Industrial vehicle control device, industrial vehicle, and industrial vehicle control program

Abstract

To provide a control device of an industrial vehicle, an industrial vehicle, and a control program of the industrial vehicle capable of improving accuracy of estimating a state of the industrial vehicle.SOLUTION: A control device 100 acquires a first signal and a second signal such that estimation of an industrial vehicle can be performed accurately by using a plurality of signals rather than a single signal. A data processing unit 42 performs data processing based on time series data of the first signal and the second signal. The data processing unit 42 can perform the data processing based on the time series data of the first signal and the second signal so as to become in a mode suitable for estimation of a state of the industrial vehicle. Accordingly, a state estimation unit 43 can estimate the state of the industrial vehicle correctly by discriminating results of the data processing in which adjustment is made to facilitate the estimation of the state. Thus, the accuracy of estimating the state of the industrial vehicle can be enhanced.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a control device for an industrial vehicle, an industrial vehicle, and a control program for an industrial vehicle. [Background technology]

[0002] A known conventional control device for an industrial vehicle is, for example, the technology described in Patent Document 1. The control device described in Patent Document 1 is mounted on an industrial vehicle. This control device estimates the state of the industrial vehicle based on signals acquired by multiple sensors provided on the industrial vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 5-24796 Summary of the Invention [Problem to be solved by the invention]

[0004] To estimate the state of an industrial vehicle more accurately, it is necessary to consider multiple signals. However, simply acquiring a signal does not allow one to determine whether the acquired results are necessary for estimation. Therefore, it is necessary to improve the accuracy of estimating the state of an industrial vehicle by separating the acquired results of each signal into information necessary for estimation.

[0005] An object of the present invention is to provide an industrial vehicle control device, an industrial vehicle, and an industrial vehicle control program that can improve the accuracy of estimating the state of an industrial vehicle. [Means for solving the problem]

[0006] An industrial vehicle control device according to one embodiment of the present invention is an industrial vehicle control device that controls an industrial vehicle, and includes a first signal acquisition unit that acquires a first signal, a second signal acquisition unit that acquires a second signal, a data processing unit that performs data processing based on time series data of the first signal and the second signal, and a state estimation unit that estimates the state of the industrial vehicle by distinguishing the results of the data processing.

[0007] An industrial vehicle control device according to one aspect of the present invention acquires a first signal and a second signal, thereby enabling accurate estimation of the industrial vehicle state using multiple signals rather than a single signal. Here, the data processing unit processes data based on the time-series data of the first signal and the second signal. This allows the data processing unit to process data in a manner suitable for estimating the state of the industrial vehicle based on the time-series data of the first signal and the second signal. The state estimation unit can accurately estimate the state of the industrial vehicle by distinguishing between the results of data processing adjusted to facilitate state estimation in this way. As a result, the accuracy of estimating the state of the industrial vehicle can be improved.

[0008] The first signal acquisition unit may acquire a first signal indicating the surrounding environment of the industrial vehicle, and the second signal acquisition unit may acquire a second signal indicating the state of the industrial vehicle itself. In this case, the state estimation unit can accurately estimate the state of the industrial vehicle by taking into account two aspects: the surrounding environment of the industrial vehicle and the state of the industrial vehicle itself.

[0009] The first signal acquisition unit may acquire sound data from a sound sensor as a first signal, the second signal acquisition unit may acquire acceleration data from an acceleration sensor provided in a loading unit of the industrial vehicle as a second signal, and the state estimation unit may estimate the state of loading of the industrial vehicle. In this case, the state estimation unit can accurately estimate the state of the industrial vehicle by taking into account sounds generated in the surrounding area due to the operation of the industrial vehicle, and acceleration due to the operation of the loading unit and the traveling of the industrial vehicle.

[0010] The data processing unit may acquire time-series data of sound data as a first signal and acceleration data as a second signal, extract multiple feature quantities based on different perspectives from the time-series data at predetermined time intervals, and the state estimation unit may estimate the state by clustering the feature quantity extraction results of the data processing unit. In this case, the data processing unit can extract multiple feature quantities at predetermined time intervals from data of different properties, namely sound data and acceleration data, so as to make it easier to estimate the state of the industrial vehicle. Then, the state estimation unit can cluster the extraction results into classifications that indicate multiple states of the industrial vehicle based on trends in the extracted feature quantities. This allows the state estimation unit to accurately estimate the state of the industrial vehicle.

[0011] An industrial vehicle according to one aspect of the present invention is provided with the control device for an industrial vehicle described above, and this industrial vehicle can obtain the same functions and effects as the control device described above.

[0012] An industrial vehicle control program according to one embodiment of the present invention is a control program for an industrial vehicle that controls an industrial vehicle, and causes a computer system to execute a first signal acquisition step of acquiring a first signal, a second signal acquisition step of acquiring a second signal, a data processing step of processing data based on time series data of the first signal and the second signal, and a state estimation step of estimating the state of the industrial vehicle by distinguishing the results of the data processing.

[0013] This industrial vehicle control program can achieve the same effects and advantages as the above-mentioned control device. [Effects of the Invention]

[0014] According to the present invention, it is possible to provide an industrial vehicle control device, an industrial vehicle, and an industrial vehicle control program that can improve the accuracy of estimating the state of an industrial vehicle. [Brief explanation of the drawings]

[0015] [Figure 1]1 is a side view of a reach forklift equipped with a control device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the control device shown in FIG. 1 and its related components. [Figure 3] FIG. 10 is a diagram illustrating an example of feature amounts of sound data. [Figure 4] 10 is a table showing an example of time-series data that has been subjected to data processing. [Figure 5] 1 is a table showing an example of a color scale conversion table. [Figure 6] 10 is a graph showing the results of clustering feature amounts at each time. [Figure 7] 4 is a flowchart showing the control content of the control device. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0017] FIG. 1 is a side view of a reach forklift equipped with a control device according to this embodiment. In the following description, "left" and "right" are used, but these correspond to "left" and "right" when viewed from the rear. As shown in FIG. 1, a reach forklift (hereinafter simply referred to as a forklift) 50 as an industrial vehicle is a three-wheeled vehicle with two front driven wheels and one rear wheel driven, and is a battery-powered vehicle that runs on a battery housed in the front of the vehicle (machine base) 2. The forklift 50 is equipped with the vehicle 2 and a loading device 3.

[0018] The vehicle 2 has a pair of left and right reach legs 4 extending forward. Left and right front wheels 5 are rotatably supported on the left and right reach legs 4, respectively. The rear wheel 6 is the only rear wheel and is a drive wheel that also serves as a steering wheel. The rear of the vehicle 2 is a standing-type driver's seat 12. An instrument panel 9 in front of the driver's seat 12 is provided with a load handling lever 10 for loading and unloading operations and an accelerator lever 11 for forward and reverse operation. In addition, a steering wheel 13 is provided on the top surface of the instrument panel 9.

[0019] The cargo handling device 3 is provided at the front of the vehicle 2. When the reach lever of the cargo handling levers 10 is operated, the reach cylinder is driven to extend and retract, causing the cargo handling device 3 to move forward and backward along the reach leg 4 within a predetermined stroke range. The cargo handling device 3 also includes a two-stage mast 23, a lift cylinder 24, a tilt cylinder, and a fork 25. When the lift lever of the cargo handling levers 10 is operated, the lift cylinder 24 is driven to extend and retract, causing the mast 23 to slide up and down, and the fork 25 to move up and down in conjunction with this.

[0020] The forklift 50 has a control device 100 according to this embodiment mounted on the vehicle 2. The forklift 50 also has a camera 30 positioned to easily capture images of the environment surrounding the forklift 50. The forklift 50 has an acceleration sensor 31 on the fork 25 (loading section). The positions of the camera 30 and the acceleration sensor 31 are not particularly limited, and the positions may be changed as appropriate. For example, the acceleration sensor 31 may be attached to a member that moves up and down together with the fork 25, such as a backrest.

[0021] Next, the control device 100 of the forklift 50 according to this embodiment will be described in more detail with reference to Fig. 2. Fig. 2 is a block diagram showing the control device 100 according to this embodiment and its related components. As shown in Fig. 2, the forklift 50 includes a camera 30, an acceleration sensor 31, an output unit 32, and the control device 100.

[0022] The camera 30 is a device that acquires video and audio data showing the environment around the forklift 50. The camera 30 has a video sensor 33 that acquires video data and a sound sensor 34 that acquires audio data. The camera 30 can also acquire the video and audio data in time series. The camera 30 transmits the time series video and audio data to the control device 100.

[0023] The acceleration sensor 31 is a device that acquires acceleration data, which is information indicating the state of the forklift 50 itself. Since the acceleration sensor 31 is provided on the fork 25 (see FIG. 1), it can acquire acceleration data when the fork 25 moves up and down and stops, in addition to acceleration data when the forklift 50 itself is traveling and stopping. The acceleration sensor 31 can also acquire acceleration data in time series. The acceleration sensor 31 transmits the time series acceleration data to the control device 100.

[0024] The control device 100 is a device that controls the forklift 50. The control device 100 is equipped with an ECU (Electronic Control Unit) that performs overall management of the device. The ECU is an electronic control unit that includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a CAN (Controller Area Network) communication circuit, and the like. The ECU, for example, loads a program stored in the ROM into the RAM and executes the program loaded into the RAM with the CPU, thereby realizing various functions. The ECU may be composed of multiple electronic units.

[0025] The control device 100 includes a first signal acquisition unit 40, a second signal acquisition unit 41, a data processing unit 42, a state estimation unit 43, and a storage unit 44.

[0026] The first signal acquisition unit 40 acquires, as the first signal, sound data indicating the surrounding environment of the forklift 50. The first signal acquisition unit 40 acquires time-series sound data from the sound sensor 34 of the camera 30.

[0027] The second signal acquisition unit 41 acquires, as a second signal, acceleration data indicating the state of the forklift 50. The second signal acquisition unit 41 acquires time-series acceleration data from the acceleration sensor 31. The acceleration data includes information on acceleration in each direction in three-dimensional space, and includes information on acceleration in the X-axis direction, Y-axis direction, and Z-axis direction.

[0028] The data processing unit 42 performs data processing based on the first signal and the second signal. The data processing unit 42 acquires time-series data of sound data as the first signal and acceleration data as the second signal. Here, since the sound data and the acceleration data have different data acquisition periods, data formats, etc., it is difficult to handle the sound time-series data and the acceleration time-series data as they are simultaneously. Therefore, the data processing unit 42 extracts multiple feature amounts based on different perspectives from the time-series data at predetermined time intervals. The data processing unit 42 extracts multiple feature amounts using the time-series sound data at predetermined time intervals. Furthermore, the data processing unit 42 extracts multiple feature amounts using the time-series acceleration data at predetermined time intervals.

[0029] First, a data processing method for sound data will be described. For example, if the sampling frequency of the sound data is 16 kHz, the first signal acquisition unit 40 acquires sound data of that frequency. The data processing unit 42 uses the sound data every second to extract three feature quantities based on different perspectives. As the first feature quantity, the data processing unit 42 calculates a sonogram (FIG. 3(a): horizontal axis represents time, vertical axis represents the Bark scale), which is a feature quantity based on the perspective of the loudness of the sound. As the second feature quantity, the data processing unit 42 calculates a spectrogram (FIG. 3(b): horizontal axis represents time, vertical axis represents sound frequency), which is a feature quantity based on the perspective of the pitch of the sound. As the third feature quantity, the data processing unit 42 calculates a chromagram (FIG. 3(c): horizontal axis represents time change, vertical axis represents musical scale), which is a feature quantity based on the perspective of the duration of the sound. As a result, for example, values ​​shown in the "loudness," "pitch," and "continuity" items of the "sound data feature quantity" in Figure 4 can be obtained in time series (every second). Figure 4 shows an example of converted time series data. Regarding the "sound data feature quantity," the pitch of the sound can also be obtained from the chromagram (Figure 3(c)), and the continuity of the sound can be obtained from the spectrogram (Figure 3(b)). There is only one type of "loudness." Therefore, two sets of data sets for the "sound data feature quantity" are obtained: "scale value," "loudness," "pitch," and "continuity."

[0030] The data processing unit 42 uses the acceleration data every second to extract three feature quantities based on different perspectives. The data processing unit 42 calculates three custom quantities, "loudness," "pitch," and "continuity," by performing calculations similar to those for sound data. As a result, for example, the values ​​shown in the "loudness," "pitch," and "continuity" items of the "acceleration data feature quantities" in FIG. 4 are obtained in time series (every second) for each of the X-axis, Y-axis, and Z-axis.

[0031] The data processing unit 42 calculates a scale value based on the three feature quantities of the sound data and acceleration data. The scale value is calculated using a color scale conversion table prepared in advance and stored in the storage unit 44. As shown in FIG. 5, the color scale conversion table is a table for determining one color from three color elements, R, G, and B, and one scale value can be determined by applying the R, G, and B values. If there is no perfectly matching combination of R, G, and B in the color scale conversion table, the data processing unit 42 calculates the scale value using a similar value. Note that the maximum value of R, G, and B shown in FIG. 5 is 255, while the maximum value of "loudness," "high / low," and "continuity" shown in FIG. 4 is 25. Therefore, the data processing unit 42 adjusts the scale of the values ​​and then applies the "loudness," "high / low," and "continuity" to the color scale conversion table to calculate the scale value. Therefore, as shown in FIG. 4, the data processing unit 42 calculates a value indicated as a "scale value" from the values ​​of "loudness," "high / low," and "continuity" at each time of the "feature quantity of sound data." Furthermore, as shown in FIG. 4, the data processing unit 42 calculates a value shown in the "scale value" from the values ​​of "magnitude," "high / low," and "continuity" at each time on the "X-axis," "Y-axis," and "Z-axis" of the "feature amount of acceleration data."

[0032] The state estimation unit 43 estimates the state of the forklift 50 by distinguishing the results of data processing by the data processing unit 42. The state estimation unit 43 estimates the state of cargo handling by the forklift 50. The state estimation unit 43 estimates the state of the forklift 50 by clustering the feature quantity extraction results by the data processing unit 42.

[0033] The state estimation unit 43 estimates the state of the forklift 50 by selecting items from the "feature amounts of sound data" and "feature amounts of acceleration data" shown in FIG. 4 and clustering (distinguishing) the trends of combinations of the selected features. Regarding the "feature amounts of sound data," the state estimation unit 43 selects all items (i.e., eight values) of "scale value," "loudness," "high / low level," and "continuity." Meanwhile, as a result of extensive research, the inventors have found that, regarding acceleration data, estimation accuracy can be improved by including only the "high / low level" item in the clustering, but not the "loudness" and "continuity" items other than the "scale value." Therefore, regarding the "feature amounts of acceleration data," the state estimation unit 43 selects the items surrounded by virtual lines in FIG. 4, i.e., the "scale value" and "high / low level" items on the "X-axis," "Y-axis," and "Z-axis."

[0034] The state estimation unit 43 acquires the trend of the combination of the picked feature quantities at a certain time (t seconds) and compares the trend with a state transition model prepared in advance to estimate the state of the forklift 50 at t seconds. The state transition model classifies the states of the forklift 50 into multiple categories and sets the trend of the combination of feature quantities for each state. The state transition model is obtained by actually operating the forklift 50 at a test site or other location, acquiring the trend of the combination of feature quantities based on the acquired time-series data, and clustering the data. The acquired state transition model is stored in the storage unit 44. Note that the classes are configured based on the states of the forklift 50 that have similar operations and sounds. For example, a "class containing many states in which the forklift has lifted the forklift and started work" and a "class containing many states in which an object has been loaded onto the lift and dragged" are included. The acquired states include a "state in which the forklift is operating normally" and a "state in which an object being handled is interfering with the work."

[0035] In the example shown in FIG. 6, the states of the forklift 50 are classified into six states, "0" to "5." When the forklift 50 is actually operated, the state estimation unit 43 acquires the trend of the combination of feature quantities over a certain time period (t seconds), compares it with the state transition model, and determines to which state, "0" to "5," the trend belongs. The state estimation unit 43 then estimates that the forklift 50 is in the determined state at t seconds. In FIG. 6, the state estimation unit 43 estimates that the forklift 50 is in state "5" at 20 seconds (see P1 in FIG. 6). The state estimation unit 43 estimates that the forklift 50 is in state "0" at 60 seconds (see P2 in FIG. 6).

[0036] The state estimation unit 43 effectively utilizes the obtained estimation results in the operation of the forklift 50. For example, if the forklift 50 is automatically operated, the estimation results can be fed back to the automatic control of the forklift 50. If the forklift 50 is manned, the estimation results may be output to the driver. Such estimation results can be effectively utilized, for example, in driving, particularly driving to avoid work hazards. Furthermore, if a worker operates the forklift 50, it becomes possible to check whether cargo handling is normal when working at a high height or at the back of a shelf, where visual confirmation is difficult for the worker.

[0037] Next, the control content by the control device 100 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the control content by the control device 100. This control processing is carried out by the computer system executing a control program P (see Fig. 2) stored in the storage unit 45.

[0038] First, the first signal acquisition unit 40 of the control device 100 acquires sound data as a first signal (step S10: first signal acquisition step). Next, the second signal acquisition unit 41 acquires acceleration data as a second signal (step S20: second signal acquisition step). Next, the data processing unit 42 performs data processing based on the time-series data of the first signal and the second signal (step S30: data processing step). Next, the state estimation unit 43 estimates the state of the forklift 50 by distinguishing the results of the data processing (step S40: state estimation step). With the above, the control process shown in FIG. 7 ends, and the process is repeated again from step S10.

[0039] Next, the functions and effects of the control device 100 for the forklift 50, the forklift 50, and the control program according to this embodiment will be described.

[0040] Sounds and vibrations generated during industrial vehicle operation and work are useful signals for understanding operating conditions and abnormalities. However, in typical worksites, in addition to the sounds generated by the vehicle itself, there is also environmental noise generated in the surrounding area, making it necessary to first distinguish between sounds related to the vehicle's operation and environmental noise. However, the location of environmental noise cannot be determined in advance, and when similar tasks or equipment are operating in the surrounding area, there may be no clear difference in the characteristics of the acquired signals between sounds related to the vehicle's operation and environmental noise. This makes it difficult for control devices that handle sound data signals alone to distinguish between sounds related to the vehicle's own operation and environmental noise. Similar to sound, vibration signals may not show clear differences even when the operating situation or state changes, such as when the same axis is operating. This makes it difficult to estimate the operating situation or state from acceleration signals alone.

[0041] As a solution to the above issues, combining sound and vibration signals may improve the accuracy of estimating the operating situation and state, and of distinguishing between sounds generated by industrial vehicles and environmental sounds. To achieve this solution, it is necessary to establish a method for fusing sound and acceleration signals acquired by different sensors as time-series information. Furthermore, while there are methods that use machine learning to estimate states using sound and vibration, and to distinguish between sound and environmental sounds, machine learning requires a large amount of training data, and there is a problem in that a large amount of training data must be prepared every time the operating environment of the industrial vehicle changes. Therefore, a method that does not use machine learning is needed to solve the above issues.

[0042] To address the above-mentioned issues, the industrial vehicle control device 100 according to this embodiment acquires a first signal and a second signal, thereby enabling accurate estimation of the industrial vehicle state using multiple signals rather than a single signal. Here, the data processing unit 42 processes data based on the time-series data of the first signal and the second signal. This allows the data processing unit 42 to process data in a manner suitable for estimating the state of the industrial vehicle based on the time-series data of the first signal and the second signal. This allows the state estimation unit 43 to accurately estimate the state of the industrial vehicle by distinguishing between the results of data processing adjusted to facilitate state estimation. As a result, the accuracy of the estimation of the state of the industrial vehicle can be improved.

[0043] The first signal acquisition unit 40 may acquire a first signal indicating the surrounding environment of the industrial vehicle, and the second signal acquisition unit 41 may acquire a second signal indicating the state of the industrial vehicle itself. In this case, the state estimation unit 43 can accurately estimate the state of the industrial vehicle by taking into account two aspects: the surrounding environment of the industrial vehicle and the state of the industrial vehicle itself.

[0044] The first signal acquisition unit 40 may acquire sound data from the sound sensor 34 as a first signal, the second signal acquisition unit 41 may acquire acceleration data from the acceleration sensor 31 provided in the loading unit of the industrial vehicle as a second signal, and the state estimation unit 43 may estimate the state of loading of the industrial vehicle. In this case, the state estimation unit 43 can accurately estimate the state of the industrial vehicle by taking into account sounds generated in the surrounding area due to the operation of the industrial vehicle, the operation of the forks 25 of the loading unit, and the acceleration due to the traveling of the industrial vehicle.

[0045] The data processing unit 42 may acquire time-series data of sound data as a first signal and acceleration data as a second signal, extract multiple feature quantities based on different perspectives from the time-series data at predetermined time intervals, and the state estimation unit 43 may estimate the state by clustering the feature quantity extraction results of the data processing unit 42. In this case, the data processing unit 42 can extract multiple feature quantities at predetermined time intervals from data of different properties, namely sound data and acceleration data, so as to make it easier to estimate the state of the industrial vehicle. Then, the state estimation unit 43 can cluster the extraction results into classifications that indicate multiple states of the industrial vehicle based on trends in the extracted feature quantities. This allows the state estimation unit 43 to accurately estimate the state of the industrial vehicle.

[0046] The industrial vehicle according to this embodiment is equipped with the above-described industrial vehicle control device 100. This industrial vehicle can obtain the same functions and effects as the above-described control device.

[0047] The industrial vehicle control program of this embodiment is a control program for an industrial vehicle that controls an industrial vehicle, and causes a computer system to execute a first signal acquisition step S10 for acquiring a first signal, a second signal acquisition step S20 for acquiring a second signal, a data processing step S30 for performing data processing based on time series data of the first signal and the second signal, and a state estimation step S40 for estimating the state of the industrial vehicle by distinguishing the results of the data processing.

[0048] This industrial vehicle control program can achieve the same effects and advantages as the above-mentioned control device.

[0049] The present invention is not limited to the above-described embodiments.

[0050] For example, in the above embodiment, a reach forklift is used as an example of an industrial vehicle, but various types of forklifts, such as a counterbalance forklift, may also be used. Note that when a counterbalance forklift is used, the detection of the reach operation is omitted. Furthermore, the traveling drive system may include a traveling motor or an engine.

[0051] [Form 1] An industrial vehicle control device for controlling an industrial vehicle, a first signal acquisition unit that acquires a first signal; a second signal acquisition unit that acquires a second signal; a data processing unit that processes data based on time series data of the first signal and the second signal; a state estimation unit that estimates a state of the industrial vehicle by distinguishing results of the data processing. [Form 2] the first signal acquisition unit acquires the first signal indicating a surrounding environment of the industrial vehicle; 2. The control device for an industrial vehicle according to claim 1, wherein the second signal acquisition unit acquires the second signal indicating a state of the industrial vehicle itself. [Form 3] the first signal acquisition unit acquires sound data from a sound sensor as the first signal; the second signal acquisition unit acquires acceleration data as the second signal from an acceleration sensor provided in a loading / unloading unit of the industrial vehicle; 3. The control device for an industrial vehicle according to aspect 2, wherein the state estimation unit estimates a state of cargo handling of the industrial vehicle. [Form 4] The data processing unit acquiring time series data of sound data as the first signal and acceleration data as the second signal; extracting a plurality of feature amounts based on different viewpoints from the time-series data at predetermined time intervals; 4. The control device for an industrial vehicle according to any one of aspects 1 to 3, wherein the state estimation unit estimates the state by clustering a result of extraction of the feature amount by the data processing unit. [Form 5] An industrial vehicle equipped with the industrial vehicle control device according to any one of the first to fourth aspects. [Form 6] An industrial vehicle control program for controlling an industrial vehicle, a first signal acquisition step of acquiring a first signal; a second signal acquisition step of acquiring a second signal; a data processing step of performing data processing based on time series data of the first signal and the second signal; and a state estimation step of estimating a state of the industrial vehicle by distinguishing results of the data processing. [Explanation of symbols]

[0052] 2...vehicle, 40...first signal acquisition unit, 41...second signal acquisition unit, 42...data processing unit, 43...state estimation unit, 50...forklift (industrial vehicle), 100...control device.

Claims

1. An industrial vehicle control device for controlling an industrial vehicle, a first signal acquisition unit that acquires a first signal; a second signal acquisition unit that acquires a second signal; a data processing unit that processes data based on time series data of the first signal and the second signal; a state estimation unit that estimates a loading state of the industrial vehicle by distinguishing the results of the data processing, the first signal acquisition unit acquires sound data from a sound sensor as the first signal indicating a surrounding environment of the industrial vehicle; the second signal acquisition unit acquires acceleration data from an acceleration sensor as the second signal indicating the state of the industrial vehicle itself; A control device for an industrial vehicle, wherein the acceleration sensor is provided in a loading section of the industrial vehicle, and the sound sensor is provided in a section different from the loading section.

2. The control device for an industrial vehicle described in Claim 1, wherein the data processing unit extracts features including at least scale values ​​and elevation degrees in three axial directions based on the acceleration data.

3. The data processing unit acquiring time series data of sound data as the first signal and acceleration data as the second signal; extracting a plurality of feature amounts based on different viewpoints from the time-series data at predetermined time intervals; The control device for an industrial vehicle according to claim 1 , wherein the state estimation unit estimates the state by clustering a result of extraction of the feature amount by the data processing unit.

4. An industrial vehicle equipped with the industrial vehicle control device according to any one of claims 1 to 3.

5. An industrial vehicle control program for controlling an industrial vehicle, a first signal acquisition step of acquiring sound data from a sound sensor provided in a portion different from a loading unit of the industrial vehicle as a first signal indicating a surrounding environment of the industrial vehicle; a second signal acquiring step of acquiring acceleration data from an acceleration sensor provided in the loading / unloading section as a second signal indicating a state of the industrial vehicle itself; a data processing step of performing data processing based on time series data of the first signal and the second signal; and a state estimation step of estimating a loading state of the industrial vehicle by distinguishing the results of the data processing.

Images