Data processing device, data processing method and computational model generation system

Abstract

To provide a data processing device, a data processing method and a calculation model generation system that select measurement data of an abrasion loss of a tire and can efficiently generate a database.SOLUTION: A data processing device 20 comprises: a data acquisition unit 22a; a threshold setting unit 22b; a continuity determination unit 22c; and a database generation unit 22d. The data acquisition unit 22a acquires data associated with an abrasion loss of a tire in a predetermined period. The threshold setting unit 22b sets a lower limit side threshold value and an upper limit side threshold value for the data acquired by the data acquisition unit 22a. The continuity determination unit 22c determines whether or not change in the predetermined period is continuous with data outside a range between the lower limit side threshold value and the upper limit side threshold value that is set by the threshold setting unit 22b. The database generation unit 22d generates an abrasion loss database 23a excluding data with a negative determination result made by the continuity determination unit 22c.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a data processing device and a data processing method for processing data on the amount of wear of tires mounted on a vehicle, and a computational model generation system for generating a computational model for estimating the amount of wear of tires. [Background technology]

[0002] Generally, tires wear depending on driving conditions, distance traveled, etc. Recently, sensors that measure tire pressure and temperature have been attached to tires, and devices that display the measured pressure and temperature have been commercialized.

[0003] Patent Document 1 describes a conventional abnormal data detection method for detecting abnormal data from tire usage history data. This abnormal data detection method collects data related to tire usage history, and then extracts a dataset that is a combination of multiple correlated items selected from multiple items in the collected tire usage history, such as mileage and wear amount. Then, abnormal data is detected from the extracted dataset using a machine learning algorithm such as isolation forest. When detecting abnormal data, it is determined whether the dataset is abnormal based on a discriminant model constructed using multiple datasets previously determined to be normal as training data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-074927 Summary of the Invention [Problem to be solved by the invention]

[0005] The abnormal data detection method described in Patent Document 1 requires that a discrimination model be trained in advance based on training data and then constructed according to the input variables of the discrimination model, which makes the process for detecting abnormal data complicated and increases the processing load.In addition, the measured values ​​of wear amount, which are training data used to train a calculation model that estimates tire wear amount, are subject to measurement errors depending on the skill level of the worker, and even when measurements are taken using an optical measuring device, there is a possibility that measurement errors will occur due to stones or other objects being stuck in the tire grooves.

[0006] The present invention has been made in consideration of the above circumstances, and its object is to provide a data processing device, a data processing method, and a calculation model generation system that can select measurement data of tire wear and efficiently generate a database. [Means for solving the problem]

[0007] A data processing device according to one embodiment of the present invention comprises a data acquisition unit that acquires data relating to the amount of wear of tires mounted on a vehicle over a predetermined period of time; a threshold setting unit that sets a lower limit threshold and an upper limit threshold for the data acquired by the data acquisition unit; a continuity determination unit that determines whether or not changes over the predetermined period of time are continuous for data outside the range of the lower limit threshold and the upper limit threshold set by the threshold setting unit; and a database generation unit that generates a wear amount database by excluding data for which the continuity determination unit has determined that the change is negative.

[0008] Another aspect of the present invention is a data processing method, which includes a data acquisition step of acquiring data relating to the amount of wear of tires mounted on a vehicle over a predetermined period of time, a threshold setting step of setting a lower limit threshold and an upper limit threshold for the data acquired in the data acquisition step, a continuity determination step of determining whether or not changes over the predetermined period of time are continuous for data outside the range between the lower limit threshold and the upper limit threshold set in the threshold setting step, and a database generation step of generating a wear amount database by excluding data for which the determination result in the continuity determination step is negative.

[0009] Another aspect of the present invention is a computational model generation system, which includes the above-mentioned data processing device, a wear amount calculation unit having a learning-type computational model that calculates tire wear amount based on input information, and that calculates tire wear amount by inputting information including at least the vehicle's mileage into the computational model, and a learning processing unit that compares wear amount data included in a wear amount database generated by the data processing device with the wear amount calculated by the wear amount calculation unit to train the computational model. [Effects of the Invention]

[0010] According to the present invention, measurement data of tire wear can be selected and a database can be efficiently generated. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a functional configuration of a computation model generation system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the on-board measuring device. [Figure 3] FIG. 10 is a schematic diagram for explaining wear amount estimation and learning of a calculation model. [Figure 4] FIG. 2 is a block diagram showing the functional configuration of a data processing device. [Figure 5]10 is a flowchart showing the procedure of a database generation process performed by the data processing device. [Figure 6] 10 is a table showing the results of wear amount estimation by a computation model trained on measured wear amount data. DETAILED DESCRIPTION OF THE INVENTION

[0012] The present invention will be described below based on preferred embodiments with reference to Figures 1 to 6. The same or equivalent components and members shown in each drawing are designated by the same reference numerals, and duplicate descriptions will be omitted where appropriate. The dimensions of the members in each drawing are enlarged or reduced as appropriate to facilitate understanding. Some members that are not important for explaining the embodiments will be omitted from the drawings.

[0013] (Embodiment) 1 is a block diagram showing the functional configuration of a computational model generation system 100 according to an embodiment. The computational model generation system 100 includes a tire wear amount measurement device 60, an on-vehicle measurement device 70, a weather information server device 80, a computational model generation device 10, and a data processing device 20, and generates a computational model 13a that estimates the amount of wear of a tire 7.

[0014] The computational model generating device 10 acquires vehicle measurement information such as vehicle speed and position information, as well as tire measurement information measured on the tires 7, from an on-board measurement device 70 mounted on the vehicle via a communication network 9 such as the Internet. The computational model generating device 10 acquires weather information from a weather information server device 80. The computational model generating device 10 also acquires each piece of data in the wear amount database for the tires 7 generated by the data processing device 20 based on data on the wear amount of the tires 7 measured by the tire wear amount measuring device 60.

[0015] The data processing device 20 generates a wear amount database by excluding data of the wear amount of the tire 7 measured by the tire wear amount measuring device 60, the data whose numerical values ​​are outside the distribution range of other wear amount data due to measurement errors or the like. The computational model generating device 10 uses each piece of data in the wear amount database generated by the data processing device 20 as training data to train the computational model 13a, thereby improving the accuracy of estimating the wear amount by the computational model 13a.

[0016] The tire wear measurement device 60 directly measures the depth of the grooves in the tread of the tire 7 multiple times over a predetermined period (several months to several years) to obtain the wear amount of the tire 7. The tire wear measurement device 60 transmits the measured wear amount data of the tire 7 to the data processing device 20 via the communication network 9. A tire worker may measure the depth of each groove using a measuring tool, a camera, or visually, and the tire wear measurement device 60 may store the measurement data input by the worker. Alternatively, the tire wear measurement device 60 may be a dedicated device that measures groove depth using a mechanical or optical method and stores the wear amount.

[0017] Specifically, for example, if a tire has four grooves, the tire wear measurement device 60 measures the depth at four locations in the width direction and then measures the depth at three locations in the circumferential direction of the same groove, for example, at 120° intervals. This allows data on uneven wear in the width direction or circumferential direction of the tire to be stored in the tire wear measurement device 60. Note that, because tire diameter changes with wear, the tire wear measurement device 60 may indirectly measure groove depth by calculation based on information on the mileage and the tire rotation speed and speed. In addition, a device that directly measures groove depth may be used in combination with a device that predicts groove depth by calculation based on the mileage and the tire rotation speed and speed.

[0018] 2 is a block diagram showing the functional configuration of the on-vehicle measurement device 70. The on-vehicle measurement device 70 includes a vehicle measurement unit 71, a tire measurement unit 72, an information acquisition unit 73, and a communication unit 74. Each unit in the on-vehicle measurement device 70 can be realized in terms of hardware using electronic elements and mechanical parts, such as a computer CPU, and in terms of software using a computer program, but the functional blocks shown here are realized by the cooperation of these elements. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0019] The vehicle measurement unit 71 has a speedometer 71a, a GPS receiver 71b, and an acceleration sensor 71c mounted on the vehicle. The speedometer 71a measures the vehicle's speed. The GPS receiver 71b measures the vehicle's current position information (latitude, longitude, and altitude). The acceleration sensor 71c measures the vehicle's acceleration in three axial directions.

[0020] The tire measurement unit 72 has a temperature sensor 72a and a pressure sensor 72b. The temperature sensor 72a and the pressure sensor 72b are disposed on an air valve or the like of a tire 7 mounted on a vehicle, or are firmly wrapped around and fixed to a wheel with a belt or the like, and measure the temperature and air pressure of the tire 7. The temperature sensor 72a may be disposed on an inner liner or the like of the tire 7.

[0021] The information acquisition unit 73 acquires vehicle measurement information (speed, position information, acceleration, etc.) measured by the vehicle measurement unit 71 and tire measurement information (tire temperature, air pressure, etc.) measured by the tire measurement unit 72. The information acquisition unit 73 associates measurement time information or acquired time information with each piece of measurement data included in the vehicle measurement information and tire measurement information. The information acquisition unit 73 transmits the vehicle measurement information and tire measurement information together with the time information associated with each piece of measurement data from the communication unit 74 to the computation model generation device 10.

[0022] If the vehicle is equipped with a device such as a digital tachometer, the information acquisition unit 73 may acquire information such as the vehicle's speed, acceleration, and position collected by that device. The communication unit 74 connects to the communication network 9 by wireless communication such as WiFi (registered trademark), and transmits the vehicle measurement information, tire measurement information, and time information acquired by the information acquisition unit 73 to the computational model generation device 10 via the communication network 9.

[0023] Returning to Figure 1, the weather information server device 80 provides weather information for various locations. The weather information provided by the weather information server device 80 includes information such as the amount of precipitation, snowfall, temperature, and sunshine hours for various locations. The computation model generation device 10 obtains weather information for the location where the vehicle is traveling from the weather information server device 80.

[0024] The computational model generating device 10 includes a communication unit 11, a vehicle information acquiring unit 12, a wear amount calculating unit 13, a storage unit 14, and a learning processing unit 15. Each unit in the computational model generating device 10 can be realized in terms of hardware using electronic elements and mechanical parts such as a computer CPU, and in terms of software using a computer program, but the functional blocks realized by the cooperation of these elements are depicted here. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0025] The communication unit 11 is connected to the communication network 9 by wireless or wired communication, and communicates with the communication unit 74 of the on-vehicle measuring device 70. The communication unit 11 also communicates with the weather information server device 80 via the communication network 9.

[0026] The vehicle information acquisition unit 12 acquires vehicle measurement information (speed, position information, acceleration, etc.) and tire measurement information (tire temperature, air pressure, etc.) transmitted from an on-board measurement device 70 mounted on the vehicle. The vehicle information acquisition unit 12 calculates and acquires the vehicle's traveling distance based on the vehicle measurement information.

[0027] The vehicle information acquisition unit 12 can calculate and acquire the travel distance based on the position information of the vehicle measurement information. The travel distance of the vehicle may also be calculated based on the speed data in the vehicle measurement information and the time data associated with the speed data. That is, the travel distance of the vehicle can be calculated by multiplying the speed data arranged in chronological order by the time difference until the next point in time.

[0028] If information regarding the vehicle's mileage is provided by the vehicle or an external device for vehicle management, the vehicle information acquisition unit 12 does not need to calculate the mileage itself and may acquire information regarding the mileage from the vehicle or the external device.

[0029] The vehicle information acquisition unit 12 outputs the acquired travel distance to the wear amount calculation unit 13. The vehicle information acquisition unit 12 outputs the acquired tire measurement information (tire temperature, air pressure, etc.) to the wear amount calculation unit 13. When the wear amount calculation unit 13 estimates the amount of tire wear based on a calculation model that uses vehicle acceleration as an input element, the vehicle information acquisition unit 12 outputs acceleration data in the vehicle measurement information to the wear amount calculation unit 13.

[0030] Furthermore, the vehicle information acquisition unit 12 acquires data used to estimate the wear amount of the tire 7 from the vehicle specification data 14a and the tire specification data 14b from the storage unit 14, and outputs the data to the wear amount calculation unit 13. The storage unit 14 is a storage device configured, for example, with an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, etc., and stores data provided in advance regarding the specifications of various vehicles and tires 7.

[0031] The vehicle specification data 14a includes information about vehicle performance, such as the manufacturer, vehicle name, vehicle model, vehicle weight, drivetrain, overall length, vehicle width, vehicle height, and maximum load capacity. The tire specification data 14b also includes information about the performance of the tire 7, such as tire identification information, manufacturer, product name, tire size, tire width, aspect ratio, wear resistance, tire strength, static stiffness, dynamic stiffness, tire outer diameter, load index, and manufacturing date. For example, an RFID tag may be embedded in the tire 7, and when the tire wear measurement device 60 measures the wear, the RFID tag may be read and data correlating the tire identification information with the axle position on the vehicle may be stored in the storage unit 14. The axle position of the tire 7 on the vehicle changes with tire rotation. However, even if the rotation history is not recorded, the axle position on which the tire 7 is mounted and the time when the axle position was changed may be determined by referring to the correspondence between the tire identification information and the axle position on the vehicle stored in the storage unit 14. In addition, by storing in the memory unit 14 that the wheel orientation of the tire 7 has been changed, it is possible to track whether each groove of the tire 7 is on the front or back side of the wheel.

[0032] The wear amount calculation unit 13 has a calculation model 13a and estimates the wear amount of the tire 7. The calculation model 13a is a learning model that calculates the wear amount of the tire 7 based on input information. FIG. 3 is a schematic diagram for explaining the wear amount estimation and learning of the calculation model 13a. The input data to the calculation model 13a is roughly classified into vehicle measurement information, tire measurement information, and other information.

[0033] Input data related to vehicle measurement information includes vehicle acceleration and travel distance. The travel distance is acquired by the vehicle information acquisition unit 12 as described above. Input data related to tire measurement information includes the temperature and air pressure of the tires 7. Note that the vehicle acceleration is used as input data to the calculation model as appropriate.

[0034] The input data based on other information includes road surface conditions estimated based on weather information, the maximum vehicle load included in the vehicle specification data 14a, and the wear resistance performance of the tire 7 included in the tire specification data 14b. The wear resistance performance of the tire 7 is measured using, for example, a tire wear index value obtained by indexing the wear resistance performance of various tread blends based on a Lambourn wear test, with a standard blend being set at 100.

[0035] The computational model 13a uses a learning model such as a neural network. The computational model 13a is constructed using a method such as a deep neural network (DNN) or a decision tree. The computational model 13a may be a multiple linear regression model for input information, for example, and may be generated by learning.

[0036] The learning processing unit 15 acquires each data in the wear amount database of the tire 7 generated by the data processing device 20, and sets it as training data to be used for training the calculation model 13a. In the training process of the calculation model 13a, the wear amount of the tire 7 is estimated as output data by the calculation model 13a based on input information, and is compared with the training data.

[0037] The learning processing unit 15 compares the wear amount of the tire 7 estimated by the calculation model 13a with the training data, newly sets various coefficients in the calculation process, such as weighting, in the calculation model 13a, and repeatedly updates the model to perform learning. The learning processing unit 15 can use a known learning method such as gradient boosting. Also, known verification methods such as random data sampling and cross-validation can be used to verify the calculation model 13a.

[0038] 4 is a block diagram showing the functional configuration of data processing device 20. Data processing device 20 includes a communication unit 21, a data processing unit 22, and a storage unit 23. Each unit in data processing device 20 can be realized in terms of hardware using electronic elements and mechanical parts, such as a computer CPU, and in terms of software using a computer program, but the functional blocks shown here are realized by the cooperation of these elements. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0039] The communication unit 21 is connected to the communication network 9 via wireless or wired communication and communicates with the tire wear amount measuring device 60. The storage unit 23 is a storage device configured, for example, by an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, or the like, and stores the wear amount database 23a generated by the data processing unit 22. The data processing device 20 outputs each piece of data in the generated wear amount database 23a to the computational model generating device 10, but may also transmit each piece of data to the computational model generating device 10 via the communication unit 21.

[0040] The data processing unit 22 includes a data acquisition unit 22a, a threshold setting unit 22b, a continuity determination unit 22c, and a database generation unit 22d. The data acquisition unit 22a acquires measurement data on the amount of wear of the tire 7 mounted on the selected axle position (wheel position) of the vehicle from the tire wear measurement device 60 via the communication unit 21. As described above, the tire wear measurement device 60 measures the amount of wear of the tire 7 multiple times over a predetermined period (for example, several months to several years), and the data acquisition unit 22a acquires all of the measured wear amount data. The data acquisition unit 22a is capable of identifying tires and multiple grooves on the tire over a predetermined period, and it is desirable to be able to acquire wear amount data for the same groove on the same tire in chronological order.

[0041] The threshold setting unit 22b sets a lower limit threshold and an upper limit threshold for the data related to the amount of wear acquired by the data acquiring unit 22a. The threshold setting unit 22b calculates a wear index value WI for each piece of measurement data of the amount of wear by dividing the mileage by the amount of wear. The threshold setting unit 22b may acquire data related to the mileage of the vehicle from the on-board measurement device 70 or the computational model generating device 10.

[0042] If the wear amount and travel distance of the tire 7 increase by 0.5 mm between one wear measurement point and the next, and the tire has traveled 1,000 km during that time, the threshold setting unit 22b calculates the wear index value as follows: WI = 1,000 / 0.5 = 2,000. The threshold setting unit 22b can calculate the wear index value for each wear measurement point. As described above, if the tire wear measurement device 60 measures the wear amount at four locations in the width direction of a tire with four grooves, for example, the threshold setting unit 22b calculates the wear index value for each measured wear amount. In addition to the four locations in the width direction, the wear amount may also be measured at three locations circumferentially around the same groove, for example, at 120° intervals.

[0043] The threshold setting unit 22b calculates quartiles for all wear index value data by the quartile method, and temporarily sets the first quartile as a first lower threshold and the third quartile as a second upper threshold. The threshold setting unit 22b calculates an average value WIa for the wear index value data within the range between the lower threshold and the upper threshold.

[0044] The threshold setting unit 22b calculates the ratio PA by dividing all data of the wear index value WI by the average value WIa, and sets a predetermined range for the ratio PA. For example, the predetermined range may be a range in which the value of the ratio PA is greater than or equal to 1 / 3 and less than or equal to 3, with 1 / 3 being the second lower limit threshold and 3 being the second upper limit threshold. The predetermined range set by the threshold setting unit 22b is not limited to this, and the second lower limit threshold may be set to 1 / 4 and the second upper limit threshold to 4, for example. When calculating the average value of the wear index value WI, the threshold setting unit 22b and the continuity determining unit 22c may target a data group of wear index values ​​for the same groove of the same tire, or may target a data group of wear index values ​​for multiple grooves of the same tire. Furthermore, when calculating the average value of the wear index value WI, the threshold setting unit 22b and the continuity determining unit 22c may calculate the average value for a data group of wear index values ​​for each axle. For example, in a large vehicle with three or more axles, the average wear index value WI for all grooves of multiple tires located on the first axle (steering axle) at the front may be calculated, the average wear index value WI for all grooves of multiple tires located on the second axle (drive axle) in the middle may be calculated, and the average wear index value WI for all grooves of multiple tires located on the third axle (floating axle) at the rear may be calculated.

[0045] Data corresponding to a wear index value WI with a ratio PA smaller than the second lower limit threshold set by the threshold setting unit 22b is temporarily determined to be inappropriate data caused by, for example, an error in measuring the amount of wear. Similarly, data corresponding to a wear index value WI with a ratio PA larger than the second upper limit threshold set by the threshold setting unit 22b is also temporarily determined to be inappropriate. The threshold setting unit 22b outputs each piece of data determined to be inappropriate to the continuity determination unit 22c.

[0046] The continuity determination unit 22c determines whether the change in the amount of wear is continuous or not, by comparing the data input from the threshold setting unit 22b with other data acquired from the same tire and the same groove (i.e., data measured before and after in time). As described above, the data on the amount of wear is acquired multiple times within a predetermined period.

[0047] The continuity determination unit 22c calculates a ratio PB by dividing the wear index value WI of other data acquired for the same tire and the same groove by the wear index value WI of the data input from the threshold setting unit 22b, and sets a predetermined range for the ratio PB. The predetermined range is, for example, a range in which the value of the ratio PB is equal to or greater than 1 / 3 and equal to or less than 3. Note that the predetermined range set by the continuity determination unit 22c is not limited to this, and the value of the ratio PB may be set to a range in which the value of the ratio PB is equal to or greater than 1 / 4 and equal to or less than 4, for example.

[0048] As another method for determining continuity, the continuity determination unit 22c calculates an average value WIc of the wear index values ​​WI of other data acquired for the same tire and the same groove as the data once determined to be inappropriate. The data once determined to be inappropriate is divided by WIc to calculate a ratio PC, and a predetermined range is set for the ratio PC. The predetermined range is, for example, a range in which the value of the ratio PC is greater than or equal to 1 / 3 and less than or equal to 3. Note that the predetermined range set by the continuity determination unit 22c is not limited to this, and the value of the ratio PC may be set to a range in which the value of the ratio PC is greater than or equal to 1 / 4 and less than or equal to 4, for example.

[0049] The continuity determination unit 22c determines that the ratio PB is continuous if it is within the above-mentioned predetermined range, and re-determines that the input data that was determined to be inappropriate by the threshold setting unit 22b is appropriate data. The continuity determination unit 22c determines that the ratio PB is not continuous if it is outside the predetermined range, and deems that the input data that was determined to be inappropriate by the threshold setting unit 22b is still inappropriate data.

[0050] The continuity determination unit 22c determines whether the data has continuity, and outputs data for which the determination result is negative to the database generation unit 22d. The database generation unit 22d generates the wear amount database 23a by excluding the data input from the continuity determination unit 22c from the wear amount data. That is, the wear amount database 23a is obtained by excluding data for which the continuity determination unit 22c has denied the data from being continuity, from all the measured wear amount data acquired by the data acquisition unit 22a.

[0051] Next, the operation of the data processing device 20 will be described. Fig. 5 is a flowchart showing the procedure of the database generation process by the data processing device 20. The data acquisition unit 22a of the data processing device 20 acquires data on the amount of wear of the tire 7 measured by the tire wear amount measuring device 60 (S1). The threshold setting unit 22b calculates a wear index value WI for each piece of wear amount data acquired by the data acquisition unit 22a (S2).

[0052] The threshold setting unit 22b sets a first lower limit threshold and a first upper limit threshold for the wear index value WI of each piece of wear amount data based on the quartile method (S3).The threshold setting unit 22b calculates an average value WIa for the wear index value WI data within a range between the lower limit threshold and the upper limit threshold (S4).

[0053] The threshold setting unit 22b calculates a ratio PA by dividing all data of the wear index value WI by the average value WIa (S5). The threshold setting unit 22b temporarily determines that data out of a predetermined range of the ratio PA of each data of the wear index value WI is inappropriate data, and outputs the determined data to the continuity determination unit 22c (S6).

[0054] The continuity determination unit 22c calculates a ratio PB by dividing the wear index value WI of other data acquired for the same tire and the same groove by the wear index value WI of the data once determined to be inappropriate (S7). The continuity determination unit 22c determines whether the ratio PB is within a predetermined range (S8).

[0055] If it is determined in step S8 that the ratio PB is within the predetermined range (S8: YES), the database generation unit 22d includes the data input from the continuity determination unit 22c in the wear amount database 23a (S9), and ends the process. If it is determined in step S8 that the ratio PB is not within the predetermined range (S8: NO), the database generation unit 22d excludes the data input from the continuity determination unit 22c from the wear amount database 23a (S10), and ends the process.

[0056] The data processing device 20 determines whether data relating to the amount of wear of the tire 7 measured multiple times over a predetermined period of time that falls outside the range between the lower limit threshold and the upper limit threshold is continuous, and if it determines that the data is not continuous, it excludes the data from the database. This allows the data processing device 20 to exclude inappropriate data, select measurement data of the amount of wear of the tire 7, and efficiently generate the database.

[0057] The data processing device 20 calculates a wear index value WI by dividing the vehicle's travel distance by the amount of wear for the wear amount data of the tires 7, and determines whether the wear index value WI is continuous for data outside the range between the lower threshold and the upper threshold. The wear amount of the tires 7 increases as the vehicle travel distance increases. The data processing device 20 can suppress data variation due to travel distance by using the wear index value WI, which is calculated by dividing the vehicle's travel distance between a certain measurement point of the wear amount and the previous measurement point of the wear amount within a predetermined period of time.

[0058] The threshold setting unit 22b of the data processing device 20 calculates the first quartile as the lower limit value and the third quartile as the upper limit value based on the quartile method, and sets the lower limit value as the first lower limit threshold and the upper limit value as the first upper limit threshold. The threshold setting unit 22b calculates an average value WIa for data of wear index values ​​WI within the range between the first lower limit threshold and the first upper limit threshold, predetermines a predetermined range for the ratio obtained by dividing each data by the average value WIa, and sets the lower limit value of the predetermined range as the second lower limit threshold and the upper limit value as the second upper limit threshold. In this way, the data processing device 20 can include data outside the range between the first lower limit threshold and the first upper limit threshold in the wear amount database 23a as long as it is within the range between the second lower limit threshold and the second upper limit threshold.

[0059] The data processing device 20 may determine whether data outside the range of the first lower limit threshold and the first upper limit threshold set by the threshold setting unit 22b has continuity with other data using the continuity determination unit 22c, and decide whether to include or exclude the data in the wear amount database 23a. In this way, the data processing device 20 can exclude from the wear amount database 23a data that is determined to have no continuity with other data among the data outside the range of the first lower limit threshold and the first upper limit threshold.

[0060] The computational model generation system 100 can generate a computational model 13a that improves the accuracy of estimating the wear amount of the tire 7 by training the computational model 13a using each piece of wear amount data in the wear amount database 23a generated by the data processing device 20 as training data.

[0061] Figure 6 is a diagram showing the results of wear amount estimation by the calculation model 13a trained using measured wear amount data. The wear amount data used was measured on an actual vehicle. The calculation model 13a was verified using a calculation model based on a decision tree model and a calculation model based on a neural network model as examples.

[0062] Fig. 6 shows the results of calculating the root mean square error (RMSE) for the case where all measurement data of the wear amount of the tire 7 was used (all data used) and the case where inappropriate data was excluded from the measurement data as described above (data excluded). The results of wear amount estimation by the calculation model 13a show that the RMSE value was lower in the case where inappropriate data was excluded, in both the cases using the decision tree and the neural network, and the estimation accuracy was improved.

[0063] (Variation) In the above-described embodiment, the threshold setting unit 22b sets the first lower limit threshold and the first upper limit threshold based on the quartile method, but the first lower limit threshold and the first upper limit threshold may be set using other statistical methods, such as standard deviation. The threshold setting unit 22b may also use other statistical methods to set the second lower limit threshold and the second upper limit threshold. The continuity determination unit 22c determines continuity by setting a predetermined range for the ratio PB, but the method for determining continuity is not limited to this.

[0064] Furthermore, the threshold setting unit 22b calculates a wear index value WI for each data of the wear amount of the tire 7, but if the distance traveled between the respective wear amount measurement points is the same over a predetermined period, there is no need to use the wear index value WI, and each threshold value may be set for the wear amount.

[0065] The data processing device 20 excludes data for which the continuity determination unit 22c has determined that there is no continuity from the wear amount database 23a. For example, if the tire air pressure is lower than a predetermined threshold and the amount of wear on the tire 7 is large, the database generation unit 22d of the data processing device 20 may include the data for which there is no continuity in the wear amount database 23a.

[0066] The data processing device 20 may be configured as a device separate from the computational model generating device 10, or may be configured as a single device integrated with the computational model generating device 10.

[0067] Next, features of the data processing device 20, the data processing method, and the computational model generation system 100 according to the embodiment and the modified examples will be described. The data processing device 20 includes a data acquisition unit 22a, a threshold setting unit 22b, a continuity determination unit 22c, and a database generation unit 22d. The data acquisition unit 22a acquires data related to the wear amount of tires 7 mounted on a vehicle over a predetermined period. The threshold setting unit 22b sets a lower limit threshold and an upper limit threshold for the data acquired by the data acquisition unit 22a. The continuity determination unit 22c determines whether changes over a predetermined period are continuous for data outside the range of the lower limit threshold and the upper limit threshold set by the threshold setting unit 22b. The database generation unit 22d generates the wear amount database 23a by excluding data for which the continuity determination unit 22c has determined that the data is not continuous. This allows the data processing device 20 to select measurement data for the wear amount of tires 7 while excluding inappropriate data, thereby efficiently generating the wear amount database 23a.

[0068] The data is a wear index value obtained by dividing the vehicle's travel distance by the amount of wear, which allows the data processing device 20 to reduce variations in data due to travel distance.

[0069] The threshold setting unit 22b calculates the lower limit and the upper limit by the quartile method, and sets the lower limit as a first lower threshold and the upper limit as a first upper threshold. This allows the data processing device 20 to exclude from the wear amount database 23a data that is outside the range of the first lower threshold and the first upper threshold and that is determined to have no continuity with other data.

[0070] The threshold setting unit 22b calculates an average value for data within a range between lower and upper limits calculated by the quartile method, and predetermines a predetermined range for the ratio obtained by dividing each data by the average value, with the lower limit of the predetermined range set as a second lower threshold and the upper limit set as a second upper threshold. This allows the data processing device 20 to include data in the wear amount database 23a even if the data is outside the range between the first lower threshold and the first upper threshold, as long as it is within the range between the second lower threshold and the second upper threshold.

[0071] The data processing method includes a data acquisition step, a threshold setting step, a continuity determination step, and a database generation step. The data acquisition step acquires data related to the amount of wear of tires 7 mounted on a vehicle over a predetermined period of time. The threshold setting step sets a lower limit threshold and an upper limit threshold for the data acquired in the data acquisition step. The continuity determination step determines whether changes over the predetermined period are continuous for data outside the range of the lower limit threshold and the upper limit threshold set in the threshold setting step. The database generation step generates a wear amount database 23a by excluding data for which the determination result in the continuity determination step is negative. This data processing method allows for the efficient generation of a database by excluding inappropriate data and selecting measurement data for the amount of wear of tires 7.

[0072] The computational model generation system includes the above-described data processing device 20, wear amount calculation unit 13, and learning processing unit 15. The wear amount calculation unit 13 has a learning-type computational model 13a that calculates the amount of wear of the tire 7 based on input information, and inputs information including at least the vehicle's traveling distance into the computational model 13a to calculate the amount of wear of the tire 7. The learning processing unit 15 compares the wear amount data included in the wear amount database 23a generated by the data processing device 20 with the amount of wear calculated by the wear amount calculation unit 13, and causes the computational model 13a to learn. In this way, the computational model generation system can generate a computational model 13a that improves the accuracy of estimating the amount of wear of the tire 7.

[0073] The present invention has been described above based on the embodiments. These embodiments are merely examples, and it will be understood by those skilled in the art that various modifications and changes are possible within the scope of the claims of the present invention, and that such modifications and changes also fall within the scope of the claims of the present invention. Therefore, the descriptions and drawings in this specification should be treated as illustrative rather than restrictive. [Explanation of symbols]

[0074] 7 tire, 13 wear amount calculation unit, 13a calculation model, 15 learning processing unit, 20 data processing device, 22a data acquisition unit, 22b threshold setting unit, 22c continuity determination unit; 22d database generation unit; 23a Wear volume database, 100 Computational model generation system.

Claims

1. a data acquisition unit that acquires data relating to the amount of wear of tires mounted on a vehicle for a predetermined period of time; a threshold setting unit that sets a lower limit threshold and an upper limit threshold for the data acquired by the data acquisition unit; a continuity determination unit that determines whether or not a change in data outside the range of the lower limit threshold and the upper limit threshold set by the threshold setting unit during the predetermined period is continuous; a database generating unit that generates a wear amount database by excluding data for which the result of the determination by the continuity determining unit is negative; Equipped with a data processing device characterized in that the threshold setting unit calculates an average value for data within a range between a lower limit value and an upper limit value calculated by the quartile method, and predetermines a predetermined range for the ratio obtained by dividing each data by the average value, and the lower limit value of the predetermined range is set as the lower limit threshold and the upper limit value is set as the upper limit threshold.

2. 2. The data processing device according to claim 1, wherein the data is a wear index value obtained by dividing a vehicle's travel distance by the amount of wear.

3. a data acquisition step of acquiring data relating to the amount of wear of tires mounted on a vehicle for a predetermined period of time; a threshold setting step of setting a lower limit threshold and an upper limit threshold for the data acquired by the data acquisition step; a continuity determination step of determining whether or not changes in data outside the range of the lower limit threshold and the upper limit threshold set in the threshold setting step are continuous over the predetermined period; a database generating step of generating a wear amount database by excluding data for which the determination result in the continuity determining step is negative; Equipped with The threshold setting step calculates an average value for data within a range between a lower limit value and an upper limit value calculated by the quartile method, and predetermines a predetermined range for the ratio obtained by dividing each data by the average value, with the lower limit value of the predetermined range being set as the lower limit threshold and the upper limit value being set as the upper limit threshold.

4. A data processing device according to any one of claims 1 and 2; a wear amount calculation unit having a learning-type calculation model that calculates tire wear amounts based on input information, the wear amount calculation unit inputting information including at least the vehicle's travel distance into the calculation model to calculate tire wear amounts; a learning processing unit that learns the calculation model by comparing wear amount data included in a wear amount database generated by the data processing device with the wear amount calculated by the wear amount calculation unit; A computational model generation system comprising:

Images