JP7797982B2 - Abnormality detection device and machining system - Google Patents

Description

The present invention relates to an abnormality detection device and a machining system.

Some abnormality detection devices for machining equipment detect the presence or absence of abnormalities based on status data such as the motor status and machining sounds during machining operations (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2019-169003

In the conventional anomaly detection device, it is conceivable that sounds during work are collected by a sound collection microphone and the presence or absence of an abnormality is determined based on the collected sounds. In this case, the anomaly detection device can determine the presence or absence of an abnormality based on sound data acquired from the output of the sound collection microphone.
The sounds collected during the work period are continuous. Therefore, one possible method for acquiring the sounds during the work period as data based on the output of the sound collection microphone is to acquire sound data over time at regular intervals.

In this case, it is conceivable to have the computer perform an acquisition process in which sound data is acquired over time at regular acquisition intervals and a group of sound data corresponding to the machining processing period from the start to the end of machining processing for one workpiece, and a determination process in which the group of sound data is used to determine whether or not there is an abnormality.
In this case, in the acquisition process, while the acquired sound data group is being provided to the determination process, it is not possible to acquire sound data over time based on the output of the sound collection microphone.
Here, if the amount of data in the sound data group provided from the acquisition process to the determination process becomes large, the period during which sound data cannot be acquired in the acquisition process will increase, and there is a risk that some of the sound during the work period will not be acquired, resulting in so-called data loss.

(1) An embodiment of an anomaly detection device is an anomaly detection device for a machining device that performs machining processing on a workpiece. The anomaly detection device includes a sound collection unit that collects sounds from the machining device and a processing unit that receives an output from the sound collection unit. The processing unit includes a processing unit that performs an acquisition process that acquires sound data over time at predetermined acquisition intervals based on the output, and a generation process that generates an anomaly determination process described below each time the sound data is acquired in the acquisition process and executes the anomaly determination processes in parallel.
The abnormality determination process is a process that determines whether a sound data group consisting of multiple sound data acquired from the time the sound data was acquired until a predetermined period in the past includes sound data corresponding to the machining processing period from the start to the end of the machining processing, and if it is determined that the sound data group includes sound data corresponding to the machining processing period, determines whether or not there is an abnormality based on the sound data group.

(6) From another perspective, this embodiment is a machining system. This machining system includes a machining device that performs machining processing on a workpiece, and the abnormality detection device described in (1) above.

This disclosure makes it possible to reduce data loss, which results in audio data not being able to be acquired.

FIG. 1 is an external view of a machining system according to an embodiment. FIG. 2 is a diagram showing devices arranged on a bed. FIG. 3 is a diagram showing an example of a work process when grinding a workpiece using a grinding device. FIG. 4 is a block diagram showing an example of the configuration of the processing device. FIG. 5 is a diagram illustrating an example of processing performed by a processing unit of the processing device. FIG. 6 is a flowchart showing an example of an abnormality determination process. FIG. 7 is a diagram for explaining the update of the sound data group. FIG. 8 is a diagram showing an example of sound data acquired by the processing unit 14. As shown in FIG.

First, the contents of the embodiment will be listed and explained.
[Outline of the embodiment]
(1) An embodiment of an anomaly detection device is an anomaly detection device for a machining device that performs machining processing on a workpiece. The anomaly detection device includes a sound collection unit that collects sounds from the machining device and a processing unit that receives an output from the sound collection unit. The processing unit includes a processing unit that performs an acquisition process that acquires sound data over time at predetermined acquisition intervals based on the output, and a generation process that generates an anomaly determination process described below each time the sound data is acquired in the acquisition process and executes the anomaly determination processes in parallel.
The abnormality determination process is a process that determines whether a sound data group consisting of multiple sound data acquired from the time the sound data was acquired until a predetermined period in the past includes sound data corresponding to the machining processing period from the start to the end of the machining processing, and if it is determined that the sound data group includes sound data corresponding to the machining processing period, determines whether or not there is an abnormality based on the sound data group.

According to the anomaly detection device, an anomaly determination process is generated each time sound data is acquired in the acquisition process, and the determination of the presence or absence of an anomaly is executed in parallel. Therefore, in the acquisition process, it is not necessary to provide a large amount of sound data to the generation process at once.
As a result, the amount of data given at one time from the acquisition process to the generation process can be reduced, periods during which sound data cannot be acquired during the acquisition process can be eliminated, and data loss can be reduced when using sound data to determine whether or not there are any abnormalities in the machining of the workpiece.

(2) In the above-described anomaly detection device, it is preferable that the sound data group is obtained based on the sound data and another sound data group of another anomaly determination process generated before the anomaly determination process.
In this case, a plurality of abnormality determination processes can be executed while updating the sound data group in accordance with the acquisition of sound data.

(3) In the abnormality detection device, the predetermined period is preferably longer than the machining processing period.
In this case, the sound data group can include sound data corresponding to the entire machining processing period, and in the abnormality determination process, if the sound data group includes sound data corresponding to the entire machining processing period, the presence or absence of an abnormality can be determined based on the sound data group.

(4) The sound data may include sound pressure. In this case, the abnormality determination process can determine whether the sound data group includes sound data corresponding to the machining processing period based on the sound pressure.

(5) In the above-mentioned abnormality detection device, it is preferable that the machining device is a grinding device.

(6) From another perspective, this embodiment is a machining system. This machining system includes a machining device that performs machining processing on a workpiece, and the abnormality detection device described in (1) above.

[Details of the embodiment]
Preferred embodiments will now be described with reference to the drawings.
[Overall structure]
FIG. 1 is an external view of a machining system according to an embodiment.
The machining system 1 according to the embodiment includes a grinding device 2 , a workpiece transport device 3 , and a processing device 4 .
The grinding device 2, which is a machining device, includes a bed 2a and a cover 2b. A headstock, grinding stone, etc., which will be described later, are placed on the upper surface of the bed 2a. The cover 2b accommodates the headstock, grinding stone, etc., which are placed on the upper surface of the bed 2a. The cover 2b prevents a cooling liquid (coolant) from splashing outside during machining.
The workpiece transport device 3 is disposed above the cover 2b. The workpiece transport device 3 has an arm that grips and transports the workpiece W inside the cover 2b of the grinding device 2. The workpiece transport device 3 has the function of removing the processed workpiece W from the grinding device 2 using the arm and supplying a new workpiece W to the grinding device 2 before processing.
The cover 2b has an openable/closable shutter on its upper surface. By opening the shutter of the cover 2b, the workpiece transport device 3 can access the workpiece W on the bed 2a.
The processing device 4 is, for example, a computer. The processing device 4 has a function of executing a process for determining whether or not an abnormality occurs during grinding.

FIG. 2 is a diagram showing the devices arranged on the bed 2a.
The grinding device 2 further includes a table 5 , a headstock 6 , a grinding wheel 7 , and a tailstock 8 .
The headstock 6 rotatably supports the spindle 6a and the chuck 6b. The chuck 6b grips one end of the workpiece W. The chuck 6b can be controlled to open and close by an actuator or the like. The tailstock 8 holds the other end of the workpiece W. The spindle 6a, the chuck 6b, and the workpiece W gripped by the chuck 6b are rotated by a motor included in the headstock 6. The grinding wheel 7 is supported by a grinding wheel head (not shown). The grinding wheel 7 can be rotated by a motor included in the grinding wheel head. The grinding wheel 7 can also be moved by an actuator or the like.
The headstock 6 and tailstock 8 are provided on a table 5. The table 5 can be moved longitudinally (left and right on the page) by an actuator or the like. The table 5 moves the headstock 6, tailstock 8, and the workpiece W held thereon relative to the grinding wheel 7. This allows the grinding wheel 7 to grind the necessary portions of the workpiece W in the axial direction.
The table 5, headstock 6, grinding wheel 7, and tailstock 8 constitute a main body 15 that performs grinding processing on the workpiece W.
The grinding device 2 also has a nozzle 9 for supplying a coolant to the location where the workpiece W and the grinding wheel 7 come into contact.

A sound collecting microphone 10 is fixed to the tailstock 8. The sound collecting microphone 10 (sound collecting unit) is an ultrasonic microphone or a general-purpose microphone. The sound collecting microphone 10 is fixed to the tailstock 8 by a fixing base 11. The sound collecting microphone 10 is disposed inside the cover 2b. Therefore, a waterproof cover 12 is attached to the sound collecting microphone 10 to prevent the coolant from splashing on the sound collecting microphone 10.
The sound collecting microphone 10 is disposed inside the cover 2b and collects sounds inside the cover 2b.
The sound collecting microphone 10 is connected to the processing device 4. The output of the sound collecting microphone 10 is provided to the processing device 4.

The grinding device 2 also has a control unit (not shown) that controls each component. The control unit controls the motor that rotates the spindle 6a and the motor that rotates the grinding wheel 7. The control unit also controls actuators for opening and closing the chuck 6b, moving the table 5 and grinding wheel 7, and opening and closing the shutter of the cover 2b. The control unit also controls the supply of coolant according to a preset procedure. This control unit has the function of operating each component according to a preset procedure and grinding the workpiece W supplied from the workpiece transport device 3.

FIG. 3 is a diagram showing an example of a work process when grinding a workpiece W using the grinding device 2.
When grinding the workpiece W, first, the power supply of the grinding device 2 is switched from an off state to an on state (step S1 in FIG. 3).
Thereafter, preparations necessary for grinding, including preparation of the grinding wheel 7, preparation of a jig appropriate for the workpiece W, and test grinding, are carried out (step S2 in FIG. 3).

Note that the power off state of the grinding device 2 refers to a state in which the power switch of the grinding device 2 is off and power is not being supplied to some or all of the components of the grinding device 2, making it impossible to immediately perform processing operations. Note that the power on state of the grinding device 2 refers to a state in which the power switch of the grinding device 2 is on and making it possible to immediately perform processing operations.

Next, the workpiece W before machining is carried into the grinding device 2 (step S3 in FIG. 3).
When the workpiece W is carried in, the shutter of the cover 2b is opened, and the workpiece transport device 3 carries the workpiece W before machining into the cover 2b, and the workpiece W is supplied to the grinding device 2. Once the workpiece W has been supplied, the grinding device 2 holds the supplied workpiece W with the chuck 6b and tailstock 8 and closes the shutter of the cover 2b. This completes the carrying in of the workpiece W into the grinding device 2.

Thereafter, the grinding device 2 performs a grinding process (machining process) on the workpiece W (step S4 in FIG. 3).
In the grinding process, the grinding device 2 starts rotating the workpiece W (spindle 6a) and the grindstone 7, and also starts supplying the coolant (step S11 in FIG. 3).

Next, the grinding device 2 moves the workpiece W and grinding wheel 7 and performs grinding on the workpiece W (step S12 in Figure 3). In the grinding process of step S12, the grinding wheel 7 is moved relatively to the grinding location on the workpiece W, and then the grinding wheel 7 is brought into contact with the workpiece W to perform processing. The grinding wheel 7 is then moved relatively to another grinding location on the workpiece W, and the grinding wheel 7 is brought into contact with the workpiece W to perform processing. In this way, when grinding one workpiece W, the grinding process includes an actual processing period in which the grinding wheel 7 is in contact with the workpiece W, and a non-processing period in which the grinding wheel 7 is not in contact with the workpiece W due to the movement of the grinding wheel 7.

The cutting procedure in step S12 is set in advance using numerical control, etc. Once cutting is completed according to the set procedure, the grinding device 2 stops the supply of coolant and the rotation of the workpiece W and grinding wheel 7 (step S13 in Figure 3), thereby completing the grinding process.

As described above, in this embodiment, the process from the start of rotation of the workpiece W and the supply of cooling liquid (step S11 in Figure 3) to the stop of rotation of the workpiece W and the supply of cooling liquid (step S13 in Figure 3) is called the grinding process (machining process) for one workpiece W.
The period from the start to the end of the grinding process is called the grinding process period.

After the grinding process is completed, the workpiece W is carried in and out of the grinding device 2 (step S5 in FIG. 3).
When the workpiece W is carried in or out, the shutter of the cover 2b is opened, and the grinding device 2 releases the workpiece W. The released workpiece W is gripped by the work transport device 3 and carried out to the outside of the cover 2b. The work transport device 3 also carries a new workpiece W to be machined into the cover 2b, and the workpiece W is supplied to the grinding device 2. When the workpiece W is supplied, the grinding device 2 holds the supplied workpiece W and closes the shutter of the cover 2b, as in step S3.

The grinding device 2 performs the grinding process on the new workpiece W (step S6 in FIG. 3). The grinding process is as described above.
After the grinding process is completed, the workpiece W is loaded into and unloaded from the grinding device 2 (step S7 in FIG. 3). The loading and unloading of the workpiece W is as described above.
The machining system 1 continuously grinds a plurality of workpieces W by repeating the grinding process by the grinding device 2 and the loading and unloading of the workpieces W.

When the grinding process of the last workpiece W among the plurality of workpieces W is completed, the last workpiece W is carried out (step S8 in FIG. 3).
When the workpiece W is removed, the workpiece W is released from the grinding device 2, and the workpiece transport device 3 carries the released workpiece W away.
Thereafter, the power supply of the grinding device 2 is switched from the on state to the off state (step S9 in FIG. 3), thereby completing the work process for grinding the plurality of workpieces W.

FIG. 4 is a block diagram showing an example of the configuration of the processing device 4.
In this embodiment, the processing device 4 and the sound collecting microphone 10 constitute an abnormality detection device 13 for the grinding device 2. That is, the abnormality detection device 13 includes the processing device 4 and the sound collecting microphone 10.
As shown in FIG. 4, the processing device 4 includes a processing unit 14 including a processor and the like, and a storage unit 16 including a memory and a hard disk.

The storage unit 16 stores computer programs to be executed by the processing unit 14, necessary information, and the like.
The processing unit 14 executes a computer program stored in a computer-readable non-transitory recording medium such as the storage unit 16 to realize various processing functions of the processing unit 14 .
The storage unit 16 also stores a determination model 16a and a sound data group 16b, which will be described later.
The sound data group 16b is a data group including a plurality of pieces of sound data acquired by the processing unit 14 during a predetermined period of time.

By executing the above-mentioned computer program, the processing unit 14 can perform the acquisition process 14a and the generation process 14b. These processes will be described later.

[Regarding the processing performed by the processing device]
FIG. 5 is a diagram showing an example of processing performed by the processing unit 14 of the processing device 4.
The processing unit 14 executes a process for determining whether or not an abnormality has occurred during the grinding process based on the sound data obtained from the output of the sound collecting microphone 10 .
As shown in FIG. 5, the processing unit 14 executes an acquisition process and a generation process.

The acquisition process is a process of acquiring sound data over time at predetermined acquisition intervals based on the output from the sound collection microphone 10 .
The generation process is a process of generating an abnormality determination process each time one piece of sound data is acquired in the acquisition process, and executing the generated abnormality determination processes in parallel.
The processing unit 14 can execute the acquisition process and the generation process in parallel.
The abnormality determination process will be explained later.

As shown in Fig. 5, the processing unit 14 starts acquiring sound data in the acquisition process (step S21 in Fig. 5). The processing unit 14 obtains sound pressure as sound data based on the output from the sound collection microphone 10. The processing unit 14 acquires the output from the sound collection microphone 10 at a predetermined sampling rate (e.g., 192 kHz). The sound data acquired by the processing unit 14 is a group of discrete sound pressure values arranged in time series.
The sound data is acquired over time at predetermined acquisition intervals. The processing unit 14 acquires the sound data as data for each acquisition interval during the acquisition process. Therefore, each sound data includes discrete values of sound pressure included in each acquisition interval.
The acquisition interval is, for example, one second.

When a predetermined acquisition interval has elapsed, the processing unit 14 finishes acquiring the sound data (step S23 in FIG. 5) and provides the acquired sound data to the abnormality determination process (step S23 in FIG. 5).
After providing the sound data to the abnormality determination process, the processing unit 14 again acquires sound data during the acquisition interval (step S23 in FIG. 5).
Every time the processing unit 14 acquires sound data at the acquisition interval, it provides the sound data to the abnormality determination process (steps S23 and S26 in FIG. 5).
In this embodiment, only sound data acquired at relatively short intervals is provided to the abnormality determination process, so the processing unit 14 can finish outputting sound data to the abnormality determination process before starting to acquire sound data for the next acquisition period.

In the generation process, the processing unit 14 generates an abnormality determination process each time sound data is acquired in the acquisition process.
5, when the acquisition of sound data is started in the acquisition process (step S21 in FIG. 5), the processing unit 14 generates a first abnormality determination process in the generation process (step S22 in FIG. 5). The generated first abnormality determination process is executed by the processing unit 14.
The sound data acquired in step S21 is provided to a first abnormality determination process (step S23 in FIG. 5).
The first abnormality determination process, to which the sound data is given, executes a determination of the presence or absence of an abnormality using the sound data.

In the acquisition process, sound data is provided to the abnormality determination process, and acquisition of sound data is resumed (step S23 in FIG. 5 ). In the generation process, the processing unit 14 generates a second abnormality determination process (step S25 in FIG. 5 ). The generated second abnormality determination process is executed by the processing unit 14.
The sound data acquired between steps S23 and S26 is provided to a second abnormality determination process (step S26 in FIG. 5).
The second abnormality determination process, to which the sound data is given, executes a determination of the presence or absence of an abnormality using the sound data.
The first abnormality determination process and the second abnormality determination process are executed in parallel.
Although only two abnormality determination processes are shown in FIG. 5, a larger number of abnormality determination processes, such as a third abnormality determination process and a fourth abnormality determination process, can be generated.

When the acquisition process is regarded as a parent process among the processes of the processing unit 14, steps S22 and S25 of the generation process are child processes generated by the parent process, and the abnormality determination process is a grandchild process generated by the child process.
These parallel processes are realized by forking. In the parent process, which is the acquisition process, a child process is generated by forking to generate the anomaly determination process. Furthermore, in the child process, a double fork is used to generate a grandchild anomaly determination process.

FIG. 6 is a flowchart showing an example of an abnormality determination process.
In the abnormality determination process, the processing unit 14 first updates the sound data group 16b stored in the storage unit 16 based on the sound data provided by the acquisition process (step S42 in FIG. 6).

FIG. 7 is a diagram for explaining the update of the sound data group.
7, the sound data group includes a plurality of pieces of sound data acquired during a predetermined period of time, and is a collection of sound data that are continuous over time.
When sound data is provided to the processing unit 14, the processing unit 14 adds the provided sound data to the sound data group 16b. The processing unit 14 also discards the oldest sound data among the sound data included in the sound data group 16b. As a result, the sound data group is updated to a new sound data group that includes the provided sound data.
In other words, in the abnormality determination process, the sound data group 16b used in the abnormality determination process is obtained based on other sound data groups of other abnormality determination processes generated before this abnormality determination process and the given sound data.

As will be explained later, sound data group 16b is discarded when an abnormality is determined in the abnormality determination process. Once sound data group 16b is discarded, when the sound data group is updated in the next abnormality determination process, only the given sound data becomes sound data group 16b. Furthermore, when the sound data group is updated in the next abnormality determination process, the given sound data is added to sound data group 16b to become the new sound data group 16b. In this way, once sound data group 16b is discarded, sound data is sequentially added by the continuously executed abnormality determination process. Sound data is added to sound data group 16b until sound data group 16b contains sound data for a predetermined period.

In this embodiment, the predetermined period is set to a period longer than the grinding processing period. In this embodiment, if the grinding processing period is 45 seconds, the predetermined period is 50 seconds.
Therefore, the sound data group 16b includes a maximum of 50 pieces of sound data.

In FIG. 6, after updating the sound data group 16b in step S42, the processing unit 14 determines whether the sound data group 16b includes sound data corresponding to the entire grinding processing period (step S43 in FIG. 6).
The processing unit 14 determines whether the sound data group 16b includes sound data corresponding to the grinding processing period based on the sound pressure indicated by the sound data included in the sound data group 16b.
If the sound data group 16b contains sound data whose maximum sound pressure value is equal to or greater than a predetermined threshold value Th continuously for the same period as the grinding processing period, the processing unit 14 determines that the sound data group 16b contains sound data corresponding to the grinding processing period.

Fig. 8 is a diagram showing an example of sound data acquired by the processing unit 14. In Fig. 8, the sound data acquired by the processing unit 14 is continuously shown along the time axis. In Fig. 8, the horizontal axis represents time, and the vertical axis represents sound pressure. The dark colored portions in Fig. 8 are graphs showing sound pressure. The light colored portions surrounded by dark colored portions above and below are graphs showing RMS (Root Mean Square) (volume).
8, the sound pressure appears higher during the grinding processing period P21 than during other periods. An interval period P22 between adjacent grinding processing periods P21 is a period for loading and unloading the workpiece W.

As shown in FIG. 8, the threshold value Th is set to an intermediate value between the maximum value of the sound pressure during the grinding processing period P21 and 0.
For example, in Fig. 8, assume that the square R1 represents a predetermined period. In this case, the sound data included in the portion surrounded by the square R1 is the sound data group 16b. In this case, the processing unit 14 determines that the sound data group 16b does not include sound data corresponding to the grinding processing period P21. This is because the sound data group 16b does not include sound data whose maximum sound pressure value is equal to or greater than the preset threshold value Th for the same consecutive period as the grinding processing period P21.
8, if the square R2 represents a predetermined period, the sound data included in the portion surrounded by the square R2 is the sound data group 16b. In this case, the processing unit 14 determines that the sound data group 16b includes sound data corresponding to the grinding processing period P21. This is because the sound data group 16b includes sound data whose maximum sound pressure value is equal to or greater than the preset threshold value Th continuously for the same period as the grinding processing period P21.

In FIG. 6, if it is determined in step S43 that the sound data group 16b does not include sound data corresponding to the entire grinding processing period P21, the processing unit 14 ends this abnormality determination process.
On the other hand, if it is determined that the sound data group 16b includes sound data corresponding to the entire grinding processing period P21, the processing unit 14 proceeds to step S44 and performs an abnormality determination (step S44 in FIG. 6).

The processing unit 14 performs abnormality determination based on the sound data group 16b.
The processing unit 14 uses a determination model 16a (FIG. 4) stored in the storage unit 16 to determine whether or not an abnormality occurs during the grinding process.

The determination model 16a is a model that is constructed in advance by machine learning using a group of sound data including sound data acquired during a grinding process period during normal grinding.
In this embodiment, the determination model 16a is constructed by semi-supervised learning or unsupervised learning using a Long Short-Term Memory (LSTM) or an autoencoder as a machine learning algorithm. However, the present invention is not limited to this, and a model may be obtained by supervised learning, or other algorithms may be adopted.

The processing unit 14 provides the sound data group 16b to the determination model 16a and determines whether or not there is an abnormality (step S44 in FIG. 6).
When determining whether or not there is an abnormality, the processing unit 14 outputs the determination result to the outside (step S45 in FIG. 6), and discards the sound data group 16b (step S46 in FIG. 6).
By discarding the sound data group 16b, the processing unit 14 acquires, as the sound data group 16b, sound data for the grinding processing period next to the grinding processing period for which the determination has been completed.
After discarding the sound data group 16b, the processing unit 14 ends the abnormality determination process.

[About the effects]
In this embodiment, each time sound data is acquired in the acquisition process, an abnormality determination process is generated and the determination of the presence or absence of an abnormality is executed in parallel. Therefore, in the acquisition process, it is not necessary to provide a large amount of sound data to the abnormality determination process in the generation process at once.
That is, as shown in FIG. 5, during the output period of the acquisition interval, only one piece of sound data acquired in one acquisition interval needs to be output.
As a result, the amount of data given at one time from the acquisition process to the abnormality determination process can be reduced, the period during which sound data cannot be acquired during the acquisition process can be eliminated, and the occurrence of data loss can be suppressed when determining whether or not there is an abnormality in the grinding process of the workpiece W using sound data.

Furthermore, in this embodiment, the sound data group is obtained based on the given sound data and other sound data groups of other abnormality determination processes generated before the current abnormality determination process, so multiple abnormality determination processes can be executed while updating the sound data group as sound data is acquired.

〔others〕
The embodiments disclosed herein are illustrative in all respects and are not restrictive.
In the above embodiment, the machining system 1 is configured to include a grinding device 2 as the machining device. However, the machining system 1 may also be configured to include a device that performs cutting, such as a lathe or a milling machine. However, in grinding, the volume of noise generated when the tool comes into contact with the workpiece is smaller than in cutting, etc., making it more difficult to distinguish between an actual machining period and a non-machining period. For this reason, it is preferable that the machining system 1 include a grinding device as the machining device.

Furthermore, in the above embodiment, an example was given in which sound pressure was obtained as sound data from the output of the sound collection microphone 10, but it is also possible to obtain and use the frequency spectrum of the sound as sound data.

The scope of the present invention is not limited to the above-described embodiment, but includes all modifications within the scope of equivalents to the configurations described in the claims.

1 Machining system 2 Grinding device 4 Processing device 13 Abnormality detection device 14 Processing unit 14a Acquisition processing 14b Generation processing 16b Sound data group W Workpiece

Claims (5)

An abnormality detection device for a machining device that performs machining processing on a workpiece,
a sound collecting unit that collects sounds from the machining device;
a processing device to which the output of the sound collection unit is given,
The processing device includes:
an acquisition process for acquiring sound data over time at predetermined acquisition intervals based on the output;
a generation process for generating an abnormality determination process each time the sound data is acquired in the acquisition process and executing the abnormality determination processes in parallel;
a processing unit that performs
the abnormality determination process is a process for determining whether a sound data group consisting of a plurality of pieces of sound data acquired during a period from the time when the sound data was acquired until a predetermined period in the past includes sound data corresponding to a machining processing period from the start to the end of the machining processing, and determining whether or not an abnormality exists based on the sound data group when it is determined that the sound data group includes sound data corresponding to the machining processing period;
An anomaly detection device in which the sound data group is obtained based on the sound data and other sound data groups of other anomaly determination processes generated before the anomaly determination process. An abnormality detection device for a machining device that performs machining processing on a workpiece,
a sound collecting unit that collects sounds from the machining device;
a processing device to which the output of the sound collection unit is given,
The processing device includes:
an acquisition process for acquiring sound data over time at predetermined acquisition intervals based on the output;
a generation process for generating an abnormality determination process each time the sound data is acquired in the acquisition process and executing the abnormality determination processes in parallel;
a processing unit that performs
the abnormality determination process is a process for determining whether a sound data group consisting of a plurality of pieces of sound data acquired during a period from the time when the sound data was acquired until a predetermined period in the past includes sound data corresponding to a machining processing period from the start to the end of the machining processing, and determining whether or not an abnormality exists based on the sound data group when it is determined that the sound data group includes sound data corresponding to the machining processing period;
The predetermined period is longer than the machining processing period. the sound data includes sound pressure;
3. The abnormality detection device according to claim 1, wherein the determination of whether the sound data group includes sound data corresponding to the machining processing period in the abnormality determination process is performed based on sound pressure. The abnormality detection device according to claim 1 or 2, wherein the machining device is a grinding device. a machining device that performs machining processing on a workpiece;
A machining system comprising: the abnormality detection device according to claim 1 or 2.