JP7762788B2 - Specially equipped vehicle load weight estimation system - Google Patents

Description

The present invention relates to a load weight estimation system for specially equipped vehicles.

In recent years, it has become common for large vehicles such as trucks to be equipped with a weight scale that measures their own weight (load weight).

Conventional gravity meters use load sensors attached to both ends of the front and rear axles to measure the load on each tire, front, rear, left and right, and calculate the load weight from the sum of the outputs of each load sensor.

Japanese Patent Application Laid-Open No. 2004-132871

However, conventional weight meters use a method of converting the total output of each load sensor into the loaded weight, which can make it difficult to measure the correct loaded weight when the vehicle is on an incline or when the load on the loading platform is not evenly balanced.

The present invention aims to provide a load weight estimation system for specially equipped vehicles that can accurately estimate load weight and notify the estimated results.

A load weight estimation system for special purpose vehicles according to one embodiment of the present invention includes an acquisition unit that acquires measurement data relating to the displacement amounts from a plurality of displacement sensors that respectively measure the displacement amounts of a plurality of parts of the special purpose vehicle on which the load of the load acts, an estimation unit that estimates the load weight by inputting the measurement data acquired by the acquisition unit into a learning model that is configured to output a calculation result regarding the load weight in response to the input of the measurement data relating to the displacement amounts, and a notification unit that notifies information regarding the load weight estimated by the estimation unit.
The displacement amount refers to at least one of "the magnitude of displacement occurring in the part itself" or "the magnitude of displacement of the part relative to other parts" when a load is applied to multiple parts of a specially equipped vehicle. Furthermore, the displacement sensor refers not only to sensors directly attached to the multiple parts, but also to sensors built into measuring members (e.g., load cells) attached to the parts.

It is preferable that the acquisition unit acquires measurement data related to the inclination of the vehicle from an inclinometer that measures the inclination, and the estimation unit estimates the load weight by inputting the measurement data of the displacement and the inclination acquired by the acquisition unit into a learning model configured to output a calculation result for the load weight in response to input of the measurement data related to the displacement and the inclination.

It is also preferable that the displacement sensors be attached to multiple locations on a structure fixed to the chassis frame, spaced apart in the longitudinal or lateral direction of the vehicle.

It is also preferable that the displacement sensors be attached to multiple locations on the axle, spaced apart in the longitudinal or lateral direction of the vehicle.

A load weight estimation system for a specially equipped vehicle according to one aspect of the present invention includes, for a specially equipped vehicle equipped with a hydraulic actuator for raising and lowering a cargo box, an acquisition unit that acquires measurement data related to the magnitude of hydraulic pressure acting on the hydraulic actuator from a pressure gauge that measures the magnitude of the hydraulic pressure acting on the hydraulic actuator; an identification unit that distinguishes between a first stop state in which the cargo box stops after being raised and a second stop state in which the cargo box stops after being lowered; an estimation unit that estimates the load weight of the cargo box by selectively using either a first learning model configured to output a calculation result for the load weight when measurement data including the magnitude of hydraulic pressure measured in the first stop state is input, or a second learning model configured to output a calculation result for the load weight when measurement data including the magnitude of hydraulic pressure measured in the second stop state is input, depending on the stop state identified by the identification unit; and a notification unit that notifies information related to the load weight estimated by the estimation unit.

It is also preferable that the device further includes a control unit that controls the operation of the hydraulic actuator so that the cargo box stops after being raised when an instruction to estimate the load weight is given, and when the cargo box stops after being raised under the control of the control unit, the estimation unit estimates the load weight of the cargo box by inputting the measurement data acquired by the acquisition unit into the first learning model.

Furthermore, it is preferable that the inputs to the first learning model and the second learning model further include at least one of the tilt angle, distortion, and temperature of the specially equipped vehicle.

It is also preferable to provide a calibration unit that calibrates the estimation results from the estimation unit according to individual specially equipped vehicles.

It is also preferable that the vehicle be provided with a determination unit that determines the loading status of the load based on the load weight estimated by the estimation unit, and that the notification unit notify the loading status in a manner that corresponds to the determination result of the determination unit.

It is also preferable that the notification unit includes a display device provided in a visible location on the shipping box in which the load is placed, and that the loading status is displayed on the display device in a display mode corresponding to the determination result.

It is also preferable that the vehicle is equipped with a status detection unit that detects the status of the vehicle, and that the notification unit notify information related to the status detected by the status detection unit.

Furthermore, it is preferable that the state detected by the state detection unit includes at least one of the state of the packing box in which the load is loaded and the loading state of the load.

This application makes it possible to accurately estimate the load weight and notify the estimated results.

1 is a side view showing the overall configuration of a specially equipped vehicle according to a first embodiment. FIG. 1 is a plan view showing the overall configuration of a specially equipped vehicle according to a first embodiment. FIG. FIG. 10 is a side view of the packing box in an upright position. FIG. 1 is a block diagram illustrating a configuration of a loaded weight estimation system. FIG. 10 is a conceptual diagram illustrating an example of a measurement value table. FIG. 2 is a schematic diagram illustrating the configuration of a learning model. 10 is a flowchart illustrating a procedure for generating a learning model. 10 is a flowchart illustrating a procedure for estimating a load weight using a learning model. FIG. 10 is a schematic diagram showing an example of a load weight display. 10 is a graph showing the measurement results. 10 is a graph showing the estimation results of a learning model. FIG. 10 is a side view showing the overall configuration of a specially equipped vehicle according to a second embodiment. FIG. 10 is an explanatory diagram illustrating a mechanism for lifting and lowering a cargo box in a specially equipped vehicle. 10 is a graph showing the relationship between the pitch angle of the truck chassis and the hydraulic pressure value. FIG. 11 is a block diagram illustrating the configuration of a loaded weight estimation system according to a third embodiment. FIG. 2 is a schematic diagram illustrating the configuration of a learning model. 11 is a flowchart illustrating a procedure for estimating a load weight in the third embodiment. FIG. 10 is a block diagram illustrating the configuration of a loaded weight estimation system according to a fourth embodiment. 13 is a flowchart illustrating a procedure for estimating a loaded weight in the fourth embodiment. FIG. 10 is an explanatory diagram illustrating a calibration method. 10 is a flowchart illustrating a procedure for notifying the loading state. FIG. 10 is a schematic diagram showing an example of notification of a loading state. FIG. 13 is a side view showing the overall configuration of a specially equipped vehicle according to a seventh embodiment. 13 is a flowchart illustrating a procedure of a process executed by an estimation device according to a seventh embodiment. 10 is a schematic diagram showing an example of notification of the state of a packing box. FIG. FIG. 20 is a schematic diagram illustrating the configuration of a learning model in embodiment 7. 10 is a schematic diagram showing an example of notification of the loading status of a shipping box. FIG.

The present invention will now be described in detail with reference to the drawings showing embodiments thereof.
(Embodiment 1)
Fig. 1 is a side view showing the overall configuration of a specially equipped vehicle 1 according to a first embodiment, Fig. 2 is a plan view thereof, and Fig. 3 is a side view with a cargo box in an upright position. The specially equipped vehicle 1 illustrated in Figs. 1 to 3 is a dump truck equipped with a truck chassis 2, which is a running section, and a dump device 3, which is an example of a mounting device mounted on the running section. In the following description, the front-rear, left-right, and up-down directions refer to the front-rear, left-right, and up-down directions as seen from the driver sitting in the driver's seat of the truck chassis 2. For the sake of explanation, Fig. 2 shows the state in which the dump device 3 has been removed.

The truck chassis 2 includes a cab 20 in which a driver's seat is located, and a chassis frame 21 that supports the cab 20. The chassis frame 21 is composed of a pair of left and right main frames (vertical joists) 21A, 21A extending in the fore-and-aft direction, and cross members (horizontal joists) 21B, 21B, ..., 21B that connect the pair of left and right main frames 21A, 21A (see Figure 2). The front wheels 22F and rear wheels 22R of the truck chassis 2 are rotatably attached to the main frames via a suspension system (not shown). The truck chassis 2 also includes an engine (prime mover) (not shown) and a transmission connected to the engine via a clutch, and is configured to travel by transmitting the driving force of the engine to the drive system of the drive wheels (e.g., front wheels 22F) via the transmission.

The dump truck 3 comprises a subframe 30 fixed to the chassis frame 21, and a cargo box 4 supported by the subframe 30 and in which loads such as earth and sand are placed. The cargo box 4 is supported rotatably around a hinge shaft 31 extending in the left-right direction at the rear end of the subframe 30. The cargo box 4 is a box body with an open top, and comprises a front panel 41 arranged to surround a rectangular bottom 40, a pair of left and right side panels 42, and a rear panel (rear flap) 43. The rear panel 43 is configured to be openable and closable.

The dump device 3 is equipped with a hoist mechanism 5 for tilting the cargo box 4. The hoist mechanism 5 includes, for example, a lift arm 51, a hydraulic cylinder 52, and a tension link 53. When the hydraulic cylinder 52 is retracted, the cargo box 4 is maintained in a horizontal position. On the other hand, when the hydraulic cylinder 52 is extended, the front of the cargo box 4 is lifted and rotates around the hinge shaft 31. As a result, the cargo box 4 tilts downward toward the rear, as shown in Figure 3.

The specially equipped vehicle 1 is equipped with various sensors that detect the vehicle condition. For example, the specially equipped vehicle 1 is equipped with strain sensors 81A-81D, which are an example of displacement sensors that measure the amount of displacement at multiple locations where the load of the cargo acts. Strain sensors 81A-81D are configured, for example, with strain gauges. Here, strain sensor 81A is attached near the right end of the axle 23F of the front wheel 22F, and strain sensor 81B is attached near the left end of the axle 23F of the front wheel 22F. Strain sensor 81C is attached near the right end of the axle 23R of the rear wheel 22R, and strain sensor 81D is attached near the left end of the axle 23R of the rear wheel 22R. Strain sensors 81A, 81B and strain sensors 81C, 81D are attached symmetrically, for example, with respect to the center line of the specially equipped vehicle 1 in the fore-and-aft direction. Strain sensors 81A-81D measure the amount of strain on axles 23F, 23R in response to load over time and output measurement data related to the measured amount of strain. In the following description, when there is no need to explain each of strain sensors 81A-81D individually, they will be referred to simply as strain sensor 81 (see Figure 4).

The specially equipped vehicle 1 may be equipped with an inclinometer 82 that measures the inclination of the truck chassis 2. The inclinometer 82 is attached to an appropriate location on the chassis frame 21 (for example, near the center in the fore-aft and lateral directions). The inclinometer 82 measures the fore-aft inclination (pitch) and lateral inclination (roll) of the truck chassis 2 in a time series and outputs measurement data related to the measured inclination. The specially equipped vehicle 1 may also be equipped with an inclinometer (not shown) that measures the inclination of the cargo box 4, and may acquire measurement data related to the fore-aft inclination (pitch) and lateral inclination (roll) of the cargo box 4 in a time series.

The specially equipped vehicle 1 may be equipped with a thermometer 83 that measures the temperature (ambient temperature) at and near the mounting position of the strain sensor 81. The ambient temperature measured by the thermometer 83 can be used to calibrate the value of the strain sensor 81, so the thermometer 83 is mounted in a location suitable for measuring the ambient temperature of the strain sensor 81. For example, the thermometer 83 is mounted in at least one location, such as the chassis frame 21, subframe 30, or axles 23F and 23R. The thermometer 83 measures the ambient temperature over time and outputs measurement data related to the measured temperature.

The specially equipped vehicle 1 may be equipped with a pressure gauge 84 that measures the cylinder pressure of the hydraulic cylinder 52. The pressure gauge 84 measures the cylinder pressure of the hydraulic cylinder 52 over time and outputs measurement data related to the measured cylinder pressure.

The specially equipped vehicle 1 is equipped with an estimation device 100 that estimates the weight of the cargo (load weight) based on measurement data including strain measured by the strain sensor 81. In this embodiment, the load weight represents the total weight of the components of the specially equipped vehicle 1 other than the running gear and mounting equipment, such as the cargo loaded in the cargo box 4, the occupants aboard the specially equipped vehicle 1, and the fuel carried in the specially equipped vehicle 1. Note that the total weight of the running gear and mounting equipment when no load is loaded (hereinafter referred to as the vehicle weight) is assumed to be known. The internal configuration of the estimation device 100 and the processing performed by the estimation device 100 will be described in detail later. In this embodiment, the load weight of the specially equipped vehicle 1 is estimated using a learning model LM1 that has learned the relationship between the measurement data including strain and the load weight of the specially equipped vehicle 1. The estimation device 100 is attached to the chassis frame 21, for example. Alternatively, the estimation device 100 may be provided inside the cab 20.

In this embodiment, a dump truck equipped with a dump device 3 will be described as an example of a specially equipped vehicle 1, but the specially equipped vehicle 1 is not limited to a dump truck and may be any specially equipped vehicle whose load weight can vary depending on the cargo, such as a dry van, refrigerated vehicle, liquid transport vehicle, powder transport vehicle, water tanker truck, sprinkler truck, or garbage collection vehicle.

The configuration of the loaded weight estimation system according to this embodiment will be described below.
4 is a block diagram illustrating the configuration of the load weight estimation system. The load weight display system includes an estimation device 100 that acquires measurement data including the amount of distortion measured by a distortion sensor 81 and estimates the load weight of the specially equipped vehicle 1 based on the acquired measurement data, and a display device 120 that notifies information related to the load weight estimated by the estimation device 100.

The estimation device 100 is a dedicated or general-purpose computer, and includes a control unit 101, a memory unit 102, an operation unit 103, an input unit 104, an output unit 105, and a communication unit 106.

The control unit 101 includes, for example, a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc. The ROM included in the control unit 101 stores control programs and the like that control the operation of each hardware component included in the estimation device 100. The CPU within the control unit 101 executes the control programs stored in the ROM and various computer programs stored in the storage unit 102 (described below) and controls the operation of each hardware component, thereby realizing the functions of the estimation device 100 in this embodiment. The RAM included in the control unit 101 temporarily stores data and the like used during calculations.

The control unit 101 is configured to include a CPU, ROM, and RAM, but may alternatively be one or more arithmetic circuits or control circuits including a GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), quantum processor, volatile or non-volatile memory, etc. The control unit 101 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given until when a measurement end instruction is given, and a counter that counts numbers.

The memory unit 102 includes a storage device such as a hard disk or flash memory. The memory unit 102 stores computer programs executed by the control unit 101, various data acquired from the outside, various data generated within the estimation device 100, and the like.

The computer programs stored in the memory unit 102 include a learning program PG1 for generating the learning model LM1, and an estimation program PG2 for estimating the load weight of the specially equipped vehicle 1 using the learning model LM1.

These computer programs may be provided on a non-transitory recording medium M on which the computer programs are recorded in a readable manner. The recording medium M is, for example, a portable memory such as a CD-ROM, USB memory, or SD (Secure Digital) card. The control unit 101 reads the various programs from the recording medium M using a reading device (not shown) and stores the various programs in the memory unit 102.

The memory unit 102 may include a measurement value table TB1 that stores measurement data obtained from the strain sensor 81, inclinometer 82, thermometer 83, and pressure gauge 84 in chronological order. Figure 5 is a conceptual diagram showing an example of the measurement value table TB1. The measurement value table TB1 stores the measurement data, associated with time (measurement time), for the amount of strain measured by the strain sensor 81, the tilt angle (pitch and roll) of the specially equipped vehicle 1 measured by the inclinometer 82, the ambient temperature measured by the thermometer 83, and the cylinder pressure of the hydraulic cylinder 52 measured by the pressure gauge 84. The measurement value table TB1 is prepared for each load weight, such as a table that stores measurement values measured with a fixed load weight of 1 ton, a table that stores measurement values measured with a fixed load weight of 2 tons, and a table that stores measurement values measured with a fixed load weight of 3 tons. The values stored in the measurement value table TB1 may be sensor output values or physical quantities converted from the sensor output values.

The memory unit 102 may include a learning model LM1 for estimating the load weight of the specially equipped vehicle 1 from measurement data including distortion amounts. The learning model LM1 is configured to output a calculation result related to the load weight when measurement data including distortion amounts is input. The learning model LM1 is defined by its definition information. The definition information for the learning model LM1 includes, for example, information specifying the structure of the learning model LM1 (type and number of layers, number of nodes, etc.) and parameters such as connection weights determined by learning. Details of the learning model LM1 will be described later.

The operation unit 103 is composed of switches, buttons, etc., and accepts various operations. The control unit 101 executes appropriate processing based on the operations accepted through the operation unit 103. Note that, in this embodiment, the estimation device 100 is configured to include the operation unit 103, but the operation unit 103 is not essential, and operations may be accepted via an externally connected device or the communication unit 106.

The input unit 104 has an interface for connecting various sensors, and sensors such as the strain sensor 81, inclinometer 82, thermometer 83, and pressure gauge 84 are connected to it. These sensors may be connected to the input unit 104 by wire or wirelessly. Measurement data relating to the amount of strain output from the strain sensor 81, measurement data relating to the inclination of the specially equipped vehicle 1 output from the inclinometer 82, measurement data relating to the temperature output from the thermometer 83, measurement data relating to the cylinder pressure of the hydraulic cylinder 52 output from the pressure gauge 84, etc. are input to the input unit 104 as appropriate.

The output unit 105 has an output interface for connecting a display device 120 such as an LCD monitor. The display device 120 is provided, for example, near the driver's seat in the cab 20. Alternatively, the display device 120 may be provided on the rear side of the front panel 41. The output interface provided in the output unit 105 may be an output interface that outputs analog video signals, or an output interface that outputs digital video signals such as DVI (Digital Visual Interface) or HDMI (High-Definition Multimedia Interface, registered trademark). The output unit 105 outputs display data to the display device 120 so that the load weight estimation result using the learning model LM1 is displayed on the display device 120, for example.

In this embodiment, the display device 120 is connected to the outside of the estimation device 100, but the estimation device 100 may also be equipped with the display device 120.

The communication unit 106 includes a communication interface for transmitting and receiving various data to and from external devices. Examples of devices with which the estimation device 100 communicates via the communication unit 106 include various ECUs (Electronic Controller Units) and PLCs (Programmable Logic Controllers) installed in the specially equipped vehicle 1. In this case, the communication unit 106 may include, for example, a communication port compliant with RS-485 to communicate with the various ECUs and PLCs installed in the specially equipped vehicle 1, or a communication interface compliant with a communication standard for in-vehicle communication such as CAN (Controller Area Network). Other examples of devices with which the estimation device 100 communicates via the communication unit 106 include a server device installed outside the specially equipped vehicle 1 and a mobile terminal carried by the user. In this case, the communication unit 106 may include a communication interface compliant with a wireless communication standard such as Wi-Fi (registered trademark), 3G, 4G, 5G, or LTE (Long Term Evolution) to communicate with an external server device or the like.

The learning model LM1 will be described below.
6 is a schematic diagram illustrating the configuration of the learning model LM1. The learning model LM1 in this embodiment is, for example, a support vector regression model, and includes an input layer to which various measurement data are input, an intermediate layer including a kernel that performs predetermined calculations based on the measurement data input to the input layer, and an output layer that combines outputs from the intermediate layer and outputs the calculation results.

The input, intermediate, and output layers of the learning model LM1 each contain one or more nodes, and the nodes in each layer are connected in one direction to the nodes in the previous and next layers via connection weights. In a support vector machine that has been nonlinearly extended using the kernel trick, the connection weights from the intermediate layer to the output layer are adaptively determined through learning. On the other hand, the connection weights from the input layer to the intermediate layer are fixed and are mechanically determined from the training data.

Measurement data including strain amounts is input to the input layer of learning model LM1. For example, as shown in FIG. 6, measurement data related to the strain amount of the right front axle (strain amount measured by strain sensor 81A), the strain amount of the left front axle (strain amount measured by strain sensor 81B), the strain amount of the right rear axle (strain amount measured by strain sensor 81C), the strain amount of the left rear axle (strain amount measured by strain sensor 81D), tilt including roll and pitch (tilt measured by inclinometer 82), and environmental temperature (temperature measured by thermometer 83) are input to the input layer of learning model LM1.

Measurement data input to the input layer is weighted by connection weights determined using training data and output to the middle layer. The middle layer performs calculations using kernels based on the data input from the input layer. Data calculated in each kernel in the middle layer is weighted by connection weights determined through learning and output to the output layer. The output layer outputs calculation results related to the load weight by combining the data input from the middle layer. Here, the calculation results output by the output layer may be an estimated load weight value or a probability that a certain load weight applies. In the latter case, the output layer is composed of multiple nodes, and the first node outputs the probability that the load weight is 1 ton, the second node the probability that the load weight is 2 tons, ..., and the Nth node (N is an integer greater than or equal to 2) the probability that the load weight is N tons, outputting the probability of a certain load weight.

The learning model LM1 shown in FIG. 6 is configured to output a calculation result related to the load weight in response to input measurement data related to the amount of strain measured by the strain sensor 81, the inclination measured by the inclinometer 82, and the ambient temperature measured by the thermometer 83. However, the input/output relationship in the learning model LM1 is not limited to the above and can be set as appropriate. For example, the learning model LM1 may be configured to output a calculation result related to the load weight in response to input measurement data further including the cylinder pressure of the hydraulic cylinder 52 measured by the pressure gauge 84. The learning model LM1 may also be configured to input measurement data related to the amount of strain measured by the strain sensor 81 and output a calculation result related to the load weight. Furthermore, two or three selected measurement data from the measurement data of the strain sensors 81A to 81D may be input to the learning model LM1 and output a calculation result related to the load weight. The learning model LM1 may also be configured to input measurement data related to the amount of strain and either measurement data related to the inclination or the ambient temperature and output a calculation result related to the load weight.

Furthermore, the control unit 101 may perform preprocessing to correct the amount of distortion measured by the distortion sensor 81 using the environmental temperature measured by the thermometer 83, and input data including the corrected amount of distortion to the learning model LM1.

During the learning phase prior to the start of operation, the estimation device 100 collects measurement data including distortion amounts and uses the collected measurement data as training data for learning, thereby generating the learning model LM1 described above.

Figure 7 is a flowchart illustrating the procedure for generating the learning model LM1. Prior to learning, the control unit 101 of the estimation device 100 collects measurement data including strain measured by multiple strain sensors 81 (step S101). At this time, the control unit 101 collects measurement data including strain with a fixed load weight. When sufficient measurement data for that load weight is obtained, the control unit 101 changes the load weight and collects measurement data including strain at the changed load weight. The control unit 101 sequentially collects measurement data while changing the load weight. In this way, measurement data including strain when the load weight is changed in various ways is obtained. Note that the orientation of the specially equipped vehicle 1 when measuring strain and other parameters may be horizontal or may be inclined in various ways, such as with the front downward, rear downward, left downward, or right downward. The load weight may be determined by loading items of known weight into the shipping box 4, or may be measured using a measuring instrument such as a truck scale. The measurement data collected in step S101 is stored for each load weight in the measurement value table TB1 of the memory unit 102.

The type of measurement data collected in step S101 may be selected depending on the configuration of the learning model LM1 to be generated. For example, when generating a learning model LM1 that outputs a calculation result related to the load weight in response to input measurement data related to the amount of distortion, inclination, and environmental temperature, the control unit 101 may collect measurement data related to the amount of distortion measured by the distortion sensor 81, the inclination measured by the inclinometer 82, and the environmental temperature measured by the thermometer 83. The same applies to generating a learning model LM1 with a different input/output relationship from the above. For example, when generating a learning model LM1 that outputs a calculation result related to the load weight in response to input measurement data related to the amount of distortion, the control unit 101 may collect only measurement data related to the amount of distortion measured by the distortion sensor 81.

After collecting the measurement data, the control unit 101 reads and executes the learning program PG1 from the memory unit 102, thereby performing the following processing.

The control unit 101 selects a set of training data from the measurement value table TB1 (step S102). The training data includes a series of measurement data measured at the same time and the load weight value when this measurement data was obtained.

Next, the control unit 101 inputs the selected training data into the learning model LM1 (step S103) and executes calculations using the learning model LM1 (step S104). That is, the control unit 101 inputs measurement data such as distortion, tilt, and environmental temperature into the nodes that make up the input layer of the learning model LM1, executes calculations using kernels in the intermediate layer, and outputs the calculation results from the output layer. Note that in the initial stage before learning begins, initial values are assigned to the definition information describing the learning model LM1.

Next, the control unit 101 evaluates the calculation result obtained in step S104 (step S105) and determines whether learning is complete (step S106). Specifically, the control unit 101 can evaluate the calculation result using an error function (also referred to as an objective function, loss function, or cost function) based on the calculation result obtained in step S104 and the training data. For example, the control unit 101 may determine that learning is complete when the error function becomes equal to or less than a threshold (or equal to or greater than a threshold) during the process of optimizing (minimizing or maximizing) the error function using a gradient descent method such as steepest descent. Note that to avoid the problem of overfitting, techniques such as cross-validation and early termination may be used to terminate learning at an appropriate time.

If it is determined that learning is not complete (S106: NO), the control unit 101 updates the connection weights between nodes in the learning model LM1 (step S107), returns the process to step S102, and continues learning using other training data. The control unit 101 can update the connection weights between nodes using the backpropagation method, which sequentially updates the connection weights between nodes from the output layer to the input layer of the learning model LM1.

If it is determined that learning is complete (S106: YES), the control unit 101 stores the learned learning model LM1 in the memory unit 102 (step S108) and terminates the processing according to this flowchart.

As described above, the estimation device 100 according to this embodiment can generate a learning model LM1 by collecting measurement data including distortion amounts when the load weight is known and using the load weight and measurement data as training data.

In this embodiment, the learning model LM1 is generated in the estimation device 100, but an external server (not shown) that generates the learning model LM1 may be provided, and the learning model LM1 may be generated by the external server. In this case, the external server may acquire training data collected by the specially equipped vehicle 1 via communications or the like, and generate the learning model LM1 using the acquired training data. Furthermore, the estimation device 100 may acquire the trained learning model LM1 from the external server via communications or the like, and store the acquired learning model LM1 in the memory unit 102.

During the operational phase, the estimation device 100 can estimate the load weight by inputting measurement data including the amount of distortion into the trained learning model LM1.

Figure 8 is a flowchart explaining the procedure for estimating the load weight using the learning model LM1. The control unit 101 of the estimation device 100 reads and executes the estimation program PG2 from the memory unit 102, thereby performing the following processing.

When the control unit 101 acquires measurement data including strain amounts measured by multiple strain sensors 81 via the input unit 104, it inputs the acquired measurement data to the learning model LM1 (step S121) and executes a calculation using the learning model LM1 (step S122). At this time, the control unit 101 provides the acquired measurement data to the nodes constituting the input layer of the learning model LM1. The data provided to the input layer is weighted by connection weights determined using the training data and output to the intermediate layer. In the intermediate layer, a calculation using a kernel is performed, and the data is weighted by connection weights determined by learning and output to the output layer. The nodes in the output layer output the calculation results related to the load weight.

The control unit 101 estimates the load weight based on the calculation results of the learning model LM1 (step S123). If the learning model LM1 is configured to output an estimated value of the load weight, the control unit 101 can estimate the output value of the learning model LM1 as the load weight. Also, if the learning model LM1 is configured to output the probability of a certain load weight, the control unit 101 can estimate the load weight by selecting the load weight value with the highest probability.

Next, the control unit 101 notifies the estimated load weight (step S124). At this time, the control unit 101 outputs information on the estimated load weight from the output unit 105 and displays it on the display device 120. Figure 9 is a schematic diagram showing an example of a load weight display. Figure 9 shows an example in which information on the estimated load weight, loading rate, and estimated date and time is displayed as text information on the display device 120. Here, the estimated load weight is the value of the load weight estimated using the above-mentioned learning model LM1. The loading rate is a value calculated as the ratio of the load weight (estimated value) to the upper limit value. The estimated date and time is the date and time when the load weight was estimated using the learning model LM1, and is information obtained, for example, from the built-in clock of the control unit 101. The control unit 101 generates display screen data based on the estimated load weight estimated using the learning model LM1, the load rate calculated as a percentage of the upper limit, and date and time information obtained from the built-in clock, and outputs the generated display screen data to the display device 120, thereby causing the display device 120 to display a screen such as that shown in Figure 9.

In this embodiment, the estimated load weight is displayed as text information on the display device 120, but the estimated load weight may also be displayed schematically as a graph or meter display.
Furthermore, in this embodiment, the estimated load weight is displayed on the display device 120, but the information on the estimated load weight may be sent to a user terminal or the like by transmitting it from the communication unit 106. If an audio output device such as a speaker is connected to the estimation device 100, the information on the estimated load weight may be output as audio.

Below, an example of actual measured values of the measurement data and estimation results using the learning model LM1 is shown.
Fig. 10 is a graph showing the measurement results. The graph shown in Fig. 10 shows the results of measurements of the strain amount, tilt angle, and environmental temperature using a strain sensor 81, an inclinometer 82, and a thermometer 83 while the specially equipped vehicle 1 is stopped while traveling on a public road with a load of a known weight (4000 kg in this example), the load is unloaded at the destination, and the vehicle continues traveling without the load. The horizontal axis of the graph represents elapsed time (more precisely, the measurement timing), and the vertical axis represents the strain amount (μST), tilt angle (degrees), or environmental temperature (°C).

In the graph shown in Figure 10, the strain amount of the right front axle represents the strain amount measured by strain sensor 81A attached near the right end of axle 23F of front wheel 22F. Similarly, the strain amounts of the left front axle, right rear axle, and left rear axle represent the strain amounts measured by strain sensors 81B to 81D attached near the left end of axle 23F of front wheel 22F, near the right end of axle 23R of rear wheel 22R, and near the left end of axle 23R of rear wheel 22R, respectively. Furthermore, inclination (roll and pitch) represents the inclination angle (roll and pitch) of the specially equipped vehicle 1 measured by inclinometer 82, and environmental temperature represents the temperature measured by thermometer 83. As shown in Figure 10, the strain amount measured by strain sensor 81 includes measurement values when the specially equipped vehicle 1 is tilted within a range of ±5 degrees in the fore-aft and lateral directions, as well as measurement values when the environmental temperature changes variously. These measurement values are associated with elapsed time and stored in the measurement value table TB1.

Figure 11 is a graph showing the estimation results of learning model LM1. The horizontal axis of the graph represents elapsed time, and the vertical axis represents the estimated load weight (kg). In the example of Figure 11, a portion of the measurement data when the load weight was 4,000 kg (see Figure 10) and a portion of the measurement data when the load weight was 0 kg (not shown) were used as training data to generate learning model LM1, and the remaining measurement data was input into the trained learning model LM1 to estimate the load weight of special purpose vehicle 1. More specifically, of the 4,809 sets of measured values of the measured distortion, tilt angle, and ambient temperature, 70% were used as training data to generate learning model LM1, and the remaining 30% were input into learning model LM1 to estimate the load weight of special purpose vehicle 1. Note that the measurement data is not limited to load weights of 4,000 kg and 0 kg; measurement data based on other load weights can also be used.

The solid line (after correction) shows the estimation results using the trained learning model LM1. For reference, the dashed line (before correction) shows the measurement results of the load weight measured using a conventional weight scale. When the load weight of special purpose vehicle 1 is 4000 kg, the conventional weight scale shows measurement values ranging from approximately 2200 kg to 4500 kg, with an error of ±1150 kg with a median value of 3350 kg. In contrast, when the load weight of special purpose vehicle 1 was estimated using learning model LM1, an estimated value of approximately 4000 ±50 kg was obtained, demonstrating that the load weight can be estimated more accurately than with a conventional weight scale.

Note that the estimation results shown in Figure 11 are those of a learning model LM1 generated using as training data a portion of the measurement data when the load weight is 4000 kg and a portion of the measurement data when the load weight is 0 kg. However, it is possible to estimate various load weights by collecting measurement data with various load weights and generating a learning model LM1 using the collected measurement data.

Furthermore, Figure 11 shows the results of estimating the load weight using the learning model LM1 configured to output a calculation result related to the load weight in response to input measurement data related to the amount of strain measured by the strain sensor 81, the inclination measured by the inclinometer 82, and the environmental temperature measured by the thermometer 83. However, the input/output relationship in the learning model LM1 is not limited to the above and can be set as appropriate. As described above, the learning model LM1 may be configured to output a calculation result related to the load weight in response to input measurement data further including the cylinder pressure of the hydraulic cylinder 52 measured by the pressure gauge 84. Furthermore, the learning model LM1 may be configured to input measurement data related to the amount of strain measured by the strain sensor 81 and output a calculation result related to the load weight. Furthermore, two or three selected measurement data from the measurement data of the strain sensors 81A to 81D may be input to the learning model LM1 and output a calculation result related to the load weight. Furthermore, the learning model LM1 may be configured to input either measured data on the amount of distortion or measured data on the inclination or ambient temperature, and output a calculation result related to the load weight.

As described above, in this embodiment, by using the learning model LM1 that has learned the relationship between measurement data including distortion and load weight, it is possible to accurately estimate the load weight regardless of whether the special purpose vehicle 1 is tilted or not, and to notify the estimated load weight.

In this embodiment, a support vector regression model has been described as an example of the learning model LM1, but other regression analysis methods such as linear regression and logistic regression may also be used. Furthermore, learning models trained using methods such as methods using search trees such as decision trees, regression trees, random forests, and gradient boosting trees; Bayesian estimation methods including naive Bayes; time series prediction methods including AR (Auto Regressive), MA (Moving Average), and state space models; clustering methods including K-nearest neighbor methods; ensemble learning methods including boosting and bagging; clustering methods including hierarchical clustering, non-hierarchical clustering, and topic models; association analysis; and other methods including emphasis filtering may also be used. Furthermore, the learning model LM1 may be configured using a deep learning neural network, a convolutional neural network, a recurrent neural network, or the like.

In the above embodiment, the strain sensor 81 is made up of a strain gauge, but the present invention is not limited to this. The strain sensor 81 can also be a strain gauge type load cell. In this case, the shape of the load cell can be either bar-type or pin-type.

While the strain sensor 81 was attached to the axles 23F, 23R or the subframe 30 in the above embodiment, the present invention is not limited to this configuration and the strain sensor 81 may be attached to other locations. For example, the strain sensor may be attached to the cargo box 4 of the dump truck 3 or to the hinge shaft 31 connecting the cargo box 4 to the subframe 30. The strain sensor 81 may also be attached to the chassis frame 21 or the suspension system (not shown). For example, when attaching the strain sensor to the suspension system, it is useful to measure the degree to which the mounting location of the strain sensor 81 sinks compared to other locations. Therefore, in such cases, a displacement sensor (such as a laser distance sensor) may be used that measures the amount of sinking relative to other locations rather than measuring the strain at the mounting location. Note that when measuring displacement amounts such as sinking, the measurement is likely to be affected by the air pressure of the front wheels 22F or rear wheels 22R of the specially equipped vehicle 1. Therefore, it is preferable to use a tire pressure monitor or the like to add this measurement data to the measurement value table TB1.

In addition, in the above embodiment, the estimation device 100 was provided inside the chassis frame 21 or cab 20 of the specially equipped vehicle 1, but the present invention is not limited to this. The estimation device 100 may be provided in a location separate from the specially equipped vehicle 1, such as a management center. In this case, the specially equipped vehicle 1 may be provided with various sensors such as a strain sensor 81, an inclinometer 82, a thermometer 83, and a pressure gauge 84, as well as a communication device and a display device, and data from these various sensors may be transmitted to the estimation device 100 via the communication device. The estimation device 100 may process the data received from the various sensors and transmit the results to the communication device of the specially equipped vehicle 1, thereby displaying the estimated load weight on the display device of the specially equipped vehicle 1.

Furthermore, in the above embodiment, the load weight is estimated based on measurement data relating to the amount of strain from multiple strain sensors 81. However, it is also possible to estimate the load weight based on other indicators, such as measurement data relating to hydraulic pressure changes from multiple hydraulic sensors. For example, a hydraulic load cell may be installed near the hinge axis 31, along with a pressure gauge 84 that measures the cylinder pressure of the hydraulic cylinder 52 in the hoist mechanism 5. In this case, the hydraulic cylinder 52 is slightly extended to slightly tilt the cargo box 4, and the load weight is estimated based on the hydraulic pressure measurement data from the pressure gauge 84 and the load cell. Such measurement data is not limited to the above-mentioned strain, hydraulic pressure, etc., and other displacement amounts can also be measured as appropriate.

(Embodiment 2)
In the first embodiment, measurement data relating to the amount of strain is acquired from the strain sensor 81 attached to the axles 23F, 23R, but the attachment location of the strain sensor 81 is not limited to the axles 23F, 23R.
In the second embodiment, a configuration in which a strain sensor 81 is attached to a structure fixed to the chassis frame 21 will be described.

Figure 12 is a side view showing the overall configuration of a specially equipped vehicle 1 according to embodiment 2. The specially equipped vehicle 1 shown in Figure 12 differs from embodiment 1 only in the location where the strain sensors 81 are attached. In embodiment 2, the strain sensors 81 are attached to multiple locations on a structure fixed to the chassis frame 21. One example of a structure fixed to the chassis frame 21 is the subframe 30. The example in Figure 12 shows a configuration in which the strain sensors 81 are attached to two locations on the subframe 30, spaced apart in the fore-and-aft direction.

In Figure 12, the strain sensors 81 are attached to two locations spaced apart in the fore-and-aft direction of the subframe 30, but the strain sensors 81 may also be attached to two locations symmetrical to the left and right about the center line of the specially equipped vehicle 1 in the fore-and-aft direction. Furthermore, the number of attached strain sensors 81 is not limited to two, and strain sensors 81 may be attached to three or more locations. Furthermore, a dedicated bracket for attaching the strain sensors 81 may be prepared, and the strain sensors 81 may be attached to the subframe 30 via the dedicated bracket.

The estimation device 100 generates a learning model LM1 similar to that in embodiment 1 using measurement data including the amount of strain measured by the strain sensor 81 attached to the subframe 30, and can estimate the weight of the cargo loaded in the shipping box 4 using the generated learning model LM1.

As described above, in the second embodiment, the strain sensor 81 is attached to the subframe 30, making it possible to estimate the load weight without making any modifications to the truck chassis 2.

(Embodiment 3)
In embodiment 3, a configuration is described in which the magnitude of the hydraulic pressure acting on a hydraulic actuator (in this embodiment, hydraulic cylinder 52) for raising and lowering the cargo box 4 is measured, and the load weight is estimated based on the measured magnitude of the hydraulic pressure.

Figure 13 is an explanatory diagram illustrating the lifting mechanism for the cargo box 4 in the specially equipped vehicle 1. The specially equipped vehicle 1 is equipped with a hoist mechanism 5 as a mechanism for lifting and lowering the cargo box 4. As described above, the hoist mechanism 5 includes a lift arm 51, a hydraulic cylinder 52, and a tension link 53. When the hydraulic cylinder 52 of the hoist mechanism 5 is extended, the front of the cargo box 4 is lifted and the cargo box 4 rotates in a direction that increases the tilt angle. In this embodiment, the rotation of the cargo box 4 in a direction that increases the tilt angle is also referred to as the cargo box 4 being raised. On the other hand, when the hydraulic cylinder 52 of the hoist mechanism 5 is contracted, the front of the cargo box 4 is lowered and the cargo box 4 rotates in a direction that decreases the tilt angle. In this embodiment, the rotation of the cargo box 4 in a direction that decreases the tilt angle is also referred to as the cargo box 4 being lowered.

The hydraulic mechanism that extends and retracts the hydraulic cylinder 52 includes a hydraulic pump 61, hydraulic oil tank 62, and control valve 63. The hydraulic pump 61, which serves as the hydraulic supply source, is driven by power from the engine 70 transmitted via a PTO (Power Take-Off) 71. It draws hydraulic oil from the hydraulic oil tank 62 through hydraulic piping 64 and supplies the hydraulic oil (pressurized oil) to the hydraulic cylinder 52 through a main pipe 65 connected to the discharge port. The power transmission of the engine 70 can be connected or disconnected using a PTO switch 72 located inside the cab 20.

The supply direction of hydraulic oil discharged from the hydraulic pump 61 is switched by a control valve 63 operated by a manual operating lever 67. For example, when the control valve 63 is in the neutral position due to the operation of the operating lever 67, hydraulic oil is not supplied from the hydraulic pump 61 to the hydraulic cylinder 52, and the cargo box 4 does not tilt. When the operating lever 67 is operated to the raised position, the control valve 63 is switched, and hydraulic oil (pressurized oil) is supplied from the hydraulic pump 61 to the hydraulic cylinder 52. The hydraulic cylinder 52 extends as the hydraulic oil is supplied, raising the cargo box 4. On the other hand, when the operating lever 67 is operated to the lowered position, the control valve 63 is switched, and the hydraulic oil supplied to the hydraulic cylinder 52 flows back to the hydraulic oil tank 62. As a result, the hydraulic cylinder 52 contracts, lowering the cargo box 4.

The hydraulic mechanism is provided with a pressure gauge 84 for measuring the magnitude of the hydraulic pressure acting on the hydraulic cylinder 52. The specially equipped vehicle 1 is also provided with an inclinometer 82 for measuring the inclination (pitch and roll) of the truck chassis 2 and an inclinometer 85 for measuring the inclination (pitch and roll) of the cargo box 4. The specially equipped vehicle 1 may also be provided with the strain sensor 81 and thermometer 83 described in embodiment 1.

The inventors of the present application conducted a detailed investigation into the relationship between the pitch angle of the truck chassis 2 and the hydraulic pressure value, and discovered that a gap occurs between the hydraulic pressure value when the cargo box 4 is stopped after being raised and the hydraulic pressure value when the cargo box 4 is stopped after being lowered.

Figure 14 is a graph showing the relationship between the pitch angle of the truck chassis 2 and the hydraulic pressure value. The horizontal axis of the graph represents the pitch angle (deg) of the truck chassis 2, and the vertical axis represents the hydraulic pressure value (MPa). The graph shown in Figure 14 shows the results of measuring the hydraulic pressure value while varying the pitch angle of the truck chassis 2 and the known load weight of the cargo box 4. When the pitch angle is less than 0 degrees, the specially equipped vehicle 1 is in a downward-facing position at the front, and when the pitch angle is greater than 0 degrees, the specially equipped vehicle 1 is in a upward-facing position at the front.

In the graph of Figure 14, the black circles indicate the oil pressure values measured when the cargo box 4 is raised and then stopped at a predetermined dump angle (e.g., 0.5 degrees). The white circles indicate the oil pressure values measured when the cargo box 4 is lowered and then stopped at a predetermined dump angle (e.g., 0.5 degrees). The dump angle is the relative angle of the cargo box 4 with respect to the truck chassis 2, and is calculated by subtracting the tilt angle of the truck chassis 2 (measured by the inclinometer 82) from the tilt angle of the cargo box 4 (measured by the inclinometer 85).

Furthermore, each dashed line in the graph of Figure 14 is a regression line of multiple black circles measured when the pitch angle of the truck chassis 2 is changed at a predetermined known load weight (e.g., 10 tons) among all the black circles on the graph. Furthermore, each dot-dash line in the graph of Figure 14 is a regression line of multiple white circles measured when the pitch angle of the truck chassis 2 is changed at a predetermined known load weight (e.g., 10 tons) among all the white circles on the graph.

From the graph shown in Figure 14, it can be seen that even with the same load weight, the hydraulic pressure value increases as the pitch angle of the truck chassis 2 decreases (the more downward the front). It can also be seen that even with the same load weight, a gap occurs between the hydraulic pressure value measured when the cargo box 4 is raised and then stopped at a specified dump angle (hydraulic pressure value indicated by a black circle) and the hydraulic pressure value measured when the cargo box 4 is lowered and then stopped at a specified dump angle (hydraulic pressure value indicated by a white circle). It can also be seen that this gap widens as the load weight increases.

The load weight estimation system in embodiment 3 estimates the weight of the cargo (load weight) loaded on the cargo box 4 using measurement data including hydraulic pressure values. The inventors' studies have found that a gap occurs between the hydraulic pressure values when the cargo box 4 is stopped after being raised and the hydraulic pressure values when the cargo box 4 is stopped after being lowered. Therefore, the load weight estimation system in embodiment 3 estimates the load weight using different learning models when the cargo box 4 is stopped after being raised and when the cargo box 4 is stopped after being lowered.

Figure 15 is a block diagram illustrating the configuration of a loaded weight estimation system in embodiment 3. The estimation device 100 includes a control unit 101, a memory unit 102, an operation unit 103, an input unit 104, an output unit 105, and a communication unit 106. The configuration of each of these hardware units is the same as that described in embodiment 1, so a description thereof will be omitted.

In embodiment 3, a distinction is made between a state in which the cargo box 4 has stopped after rising (first stopped state) and a state in which the cargo box 4 has stopped after falling (second stopped state), and different learning models are used for each state to estimate the load weight of the cargo box 4. That is, in embodiment 3, a learning model LM10 is prepared for estimating the load weight using measurement data including hydraulic pressure values measured in the first stopped state, and a learning model LM20 is prepared for estimating the load weight using measurement data including hydraulic pressure values measured in the second stopped state. The learning models LM10 and LM20 are defined by their respective definition information and are stored, for example, in the memory unit 102. The definition information for the learning models LM10 and LM20 includes parameters that define the model structure, such as the type and number of layers and the number of nodes, as well as parameters determined by learning, such as the connection weights set between nodes.

When the control unit 101 of the estimation device 100 acquires measurement data including hydraulic pressure values measured in the first stop state, it inputs the acquired measurement data to the learning model LM10 and estimates the load weight of the cargo box 4 by performing calculations using the learning model LM10. Furthermore, when the control unit 101 acquires measurement data including hydraulic pressure values measured in the second stop state, it inputs the acquired measurement data to the learning model LM20 and estimates the load weight of the cargo box 4 by performing calculations using the learning model LM20. A metering switch 89, which is provided inside the cab 20 and is used to issue an instruction to start the estimation process, may be connected to the input unit 104 of the estimation device 100.

Figure 16 is a schematic diagram illustrating the configuration of learning models LM10 and LM20. Learning models LM10 and LM20 are similar to learning model LM1 described in embodiment 1, and comprise an input layer to which various measurement data is input, an intermediate layer in which predetermined calculations are performed based on the measurement data input to the input layer, and an output layer that combines outputs from the intermediate layer and outputs the calculation results.

Figure 16A shows the configuration of the learning model LM10. The input layer of the learning model LM10 receives the hydraulic pressure value measured by the pressure gauge 84 in the first stop state (the state after the cargo box 4 has stopped rising). The measurement data input to the input layer of the learning model LM10 may further include at least one of the tilt angle of the truck chassis 2 measured by the inclinometer 82, the distortion of the axles 23F, 23R measured by the distortion sensor 81, and the ambient temperature measured by the thermometer 83. The ambient temperature may be the ambient temperature of the specially equipped vehicle 1 or the oil temperature. The middle layer has multiple layers, each composed of multiple nodes. When the above measurement data is input to the input layer of the learning model LM10, the control unit 101 of the estimation device 100 performs a predetermined calculation using parameters set for each node constituting the middle layer. The output layer combines the outputs from the middle layers and outputs an estimated value of the load weight of the cargo box 4 as the calculation result.

The learning model LM10 is trained to output information related to an estimated value of the load weight of the shipping box 4 in response to the input of the various measurement data described above. When generating the learning model LM10, for example, the estimation device 100 collects the various measurement data described above while varying the weight (known) of the cargo to be loaded onto the shipping box 4. The estimation device 100 uses a dataset containing a large number of the collected measurement data and known load weights as training data, and trains the learning model LM10 to output information related to an estimated value of the load weight in response to the input of measurement data. The learning algorithm is the same as in embodiment 1, so its description is omitted. The learning model LM10 may be generated on an external server (not shown). In this case, the estimation device 100 may acquire the learning model LM10 via communication and store it in the memory unit 102.

Figure 16B shows the configuration of learning model LM20. Learning model LM20 differs from learning model LM10 in that the hydraulic pressure value in the second stopped state (the state after the lowering of the cargo box 4 has stopped) is input to the input layer instead of the hydraulic pressure value in the first stopped state, but the rest of the configuration is the same as learning model LM10. Learning model LM20 is generated by learning using measurement data including the hydraulic pressure value measured in the second stopped state and a dataset including the known load weight as training data.

Figure 17 is a flowchart explaining the procedure for estimating the load weight in embodiment 3. The control unit 101 of the estimation device 100 monitors the signal input through the input unit 104 to determine whether the weighing switch 89 has been turned on (step S301). If the switch has not been turned on (S301: NO), the control unit 101 waits until the weighing switch 89 is turned on.

When the weighing switch 89 is turned on (S301: YES), the control unit 101 starts the load weight estimation process. When the estimation process starts, the control unit 101 may instruct the user to adjust the dump angle to a predetermined angle. The predetermined angle is, for example, an angle in the range of greater than 0.1 degrees and less than 0.8 degrees. The control unit 101 may instruct the user by displaying text information on the display device 120, or by outputting audio from a speaker (not shown). In embodiment 3, the dump angle is manually adjusted using the operating lever 67.

The control unit 101 sequentially acquires measurement data of the tilt angle measured over time by the inclinometers 82 and 85 via the input unit 104, and detects the current dump angle based on the acquired measurement data (step S302). The control unit 101 can determine the dump angle by subtracting the tilt angle of the truck chassis 2 obtained as the measurement value of the inclinometer 82 from the tilt angle of the cargo box 4 obtained as the measurement value of the inclinometer 85. The control unit 101 stores the detected dump angles in chronological order in the memory unit 102.

The control unit 101 determines whether the dump angle detected in step S302 is greater than the minimum angle θ1 (step S303). The minimum angle θ1 is a value set as the minimum value of the angle range suitable for measuring the load weight of the cargo box 4. An example of the minimum angle θ1 is 0.1 degrees.

If it is determined that the current dump angle is equal to or less than the minimum angle θ1 (S303: NO), the control unit 101 instructs the user to raise the cargo box 4 (step S304). The control unit 101 instructs the user by displaying text information on the display device 120 instructing the user to raise the cargo box 4. Alternatively, the control unit 101 may instruct the user by outputting audio from a speaker (not shown) instructing the user to raise the cargo box 4. After instructing the user, the control unit 101 returns the process to step S302.

If it is determined that the current dump angle is greater than the minimum angle θ1 (S303: YES), the control unit 101 determines whether the current dump angle is less than the maximum angle θ2 (step S305). The maximum angle θ2 is a value set as the maximum value of the angle range suitable for measuring the load weight of the cargo box 4. An example of the maximum angle θ2 is 0.8 degrees.

If it is determined that the current dump angle is equal to or greater than the maximum angle θ2 (S305: NO), the control unit 101 instructs the user to lower the cargo box 4 (step S306). The control unit 101 instructs the user, for example, by displaying text information on the display device 120 instructing the user to lower the cargo box 4. Alternatively, the control unit 101 may instruct the user by outputting audio from a speaker (not shown) instructing the user to lower the cargo box 4. After instructing the user, the control unit 101 returns the process to step S302.

If it is determined that the current dump angle is smaller than the maximum angle θ2 (S305: YES), the control unit 101 references the output of the built-in timer and determines whether a predetermined time has elapsed since the dump angle entered the set angle range (step S307). If the predetermined time has not elapsed (S307: NO), the control unit 101 waits until the predetermined time has elapsed.

If it is determined that the predetermined time has elapsed (S307: YES), the control unit 101 determines whether the cargo box 4 was stationary until the predetermined time elapsed (step S308). The control unit 101 can determine whether the cargo box 4 was stationary by determining whether there has been a change in the dump angle history data stored in the memory unit 102. If the cargo box 4 was not stationary (S308: NO), the control unit 101 returns the process to step S302.

If the container 4 remains stationary for the predetermined time (S308: YES), the control unit 101 notifies the user that the load weight is ready to be weighed (step S309). The control unit 101, for example, causes the display device 120 to display text information indicating that the load weight is ready to be weighed. Alternatively, the control unit 101 may cause a speaker (not shown) to output a sound indicating that the load weight is ready to be weighed.

Next, the control unit 101 determines whether the cargo box 4 has stopped after being raised (step S310). The control unit 101 can determine whether the cargo box 4 has stopped after being raised from the dump angle history data stored in the memory unit 102.

If the control unit 101 determines that the container 4 has stopped after rising (S310: YES), it sets the learning model used to estimate the load weight to the learning model LM10 for stopping ascent (step S311). On the other hand, if the control unit 101 determines that the container 4 has stopped after falling (S310: NO), it sets the learning model used to estimate the load weight to the learning model LM20 for stopping descent (step S312).

The control unit 101 acquires measurement data including hydraulic pressure values from the input unit 104 and inputs the acquired measurement data into the learning model LM10 for stopping ascent set in step S311 or the learning model LM20 for stopping descent set in step S312, thereby estimating the load weight of the cargo box 4 (step S313). At this time, the control unit 101 provides the acquired measurement data to each node constituting the input layer of the learning model LM10 (or learning model LM20), performs calculations using the intermediate layer, and acquires the calculation results output from the output layer, thereby estimating the load weight of the cargo box 4. Note that the measurement data provided to the nodes in the input layer may be hydraulic pressure values only, or may further include, in addition to hydraulic pressure values, at least one of the tilt angle of the truck chassis 2, distortion of the axles 23F, 23R, and ambient temperature.

Next, the control unit 101 notifies the user of the estimated load weight (step S314). At this time, the control unit 101 outputs information about the estimated load weight from the output unit 105 and displays it on the display device 120. The control unit 101 may display the load weight information as text information on the display device 120, or may use a schematic display method such as a graph or meter display. The control unit 101 may also be configured to output the estimated load weight information as audio from a speaker (not shown). After this series of processes is completed, the weighing switch 89 is turned off, and the cargo box 4 is lowered until the dump angle becomes 0 degrees.

The inventors of the present application have found that the hydraulic pressure value measured by the pressure gauge 84 differs between when the cargo box 4 stops after rising and when it stops after falling, even if the dump angle is the same. For this reason, if the same learning model is used to estimate the load weight for both cases, the estimation accuracy may be low. However, in embodiment 3, the load weight is estimated by selectively using the learning model LM10 for stopping when the cargo box 4 rises and the learning model LM20 for stopping when the cargo box 4 falls, so the decrease in estimation accuracy can be suppressed.

(Fourth embodiment)
In the fourth embodiment, a configuration for automatically adjusting the dump angle will be described. Note that the configuration of the specially equipped vehicle 1 is the same as that of the third embodiment, and therefore a description thereof will be omitted.

Figure 18 is a block diagram illustrating the configuration of a loaded weight estimation system according to embodiment 4. The loaded weight estimation system according to embodiment 4 includes an estimation device 100 and a lifting control device 200 connected to the estimation device 100. The estimation device 100 is similar to that described in embodiment 3, and includes a control unit 101, a memory unit 102, an operation unit 103, an input unit 104, an output unit 105, and a communication unit 106.

The lifting control device 200 has an input unit 201, a control unit 202, and an output unit 203, and controls the operation of the hydraulic mechanism equipped in the specially equipped vehicle 1 to control the lifting and lowering of the cargo box 4. The input unit 201 has an input interface. Information output from the estimation device 100, operation information of the operating lever 67, operation information of the PTO switch 72, etc. are input to the input unit 201. The information input to the input unit 201 is output to the control unit 202.

The control unit 202 is configured, for example, by a PLC (Programmable Logic Controller). The control unit 202 generates a control signal for controlling the lifting and lowering of the container 4 based on information input through the input unit 201 in accordance with programmed logic. The control unit 202 outputs the generated control signal to the control valve 63 via the output unit 203. The output unit 203 is equipped with an output interface, and is connected to the control valve 63, the estimation device 100, and the like. Note that the control valve 63 in embodiment 4 is configured as an electrically controllable electromagnetic control valve.

In this embodiment, the load weight estimation system is configured to include the estimation device 100 and the lifting control device 200 as separate entities, but the two may also be integrated into one unit.

Figure 19 is a flowchart explaining the procedure for estimating the load weight in embodiment 4. The control unit 101 of the estimation device 100 monitors the signal input through the input unit 104 to determine whether the weighing switch 89 has been turned on (step S401). If the switch has not been turned on (S401: NO), the control unit 101 waits until the weighing switch 89 is turned on.

If the metering switch 89 is turned on (S401: YES), the control unit 101 determines whether the PTO switch 72 is on (step S402). If the PTO switch 72 is not on (S402: NO), the control unit 101 instructs the user to turn on the PTO switch 72 (step S403) and switches the power transmission destination of the engine 70 to the hydraulic pump 61. The instruction to the user may be given by displaying text information on the display device 120, or by outputting audio from a speaker (not shown).

If the PTO switch 72 is on (S402: YES), the control unit 101 notifies the user that the dump angle will be adjusted (step S404). The control unit 101, for example, causes the display device 120 to display text information indicating that the dump angle will be adjusted. Alternatively, the control unit 101 may cause a speaker (not shown) to output a sound indicating that the dump angle will be adjusted.

Next, the control unit 101 instructs the lifting control device 200 to lift the cargo box 4 (step S405). Specifically, the control unit 101 generates a control signal instructing the lifting control device 200 to lift the cargo box 4, and issues the instruction to the lifting control device 200 by outputting the generated control signal to the lifting control device 200 from the output unit 105. In response to the instruction from the estimation device 100, the control unit 202 of the lifting control device 200 outputs a control signal to the control valve 63 to lift the cargo box 4, thereby lifting the cargo box 4.

The control unit 101 sequentially acquires measurement data of the tilt angle measured over time by the inclinometers 82 and 85 via the input unit 104, and detects the current dump angle based on the acquired measurement data (step S406).

The control unit 101 determines whether the dump angle detected in step S406 is greater than the minimum angle θ1 (step S407). The minimum angle θ1 is a value set as the minimum value of the angle range suitable for measuring the load weight of the cargo box 4. An example of the minimum angle θ1 is 0.1 degrees.

If it is determined that the current dump angle is equal to or less than the minimum angle θ1 (S407: NO), the control unit 101 returns the process to step S405 and continues controlling the lifting of the cargo box 4.

If it is determined that the current dump angle is greater than the minimum angle θ1 (S407: YES), the control unit 101 determines whether the current dump angle is less than the maximum angle θ2 (step S408). The maximum angle θ2 is a value set as the maximum value of the angle range suitable for measuring the load weight of the cargo box 4. An example of the maximum angle θ2 is 0.8 degrees.

If it is determined that the current dump angle is equal to or greater than the maximum angle θ2 (S408: NO), the control unit 101 issues an error notification (step S409) because the tilt angle of the cargo box 4 is outside the angle range suitable for measuring the load weight, and ends the processing according to this flowchart. After issuing the error notification, the control unit 101 may instruct the lifting control device 200 to lower the cargo box 4.

If it is determined that the current dump angle is less than the maximum angle θ2 (S408: YES), the control unit 101 instructs the cargo box 4 to stop after being raised (step S410). Specifically, the control unit 101 generates a control signal instructing the cargo box 4 to stop, and outputs the generated control signal to the lifting/lowering control device 200 from the output unit 105, thereby instructing the lifting/lowering control device 200. In response to the instruction from the estimation device 100, the control unit 202 of the lifting/lowering control device 200 stops the cargo box 4 by outputting a control signal to the control valve 63 to stop the cargo box 4.

Next, the control unit 101 notifies the user that the load weight is ready to be weighed (step S411). The control unit 101, for example, causes the display device 120 to display text information indicating that the load weight is ready to be weighed. Alternatively, the control unit 101 may cause a speaker (not shown) to output audio information indicating that the load weight is ready to be weighed.

Next, the control unit 101 sets the learning model used to estimate the load weight to the learning model LM10 for stopping lifting (step S412). The control unit 101 acquires measurement data including hydraulic pressure values from the input unit 104 and inputs the acquired measurement data into the learning model LM10 for stopping lifting set in step S412, thereby estimating the load weight of the cargo box 4 (step S413).

The control unit 101 then notifies the user of the estimated load weight (step S414). At this time, the control unit 101 outputs information about the estimated load weight from the output unit 105 and displays it on the display device 120. The control unit 101 may display the load weight information as text information on the display device 120, or may use a schematic display method such as a graph or meter display. The control unit 101 may also be configured to output the estimated load weight information as audio information from a speaker (not shown).

The control unit 101 may estimate the load weight, notify the user, and then instruct the lifting control device 200 to lower the cargo box 4. In response to the instruction from the estimation device 100, the control unit 202 of the lifting control device 200 may lower the cargo box 4 by outputting a control signal for lowering the cargo box 4 to the control valve 63.

When measuring the load weight manually, the dump angle must be adjusted to a specified angle (e.g., 0.5 degrees), which can be cumbersome for the user. In contrast, in this embodiment, the load weight can be measured automatically by operating the weighing switch 89, reducing the cumbersomeness of the operation.

In addition, in embodiment 4, the load weight is estimated after the lifting of the cargo box 4 has stopped, so the memory unit 102 only needs to store the learning model LM10 for lifting stop, and does not need to store the learning model LM20 for lowering stop.

Fifth Embodiment
In the fifth embodiment, a configuration will be described in which the estimation results of the learning model LM1 are calibrated according to each specially equipped vehicle 1.

Figure 20 is an explanatory diagram illustrating the calibration method. In embodiment 5, a calibration layer CL is provided downstream of the learning model LM1. The calibration layer CL calibrates the output (load weight) of the learning model LM1 according to each individual special purpose vehicle 1. The parameters used for calibration are determined when the special purpose vehicle 1 is shipped. For example, the output of the learning model LM1 when a load of a known weight is loaded can be obtained, and parameters that convert the output of the learning model LM1 into the actual load weight can be derived in advance. For example, if the output of the learning model LM1 is X1 and the actual load weight is X2, parameters a and b can be derived to satisfy X2 = aX1 + b.

The memory unit 102 of the estimation device 100 stores calibration parameters (parameters a and b in the above example) that have been derived in advance. When the control unit 101 inputs measurement data into the learning model LM1 and obtains the calculation results of the learning model LM1, it reads the calibration parameters stored in the memory unit 102 and calibrates the calculation results, thereby obtaining an estimated value of the calibrated load weight.

As described above, in embodiment 5, the calculation results of the learning model LM1 can be calibrated to accommodate multiple specially equipped vehicles 1 with different sizes, shapes, weights, etc. of cargo boxes 4. Therefore, there is no need to generate a learning model LM1 that is dependent on each individual specially equipped vehicle 1; instead, a standard learning model can be generated in an external computer and installed in each estimation device 100.

The above-described calibration technique can be applied not only to the learning model LM1 described in embodiment 1, but also to the learning models LM10 and LM20 described in embodiment 3, and the learning model LM2 described in embodiment 7 below.

(Embodiment 6)
In the sixth embodiment, a configuration will be described in which the loading state is determined from the estimated loading weight and the loading state is notified in a manner according to the determination result.

Figure 21 is a flowchart explaining the procedure for reporting the loading status. The control unit 101 of the estimation device 100 executes the following processing, for example, at regular intervals after the loading operation into the shipping box 4 has begun.

The control unit 101 estimates the load weight using a procedure similar to that shown in the flowchart of Figure 8. That is, the control unit 101 inputs measurement data including the amount of distortion measured by the multiple distortion sensors 81 into the learning model LM1 (step S601), performs calculations using the learning model LM1 (step S602), and estimates the load weight based on the calculation results of the learning model LM1 (step S603).

The control unit 101 determines the loading status based on the estimated loading weight (step S604). For example, the control unit 101 stores the estimated loading weight in its internal memory, compares the estimated loading weight in step S603 with a preset upper limit, and determines that the loading status is "loadable" if there is still room for the estimated loading weight (for example, if it is less than 90% of the upper limit). The control unit 101 may also compare the estimated loading weight with a preset upper limit and determine that the loading status is "close to the upper limit" if the estimated loading weight is close to the upper limit (for example, if it is greater than 90% but less than 100% of the upper limit). Furthermore, the control unit 101 may determine that the loading status is "loading stopped" if the estimated loading weight reaches the upper limit. Furthermore, the control unit 101 may determine that the loading status is "overloaded" if the estimated loading weight exceeds the preset upper limit.

The control unit 101 notifies the loading status in a manner corresponding to the determination result of step S604 (step S605).

Figure 22 is a schematic diagram showing an example of loading status notification. Figure 22 shows the specially equipped vehicle 1 as viewed from the rear. In the example of Figure 22, the display device 120 is composed of an indicator light that can light up, flash, or turn off in blue or red, and is located at the top of the rear side of the front panel 41.

Figure 22A shows an example of a notification when the loading status is determined to be "loading permitted." When the control unit 101 determines that the current loading status is "loading permitted" based on the loading weight estimated using the learning model LM1, it executes control to cause the display device 120 to flash, for example, in blue once per second. As a result, the display device 120 transitions from an off state to a state in which it flashes slowly in blue. By checking the display mode on the display device 120 (in this case, slow flashing in blue), the worker can determine that the current loading status is "loading permitted."

Figure 22B shows an example of a notification when it is determined that the loading status is "close to the upper limit." When the control unit 101 determines that the current loading status is "close to the upper limit" based on the loading weight estimated using the learning model LM1, it executes control to cause the display device 120 to flash, for example, in blue five times per second. As a result, the display device 120 transitions from a slow flashing state to a fast flashing state. By checking the display mode on the display device 120 (in this case, fast flashing in blue), the worker can understand that the current loading status is "close to the upper limit."

Figure 22C shows an example of a notification when the loading status is determined to be "loading stop." When the control unit 101 determines that the current loading status is "loading stop" based on the loading weight estimated using the learning model LM1, it executes control to, for example, light up the display device 120 in blue. As a result, the display device 120 transitions from a flashing blue state to a lit state. By checking the display mode on the display device 120 (in this case, lit in blue), the worker can understand that the current loading status is "loading stop."

Figure 22D shows an example of a notification when the loading status is determined to be "overloaded." When the control unit 101 determines that the current loading weight is "overloaded" based on the loading weight estimated using the learning model LM1, it executes control to cause the display device 120 to flash, for example, in red. As a result, the display device 120 transitions from a lit blue state to a flashing red state. By checking the display mode on the display device 120 (in this case, flashing red), the worker can determine that the current loading status is "overloaded."

As described above, in this embodiment, the current loading status of the shipping box 4 can be notified to the worker by changing the display mode on the display device 120.

In this embodiment, as an example, a configuration in which the display device 120 is provided at the top rear side of the front panel 41 has been described, but the installation location of the display device 120 is not limited to the location shown in FIG. 22 and may be installed in any location that is visible to the operator. For example, the display device 120 may be installed on the side of the front panel 41, or on a side panel 42 or rear panel 43 other than the front panel 41. The display device 120 may also be installed near the driver's seat. Furthermore, a configuration in which a notification is sent via communication to a mobile device carried by the operator may also be used.

In addition, in this embodiment, the display mode on the display device 120 is configured to vary depending on the loading status by changing the color and lighting/flashing state, but characters or figures corresponding to the loading status may also be displayed on the display device 120. Furthermore, the loading status may be notified not only by display on the display device 120 but also by sound or voice.

Seventh Embodiment
In the seventh embodiment, a configuration will be described in which the state of the vehicle is detected and information relating to the detected state of the vehicle is notified.

Figure 23 is a side view showing the overall configuration of a specially equipped vehicle 1 according to embodiment 7. In addition to the configuration described above, the specially equipped vehicle 1 according to embodiment 7 is equipped with an inclinometer 85 that measures the inclination of the loading platform, and an imaging device 86 that captures images of the inside of the loading box 4. The specially equipped vehicle 1 may further be equipped with a GPS (Global Positioning System) receiver 87 that determines the current position of the vehicle.

The inclinometer 85 is attached to an appropriate location on the cargo box 4, measures the fore-and-aft tilt (pitch) of the cargo box 4 over time, and outputs measurement data related to the measured tilt to the estimation device 100. In addition to the fore-and-aft tilt (pitch) of the cargo box, the inclinometer 85 may also measure the left-and-right tilt (roll) over time.

The imaging device 86 is installed, for example, to capture images of the area from the top of the front panel 41 diagonally downward and rearward, and captures images of the inside of the cargo box 4 in a time-series manner. The imaging device 86 is equipped with a solid-state imaging element, such as a CMOS (Complementary Metal Oxide Semiconductor), and outputs digital image data obtained from the solid-state imaging element to the estimation device 100. It is more preferable that the imaging device 86 be one that can acquire distance information, such as a stereo camera or a range image sensor.

The GPS receiver 87 receives radio waves transmitted from GPS satellites (not shown) and chronologically measures the current position of the specially equipped vehicle 1. The GPS receiver 87 outputs position information related to the current position of the specially equipped vehicle 1 to the estimation device 100.

Figure 24 is a flowchart illustrating the processing steps executed by the estimation device 100 in embodiment 7. When the control unit 101 of the estimation device 100 acquires measurement data output from the inclinometer 85 via the input unit 104 (step S701), it determines the state of the cargo box 4 based on the acquired measurement data (step S702). At this time, the control unit 101 may determine whether the cargo box 4 is inclined (lifted up) relative to the chassis frame 21. The control unit 101 may also calculate the height of the top of the cargo box 4 (vehicle height) from the angle of inclination as the state of the cargo box 4.

The control unit 101 notifies the user of the status of the cargo box 4 determined in step S702 (step S703). Figure 25 is a schematic diagram showing an example of notification of the status of the cargo box 4. The control unit 101 can notify the user of the status of the dump truck by outputting text or graphics indicating the status of the dump truck from the output unit 105 to the display device 120. Figure 25A shows a state in which text information indicating that dumping is in progress is displayed on the display device 120. Figure 25B shows a state in which a schematic display indicating that the height of the top of the cargo box 4 has reached 4.8 m is displayed on the display device 120. The control unit 101 may also output an alert if the calculated height of the top of the cargo box 4 exceeds a set value.

When the control unit 101 acquires image data output from the imaging device 86 via the input unit 104 (step S704), it determines the loading status of the shipping box 4 based on the acquired image data (step S705). The control unit 101 can determine the loading status using, for example, a learning model LM2 (see FIG. 26) configured to output information related to the loading status in response to input image data of the interior of the shipping box 4.

Figure 26 is a schematic diagram illustrating the configuration of learning model LM2 in embodiment 7. Learning model LM2 in embodiment 7 is, for example, a learning model using CNN (Convolutional Neural Networks), and includes an input layer, an intermediate layer, and an output layer. Learning model LM2 is trained in advance to output information regarding, for example, the height of the loaded object in response to input image data obtained by capturing an image of the inside of a shipping box 4.

The input layer receives image data from the imaging device 86, which captures an image of the inside of the shipping box 4. The image data input to the input layer is sent to the intermediate layer via the nodes that make up the input layer.

The intermediate layer is composed of, for example, a convolutional layer, a pooling layer, and a fully connected layer. Multiple convolutional layers and pooling layers may be provided, alternating between them. The convolutional layer and pooling layer extract features of the image input through the input layer through calculations using the nodes of each layer. The fully connected layer combines the data from which features have been extracted by the convolutional layer and pooling layer into one node, and outputs feature variables transformed by an activation function. The feature variables are output to the output layer via the fully connected layer.

The output layer has one or more nodes. Based on the feature variables input from the fully connected layer in the intermediate layer, the output layer converts them into probabilities using a softmax function and outputs an estimation result regarding the height of the cargo. The output form of the estimation result from the output layer is arbitrary. For example, the output layer can be composed of n nodes from the first node to the nth node, and each node constituting the output layer can output a probability regarding the height of the cargo, such as the probability that the height of the cargo exceeds the upper limit from the first node, the probability that the height of the cargo has reached the upper limit from the second node, the probability that the height of the cargo is 90% of the upper limit from the third node, the probability that the height of the cargo is 80% of the upper limit from the fourth node, etc. The number of nodes constituting the output layer and the content output from each node are not limited to the above and can be designed as appropriate.

The estimation device 100 can generate a learning model LM2 as shown in FIG. 26 by collecting a large amount of image data captured by the imaging device 86 and data on the height of the cargo when the image data was captured (e.g., actual measurements), and learning using the collected image data and height data as training data. Also, instead of generating the learning model LM2 in the estimation device 100, an external server may generate the learning model LM2 and acquire the trained learning model LM2 from the external server. The estimation device 100 stores the learning model LM2 generated by the device itself or the learning model LM2 acquired from the external server in the memory unit 102.

When the control unit 101 of the estimation device 100 acquires image data output from the imaging device 86 in step S704 of the flowchart shown in FIG. 26, it inputs the acquired image data into learning model LM2 and performs calculations using learning model LM2. The control unit 101 references the calculation results from learning model LM2 and determines the loading state (height of the loaded items in this example). At this time, the control unit 101 can determine the loading state of the shipping box 4 by selecting the state with the highest probability from the probabilities output from each node in the output layer.

The control unit 101 notifies the loading status of the shipping box 4 determined in step S705 (step S706). Figure 27 is a schematic diagram showing an example of notifying the loading status of the shipping box 4. The control unit 101 can notify the loading status by outputting text information indicating the height of the loaded items from the output unit 105 to the display device 120. The example in Figure 27 shows a state in which text information indicating that the height of the loaded items exceeds the upper limit is displayed on the display device 120.

As described above, in this embodiment, the state of the specially equipped vehicle 1 can be detected and the detected state of the specially equipped vehicle 1 can be notified to the occupants.

In the flowchart shown in Figure 24, the loading status is determined and notified after the status of the cargo box 4 is determined and notified, but these steps may be performed in any order. Furthermore, only one of determining and notifying the status of the cargo box 4 or determining and notifying the loading status may be performed.

In addition, in this embodiment, a configuration has been described in which the state of the specially equipped vehicle 1 is detected by detecting the state of the cargo box 4 and the state of the cargo in the cargo box 4, and the detection results are reported. However, the inclination (roll and pitch) of the specially equipped vehicle 1 measured by the inclinometer 82 and the upper limit value for the inclination may also be reported.

In addition, in this embodiment, the status of the specially equipped vehicle 1 is displayed on the display device 120, but it may also be notified to an external management server. In this case, an identifier that identifies the specially equipped vehicle 1 and the location information of the specially equipped vehicle 1 measured by the GPS receiver 87 may be added, and the location information and status of the specially equipped vehicle 1 may be managed by the management server for each specially equipped vehicle 1. Furthermore, the display device 120 is not limited to being installed in a visible location on the cargo box 4, but may also be a mobile terminal such as a smartphone carried by the worker.

In addition, in this embodiment, the height of the cargo is estimated using learning model LM2, but the height of the cargo may also be estimated by analyzing the image obtained from the imaging device 86 and identifying the height position of the cargo within the image.

The embodiments disclosed herein should be considered in all respects as illustrative and not restrictive. The scope of the present invention is indicated by the claims, not by the meaning described above, and is intended to include all modifications within the meaning and scope of the claims.

For example, in this embodiment, the specially equipped vehicle 1 is described as a dump truck equipped with an estimation device 100 that estimates the load weight, a display device 120 that displays information related to the load weight estimated by the estimation device 100, and a dump device 3. However, the present invention is not limited to dump trucks and can be applied to various specially equipped vehicles. For example, the present invention can be applied to specially equipped vehicles such as refuse trucks, mixer trucks, tank trucks, suction trucks, and container loading/unloading vehicles.

Furthermore, in Embodiments 1 to 7, the special purpose vehicle 1 is configured to include the estimation device 100, but the estimation device 100 may also be a computer provided external to the special purpose vehicle 1. For example, the computer may be a server device that is communicatively connected to a control device mounted on the special purpose vehicle 1. In this case, the estimation device 100 may acquire measurement data such as strain, hydraulic pressure, tilt angle, and temperature from the control device mounted on the special purpose vehicle 1 via communication, and input the acquired measurement data into a learning model LM1, etc., to estimate the load weight of the special purpose vehicle 1.

REFERENCE SIGNS LIST 1 Specially equipped vehicle 2 Truck chassis 3 Dump device 4 Cargo box 5 Hoist mechanism 20 Cab 21 Chassis frame 22F Front wheels 22R Rear wheels 23F, 23R Axles 30 Subframe 81 Strain sensor 82 Inclinometer 83 Thermometer 84 Pressure gauge 85 Inclinometer 86 Imaging device 87 GPS receiver 100 Estimation device 101 Control unit 102 Memory unit 103 Operation unit 104 Input unit 105 Output unit 106 Communication unit PG1 Learning program PG2 Estimation program TB1 Measurement value table LM1, LM2 Learning model

Claims (8)

an acquisition unit that acquires measurement data relating to the magnitude of hydraulic pressure acting on a hydraulic actuator from a pressure gauge that measures the magnitude of hydraulic pressure acting on the hydraulic actuator for a specially equipped vehicle that is equipped with a hydraulic actuator for raising and lowering a cargo box;
an identification unit that distinguishes and identifies a first stop state in which the container is stopped after being raised and a second stop state in which the container is stopped after being lowered;
an estimation unit that estimates the load weight of the shipping box by selectively using either a first learning model configured to output a calculation result for the load weight when measurement data including the magnitude of hydraulic pressure measured in the first stop state is input according to the stop state identified by the identification unit, or a second learning model configured to output a calculation result for the load weight when measurement data including the magnitude of hydraulic pressure measured in the second stop state is input;
and a notification unit that notifies information related to the load weight estimated by the estimation unit. a control unit that controls the operation of the hydraulic actuator so that the container stops after being raised when a load weight estimation instruction is given,
2. The special purpose vehicle load weight estimation system according to claim 1, wherein, when the loading box is stopped after being raised by the control of the control unit, the estimation unit estimates the load weight of the loading box by inputting the measurement data acquired by the acquisition unit into the first learning model. The system for estimating the load weight of a specially equipped vehicle according to claim 1 , wherein the input to the first learning model and the second learning model further includes at least one of an inclination angle, a distortion, and a temperature of the specially equipped vehicle. The system for estimating a load weight of a specially equipped vehicle according to claim 1 , further comprising a calibration unit that calibrates the estimation result by the estimation unit according to each individual specially equipped vehicle. a determination unit that determines a loading state of a load on the specially equipped vehicle in accordance with the load weight estimated by the estimation unit,
The system for estimating the load weight of a specially equipped vehicle according to claim 1, wherein the notification unit notifies the load state in a manner corresponding to the determination result of the determination unit. 6. The specially equipped vehicle load weight estimation system according to claim 5, wherein the notification unit includes a display device provided in a visible portion of a cargo box in which the load is loaded, and displays the loading status on the display device in a display mode corresponding to the determination result. a state detection unit that detects the state of the vehicle;
The system for estimating the load weight of a specially equipped vehicle according to claim 1 , wherein the notification unit notifies information about the state detected by the state detection unit. The system for estimating the load weight of a specially equipped vehicle according to claim 7, wherein the state detected by the state detection unit includes at least one of a state of a packing box in which the load is loaded and a loading state of the load.