, a sensor 4, a main welding robot MC1a, and a repair welding robot MC1b. The main welding robot MC1a and the repair welding robot MC1b may be configured as separate robots or may be configured as the same welding robot MC1. For ease of understanding, the following description will be given assuming that the main welding and repair welding processes are performed by the welding robot MC1. Note that FIG. 1 illustrates only one pair of a robot control device 2 and a main welding robot MC1a and a repair welding robot MC1b, but multiple pairs may be provided. While FIG. 1 illustrates the sensor 4 as separate from the welding robot MC1, it may also be integrated with the welding robot MC1 (see FIG. 2).

The host device 1 controls the start and completion of the main welding performed by the welding robot MC1 via the robot control device 2. For example, the host device 1 reads welding-related information previously input or set by a user (e.g., a welding operator or a system administrator; the same applies below) from the external storage ST, and uses the welding-related information to generate a main welding execution command including the contents of the welding-related information and sends it to the corresponding robot control device 2. When the main welding by the welding robot MC1 is completed, the host device 1 receives a main welding completion report from the robot control device 2 indicating that the main welding by the welding robot MC1 has been completed, updates the status to indicate that the corresponding main welding has been completed, and records it in the external storage ST. Note that the main welding execution command described above does not necessarily have to be generated by the host device 1, but may also be generated, for example, by the operation panel of the equipment in the factory where the main welding is performed (e.g., a programmable logic controller (PLC)) or the operation panel of the robot control device 2 (e.g., a teach pendant (TP)). The teach pendant (TP) is a device for operating the welding robot MC1 connected to the robot control device 2.

The host device 1 also controls the initiation and completion of bead visual inspection using the robot control device 2, inspection control device 3, and sensor 4. For example, when the host device 1 receives a report of the completion of main welding from the robot control device 2, it generates an instruction to execute a bead visual inspection of the workpiece produced by the welding robot MC1 and sends it to each of the robot control device 2 and the inspection control device 3. When the bead visual inspection is completed, the host device 1 receives an appearance inspection report from the inspection control device 3 indicating that the bead visual inspection has been completed, updates the status to indicate that the corresponding bead visual inspection has been completed, and records this in the external storage ST.

The host device 1 also controls the start and completion of repair welding performed by the welding robot MC1 via the robot control device 2. For example, when the host device 1 receives an appearance inspection report from the inspection control device 3, it generates an execution command for repair welding of the workpiece produced by the welding robot MC1 and sends it to the robot control device 2. When repair welding is completed, the host device 1 receives a repair welding completion report from the robot control device 2 indicating that the repair welding has been completed, updates the status to indicate that the corresponding repair welding has been completed, and records this in the external storage ST.

Here, welding-related information refers to information indicating the details of the main welding performed by the welding robot MC1. It is created in advance for each main welding process and registered in the external storage ST. The welding-related information includes, for example, the number of original workpieces used in the main welding; workpiece information including the ID, name, and welding location of the original workpieces used in the main welding; the planned execution date of the main welding; the number of workpieces to be welded; and various welding conditions for the main welding. Note that the welding-related information need not be limited to the data items described above. Based on a main welding execution command sent from the host device 1, the robot control device 2 causes the welding robot MC1 to begin main welding using the original workpieces specified in the execution command. Note that the above-mentioned welding-related information does not necessarily have to be managed by the host device 1 with reference to the external storage ST; it may also be managed, for example, by the robot control device 2. In this case, since the robot control device 2 can grasp the state when the main welding is completed, the actual execution date of the welding process may be managed instead of the planned execution date of the welding-related information. Note that the type of welding is not important in this specification, but for ease of understanding, the following explanation will be given using as an example the process of joining multiple original workpieces to produce a single workpiece.

The host device 1 is connected to the monitor MN1, input interface UI1, and external storage ST so as to enable data input and output, and is further connected to the robot control device 2 so as to enable data communication. The host device 1 may be a terminal device P1 that integrates the monitor MN1 and input interface UI1, or may also integrate the external storage ST. In this case, the terminal device P1 is a PC (Personal Computer) used by the user prior to performing the actual welding. Note that the terminal device P1 is not limited to the PC described above, and may be a computer device with communication capabilities, such as a smartphone or tablet terminal.

The monitor MN1 may be configured using a display device such as an LCD (Liquid Crystal Display) or organic EL (Electroluminescence). The monitor MN1 may display a screen showing, for example, a notification output from the higher-level device 1 that the main welding has been completed, that the bead visual inspection has been completed, or that the repair welding has been completed. Alternatively, a speaker (not shown) may be connected to the higher-level device 1 in place of or together with the monitor MN1, and the higher-level device 1 may output a voice message via the speaker announcing that the main welding has been completed, that the bead visual inspection has been completed, or that the repair welding has been completed.

The input interface UI1 is a user interface that detects user input operations and outputs them to the higher-level device 1, and may be configured using, for example, a mouse, keyboard, or touch panel. The input interface UI1 accepts input operations, for example, when the user creates welding-related information, or when sending a command to execute the actual welding to the robot control device 2.

The external storage ST is configured using, for example, a hard disk drive or solid state drive. The external storage ST stores, for example, welding-related information data created for each actual welding, the status (production status) of the work produced by actual welding or repair work repaired by repair welding, and work information for the work or repair work (see above).

A robot control device 2, as an example of a bead appearance inspection device, is connected to a host device 1 so that data can be exchanged, and is also connected to a welding robot MC1 so that data can be exchanged. When the robot control device 2 receives a command to execute main welding from the host device 1, it controls the corresponding welding robot MC1 to execute the main welding based on the command. When the robot control device 2 detects the completion of main welding, it generates a main welding completion report indicating that main welding has been completed and notifies the host device 1. This allows the host device 1 to properly detect the completion of main welding by the robot control device 2. Note that the method for detecting the completion of main welding by the robot control device 2 may be, for example, a method based on a signal indicating the completion of main welding from a sensor (not shown) provided in the wire feeder 300, or a known method, and the method for detecting the completion of main welding need not be limited.

Furthermore, when the robot control device 2 receives a command to perform a bead visual inspection sent from the host device 1, it controls the welding robot MC1 (see Figure 2) equipped with a sensor 4 in accordance with a visual inspection program created or prepared in advance by the robot control device 2, and performs a bead visual inspection of the corresponding workpiece based on the execution command. An visual inspection report indicating that the bead visual inspection has been completed is sent from the inspection control device 3 to the host device 1, but it may also be sent to the host device 1 by the robot control device 2 itself, or by the robot control device 2 upon receiving an instruction from the inspection control device 3. This allows the host device 1 to properly detect the completion of the bead visual inspection.

Furthermore, when the robot control device 2 receives a repair welding execution command sent from the higher-level device 1, it controls the corresponding welding robot MC1 to perform repair welding based on the execution command in accordance with the repair welding program created by the inspection control device 3. When the robot control device 2 detects the completion of repair welding, it generates a repair welding completion report indicating that repair welding has been completed and notifies the higher-level device 1. This allows the higher-level device 1 to properly detect the completion of repair welding based on the robot control device 2. Note that the method for detecting the completion of repair welding by the robot control device 2 may be, for example, a method of determining the completion of repair welding based on a signal indicating the completion of repair welding from a sensor (not shown) provided in the wire feeder 300, or a known method, and the details of the method for detecting the completion of repair welding need not be limited.

Welding robot MC1 is connected to robot control device 2 so that data can be communicated with it. Welding robot MC1 performs main welding or repair welding as instructed by host device 1 under the control of the corresponding robot control device 2. As mentioned above, welding robot MC1 may be composed of main welding robot MC1a provided for main welding and repair welding robot MC1b provided for repair welding. Furthermore, if sensor 4 is integrally attached to welding robot MC1, welding robot MC1 assists in the execution of bead appearance inspection as instructed by host device 1 by moving sensor 4 along the movement trajectory of welding robot MC1 during main welding or repair welding in accordance with the appearance inspection program.

The inspection control device 3, an example of a bead visual inspection device, is connected to the host device 1, the robot control device 2, and the sensor 4 so that data can be exchanged. When the inspection control device 3 receives a command to perform a bead visual inspection from the host device 1, it, together with the sensor 4, performs a bead visual inspection of the welded portion of the workpiece produced by the welding robot MC1 (e.g., inspecting whether the weld bead formed on the workpiece meets pre-defined welding standards). Details of the bead visual inspection will be described later with reference to Figures 4 and 5. For example, the inspection control device 3 performs a bead visual inspection based on the workpiece welded portion information included in the command to perform the bead visual inspection, using input data regarding the shape of the weld bead acquired by the sensor 4 (e.g., point cloud data capable of identifying the three-dimensional shape of the weld bead), and comparing the data with pre-defined master data for a non-defective workpiece for each workpiece. Hereinafter, this type of bead visual inspection is defined as the "first inspection judgment." The inspection control device 3 is also equipped with k (k: integer greater than or equal to 1) types of artificial intelligence (AI), which each form a neural network using the AI and perform a bead visual inspection to determine whether or not there are any welding defects based on the AI targeting the input data described above. Hereinafter, this type of bead visual inspection is defined as a "second inspection judgment." In embodiment 1, the inspection control device 3 is capable of performing the first and second inspection judgments described above. The inspection control device 3 performs an overall judgment of the bead visual inspection using the results of the first and second inspection judgments, and generates an appearance inspection report including this overall judgment result and a notification that the bead visual inspection has been completed. The inspection control device 3 sends this report to the higher-level device 1 and outputs it to the monitor MN2.

Furthermore, if the inspection control device 3 determines that a poor weld has been detected by the second inspection judgment during the work bead visual inspection, it uses the visual inspection results, including the position information of the poor weld location (so-called detection point), to create a repair welding program to repair or correct the poor weld location. The inspection control device 3 associates this repair welding program with the visual inspection results and sends them to the robot control device 2.

Sensor 4 is connected to inspection control device 3 so that data can be communicated between them. When sensor 4 is attached to welding robot MC1 (see Figure 2), sensor 4 is operable to perform three-dimensional scanning of the mounting table on which workpiece Wk is placed, in response to the driving of manipulator 200 under the control of robot control device 2. Sensor 4 acquires data (e.g., point cloud data OD1, described below) that can identify the three-dimensional shape of the workpiece placed on the mounting table (see Figure 2) in response to the driving of manipulator 200 under the control of robot control device 2, and sends this data to inspection control device 3.

Monitor MN2, an example of an output device, may be configured using a display device such as an LCD or organic EL. Monitor MN2 displays, for example, a notification output from inspection control device 3 that the bead visual inspection has been completed, or a screen showing that notification and the results of the bead visual inspection (for example, the results of the overall judgment described above). Alternatively, a speaker (not shown) may be connected to inspection control device 3 in place of monitor MN2, or in addition to monitor MN2, and inspection control device 3 may output a sound via the speaker that shows the notification that the bead visual inspection has been completed, or the notification and the results of the bead visual inspection (for example, the results of the overall judgment described above).

Figure 2 is a diagram showing an example of the internal configuration of the inspection control device 3, robot control device 2, and upper device 1 according to embodiment 1. To make the explanation easier to understand, the monitors MN1 and MN2 and input interface UI1 are not shown in Figure 2. Note that the workpiece Wk shown in Figure 2 may be the original workpiece placed before actual welding, the workpiece to be inspected for bead appearance (i.e., the workpiece produced by actual welding), or the workpiece to be repair welded.

Under the control of the robot control device 2, the welding robot MC1 executes various processes, such as main welding as instructed by the higher-level device 1, moving the sensor 4 during bead visual inspection, and repair welding. The welding robot MC1 performs, for example, arc welding during the main welding or repair welding process. However, the welding robot MC1 may also perform welding methods other than arc welding (e.g., laser welding, gas welding). In this case, although not shown, a laser head may be connected to the laser oscillator via an optical fiber instead of the welding torch 400. The welding robot MC1 is configured to include at least the manipulator 200, the wire feeder 300, the welding wire 301, and the welding torch 400.

The manipulator 200 has articulated arms, and moves each arm based on control signals from the robot control unit 25 of the robot control device 2. This allows the manipulator 200 to change the positional relationship between the workpiece Wk and the welding torch 400 (for example, the angle of the welding torch 400 relative to the workpiece Wk) by driving the arms.

The wire feeder 300 controls the feed speed of the welding wire 301 based on a control signal from the robot control device 2. The wire feeder 300 may be equipped with a sensor (not shown) that can detect the remaining amount of welding wire 301. Based on the output of this sensor, the robot control device 2 can detect that the main welding or repair welding process has been completed.

The welding wire 301 is held by the welding torch 400. When power is supplied to the welding torch 400 from the power supply unit 500, an arc is generated between the tip of the welding wire 301 and the workpiece Wk, and arc welding is performed. For the sake of convenience, illustrations and descriptions of the configuration for supplying shielding gas to the welding torch 400 are omitted.

Using welding-related information previously input or set by the user, the host device 1 generates execution commands for various processes, such as main welding, bead visual inspection, and repair welding, and sends these to the robot control device 2. As mentioned above, if the sensor 4 is integrally attached to the welding robot MC1, the execution command for bead visual inspection is sent to both the robot control device 2 and the inspection control device 3. The host device 1 is configured to include at least a communication unit 10, a processor 11, and a memory 12.

The communication unit 10 is connected to the robot control device 2 and the external storage ST so that data can be exchanged between them. The communication unit 10 sends execution commands for various processes, such as main welding, bead visual inspection, or repair welding, generated by the processor 11 to the robot control device 2. The communication unit 10 receives main welding completion reports, visual inspection reports, and repair welding completion reports sent from the robot control device 2 and outputs them to the processor 11. Note that the execution command for main welding or repair welding may include, for example, control signals for controlling the manipulator 200, wire feeder 300, and power supply 500 provided on the welding robot MC1.

Processor 11 is configured using, for example, a CPU (Central Processing Unit) or FPGA (Field Programmable Gate Array) and works in conjunction with memory 12 to perform various processes and controls. Specifically, processor 11 references and executes programs stored in memory 12 to functionally realize cell control unit 13.

Memory 12 includes, for example, RAM (Random Access Memory) as work memory used when executing the processing of processor 11, and ROM (Read Only Memory) that stores programs that define the processing of processor 11. Data generated or acquired by processor 11 is temporarily stored in RAM. Programs that define the processing of processor 11 are written in ROM. Memory 12 also stores welding-related information data read from external storage ST, the status of work or repair work, and work information (see above) for work or repair work sent from robot control device 2.

Based on the welding-related information stored in external storage ST, the cell control unit 13 generates execution commands for performing main welding, workpiece bead visual inspection, or repair welding. Based on the welding-related information stored in external storage ST, the cell control unit 13 also generates an appearance inspection program for driving the welding robot MC1 during bead visual inspection of the workpiece Wk (e.g., workpiece) after main welding, as well as an execution command for the appearance inspection program including this appearance inspection program. This appearance inspection program may be created in advance and stored in external storage ST. In this case, the cell control unit 13 simply reads and acquires the appearance inspection program from external storage ST. The cell control unit 13 may generate different execution commands for each process of main welding or repair welding performed by the welding robot MC1. The execution command for main welding or repair welding, or the execution command for the appearance inspection program including the appearance inspection program, generated by the cell control unit 13, is sent via the communication unit 10 to the corresponding robot control device 2, or to the robot control device 2 and the inspection control device 3, respectively.

The robot control device 2 controls the processing of the corresponding welding robot MC1 (e.g., sensor 4, manipulator 200, wire feeder 300, power supply 500) based on execution commands for main welding, bead visual inspection, or repair welding sent from the host device 1. The robot control device 2 is configured to include at least a communication unit 20, a processor 21, and a memory 22.

The communication unit 20 is connected to enable data communication between the host device 1, the inspection control device 3, and the welding robot MC1. Although the illustration is simplified in Figure 2, data is sent and received between the robot control unit 25 and the manipulator 200, between the robot control unit 25 and the wire feeder 300, and between the power supply control unit 26 and the power supply 500 via the communication unit 20. The communication unit 20 receives commands to perform main welding, bead visual inspection, or repair welding sent from the host device 1. The communication unit 20 sends work information for work produced by main welding or repair work produced by correction through repair welding to the host device 1.

Here, the workpiece information includes not only the ID of the workpiece or repair workpiece, but also at least the ID, name, welding location, welding conditions during main welding, and welding conditions during repair welding of the original workpiece used for main welding. Furthermore, the workpiece information may also include information indicating the location of detection points (e.g., coordinates) that indicate defective areas on the workpiece. Welding conditions or repair welding conditions include, for example, the material and thickness of the original workpiece, the material and wire diameter of the welding wire 301, the type of shielding gas, the flow rate of the shielding gas, the set average welding current, the set average welding voltage, the feed speed and feed amount of the welding wire 301, the number of welds, and the welding time. In addition to these, information indicating the type of main welding or repair welding (e.g., TIG welding, MAG welding, pulse welding), and the movement speed and movement time of the manipulator 200 may also be included.

The processor 21 is configured using, for example, a CPU or FPGA, and performs various processes and controls in cooperation with the memory 22. Specifically, the processor 21 references the programs stored in the memory 22 and executes them to functionally realize the welding program creation unit 23, the calculation unit 24, the robot control unit 25, and the power supply control unit 26.

Memory 22 includes, for example, RAM as work memory used when executing the processing of processor 21, and ROM for storing programs that define the processing of processor 21. Data generated or acquired by processor 21 is temporarily stored in RAM. The ROM has programs that define the processing of processor 21 written in it. Memory 22 also stores execution command data for main welding, bead appearance inspection, or repair welding sent from host device 1, and work information data for workpieces produced by main welding or repair workpieces produced by repair welding. Memory 22 also stores a main welding program for main welding executed by welding robot MC1. The main welding program is a program that defines the specific procedures (steps) for main welding, such as joining multiple original workpieces using the welding conditions for main welding.

Based on the execution command for main welding sent from the higher-level device 1 via the communication unit 20, the main welding program creation unit 23 uses the workpiece information (e.g., ID, name, and welding location of the main workpiece) for each of the multiple main workpieces included in the execution command to generate a main welding program for main welding to be performed by the welding robot MC1. The main welding program may include various parameters, such as welding current, welding voltage, offset amount, welding speed, and attitude of the welding torch 400, for controlling the power supply unit 500, manipulator 200, wire feeder 300, welding torch 400, etc., during main welding. The main welding program may be stored in the processor 21 or in RAM in the memory 22.

Calculation unit 24 performs various calculations. For example, calculation unit 24 calculates parameters for controlling welding robot MC1 (specifically, manipulator 200, wire feeder 300, and power supply 500) controlled by robot control unit 25 based on the actual welding program generated by actual welding program creation unit 23.

Based on the welding program generated by the welding program creation unit 23, the robot control unit 25 generates control signals for driving the welding robot MC1 (specifically, the manipulator 200, the wire feeder 300, and the power supply unit 500). The robot control unit 25 sends these generated control signals to the welding robot MC1. Based on the appearance inspection program sent from the higher-level device 1, the robot control unit 25 also drives the manipulator 200 of the welding robot MC1 during bead appearance inspection so as to cover the operating range of the welding robot MC1 defined in the welding program. This allows the sensor 4 (see Figure 2) attached to the welding robot MC1 to move in conjunction with the operation of the welding robot MC1 and acquire input data related to the shape of the weld bead on the workpiece Wk (e.g., point cloud data capable of identifying the three-dimensional shape of the weld bead).

The power supply control unit 26 drives the power supply device 500 based on the actual welding program generated by the actual welding program creation unit 23 and the calculation results of the calculation unit 24.

Based on a visual inspection execution command sent from the host device 1, the inspection control device 3 controls the bead visual inspection process for the workpiece or repair workpiece produced by main welding using the welding robot MC1. Bead visual inspection is, for example, an inspection to determine whether the weld bead formed on the workpiece or repair workpiece meets predetermined welding standards (e.g., quality standards), and is composed of the first and second inspection judgments described above. To simplify the following explanation, the inspection control device 3 determines whether the weld bead formed on the workpiece Wk (e.g., the workpiece or repair workpiece) meets the predetermined welding standards by making a comprehensive judgment based on the results of the first and second inspection judgments described above, based on input data regarding the shape of the weld bead acquired by the sensor 4 (e.g., point cloud data capable of identifying the three-dimensional shape of the weld bead). The inspection control device 3 is configured to include at least a communication unit 30, a processor 31, a memory 32, and an inspection result storage unit 33.

The communication unit 30 is connected to enable data communication between the host device 1, robot control device 2, and sensor 4. Although the illustration is simplified in Figure 2, data is sent and received between the shape detection control unit 35 and sensor 4 via the communication unit 30. The communication unit 30 receives a command to perform a bead appearance inspection sent from the host device 1. The communication unit 30 sends the overall judgment results of the bead appearance inspection using the sensor 4 (for example, bead chipping, bead position deviation, presence or absence of welding defects in the work or repair work, and the type and location of the welding defects) to the host device 1.

The processor 31 is configured using, for example, a CPU or FPGA, and works in conjunction with the memory 32 to perform various processes and controls. Specifically, the processor 31 references the programs stored in the memory 32 and executes them to functionally realize the judgment threshold memory unit 34, shape detection control unit 35, data processing unit 36, inspection result judgment unit 37, and repair welding program creation unit 38.

The memory 32 includes, for example, RAM as a work memory used when executing the processing of the processor 31, and ROM for storing programs that define the processing of the processor 31. The RAM temporarily stores data generated or acquired by the processor 31. The ROM contains programs that define the processing of the processor 31. The memory 32 also stores data on execution commands for workpiece bead visual inspections sent from the host device 1, and workpiece information data for workpieces produced by actual welding or repair workpieces produced by repair welding. The memory 32 also stores data on repair welding programs created by the repair welding program creation unit 38. The repair welding program defines specific procedures (steps) for repair welding to correct missing weld beads, bead misalignment, or poorly welded areas using the welding conditions for repair welding and positional information for the corresponding point (corresponding point) on the motion trajectory of the welding robot MC1 that is closest to the detection point (see above). This program is created by the repair welding program creation unit 38 and sent from the inspection control unit 3 to the robot control unit 2.

The inspection result storage unit 33 is configured using, for example, a hard disk or solid state drive. The inspection result storage unit 33 stores data indicating the results of a bead appearance inspection of a welded portion of a workpiece Wk (e.g., a workpiece or repair work), as an example of data generated or acquired by the processor 31. This data indicating the results of the bead appearance inspection is generated, for example, by the inspection result determination unit 37.

The judgment threshold memory unit 34 is configured, for example, by a cache memory provided within the processor 31. It stores thresholds (e.g., thresholds set for each type of welding defect) used in the bead visual inspection process by the inspection result judgment unit 37 according to the welding location. The thresholds include, for example, the tolerance range for weld bead misalignment, the thresholds for the length, height, and width of the weld bead, and the thresholds for holes, pits, undercuts, spatter, and protrusions. The judgment threshold memory unit 34 may store tolerance ranges (e.g., minimum and maximum tolerance values) that meet the minimum welding standards (quality) required by customers, etc., as thresholds for the bead visual inspection after repair welding. Furthermore, the judgment threshold memory unit 34 may store an upper limit on the number of bead visual inspections for each welding location. As a result, if the number of attempts to repair a defective location by repair welding exceeds a predetermined upper limit, the inspection control device 3 determines that it is difficult or impossible for the welding robot MC1 to repair the defective location by automatic repair welding, thereby preventing a decrease in the operating rate of the welding system 100.

Based on a command to perform a bead appearance inspection of a welded portion of a workpiece Wk (e.g., a workpiece) sent from the host device 1, the shape detection control unit 35 acquires input data related to the shape of the weld bead sent from the sensor 4 (e.g., point cloud data that can identify the three-dimensional shape of the weld bead) while the robot control unit 2 operates the welding robot MC1, to which the sensor 4 is attached, based on the appearance inspection program during the bead appearance inspection. When the robot control unit 2 drives the manipulator 200 as described above, the shape detection control unit 35 causes the sensor 4 to emit a laser beam, for example, to acquire input data related to the shape of the weld bead (e.g., point cloud data that can identify the three-dimensional shape of the weld bead). Upon receiving the input data acquired by the sensor 4 (see above), the shape detection control unit 35 passes the input data to the data processing unit 36.

When the data processing unit 36 receives input data (see above) regarding the shape of the weld bead from the shape detection control unit 35, it converts the data into a data format suitable for the first inspection judgment by the inspection result judgment unit 37, and also converts the data into a data format suitable for the second inspection judgment by the inspection result judgment unit 37. The data format conversion may include a correction process, as so-called preprocessing, to remove unnecessary point cloud data (e.g., noise) contained in the input data (i.e., point cloud data), or the preprocessing described above may be omitted for the first inspection judgment. The data processing unit 36 converts the data into a data format suitable for the first inspection judgment and generates image data showing the three-dimensional shape of the weld bead, for example, by performing statistical processing on the input shape data. Note that the data processing unit 36 may also perform edge enhancement correction on the data for the first inspection judgment, emphasizing the peripheral portions of the weld bead to highlight the position and shape of the weld bead. The data processing unit 36 may count the number of bead visual inspections performed for each defective weld location, and if the welding inspection results are not good even after the number of bead visual inspections exceeds the number pre-stored in memory 32, it may determine that it is difficult or impossible to correct the defective weld location through automatic repair welding. In this case, the inspection result determination unit 37 generates an alert screen including the location of the defective weld location and the type of defective weld (e.g., perforation, pit, undercut, spatter, protrusion), and sends the generated alert screen to the higher-level device 1 via the communication unit 30. The alert screen sent to the higher-level device 1 is displayed on monitor MN1. This alert screen may also be displayed on monitor MN2.

For example, converting the data format to one suitable for the second inspection and judgment includes, as preprocessing, a planarization process to convert the shape of the input data (i.e., the point cloud data of the weld bead) into a predetermined shape (e.g., a linear shape) suitable for processing by the AI (i.e., the second inspection and judgment unit 372 to the Nth inspection and judgment unit 37N described below). As described above, weld bead shapes vary widely, including linear, curved, and the presence or absence of weaving. For this reason, the training process for the AI (e.g., a neural network) capable of detecting the type of welding defect (see above) for each shape is extremely complicated and unrealistic. Therefore, in embodiment 1, the AI (i.e., the second inspection and judgment unit 372 to the Nth inspection and judgment unit 37N described below) is capable of executing a trained model that has been previously trained to enable it to detect welding defects (see above) when the weld bead shape is, for example, linear. As a result, the AI (i.e., the second inspection and determination unit 372 to the Nth inspection and determination unit 37N, described below) can detect welding defects with high accuracy simply by inputting point cloud data in which the weld bead shape has been linearized through planarization processing by the data processing unit 36.

The inspection result determination unit 37 is capable of performing a total of N (N: integer greater than or equal to 2) types of bead appearance inspection (for example, each of the first and second inspection determinations described above). Specifically, the inspection result determination unit 37 has a first inspection determination unit 371, a second inspection determination unit 372, ..., an Nth inspection determination unit. To simplify the explanation of Figure 2, N = 2 will be used, but the same applies if N = 3 or an integer greater than or equal to 2.

The first inspection/determination unit 371 uses the thresholds stored in the determination threshold memory unit 34 to perform a first inspection/determination (i.e., a bead appearance inspection based on a comparison between input data regarding the shape of the weld bead acquired by the sensor 4 and master data of a good workpiece predefined for each workpiece) to inspect the shape reliability of the weld bead (e.g., whether it follows a straight or curved weld line), bead chipping, and bead misalignment (see Figure 5). Figure 5 is a table showing appropriate examples of the first inspection/determination and the second inspection/determination for each of multiple inspection items. The first inspection/determination unit 371 compares data converted by the data processing unit 36 for the first inspection/determination (e.g., image data generated based on point cloud data) with the master data of a good workpiece (so-called image processing). Therefore, as shown in Figure 5, the first inspection/determination unit 371 can inspect the shape reliability of the weld bead, bead chipping, and bead misalignment with high accuracy. The first inspection and judgment unit 371 calculates an inspection score that indicates the inspection results for the shape reliability of the weld bead, bead chipping, and bead position misalignment, and creates the calculated value of this inspection score as the first inspection and judgment result.

The second inspection/determination unit 372 to the Nth inspection/determination unit 37N perform second inspection/determination (i.e., each forms a neural network using k = (N-1) types of artificial intelligence and performs a bead appearance inspection to determine the presence or absence of welding defects based on AI, targeting input data regarding the shape of the weld bead acquired by the sensor 4, or the input data after that input data has been preprocessed by the data processing unit 36), and inspect the weld bead for holes, pits, undercuts, and spatters (see Figure 5). Holes, pits, undercuts, spatters, and protrusions in the weld bead are merely listed as examples, and the types of defects inspected by the Nth inspection/determination unit 37N are not limited to these. When each of the second inspection/determination units 372 to 37N determines that a corresponding type of welding defect has been detected, it identifies the position of the weld bead where the welding defect was detected. Each of the second inspection and determination units 372 through 37N determines the presence or absence of a welding defect using a learning model (AI) previously obtained through a learning process for each type of welding defect or for each group of welding defect types. This allows each of the second inspection and determination units 372 through 37N to accurately inspect the presence or absence of, for example, holes, pits, undercuts, spatter, and protrusions in the weld bead. Note that each of the second inspection and determination units 372 through 37N does not inspect the shape reliability of the weld bead, bead chipping, or bead misalignment that is performed by the first inspection and determination unit 371. Each of the second inspection and determination units 372 through 37N calculates the inspection results for holes, pits, undercuts, spatter, and protrusions in the weld bead (in other words, inspection scores indicating the probability of occurrence) and creates the calculated inspection score values as the second inspection and determination results.

As shown in FIG. 5 , the inspection result determination unit 37 performs a combination of the first and second inspection determinations, appropriately tailored to each type of welding defect, enabling comprehensive and highly accurate inspection of the shape reliability of the weld bead, bead chipping, bead misalignment, holes, pits, undercuts, spatter, and protrusions. While the above description illustrates an example where N = 2, when N = 3, the second inspection determination unit 372 can use AI to detect types of welding defects, such as holes and pits in the weld bead, and the Nth inspection determination unit 37N (N = 3) can use different AI to detect types of welding defects, such as undercuts, spatter, and protrusions in the weld bead. In other words, multiple AIs (learning models) may be prepared for the second inspection determination so that different AIs can be used to detect different combinations of welding defect types (e.g., combinations of holes and pits, undercuts, spatter, and protrusions) that are inspection items.

The inspection result determination unit 37 creates a visual inspection report including the first inspection determination result created by the first inspection determination unit 371 and the second inspection determination results created by each of the second inspection determination unit 372 through the Nth inspection determination unit 37N, stores this in memory 32, and sends it to the higher-level device 1 via the communication unit 30. The inspection result determination unit 37 may determine whether repair welding by the welding robot MC1 is possible (in other words, whether repair welding by the welding robot MC1 or manual repair welding is preferable) based on the inspection score included in the first inspection determination result or the second inspection determination result, and output this determination result together with the visual inspection report.

The repair welding program creation unit 38 uses the visual inspection report of the workpiece Wk (e.g., workpiece or repair workpiece) by the inspection result determination unit 37 and workpiece information (e.g., information such as coordinates indicating the location of detection points for welding defects on the workpiece or repair workpiece) to create a repair welding program for the workpiece Wk (e.g., workpiece or repair workpiece) to be performed by the welding robot MC1. The repair welding program may include various parameters, such as welding current, welding voltage, offset amount, welding speed, and welding torch 400 posture, for controlling the power supply unit 500, manipulator 200, wire feeder 300, welding torch 400, etc., during repair welding. The generated repair welding program may be stored in the processor 31 or in RAM in the memory 32.

Sensor 4 is, for example, a three-dimensional shape sensor attached to the tip of welding robot MC1. It acquires multiple point cloud data sets capable of identifying the shape of the welded area on workpiece Wk (e.g., workpiece). Based on these point cloud data sets, it generates point cloud data capable of identifying the three-dimensional shape of the welded area and sends the data to inspection control device 3. If sensor 4 is not attached to the tip of welding robot MC1 but is located separately from welding robot MC1, it may comprise a laser light source (not shown) configured to scan the welded area on workpiece Wk (e.g., workpiece or repair work) based on the position information of the welded area sent from inspection control device 3, and a camera (not shown) positioned to capture an imaging area including the periphery of the welded area and capture the trajectory of the reflected laser light (i.e., the shape line of the welded area). In this case, sensor 4 sends shape data of the welded area (in other words, image data of the weld bead) based on the laser light captured by the camera to inspection control device 3. The camera described above comprises at least a lens (not shown) and an image sensor (not shown). The image sensor is a solid-state imaging element such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor), which converts the optical image formed on the imaging surface into an electrical signal.

(Welding system operation)
Next, a series of operational procedures for main welding, bead visual inspection, and repair welding by welding system 100 according to embodiment 1 will be described with reference to Fig. 3. Fig. 3 is a sequence diagram showing an example of a series of processing procedures including main welding, bead visual inspection, and repair welding by welding system 100 according to embodiment 1. Fig. 3 illustrates an example of the operational procedures performed between host device 1, robot control device 2, and inspection control device 3 for each step of main welding using multiple original workpieces and repair welding that is performed when the bead visual inspection of a workpiece is found to be unsuccessful (i.e., the overall determination result indicates that there is a welding defect).

In FIG. 3, the host device 1 acquires workpiece information (e.g., ID, name, and welding location of the original workpiece) of the original workpiece to be welded (St1), and generates a command to execute the actual welding, including the workpiece information of the original workpiece. The host device 1 then sends the command to execute the actual welding, including the workpiece information of the original workpiece, to the robot control device 2 (St2). Note that the robot control device 2 may execute the processes of steps St1 and St2, respectively, without going through the host device 1. In this case, it is preferable that the memory 22 of the robot control device 2 stores the same data as that stored in the external storage ST, or that the robot control device 2 is connected so that it can acquire data from the external storage ST.

When the robot control device 2 receives a main welding execution command sent from the host device 1, it uses the workpiece information for each of the multiple original workpieces included in the execution command to create a main welding program for the main welding to be performed by the welding robot MC1, and causes the welding robot MC1 to perform the main welding in accordance with the main welding program (Step 3). When the robot control device 2 determines that the main welding by the welding robot MC1 has been completed using various known methods, it generates a main welding completion notification indicating that the main welding has been completed and sends it to the host device 1 (Step 4). This main welding completion notification may include, for example, workpiece information including the IDs of each of the multiple original workpieces used in the main welding (e.g., the original workpiece ID, name, and weld location (bead ID) of the original workpiece), welding conditions for each main welding execution, etc. When the host device 1 receives the main welding completion notification, it generates an execution command for an appearance inspection program, including a program for visual inspection of the workpiece, and sends it to the robot control device 2 (Step 5), and also generates an execution command for a bead visual inspection of the workpiece and sends it to the inspection control device 3 (Step 6). The execution command (St6) sent by the host device 1 to the inspection control device 3 may include workpiece information including the IDs of each of the multiple original workpieces used in the main welding (e.g., the original workpiece's ID, name, and weld location (bead ID) on the original workpiece), welding conditions for each main welding run, etc. The robot control device 2 executes the appearance inspection program received from the host device 1 upon the start of the bead appearance inspection, and moves the sensor 4 attached to the welding robot MC1 along the weld line (St7). While the sensor 4 is moved by the robot control device 2 so that it can scan the weld location on the workpiece, it acquires point cloud data that can identify the three-dimensional shape of the workpiece (St7).

The inspection control device 3 uses as input data the point cloud data acquired by the sensor 4 that can identify the three-dimensional shape of the weld bead, and performs the first and second inspection judgments described above individually (in parallel) (St7). The inspection control device 3 performs an overall judgment of the bead appearance inspection of the workpiece weld bead based on the results of each of the individual bead appearance inspections (i.e., the first and second inspection judgments) in step St7 (St8).

If the inspection control device 3 determines, as a result of the overall judgment in step St8, that the workpiece has a welding defect and requires repair welding (St9), it obtains the actual welding program from the robot control device 2 and creates a repair welding program by modifying a portion of the actual welding program (St9). The modified portion, for example, indicates the location (area) where repair welding will be performed. Although not shown in detail in FIG. 3 , the inspection control device 3 may request the actual welding program data from the robot control device 2 in step St9 and obtain the actual welding program data sent from the robot control device 2 in response to this request. Alternatively, the inspection control device 3 may obtain the actual welding program data sent from the robot control device 2 after step St3 in advance. In this way, the inspection control device 3 can efficiently create repair welding program data by partially modifying the actual welding program data obtained from the robot control device 2. The inspection control device 3 generates an appearance inspection report including the results of the overall judgment in step St8 and the repair welding program, and sends it to the robot control device 2 (St10). The inspection control device 3 also sends a similarly generated visual inspection report to the host device 1 (St11). The visual inspection report sent from the inspection control device 3 to the robot control device 2 and the host device 1 may include data forming the "visual inspection information of the weld bead before repair welding" described below, and data forming the "repair welding information" described below. The "visual inspection information of the weld bead before repair welding" may include, for example, the time of the visual inspection, a point cloud or image data including the weld bead to be visually inspected, the position, shape, and type of defect of the weld defect, etc. The "repair welding information" may include information indicating the trajectory (weld line) of the repair welding, information indicating the welding section on the weld line where the repair welding will be performed, etc. The visual inspection report may also include information other than the above.

Upon receiving the visual inspection report in step St11, the host device 1 generates a repair welding execution command for the workpiece and sends it to the robot control device 2 (St12). Upon receiving the repair welding execution command from the host device 1, the robot control device 2 causes the welding robot MC1 to perform repair welding in accordance with the repair welding program (received in step St10) for the workpiece specified in the execution command (St13). When the robot control device 2 determines, using various known methods, that the repair welding by the welding robot MC1 is complete, it sends work information for the repair work (e.g., the ID of the repair workpiece, work information including the IDs of each of the multiple original workpieces used in the main welding (e.g., the ID, name, and weld location (bead ID) of the original workpiece), and the welding conditions for each of the main welding and repair welding) to the host device 1 (St14). Additionally, parameters related to repair welding, such as the welding current, welding voltage, and welding speed (all of which are command values and measured values) related to repair welding, may be transmitted from the robot control device 2 to the higher-level device 1 and the inspection control device 3.

When the upper device 1 receives the work information including the repair work ID sent from the robot control device 2, it sets a management ID appropriate for the user corresponding to the repair work ID and saves data indicating that welding of the repair work corresponding to this management ID has been completed in external storage ST (St15).

The above is an example of the process for performing actual welding, visual inspection, and repair welding. However, visual inspection and repair welding are not necessarily performed only once. Upon receiving the repair welding completion notification (St14), the host device 1 can again send a command to execute the visual inspection program for the repair work to the robot control device 2 and the inspection control device 3 (St5 and St6). Then, processing similar to steps St7 to St14 is performed, and a second visual inspection and second repair welding are performed on the repair work. The visual inspection report (St10, St11) sent from the inspection control device 3 to the robot control device 2 and the host device 1 may include data forming the "visual inspection information of the weld bead after repair welding" described below, as well as data forming "repair welding information" for the second repair welding. The "visual inspection information of the weld bead after repair welding" may include, for example, the time of the visual inspection, point cloud or image data including the weld bead to be visually inspected, the position, shape, and type of defect at the defective weld location.

Next, the details of the individual inspection in step St7 and the overall judgment in step St8 in FIG. 3 will be explained with reference to FIG. 4. FIG. 4 is a flowchart showing an example of a processing procedure showing details of the first inspection judgment (point cloud comparison) and the second to Nth inspection judgments (AI judgments). To make the explanation of FIG. 4 easier to understand, let N=2.

In FIG. 4, point cloud data OD1, which can identify the three-dimensional shape of the weld bead acquired by sensor 4, is used in both the first and second inspection judgments. Data processing unit 36 converts point cloud data OD1 from sensor 4 into a data format suitable for the first inspection judgment (e.g., image data showing the three-dimensional shape of the weld bead) and passes it to first inspection judgment unit 371. First inspection judgment unit 371 reads master data MD1 of a non-defective workpiece stored in memory 32 (e.g., image data showing the ideal three-dimensional shape of a non-defective workpiece weld bead) from memory 32, and performs a first inspection judgment by comparing the image data from data processing unit 36 with master data MD1 (St21A).

The first inspection determination unit 371 determines whether the inspection score calculated for each inspection item (e.g., shape reliability, bead chipping, bead misalignment) is equal to or greater than a threshold value preset for that inspection item (St22A). That is, by comparing image data based on point cloud data OD1 with master data MD1, the first inspection determination unit 371 determines whether the inspection score for shape reliability is equal to or greater than the shape reliability threshold, whether the inspection score for the presence or absence of bead chipping is equal to or greater than the bead chipping threshold, or whether the inspection score for the presence or absence of bead misalignment is equal to or greater than the bead misalignment threshold (St22A). If the first inspection determination unit 371 determines that an inspection score equal to or greater than the shape reliability threshold, the bead chipping threshold, or the bead misalignment threshold has been obtained (St23A, YES), it determines that the inspection item is "OK" (i.e., shape reliability is satisfied and no bead chipping or bead misalignment is detected) (St23A). On the other hand, if the first inspection determination unit 371 determines that the inspection score obtained is less than the shape reliability threshold, bead chipping threshold, or bead misalignment threshold (St23A, NO), it determines that the inspection item is "NG" (i.e., the shape reliability is insufficient, or a bead chip or bead misalignment was detected) (St24A). The first inspection determination unit 371 acquires the determination result of step St23A or step St24A as the first inspection determination result (St25A).

The Nth inspection determination unit 37N determines whether the defect probability value (i.e., inspection score) output by the AI engine (e.g., neural network) for each inspection item (e.g., holes, pits, undercuts, spatter, protrusions) is equal to or less than a threshold value preset for each inspection item (St22B). In other words, the Nth inspection determination unit 37N determines whether the defect probability value calculated for each inspection item by the AI engine that inputs the point cloud data OD1 is equal to or less than the hole detection threshold, pit detection threshold, undercut detection threshold, spatter detection threshold, or protrusion detection threshold (St22B). If the Nth inspection determination unit 37N determines that the output value (defect probability value) of the AI engine for each inspection item is equal to or less than the hole detection threshold, pit detection threshold, undercut detection threshold, sputter detection threshold, or protrusion detection threshold (St23B, YES), it determines that the inspection item is "OK" (i.e., none of holes, pits, undercuts, sputters, or protrusions is detected) (St23B). On the other hand, if the first inspection determination unit 371 determines that the output value (defect probability value) of the AI engine for each inspection item is equal to or greater than the hole detection threshold, pit detection threshold, undercut detection threshold, sputter detection threshold, or protrusion detection threshold (St23B, NO), it determines that the inspection item is "NG" (i.e., one of holes, pits, undercuts, sputters, or protrusions is detected) (St24B). The Nth inspection and judgment unit 37N acquires the judgment result of step St23B or step St24B as the second inspection and judgment result (St25B).

The inspection result determination unit 37 makes an overall determination of the bead visual inspection using the first inspection determination result obtained in step St25A and the second inspection determination result obtained in step St25B (St26). For example, if the inspection result determination unit 37 determines that both the first inspection determination result and the second inspection determination result indicate that there are no welding defects, it determines that the bead visual inspection is a pass (in other words, repair welding is not required). On the other hand, if the inspection result determination unit 37 determines that either the first inspection determination result or the second inspection determination result indicates that a welding defect has been detected, it determines that the bead visual inspection is a fail (in other words, repair welding is required to repair the detected welding defect).

As described above, in the welding system 100 according to the first embodiment, the inspection control device 3, which serves as an example of a bead visual inspection device, inputs input data (e.g., point cloud data OD1) related to the weld bead of a workpiece produced by welding to the processor 31. The inspection control device 3 uses the input data and master data MD1 of a non-defective workpiece to perform a first inspection judgment of the weld bead in the first inspection judgment unit 371 based on a comparison of the input data with the master data MD1. The inspection control device 3 is equipped with k (k: an integer greater than or equal to 1) types of artificial intelligence and performs a second inspection judgment of the weld bead in each of the second inspection judgment unit 372 through the Nth inspection judgment unit 37N based on processing of the k types of artificial intelligence targeting the input data. k = (N-1), and so on. The inspection control device 3 outputs the results of the bead visual inspection of the weld bead to an output device (e.g., monitor MN2) in the inspection result judgment unit 37 based on the judgment results of the first inspection judgment unit 371 and the second inspection judgment unit 372 through the Nth inspection judgment unit 37N.

As a result, the inspection control device 3 can perform both a first inspection judgment based on a comparison of input data indicating the three-dimensional shape of the weld bead with master data MD1, and a second inspection judgment that detects the presence or absence of welding defects in the weld bead based on AI processing, thereby making it possible to more efficiently inspect the appearance of weld beads on workpieces produced by actual welding. In particular, when detecting the presence or absence of welding defects using AI processing, k (= (N-1)) different AIs can be prepared to match the inspection items targeted by the user's bead appearance inspection. Therefore, the inspection control device 3 can improve the convenience of weld bead appearance inspections for users.

In addition, the visual inspection items of the weld beads that are the subject of the first inspection judgment are different from the visual inspection items of the weld beads that are the subject of the second inspection judgment. This allows the inspection control device 3 to comprehensively inspect the weld beads, including the visual inspection items of the weld beads that are detected with high accuracy by the first inspection judgment and the visual inspection items of the weld beads that are detected with high accuracy by the second inspection judgment.

Furthermore, when k is an integer greater than or equal to 2, the appearance inspection items of the weld bead that are the subject of the second inspection judgment performed by each of second inspection judgment unit 372 through Nth inspection judgment unit 37N (in other words, one example of k second inspection judgment units) are different. For example, second inspection judgment unit 372 detects the presence or absence of holes and spatter in the weld bead, and Nth inspection judgment unit 37N detects the presence or absence of pits and undercuts in the weld bead. This allows the inspection control device 3 to provide multiple combinations of second inspection judgments for each inspection item that can be detected with high accuracy using AI processing, thereby enabling the inspection of the presence or absence of each type of welding defect in the weld bead to be performed with high accuracy compared to, for example, inspecting numerous inspection items using a single type of AI processing.

The inspection control device 3 also communicates with a welding robot MC1 capable of performing repair welding on the workpiece's weld beads. If the inspection control device 3 determines that any of the visual inspection items in the respective judgment results of the first inspection judgment unit 371 and the k second judgment units (second inspection judgment unit 372 to Nth inspection judgment unit 37N) is defective, the inspection control device 3 sends to the welding robot MC1 an instruction to perform repair welding to correct the corresponding portion of the weld bead that was determined to be defective. As a result, if the inspection control device 3 determines that a welding defect has been detected in any of the inspection items as a comprehensive judgment based on the respective results of the first inspection judgment and the second inspection judgment, it can issue an instruction to the welding robot MC1 to perform repair welding to automatically correct the inspection item that resulted in the welding defect, thereby quickly and smoothly improving the quality of the workpiece.

The inspection control device 3 also converts input data into a data format suitable for input to k types of artificial intelligence. This enables the inspection control device 3 to improve the accuracy of the AI processing performed by each of the second inspection and judgment unit 372 to the Nth inspection and judgment unit 37N, thereby improving the accuracy of detecting the presence or absence of welding defects in the weld bead (e.g., holes, pits, undercuts, spatter).

The weld bead appearance inspection items that are the subject of the first inspection judgment are the weld bead shape, weld bead chipping, and weld bead misalignment. The weld bead appearance inspection items that are the subject of the second inspection judgment are weld bead perforations, pits, undercuts, spatter, and protrusions. This allows the inspection control device 3 to comprehensively inspect weld bead appearance inspection items that are detected with high accuracy by the first inspection judgment (e.g., weld bead shape, weld bead chipping, weld bead misalignment) and weld bead appearance inspection items that are detected with high accuracy by the second inspection judgment (e.g., weld bead perforations, pits, undercuts, spatter, and protrusions).

(Embodiment 2)
In the first embodiment, both the first inspection judgment and the second inspection judgment are performed in the inspection control device 3. In the second embodiment, an example will be described in which the first inspection judgment and the second inspection judgment are performed in different devices. Hereinafter, the first inspection judgment will be described as being performed in the inspection control device 3, and the second inspection judgment will be described as being performed in the higher-level device 1. However, the second inspection judgment may be performed in a device other than the higher-level device 1.

(Welding system configuration)
6 is a diagram showing an example of the internal configuration of an inspection control device 3A, a robot control device 2, and a higher-level device 1A according to embodiment 2. In the description of FIG. 6, the same components as those in FIG. 2 are given the same reference numerals, and the description thereof is simplified or omitted, and only differences are described. The configuration of a welding system 100A according to embodiment 2 is the same as that of welding system 100 according to embodiment 1 (see FIG. 1).

Welding system 100A, an example of a bead appearance inspection system, includes a host device 1A connected to external storage ST, an input interface UI1, and a monitor MN1, a robot control device 2, an inspection control device 3A, a sensor 4, a main welding robot MC1a, and a repair welding robot MC1b.

In the inspection control device 3A, which is an example of a bead appearance inspection device, the processor 31A includes a judgment threshold memory unit 34, a shape detection control unit 35, a data processing unit 36, an inspection result judgment unit 37A, and a repair welding program creation unit 38. The inspection result judgment unit 37A only has a first inspection judgment unit 371. The configuration of the first inspection judgment unit 371 is the same as in embodiment 1, so description thereof will be omitted.

In the upper device 1A, which is an example of a bead visual inspection device, the processor 11A includes a cell control unit 13 and second inspection/determination units 142 through Nth inspection/determination units 14N. Similar to second inspection/determination units 372 through Nth inspection/determination units 37N, second inspection/determination units 142 through Nth inspection/determination units 14N perform second inspection/determination (i.e., bead visual inspection that forms a neural network using k = (N-1) types of artificial intelligence and determines the presence or absence of defective welds based on input data regarding the shape of the weld bead acquired by sensor 4) to inspect the weld bead for holes, pits, undercuts, spatter, and protrusions (see Figure 5). Memory 12 or processor 11A may perform a function similar to that of the determination threshold memory unit 34 of the inspection control device 3A. Although not shown, a determination threshold memory unit may be provided within processor 11A.

(Welding system operation)
Next, a series of processing procedures including main welding, bead visual inspection, and repair welding by welding system 100A according to embodiment 2 will be described with reference to FIG. 7 . FIG. 7 is a sequence diagram showing an example of a series of processing procedures including main welding, bead visual inspection, and repair welding by welding system 100A according to embodiment 2. The explanation of FIG. 7 will exemplify the operational procedures performed between host device 1A, robot control device 2, and inspection control device 3A for each step of main welding using multiple original workpieces and repair welding performed when a workpiece fails the bead visual inspection. Furthermore, in the explanation of FIG. 7 , processes that overlap with the processes of FIG. 3 are assigned the same step numbers, and explanations thereof will be simplified or omitted, and differences will be explained.

In FIG. 7, after step St6, the robot control device 2 executes the appearance inspection program received from the host device 1A in conjunction with the start of the bead appearance inspection, and moves the sensor 4 attached to the welding robot MC1 along the weld line (St7A). While the robot control device 2 moves the sensor 4 to scan the welded portion of the workpiece, the sensor 4 acquires point cloud data capable of identifying the three-dimensional shape of the workpiece (St7A). The inspection control device 3A uses the point cloud data capable of identifying the three-dimensional shape of the weld bead acquired by the sensor 4 as input data and executes the first inspection judgment described above (St7A). The inspection control device 3A also generates an instruction to execute the second inspection judgment described above using the processor 31A and sends it to the host device 1A (St31).

When the host device 1A receives the instruction to perform the second inspection judgment sent from the inspection control device 3A in step St31, the second inspection judgment is performed in each of the second inspection judgment units 142 to the Nth inspection judgment unit 14N based on the instruction (St32). The details of the second inspection judgment performed in step St32 are the same as those described in embodiment 1, and therefore will not be described again. The host device 1A generates the processing results of the second inspection judgment (i.e., detection of the presence or absence of welding defects for each inspection item using AI processing) and sends them to the inspection control device 3A (St33). The inspection control device 3A performs an overall judgment of the bead appearance inspection of the workpiece based on the results of the first inspection judgment by the inspection control device 3A in step St7 and the second inspection judgment by the host device 1A in step St32 (St8A). The details of the overall judgment performed in step St8A are the same as those described in embodiment 1, and therefore will not be described again. The processing from step St8A onwards is the same as that in FIG. 3, and therefore will not be described again.

As described above, welding system 100A, an example of a bead appearance inspection system according to embodiment 2, receives input data (e.g., point cloud data OD1) related to the weld bead of a workpiece produced by welding in inspection control device 3A. Welding system 100A uses the input data and master data MD1 of a non-defective workpiece to perform a first inspection and judgment of the weld bead in inspection control device 3A based on a comparison of the input data with master data MD1. Furthermore, k (k: an integer greater than or equal to 1) types of artificial intelligence are installed, and second inspection and judgment of the weld bead is performed in each of second inspection and judgment unit 142 through Nth inspection and judgment unit 14N of host device 1A based on processing of the k types of artificial intelligence on the input data. In inspection control device 3A, inspection result judgment unit 37 outputs the results of the bead appearance inspection of the weld bead to an output device (e.g., monitor MN2) based on the judgment results of first inspection and judgment unit 371 of inspection control device 3A and second inspection and judgment unit 142 through Nth inspection and judgment unit 14N of host device 1A.

As a result, welding system 100A performs a first inspection judgment based on a comparison between input data indicating the three-dimensional shape of the weld bead and master data MD1 using inspection control device 3A, and a second inspection judgment that detects the presence or absence of welding defects in the weld bead based on AI processing can be performed in a distributed manner by host device 1A. Therefore, welding system 100A can reduce the processing load of bead visual inspection compared to, for example, a case in which both the first and second inspection judgments are performed solely by inspection control device 3, as in embodiment 1. Furthermore, welding system 100A can more efficiently perform visual inspection of weld beads on workpieces produced by actual welding. In particular, when detecting the presence or absence of welding defects using AI processing, k (= (N-1)) different AIs can be prepared to match the inspection items targeted by the user's bead visual inspection. Therefore, welding system 100A can improve the user's convenience when it comes to visual inspection of weld beads.

(Visual inspection visualization)
The shape and position of defects detected in the visual inspection of the weld bead (steps St6 to St11), the welding conditions and weld line trajectory during repair welding, and data on the appearance of the bead before and after repair welding are important for quality control of welded products. Displaying this information as needed is advantageous because it allows the validity of automated repair welding to be visualized. Therefore, in this embodiment, visual inspection information of the weld bead before repair welding, repair welding information, and visual inspection information of the weld bead after repair welding are visualized.

(Visual inspection information of weld bead before repair welding)
8 shows an example of a display in which visual inspection information of a weld bead before repair welding is displayed on a monitor DISP. The monitor DISP here may be the monitor MN1 or the monitor MN2 shown in FIG. 1, or may be a monitor provided in a device connected to welding system 100 by wire or wirelessly.

On the monitor DISP, visual inspection information for the weld bead before repair welding is displayed, for example, as indicated by the reference symbols D_INF, D_BD, D_PROP, and D_FP in the figure. D_INF is information such as the ID of the workpiece or bead, welding conditions, and the time of the visual inspection before repair welding (for example, the first time). D_BD is a point cloud or image data indicating the weld bead that was the subject of the visual inspection before repair welding. D_FP is information indicating the defective area detected in the visual inspection before repair welding. D_PROP is a balloon display that presents property information for the object at the end of the lead-in line (defective area D_FP in this figure), and includes, for example, the type of defect (insufficient reinforcement, missing bead, hole, etc.) for the defective area and inspection values measured in the visual inspection (reinforcement height D, missing bead length L, hole diameter R, etc.).

(Repair welding information)
9 shows an example of a display of repair welding information on a monitor DISP. The monitor DISP may be the monitor MN1 or MN2 shown in FIG. 1, or may be a monitor provided in a device connected to welding system 100 by wire or wirelessly.

On the monitor DISP, repair welding information is displayed, for example, as indicated by the reference symbols D_LINE, D_PROP, and D_SEC in the figure. D_LINE indicates the trajectory (weld line) of the repair welding. D_SEC indicates the welding section on the weld line where repair welding will be performed. D_PROP is a balloon display that presents property information of the object at the end of the lead-in line (in this figure, the welding section D_SEC where repair welding will be performed), and includes, for example, the current value used for welding in that welding section.

(Visual inspection information of weld bead after repair welding)
10 shows an example of a display in which visual inspection information of a weld bead after repair welding is displayed on a monitor DISP. The monitor DISP here may be the monitor MN1 or the monitor MN2 shown in FIG. 1, or may be a monitor provided in a device connected to welding system 100 by wire or wirelessly.

The monitor DISP displays visual inspection information for the weld bead after repair welding, such as information indicated by the reference symbols D_INF, D_BD, D_PROP, and D_FP in the figure. D_INF includes information such as the ID of the workpiece and bead, the welding conditions for the actual welding, the time of the visual inspection before repair welding (e.g., the first time), and the time of the visual inspection after repair welding (e.g., the second time). D_BD is a point cloud or image data representing the weld bead that was the subject of the visual inspection after repair welding. D_FP is information indicating the defective area detected by the visual inspection after repair welding. D_PROP is a balloon display that presents property information for the object at the end of the lead-in line (defective area D_FP in this figure), including, for example, the type of defect (insufficient reinforcement, missing bead, hole, etc.) for the defective area and the inspection values measured during the visual inspection (reinforcement height D, missing bead length L, hole diameter R, etc.). Comparing Figure 10 with Figure 8, it can be seen that the number of defective locations has decreased in Figure 10.

(Superimposed display)
11 shows an example of a display in which the visual inspection information of the weld bead before repair welding ( FIG. 8 ), the repair welding information ( FIG. 9 ), and the visual inspection information of the weld bead after repair welding ( FIG. 10 ) are superimposed on the monitor DISP. From the bottom (background) to the top (foreground) of the display layer, the visual inspection information of the weld bead before repair welding ( FIG. 8 ), the repair welding information ( FIG. 9 ), and the visual inspection information of the weld bead after repair welding ( FIG. 10 ) are superimposed and displayed in this order. By displaying the information in this manner on the monitor DISP, the user can easily visually confirm that the defective portions of the weld bead detected by the visual inspection have been properly repair welded.

However, if all of the information in the visual inspection information of the weld bead before repair welding ( FIG. 8 ), the repair welding information ( FIG. 9 ), and the visual inspection information of the weld bead after repair welding ( FIG. 10 ) were superimposed on the monitor DISP, visibility could be reduced. Therefore, it is preferable that the device that controls the display on the monitor DISP (e.g., the upper device 1 or the inspection control device 3) has one or more of the following functions, for example:
- Ability to selectively switch some display items between visible/hidden/transparent.
A function for changing the display color for each display item (for example, displaying the display items shown in FIG. 8 in black and white, and the display items shown in FIG. 10 in blue, etc.).
- Balloon (D_PROP) position change function.
- Viewpoint switching function (for example, changing the display angle of point cloud data).

In addition, if there is a chip on the side of a weld bead and repair welding is performed to increase the buildup to fill the chip, the point cloud or image data D_BD (after repair welding) representing the weld bead that was the subject of the visual inspection after repair welding may be larger in shape than the point cloud or image data D_BD (before repair welding) representing the weld bead that was the subject of the visual inspection before repair welding. In this case, a device controlling the display on the monitor DISP (e.g., the host device 1 or the inspection control device 3) may color-code the images and then superimpose them on the monitor DISP. For example, a device controlling the display on the monitor DISP (e.g., the host device 1 or the inspection control device 3) may display the point cloud or image data D_BD (before repair welding) representing the weld bead that was the subject of the visual inspection before repair welding in blue, and the point cloud or image data D_BD (after repair welding) representing the weld bead that was the subject of the visual inspection after repair welding in semi-transparent yellow. Note that the display colors are not limited to blue or yellow.

(Display modes other than superimposed display)
Because the time periods before repair welding (corresponding to FIG. 8 ), during repair welding (corresponding to FIG. 9 ), and after repair welding (corresponding to FIG. 10 ) are different, a display format other than the overlapping display shown in FIG. 11 may be used to collectively display this information. For example, as shown in FIG. 12 , there is a display format in which the information is displayed separately on the screen. FIG. 12 illustrates a display example in which visual inspection information for the weld bead before repair welding and visual inspection information for the weld bead after repair welding are displayed side by side on the monitor DISP. In FIG. 12 , the monitor DISP is divided into two display areas, left and right. The left area displays visual inspection information for the weld bead before repair welding (see FIG. 8 ), and the right area displays visual inspection information for the weld bead after repair welding (see FIG. 10 ). This display format allows the user to easily understand the status before and after repair welding by comparing them on a single screen. Note that the reference symbol D_STAT in the figure indicates the object displayed in that display area (left area or right area).

Although not shown, in the left area of the monitor DISP, repair welding information (Figure 9) may be superimposed on visual inspection information of the weld bead before repair welding (see Figure 8). In this display format, the left area of the monitor DISP displays defective areas in the weld bead and the status of the repair welding for those defective areas, and the right area of the monitor DISP clearly displays how the defective areas have been reduced (or eliminated) as a result of repair welding.

In the above example, the display area of the monitor DISP is divided into two areas, a left area and a right area. However, the manner in which the display area is divided is not limited to this. For example, the display area of the monitor DISP may be divided into two areas, top and bottom, or into three areas, a left area, a center area, and a right area, or into four areas, top and bottom and left and right. Any other manner in which the display area may be divided can be used. For example, the divided display areas may display the weld bead after main welding, the weld bead after the first repair welding, ..., and the weld bead after the Nth repair welding, respectively.

(Other display information)
In addition to the above-mentioned display items, the monitor DISP may additionally display, for example, the following information.
- A numerical value that indicates the rate of match with teaching data (master data) and evaluation value when learning the characteristics of defective parts of weld beads and making a pass/fail judgment (AI judgment).
- Numerical values indicating the dimensions (excess height D, bead chip length L, hole diameter R, etc.) and number (number of holes or pits, etc.) of defective areas in the weld bead.
Numerical values indicating detailed parameters related to welding (main welding/repair welding), such as welding current, welding voltage, welding speed, weaving width in the case of weaving welding, frequency, etc.

Welding parameters (welding current, welding voltage, welding speed, etc.) displayed on the monitor DISP may be average values over the welding interval (see D_SEC in Figure 9). The various numerical information described above may also be graphed and displayed on the monitor DISP. For example, for values that may fluctuate over time, such as welding current, welding voltage, and welding speed, graphs (waveform graphs) showing the changes in these values over time may be displayed on the monitor DISP. Figure 13 shows specific examples of graphs (waveform graphs) showing the changes in welding parameters over time that may be additionally displayed on the monitor DISP: (a) a graph of welding current with time (msec) on the horizontal axis and current (amperes) on the vertical axis; (b) a graph of welding voltage with time (msec) on the horizontal axis and voltage (volts) on the vertical axis; and (c) a graph of welding speed with time (msec) on the horizontal axis and speed (m/s) on the vertical axis.

For example, in the welding current graph shown in Figure 13(a), the welding current command value instructed by the robot control device 2 to the welding robot MC1 may not completely match the measured value of the actual welding current. Therefore, a waveform graph in which the command value and the measured value are superimposed may be displayed on the monitor DISP. Figure 14 shows an example of a waveform graph in which the welding current command value and the measured value are superimposed.

In addition, information showing changes in welding parameters between the welding performed on the workpiece (main welding or repair welding) and the next welding (repair welding) may be additionally displayed on the monitor DISP. For example, a "+10%" display could indicate that the repair welding will be performed with a current that is 110% of the previous welding current.

This allows at least the visual inspection information of the weld bead before repair welding to be displayed in a comparable manner with the repair welding information, making it possible to visualize the validity of the visual inspection of the weld bead and the repair welding.

The repair welding information includes information about the welding section of the repair welding. This allows visual inspection information of the weld bead before repair welding to be displayed in a comparable manner, with the repair welding information including information about the welding section of the repair welding.

The repair welding information is superimposed on the visual inspection information of the weld bead before the repair welding and displayed on the display device. This makes it possible to visualize that repair welding has been performed on defective areas detected in the weld bead.

Visual inspection information of the weld bead after repair welding is further acquired, and the visual inspection information of the weld bead before repair welding, the repair welding information, and the visual inspection information of the weld bead after repair welding are displayed on the display device. This makes it possible to visualize that the defective areas detected before repair welding have been repaired after repair welding.

The visual inspection information of the weld bead after the repair welding is superimposed on the visual inspection information of the weld bead before the repair welding and displayed on the display device. Alternatively, the visual inspection information of the weld bead before the repair welding and the visual inspection information of the weld bead after the repair welding are displayed in different display areas of the display device. By displaying the superimposed information, it is possible to clearly visualize, for example, that a hole has been filled by repair welding. On the other hand, by displaying the information in different display areas, it is possible to compare and confirm the different states of the weld bead (before and after repair welding).

The visual inspection information of the weld bead before repair welding includes point cloud or image data indicating the weld bead that was the subject of the visual inspection before repair welding and information indicating defective areas detected by the visual inspection before repair welding, and the visual inspection information of the weld bead after repair welding includes point cloud or image data indicating the weld bead that was the subject of the visual inspection after repair welding and information indicating defective areas detected by the visual inspection after repair welding. This makes it possible to visualize the changes in the condition of the weld bead and defective areas before and after repair welding.

The repair welding information further includes information indicating the weld line of the repair welding. This makes it possible to visualize the trajectory of the repair welding relative to the weld bead.

Although various embodiments have been described above with reference to the drawings, it goes without saying that the present disclosure is not limited to such examples. Those skilled in the art will clearly be able to conceive of various modifications, alterations, substitutions, additions, deletions, and equivalents within the scope of the claims, and it will be understood that these naturally fall within the technical scope of the present disclosure. Furthermore, the components of the various embodiments described above may be combined in any manner as long as they do not deviate from the spirit of the invention.

The present disclosure is useful as a bead appearance inspection device, bead appearance inspection method, program, and bead appearance inspection system that more efficiently inspects the appearance of weld beads on workpieces produced by this welding. The present disclosure is also useful as a control device, a control method, and a program for a display device that can visualize the appearance inspection of weld beads and the validity of repair welding.

DESCRIPTION OF SYMBOLS 1, 1A Upper device 2 Robot control device 4 Sensor 10, 20, 30 Communication unit 11, 11A, 21, 31, 31A Processor 12, 22, 32 Memory 13 Cell control unit 23 Main welding program creation unit 24 Calculation unit 25 Robot control unit 26 Power supply control unit 33 Inspection result storage unit 34 Determination threshold storage unit 35 Shape detection control unit 36 Data processing unit 37 Inspection result determination unit 371 First inspection and determination unit 142 Second inspection and determination unit 14N, 37N Nth inspection and determination unit 100, 100A Welding system 200 Manipulator 300 Wire feeder 301 Welding wire 400 Welding torch 500 Power supply unit MC1 Welding robot MC1a Main welding robot MC1b Repair welding robot MN1, MN2, DISP Monitor ST External storage

Claims (9)

Visual inspection information of the weld bead before repair welding;
repair welding information of the weld bead;
and acquiring visual inspection information of the weld bead after repair welding;
the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding are superimposed on the visual inspection information of the weld bead before repair welding and displayed on a display device.
a processor,
The visual inspection information of the weld bead before the repair welding, the repair welding information, and the visual inspection information of the weld bead after the repair welding are displayed on the display device in an aligned position, rather than as text information.
Control device. The repair welding information includes welding section information of the repair welding.
The control device according to claim 1 . the visual inspection information of the weld bead before repair welding includes point cloud or image data indicating the weld bead that was the subject of the visual inspection before repair welding, and information indicating a defective portion detected by the visual inspection before repair welding,
The visual inspection information of the weld bead after repair welding includes point cloud or image data indicating the weld bead that was the subject of the visual inspection after repair welding, and information indicating a defective portion detected by the visual inspection after repair welding.
The control device according to claim 1 or 2. The repair welding information further includes information indicating a weld line of the repair welding.
The control device according to any one of claims 1 to 3. The processor:
and displaying, on the display device, some of the display items among the appearance inspection information of the weld bead before the repair welding, the repair welding information of the weld bead, and the appearance inspection information of the weld bead after the repair welding, by selectively switching between display, non-display, and semi-transparency.
A control device according to any one of claims 1 to 4. The processor:
displaying, on the display device, a display color for each of the display items of the appearance inspection information of the weld bead before the repair welding, the repair welding information of the weld bead, and the appearance inspection information of the weld bead after the repair welding, in a different color;
A control device according to any one of claims 1 to 4. The processor:
changing a display angle of the visual inspection information of the weld bead before the repair welding and the point cloud data of the weld bead included in each of the weld beads;
A control device according to any one of claims 1 to 4. A control method for a display device executed by a control device, comprising:
A step of acquiring visual inspection information of the weld bead before repair welding;
acquiring repair welding information of the weld bead;
acquiring visual inspection information of the weld bead after repair welding;
and displaying the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding on the display device, the repair welding information of the weld bead being superimposed on the visual inspection information of the weld bead before repair welding,
The visual inspection information of the weld bead before the repair welding, the repair welding information, and the visual inspection information of the weld bead after the repair welding are displayed on the display device in an aligned position, rather than as text information.
A method for controlling a display device. The control device is a computer.
A step of acquiring visual inspection information of the weld bead before repair welding;
acquiring repair welding information of the weld bead;
acquiring visual inspection information of the weld bead after repair welding;
and displaying, on a display device, the repair welding information of the weld bead and the visual inspection information of the weld bead after repair welding superimposed on the visual inspection information of the weld bead before repair welding,
The visual inspection information of the weld bead before the repair welding, the repair welding information, and the visual inspection information of the weld bead after the repair welding are displayed on the display device in an aligned position, rather than as text information.
program.