Tire wear estimation system, tire wear estimation method, and calculation model generation system

Abstract

Provided is a technology capable of improving the estimation accuracy of the wear state of a tire. 【Solution means】The tire wear estimation system 100 includes a vehicle information acquisition unit 12, a tire severity generation unit 121, and a wear estimation unit 15. The vehicle information acquisition unit 12 acquires information including the traveling distance and traveling speed of the vehicle. The tire severity generation unit 121 generates, as tire severity information for tire wear, a value calculated based on the distribution of the traveling speed acquired by the vehicle information acquisition unit 12. The wear estimation unit 15 has an arithmetic model 15a for calculating the wear state of the tire 7 based on the input information, and inputs the traveling distance acquired by the vehicle information acquisition unit 12 and the tire severity information generated by the tire severity generation unit 121 into the arithmetic model 15a to estimate the wear state of the tire 7.

Description

Technical Field

[0001] The present invention relates to a tire wear estimation system, a tire wear estimation method, and a calculation model generation system for estimating the wear state of tires mounted on vehicles.

Background Art

[0002] Generally, tires wear as the driving state, driving distance, etc. change. Recently, the development of a technology for estimating the wear amount of tires using a calculation model with information measured by a vehicle as input data has been promoted.

[0003] Patent Document 1 describes a conventional wear amount estimation system. The vehicle information acquisition unit of the wear amount estimation system acquires information including the driving distance and acceleration. The tire severity generation unit generates, as severity information for tire wear, a value calculated from the sum of the squares of the accelerations acquired by the vehicle information acquisition unit. The wear amount calculation unit has a calculation model for calculating the wear amount of the tire based on the input information, and inputs the driving distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the calculation model to calculate the wear amount of the tire.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When the inventor uses a machine learning-based calculation model generated using learning data with, for example, the wear state of each groove of a tire as the target variable and parameters including at least the driving conditions of the vehicle as the explanatory variables, the inventor noticed that the wear of the tire may progress easily regardless of the magnitude of the vehicle's acceleration, and considered that there is room for improvement in the estimation accuracy of the tire wear state by adding explanatory variables.

[0006] The present invention has been made in view of such circumstances, and an object thereof is to provide a tire wear estimation system, a tire wear estimation method, and a calculation model generation system capable of improving the estimation accuracy of the tire wear state.

Means for Solving the Problems

[0007] A tire wear estimation system according to an aspect of the present invention includes a vehicle information acquisition unit that acquires information including the travel distance and travel speed of a vehicle, a tire severity generation unit that generates, as severity information for tire wear, a value calculated based on the distribution of the travel speed acquired by the vehicle information acquisition unit, and a calculation model that calculates the wear state of the tire based on the input information, and a wear estimation unit that inputs the travel distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the calculation model to estimate the wear state of the tire.

[0008] Another aspect of the present invention is a tire wear estimation method. The tire wear estimation method includes a vehicle information acquisition step of acquiring information including the travel distance and travel speed of a vehicle, a tire severity generation step of generating, as severity information for tire wear, a value calculated based on the distribution of the travel speed acquired in the vehicle information acquisition step, and a wear estimation step of inputting the travel distance acquired in the vehicle information acquisition step and the severity information generated in the tire severity generation step into a calculation model that calculates the wear state of the tire based on the input information to estimate the wear state of the tire.

[0009] Another aspect of the present invention is an arithmetic model generation system. The arithmetic model generation system includes a vehicle information acquisition unit that acquires information including the driving distance and driving speed of a vehicle, a tire severity generation unit that generates, as severity information for tire wear, a value calculated based on the distribution of the driving speed acquired by the vehicle information acquisition unit, an arithmetic model that calculates the wear state of a tire based on the input information, a wear estimation unit that inputs the driving distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the arithmetic model to estimate the wear state of the tire, and a learning processing unit that causes the arithmetic model to learn using the wear state measured for the tire as teacher data.

Advantages of the Invention

[0010] According to the present invention, the estimation accuracy of the wear state of a tire can be improved.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiment for Carrying out the Invention

[0012] Hereinafter, the present invention will be described based on preferred embodiments with reference to FIGS. 1 to 10. The same or equivalent components and members shown in each drawing are denoted by the same reference numerals, and redundant descriptions will be omitted as appropriate. Also, the dimensions of the members in each drawing are appropriately enlarged or reduced for easy understanding. In addition, some of the members that are not important for explaining the embodiments in each drawing are omitted from the display.

[0013] (Embodiment) FIG. 1 is a block diagram showing the functional configuration of a tire wear estimation system 100 according to an embodiment. The tire wear estimation system 100 includes an in-vehicle measurement device 70 mounted on a vehicle, a weather information server device 80, and a wear estimation device 10 that estimates the wear state of each tire 7 mounted on the vehicle.

[0014] The wear estimation device 10 acquires vehicle measurement information such as the running speed, acceleration, and position information of the vehicle from the in-vehicle measurement device 70 mounted on the vehicle via a communication network 9 such as the Internet. The wear estimation device 10 generates a value calculated based on the distribution of the running speed of the vehicle as severity information for tire wear. The wear estimation device 10 also acquires weather information from the weather information server device 80. Further, the wear estimation device 10 acquires information on the groove depth of the tire 7 in a new state (hereinafter referred to as "new groove depth") and the groove depth at the time point that is the starting point for estimating the wear state of the tire 7 (hereinafter referred to as "starting groove depth"). The wear estimation device 10 performs calculations using a learning-type calculation model 15a based on the acquired information to estimate the wear state of each tire 7.

[0015] The wear state of the tire 7 estimated by the wear estimation device 10 is represented by information such as the wear amount and wear rate of the tire 7. The wear state of the tire 7 may be, for example, the worn amount (a value such as 1 mm), or the ratio of the worn amount to the initial groove depth in the tire groove (a value such as 10%). Wear estimation means estimating the wear state of the tire 7, that is, information such as the wear amount and wear rate of the tire 7.

[0016] FIG. 2 is a block diagram showing the functional configuration of the in-vehicle measurement device 70. The in-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 in-vehicle measurement device 70 can be realized in terms of hardware by electronic elements such as a computer CPU and mechanical parts, and can be realized in terms of software by a computer program or the like. Here, however, functional blocks realized by their cooperation are depicted. Therefore, it is understood by those skilled in the art that these functional blocks can be realized in various forms by combinations of hardware and software.

[0017] The vehicle measurement unit 71 has a speedometer 71a, a GPS receiver 71b, and an acceleration sensor 71c mounted on the vehicle, and measures the running state of the vehicle. The speedometer 71a measures the running speed of the vehicle. The GPS receiver 71b measures the current position information (latitude, longitude, and altitude) of the vehicle. The acceleration sensor 71c measures the acceleration in the three-axis directions of the vehicle. The three-axis directions are, for example, the front-rear direction, left-right direction, and up-down direction of the vehicle.

[0018] 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 the tire 7 mounted on the vehicle, or are firmly wound and fixed to the 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 the inner liner or the like of the tire 7. Incidentally, the acceleration sensor 71c may be disposed on the inner liner of the tire 7.

[0019] The information acquisition unit 73 acquires vehicle measurement information (such as traveling speed, position information, acceleration, etc.) measured by the vehicle measurement unit 71, tire measurement information (such as tire temperature and air pressure, etc.) measured by the tire measurement unit 72, and tire identification information and the like described later. The information acquisition unit 73 associates the measured time information or the acquired time information with each measurement data included in the vehicle measurement information and the tire measurement information. The information acquisition unit 73 transmits the vehicle measurement information and the tire measurement information together with the time information associated with each measurement data from the communication unit 74 to the wear estimation device 10.

[0020] When an electronic control device of the vehicle or a device such as a digital tachometer is installed in the vehicle, the information acquisition unit 73 may acquire the traveling speed, acceleration, position information, etc. of the vehicle collected by the device. The communication unit 74 is communicatively connected 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 wear estimation device 10 via the communication network 9.

[0021] Returning to FIG. 1, the weather information server device 80 provides weather information for each location. The weather information provided by the weather information server device 80 is information including precipitation amount, snow accumulation amount, snowfall amount, temperature, sunshine duration, etc. at each location. The wear estimation device 10 acquires the weather information at the location where the vehicle is traveling from the weather information server device 80.

[0022] The wear estimation device 10 includes a communication unit 11, a vehicle information acquisition unit 12, a tire severity generation unit 121, a groove information acquisition unit 13, a groove information management unit 14, a wear estimation unit 15, and a storage unit 16. Each unit in the wear estimation device 10 can be realized in terms of hardware by electronic elements such as a computer CPU and mechanical parts, and can be realized in terms of software by a computer program or the like. Here, functional blocks realized by their cooperation are depicted. Therefore, it is understood by those skilled in the art that these functional blocks can be realized in various forms by a combination of hardware and software.

[0023] The communication unit 11 is communicatively connected to the communication network 9 by wireless or wired communication and communicates with the communication unit 74 of the in-vehicle measurement device 70. The communication unit 11 also communicates with the weather information server device 80 via the communication network 9.

[0024] The vehicle information acquisition unit 12 acquires vehicle measurement information (travel speed, position information, acceleration, etc.) and tire measurement information (tire temperature and air pressure, etc.) transmitted from the in-vehicle measurement device 70 mounted on the vehicle. The vehicle information acquisition unit 12 stores the acquired vehicle measurement information in the storage unit 16 as vehicle measurement data 16a. The vehicle measurement data 16a is used to calculate the driving conditions such as the driving distance of the vehicle used for estimating the wear of the tire 7. Also, when the tire measurement information is used for estimating the wear of the tire 7, the vehicle information acquisition unit 12 stores the acquired tire measurement information in the storage unit 16.

[0025] The vehicle information acquisition unit 12 can read the vehicle measurement data 16a from the storage unit 16 and calculate and acquire the driving distance based on the position information. The vehicle information acquisition unit 12 uses the first date and time information D1, the second date and time information D2, and the third date and time information D3, which will be described later. The driving distance of the vehicle may be calculated based on the speed data in the vehicle measurement data 16a and the data of the time associated with the data. That is, the driving distance of the vehicle can be calculated by multiplying the speed data arranged in time series by the time difference until the next time point. The driving speed of the vehicle may be calculated from the driving distance of the vehicle based on the position information arranged in time series and the acquisition interval of the position information.

[0026] If information regarding the driving distance of the vehicle is provided from the vehicle or an external device for vehicle management, etc., the vehicle information acquisition unit 12 does not need to calculate the driving distance itself and may acquire information regarding the driving distance from the vehicle or the external device.

[0027] The vehicle information acquisition unit 12 outputs the acquired driving distance to the wear estimation unit 15. When the vehicle information acquisition unit 12 uses tire measurement information (such as tire temperature and air pressure) for wear estimation of the tire 7, the acquired tire measurement information is output to the wear estimation unit 15.

[0028] In addition, the vehicle information acquisition unit 12 acquires data used for estimating the wear state of the tire 7 from the storage unit 16 among the vehicle specification data 16c, the tire specification data 16d, and the tire position data 16e, and outputs it to the wear estimation unit 15. The storage unit 16 is a storage device composed of, for example, an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, etc., and stores data provided in advance regarding various vehicle and tire 7 specifications.

[0029] The vehicle specification data 16c includes information regarding vehicle performance such as, for example, the manufacturer, vehicle name, vehicle model, vehicle body weight, drive train, overall length, vehicle width, vehicle height, maximum load capacity, etc. In addition, the tire specification data 16d includes information regarding the performance of the tire 7 such as, for example, the manufacturer, product name, tire size, tire width, aspect ratio, wear resistance performance, tire strength, static stiffness, dynamic stiffness, tire outer diameter, load index, manufacturing date, etc. Further, the tire position data 16e includes information regarding the mounting position of the tire 7 to be worn on the vehicle, tire identification information, and information regarding the axle to which it is attached. The tire identification information is a series of numbers such as a manufacturing number attached to each tire to identify each tire. The information regarding the tire identification information, the mounting position of the tire, and the axle may be stored in the storage unit 16, for example, when an operator performs an input operation when mounting the tire on the vehicle or by reading an RFID tag.

[0030] The tire severity generation unit 121 reads the vehicle measurement data 16a from the storage unit 16, and generates a value calculated based on the distribution of the traveling speed of the vehicle as severity information for tire wear (hereinafter referred to as tire severity information). The tire severity generation unit 121 divides the traveling speed of the vehicle into a plurality of speed ranges such as low speed, medium speed, and high speed, obtains the distribution of the traveling speed acquired during the period for estimating the wear state of the tire 7, and calculates the frequency included in each speed range as the tire severity information.

[0031] For example, the tire severity generation unit 121 sets the low speed range to less than 28 km / h, the medium speed range to 28 km / h or more and less than 56 km / h, and the high speed range to 56 km / h or more. For example, when estimating the wear of the tire 7 due to the traveling of the vehicle for one month, the tire severity generation unit 121 classifies the traveling speed data acquired during the one month into a plurality of speed ranges, and calculates the frequency included in each speed range.

[0032] FIG. 3 is a chart for explaining the generation of tire severity information based on the traveling speed. In FIG. 3, during the period for estimating the wear state of the tire 7, a total of 5000 traveling speed data have been acquired, and these data are classified into a low speed range, a medium speed range, and a high speed range. The tire severity generation unit 121 calculates the frequency by dividing the number of data included in each speed range by the total number of data, and sets the calculated values 0.7, 0.2, and 0.1 as the tire severity information.

[0033] For example, when the vehicle travels on a road with a narrow width or a poor road surface condition, and frequent turning or stopping occurs, the traveling speed is mostly distributed in the low speed range, and although there are few accelerations and decelerations, the wear of the tire 7 may increase. On the other hand, when the vehicle is traveling on an ordinary road or a highway, the traveling speed is mostly distributed in the high speed range, and although the traveling distance increases, the wear of the tire 7 tends to decrease. The tire severity generation unit 121 outputs the tire severity information generated based on the distribution of the traveling speed to the wear estimation unit 15.

[0034] Further, the tire severity generation unit 121 reads the vehicle measurement data 16a from the storage unit 16, and calculates the sum of the squares of each data for the acceleration data of the vehicle acquired during the period of estimating the wear state of the tire 7 as tire severity information for tire wear. The tire severity generation unit 121 may use the accelerations in the two axial directions of the longitudinal direction and the lateral direction of the vehicle as the acceleration of the vehicle, and calculate the sum of the squares of the acceleration data for each direction. Further, the tire severity generation unit 121 may obtain the sum of squares for the acceleration in any one axial direction or the three axial directions among the accelerations in the three axial directions.

[0035] When the acceleration of the vehicle increases during the wear of the tire 7, the load on the tire 7 increases and the wear tends to progress. The tire severity generation unit 121 includes the sum of the squares of the acceleration measured by the vehicle in the tire severity information and outputs it to the wear estimation unit 15.

[0036] The groove information acquisition unit 13 acquires the tire groove data 16b from the storage unit 16 and outputs it to the wear estimation unit 15. The tire groove data 16b is data including tire identification information, new groove depth, and starting groove depth. The groove information acquisition unit 13 acquires the tire groove data 16b based on the tire identification information of the tire 7 for which wear is to be estimated. As described above, the new groove depth is the groove depth in the new state of the tire 7, and the starting groove depth is the groove depth at the time (corresponding to the first date and time information D1) that serves as the starting point for estimating the wear state of the tire 7. The starting groove depth is assumed, for example, in the case of estimating the wear of the tire 7 that is mounted on the vehicle and is in use, and the groove depth is measured for the wear situation at the starting point of the wear estimation and used as the starting groove depth. Also, when a new tire 7 is mounted on the vehicle and wear is estimated based on the subsequent driving situation, the new groove depth and the starting groove depth have the same value.

[0037] As the starting groove depth, it is preferable to use the latest data actually measured for the tire 7 or the value obtained by subtracting the previously estimated wear amount.

[0038] Further, the tire groove data 16b includes first date-time information D1 representing the point in time that serves as the starting point for estimating the wear of the tire 7, second date-time information D2 representing the point in time for estimating the wear state of the tire 7, and third date-time information D3 representing the point in time when the tire 7 is replaced (replacement of summer and winter tires) or the mounting position is changed. Each date-time information may be just the date or may include the time in addition to the date. When the groove information acquisition unit 13 uses each date-time information as input data to the calculation model 15a in addition to the new groove depth and the starting groove depth, the groove information acquisition unit 13 may output each date-time information included in the tire groove data 16b to the wear estimation unit 15.

[0039] The groove information management unit 14 updates the starting groove depth, the first date-time information D1, the second date-time information D2, and the third date-time information D3 associated with the tire identification information of the tire 7, and stores them in the storage unit 16 as the tire groove data 16b. The groove information management unit 14 acquires the groove depth of the tire 7 measured during regular inspections or the like as the starting groove depth, and updates the tire groove data 16b. The tire wear estimation system 100 inputs tire harshness information based on the mileage, driving speed, and acceleration after the groove depth of the tire 7 is measured into a calculation model 15a described later to estimate the wear state of the tire 7. The groove information management unit 14 may acquire the measured groove depth of the tire 7 as the starting groove depth and update the tire groove data 16b when replacing summer and winter tires.

[0040] When the groove information management unit 14 performs wear estimation, for example, once a month, the groove depth at the time of the previous month is calculated as the starting groove depth based on the wear state estimated in the previous month. The vehicle information acquisition unit 12 calculates the mileage from the point in time (first date-time information D1) when the wear state was estimated in the previous month to the point in time (second date-time information D2) when wear estimation is performed as the driving situation, and outputs it to the wear estimation unit 15. The tire harshness generation unit 121 reads the vehicle measurement data 16a, generates tire harshness information based on the driving speed and acceleration data from the first date-time information D1 to the second date-time information D2, and outputs it to the wear estimation unit 15.

[0041] The vehicle information acquisition unit 12 acquires the driving situation using the third date and time information D3 indicating the time when the summer and winter tires are replaced. For example, consider the case where the winter tires used in the previous year's winter are also used this year. The vehicle information acquisition unit 12 reads the vehicle measurement data 16a from the date and time (the first date and time information D1) when the groove depth (starting groove depth) of the winter tires was measured in the previous year to the date and time (the third date and time information D3) when the winter tires were replaced with summer tires, calculates the driving distance, etc., and outputs it to the wear estimation unit 15 as the driving situation. The tire severity generation unit 121 reads the vehicle measurement data 16a from the first date and time information D1 to the third date and time information D3, generates tire severity information based on the driving speed and acceleration, and outputs it to the wear estimation unit 15. Also, the vehicle information acquisition unit 12 acquires the driving situation using the third date and time information D3 indicating the time when the mounting position is changed by tire rotation. When tire rotation is performed after the date when the starting groove depth was measured, it forms a time series of the date and time information (the first date and time information D1) of the starting groove depth, the date and time information (the third date and time information D3) of tire rotation, and the date and time information (the second date and time information D2) for estimating the tire wear state. The vehicle information acquisition unit 12 reads, regarding tire rotation, for example, the vehicle measurement data 16a from the first date and time information D1 to the third date and time information D3 at a certain mounting position M1, calculates the driving distance, etc., and outputs it to the wear estimation unit 15 as the driving situation, and the wear state of the tire is estimated by the wear estimation unit 15. At this time, the tire severity generation unit 121 reads the vehicle measurement data 16a from the first date and time information D1 to the third date and time information D3 at the mounting position M1, generates tire severity information based on the driving speed and acceleration, and outputs it to the wear estimation unit 15. Further, the vehicle information acquisition unit 12 reads the vehicle measurement data 16a from the third date and time information D3 to the second date and time information D2 at the mounting position M2 after tire rotation is performed, calculates the driving distance, etc., and outputs it to the wear estimation unit 15 as the driving situation, and the wear state of the tire is estimated by the wear estimation unit 15. At this time, the tire severity generation unit 121 reads the vehicle measurement data 16a from the third date and time information D3 to the second date and time information D2 at the mounting position M2, generates tire severity information based on the driving speed and acceleration, and outputs it to the wear estimation unit 15.

[0042] The wear estimation unit 15 has an arithmetic model 15a and estimates the wear state of the tire 7. The arithmetic model 15a is a machine learning model that calculates the wear state (information such as wear amount and wear rate) of the tire 7 based on the input information. FIG. 4 is a schematic diagram for explaining the wear estimation and learning of the arithmetic model 15a. The input data to the arithmetic model 15a is generally classified into each system of vehicle measurement information, tire severity information, tire groove information, and other information.

[0043] The input data related to vehicle measurement information includes the acceleration and driving distance of the vehicle. The driving distance is acquired by the vehicle information acquisition unit 12 as described above. It should be noted that the acceleration of the vehicle is appropriately used as input data to the arithmetic model. Also, when the temperature and air pressure of the tire 7 are used for estimating the wear of the tire 7, these pieces of information may be included in the input data.

[0044] The input data related to tire severity information is the tire severity information calculated by the tire severity generation unit 121. The tire severity information includes that calculated based on the distribution of the driving speed of the vehicle as described above and that calculated by calculating the sum of the squares of the accelerations measured in the vehicle.

[0045] The input data related to tire groove information includes the new groove depth, starting groove depth, and each date and time information (D1, D2, D3) of the tire 7 included in the tire groove data 16b. Each date and time information is used when it is input data to the arithmetic model 15a in the wear estimation of the tire 7.

[0046] The input data by other information includes the road surface state estimated based on weather information, air temperature, precipitation, etc., the maximum load capacity of the vehicle included in the vehicle specification data 16c, the wear resistance performance, etc. included in the tire specification data 16d. The wear resistance performance of the tire 7 uses, for example, a tire wear index value obtained by standardizing the wear resistance performance of various tread compounds with the standard compound as 100 based on the Lamborne wear test. Also, the input data by other information includes the mounting position of the tire 7 included in the tire position data 16e, tire identification information, and information related to the axle.

[0047] The arithmetic model 15a uses a learning model such as a neural network. The arithmetic model 15a is constructed using methods such as DNN (Deep Neural Network) or decision trees. Also, the arithmetic model 15a may be, for example, a multiple linear regression model for input information and be generated by learning.

[0048] FIG. 5 is a block diagram showing the functional configuration of the arithmetic model generation system 110. The arithmetic model generation system 110 includes, in addition to the configuration of the tire wear estimation system 100, a tire wear measurement device 60 and an arithmetic model generation device 20 having a learning processing unit 21 and the like.

[0049] The tire wear measurement device 60 directly measures the depth of the grooves provided in the tread of the tire 7 and acquires information on the wear state of the tire 7. The operator may measure or estimate the depth of each groove with a measuring instrument, a camera, etc., and the tire wear measurement device 60 may store the measurement data input by the operator. Also, the tire wear measurement device 60 may be a dedicated device that measures the depth of the grooves by mechanical or optical methods and stores information on the wear state.

[0050] Specifically, for example, when the tire has 4 grooves, the tire wear measurement device 60 measures at 4 locations in the width direction and further measures at 3 locations at intervals of, for example, 120° in the circumferential direction of the same groove. Thereby, uneven wear data in the width direction or circumferential direction of the tire is also stored in the tire wear measurement device 60. Note that since the diameter of the tire changes due to wear, the tire wear measurement device 60 may indirectly measure the depth of the groove by calculation from information on the running distance and the rotation speed and speed of the tire. In addition, a device that directly measures the depth of the groove and a device that predicts by calculation from the running distance and the rotation speed and speed of the tire may be used in combination.

[0051] The calculation model generation device 20 has a learning processing unit 21 in addition to each component of the wear estimation device 10. The parts corresponding to each component of the wear estimation device 10 in the calculation model generation device 20 have the same functions as those of the wear estimation device 10, but the calculation model 15a is before or during learning.

[0052] The learning processing unit 21 acquires information on the wear state of the tire 7 from the tire wear measurement device 60 via the communication unit 11. Referring to FIG. 4, in the learning process of the calculation model 15a, based on the input information, the wear state (such as the wear amount and wear rate) of the tire 7 as output data is estimated by the calculation model 15a and compared with the teacher data.

[0053] The learning processing unit 21 newly sets various coefficients in the calculation process such as weighting based on the comparison result between the wear state estimated by the calculation model 15a and the teacher data, and repeats the update of the model to execute learning. The tire wear estimation system 100 estimates the wear state of the tire 7 using the calculation model 15a that has been learned by the calculation model generation system 110. In addition, in the learning process of the calculation model 15a, known learning methods such as gradient boosting can be used. Also, for the verification of the calculation model 15a, known verification methods such as random data sampling and cross-validation can be used.

[0054] Next, the operations of the tire wear estimation system 100 and the calculation model generation system 110 will be described. FIG. 6 is a flowchart showing the procedure of the wear estimation process by the tire wear estimation system 100. The vehicle information acquisition unit 12 reads the vehicle measurement data 16a and acquires vehicle information such as vehicle measurement information (S1). In step S1, when using tire measurement information for estimating the wear of the tire 7, the vehicle information acquisition unit 12 acquires the tire measurement information stored in the storage unit 16. Also, in step S1, the vehicle information acquisition unit 12 reads from the storage unit 16 necessary information such as vehicle specifications, tire specifications, tire position, maximum load of the vehicle, and wear resistance performance of the tire as other information. The vehicle information acquisition unit 12 reads the tire groove data 16b and calculates the travel distance based on the first date and time information D1, the second date and time information D2, and the third date and time information D3 (S2).

[0055] The tire severity generation unit 121 reads the vehicle measurement data 16a and the tire groove data 16b and generates tire severity information regarding the vehicle's traveling speed and acceleration based on the first date and time information D1, the second date and time information D2, and the third date and time information D3 (S3). As described above, the tire severity information is generated by a value calculated based on the distribution of the vehicle's traveling speed and the sum of the squares of the accelerations.

[0056] The groove information acquisition unit 13 reads the tire groove data 16b from the storage unit 16 and acquires the new groove depth, starting groove depth, and each date and time information (S4). The wear estimation unit 15 acquires the input data from the vehicle information acquisition unit 12, the tire severity generation unit 121, and the groove information acquisition unit 13, estimates the wear state of the tire 7 by the calculation model 15a (S5), and ends the process. The calculation model 15a uses the learned calculation model generated by the calculation model generation system 110.

[0057] FIG. 7 is a flowchart showing the procedure of the generation process of the arithmetic model 15a by the arithmetic model generation system 110. The processes from step S11 to S14 shown in FIG. 7 are equivalent to the processes from step S1 to S4 shown in FIG. 6, and the description thereof is omitted for the sake of brevity. The learning processing unit 21 of the arithmetic model generation device 20 acquires information on the wear state of each tire 7 from the tire wear measurement device 60 (S15).

[0058] The wear estimation unit 15 acquires input data from the vehicle information acquisition unit 12, the tire severity generation unit 121, and the groove information acquisition unit 13, and estimates the wear state of the tire 7 using the arithmetic model 15a (S16). When the road surface condition or the like is used as the input data of the arithmetic model 15a, a processing unit (not shown) for estimating the road surface condition is provided, and the estimated road surface condition is input from the processing unit to the wear estimation unit 15.

[0059] The learning processing unit 21 compares the wear state of the tire 7 estimated by the arithmetic model 15a with the measured wear state of the tire 7 as teacher data (S17). The learning processing unit 21 updates the arithmetic model 15a based on the comparison result in step S16 (S18), and ends the process. The arithmetic model generation device 20 updates the arithmetic model 15a by repeating these processes, and improves the estimation accuracy of the wear state of the tire 7.

[0060] FIG. 8 is a chart showing an example of the estimation accuracy according to the embodiment. In the embodiment shown in FIG. 8, the frequency calculated based on the distribution of the traveling speed is generated as tire severity information and used as the input data of the arithmetic model 15a. The comparative example shows a case where the frequency calculated based on the distribution of the traveling speed is not used as the input data of the arithmetic model 15a. In the embodiment and the comparative example, after the arithmetic model 15a is learned for vehicle A and vehicle B, respectively, the root mean square error (RMSE) between the estimated value and the true value is obtained using test data.

[0061] For example, looking at vehicle A, the RMSE value in the comparative example is 0.986, while in the example it is 0.677. By generating the frequency calculated based on the distribution of the driving speed as tire severity information and using it as the input data for the calculation model 15a, it can be seen that the estimation accuracy of the wear state of tire 7 is improved. Similarly, for vehicle B, it can be seen that the estimation accuracy of the wear state of tire 7 is improved by the example.

[0062] The tire wear estimation system 100 includes a vehicle information acquisition unit 12, a tire severity generation unit 121, and a wear estimation unit 15. The vehicle information acquisition unit 12 acquires information including the driving distance and driving speed of the vehicle. The tire severity generation unit 121 generates, as tire severity information for tire wear, a value calculated based on the distribution of the driving speed acquired by the vehicle information acquisition unit 12. The wear estimation unit 15 has a calculation model 15a that calculates the wear state of tire 7 based on the input information, and inputs the driving distance acquired by the vehicle information acquisition unit 12 and the tire severity information generated by the tire severity generation unit 121 into the calculation model 15a to estimate the wear state of tire 7. Thereby, the tire wear estimation system 100 can improve the estimation accuracy of the wear state of tire 7.

[0063] The tire severity generation unit 121 divides the driving speed of the vehicle into a plurality of speed ranges, and for each speed range, generates, as tire severity information, a value obtained by calculating the frequency of the driving speed acquired by the vehicle information acquisition unit 12 within the period for estimating the wear state. Thereby, the tire wear estimation system 100 can classify and calculate the frequency of the driving speed, for example, into a low speed range, a medium speed range, and a high speed range, and use it as the input data for the calculation model 15a.

[0064] In addition, the vehicle information acquisition unit 12 further acquires information on the acceleration of the vehicle, and the tire severity generation unit 121 generates tire severity information including the sum of the squares of the accelerations acquired by the vehicle information acquisition unit 12. Thereby, the tire wear estimation system 100 can improve the estimation accuracy of the wear state of the tire 7 by using the value calculated from the sum of the squares of the accelerations of the vehicle as the tire severity information for tire wear.

[0065] The wear estimation unit 15 estimates the wear state for each of a plurality of grooves of the tire 7. Thereby, the tire wear estimation system 100 can estimate the uneven wear state of the tire 7 by estimating the wear state for each of the plurality of grooves provided in the tire width direction.

[0066] The tire wear estimation method of the present embodiment includes a vehicle information acquisition step, a tire severity generation step, and a wear estimation step. The vehicle information acquisition step acquires information including the traveling distance and traveling speed of the vehicle. The tire severity generation step generates, as tire severity information for tire wear, a value calculated based on the distribution of the traveling speed acquired in the vehicle information acquisition step. The wear estimation step inputs the traveling distance acquired in the vehicle information acquisition step and the tire severity information generated in the tire severity generation step into an arithmetic model 15a that calculates the wear state of the tire 7 based on the input information, and estimates the wear state of the tire 7. According to this tire wear estimation method, the estimation accuracy of the wear state of the tire 7 can be improved.

[0067] The calculation model generation system 110 includes a vehicle information acquisition unit 12, a tire severity generation unit 121, a wear estimation unit 15, and a learning processing unit 21. The vehicle information acquisition unit 12 acquires information including the driving distance and driving speed of the vehicle. The tire severity generation unit 121 generates, as tire severity information for tire wear, a value calculated based on the distribution of the driving speed acquired by the vehicle information acquisition unit 12. The wear estimation unit 15 has a calculation model 15a for calculating the wear state of tire 7 based on the input information, and inputs the driving distance acquired by the vehicle information acquisition unit 12 and the tire severity information generated by the tire severity generation unit 121 into the calculation model 15a to estimate the wear state of tire 7. The learning processing unit 21 learns the calculation model 15a using the measured wear state of tire 7 as teacher data. Thereby, the calculation model generation system 110 can generate the calculation model 15a that uses, as tire severity information, a value calculated based on the distribution of the driving speed of the vehicle and uses the tire severity information as input data, and can improve the estimation accuracy of the wear state of tire 7.

[0068] FIG. 9 is a chart showing the accuracy of tire wear estimation with respect to the amount of wear. In FIG. 9, the new groove depth of tire 7 is 18 mm, and the estimation error for the amount of wear from 1 mm to 12 mm is calculated. When the amount of wear is 1 mm, it means that the tire 7 has worn 1 mm from an arbitrary starting groove depth, such as a case where the groove depth of tire 7 changes from 15 mm to 14 mm, or a case where it changes from 6 mm to 5 mm. In the example, the operation model 15a is learned using the new groove depth and the starting groove depth as input data according to this embodiment, and the wear state of tire 7 is estimated by the learned operation model 15a using the new groove depth and the starting groove depth as input data. In the comparative example, the operation model 15a is learned without using the new groove depth and the starting groove depth as input data, and the wear state of tire 7 is estimated by the learned operation model 15a without using the new groove depth and the starting groove depth as input data. As shown in FIG. 9, it can be seen that the estimation error according to the example is better than that of the comparative example. When comparing the example and the comparative example, for example, the estimation error of the example at a wear amount of 6 mm is 0.11 mm better than that of the comparative example, and the estimation error of the example at a wear amount of 9 mm is 0.09 mm better than that of the comparative example. Considering that a wear amount of 0.1 mm of tire 7 corresponds to approximately a driving distance of 3000 km of the vehicle, it is considered that the estimation error is sufficiently improved in the example compared to the comparative example.

[0069] The vehicle information acquisition unit 12 of the tire wear estimation system 100 acquires information including the driving situation of the vehicle. The groove information acquisition unit 13 acquires the new groove depth, which is the groove depth of tire 7 in a new state when mounted on the vehicle, and the starting groove depth, which is the groove depth at the time point that serves as the starting point for estimating the wear of tire 7. The wear estimation unit 15 estimates the wear state of tire 7 based on the driving situation acquired by the vehicle information acquisition unit 12 and the machine-learned operation model 15a using the new groove depth and the starting groove depth acquired by the groove information acquisition unit 13 as input data.

[0070] The groove information acquisition unit 13 acquires first date and time information D1 representing the time point that is the starting point of the tire wear estimation of the tire 7, and second date and time information D2 representing the time point for estimating the wear state of the tire 7. The wear estimation unit 15 inputs the driving situation of the vehicle calculated based on the first date and time information D1 and the second date and time information D2 into the calculation model 15a to estimate the wear state of the tire 7. Thereby, the tire wear estimation system 100 can estimate the wear considering the date and time of the starting point of the wear estimation and the time point for estimating the wear, and can improve the estimation accuracy of the wear state of the tire 7.

[0071] Further, the groove information acquisition unit 13 acquires third date and time information D3 representing the time point when the tire 7 is replaced or the mounting position is changed. The wear estimation unit 15 inputs the driving situation of the vehicle calculated based on the first date and time information D1, the second date and time information D2, and the third date and time information D3 into the calculation model 15a to estimate the wear state of the tire 7. Thereby, the tire wear estimation system 100 can estimate the wear considering the time point when the tire 7 is replaced or the mounting position is changed, and can improve the estimation accuracy of the wear state of the tire 7.

[0072] In the tire wear estimation system 100, the starting groove depth may be calculated based on the wear state estimated by the wear estimation unit 15. For example, in the case where wear estimation is performed every month, the groove depth at the time of the previous month is calculated as the starting groove depth based on the wear state estimated in the previous month, and the wear state of this month is estimated. Thereby, the tire wear estimation system 100 can calculate the starting groove depth according to the period during which the wear estimation is performed, and can estimate the wear state of the tire 7.

[0073] The groove information management unit 14 of the tire wear estimation system 100 causes the storage unit 16 to store the starting groove depth in association with the tire identification information attached to the tire 7. The groove information acquisition unit 13 reads and acquires the starting groove depth corresponding to the tire identification information from the storage unit 16. Thereby, the tire wear estimation system 100 can manage the starting groove depth based on the tire identification information for each tire 7 and can use it for estimating the wear state of the tire 7.

[0074] FIG. 10 is a schematic diagram for explaining the definition of the positions of the grooves formed in the tire 7. The plurality of grooves formed in the tire 7 can be identified by attaching groove identification information such as a to d with reference to the serial surface S of the tire 7, for example. The serial number of the tire 7 and the manufacturing symbol are engraved on the serial surface, and the surface opposite to the serial surface can be identified for each tire. The serial surface of the tire 7 faces the inside (the center side of the axle) or the outside of the vehicle when mounted on the axle of the vehicle. The groove positions are identified by attaching symbols 1 to 4 in order from the outside of the vehicle. When the serial surface faces the outside, the groove identification information a, b, c, and d are respectively associated with the groove positions 1, 2, 3, and 4. When the serial surface faces the inside, the groove identification information a, b, c, and d are respectively associated with the groove positions 4, 3, 2, and 1.

[0075] The groove information management unit 14 causes the storage unit 16 to store the correspondence between the groove identification information and the groove positions in the tire groove data 16b. When the correspondence between the groove identification information and the groove positions changes, for example, during tire rotation or tire replacement, the groove information management unit 14 causes the storage unit 16 to store the changed correspondence between the groove identification information and the groove positions in the tire groove data 16b.

[0076] The groove information acquisition unit 13 may read out the correspondence relationship between the groove identification information and the groove position from the tire groove data 16b in addition to the new groove depth and the starting groove depth, etc., and output it to the wear estimation unit 15. The calculation model 15a may include the correspondence relationship between the groove identification information and the groove position in the input data. The wear estimation unit 15 estimates the wear state of the tire 7 using the calculation model 15a that includes the correspondence relationship between the groove identification information and the groove position in the input data. Thereby, the tire wear estimation system 100 can estimate the wear state of the tire 7 in consideration of the orientation when the tire 7 is mounted on the axle, and particularly can improve the estimation accuracy of the uneven wear state. Further, the calculation model generation system 110 can generate the calculation model 15a that takes into account the orientation of the tire 7 by generating the calculation model 15a that includes the correspondence relationship between the groove identification information and the groove position in the input data, and can improve the estimation accuracy of the uneven wear state by the calculation model 15a.

[0077] (Modification example) The tire groove data 16b may include elapsed information indicating the number of days elapsed from the time when the groove depth of the tire 7 was measured to the time that is the starting point of wear estimation of the tire 7. The elapsed information may be only the number of days, or may include time in addition to the number of days. The groove information acquisition unit 13 outputs the elapsed information included in the tire groove data 16b to the wear estimation unit 15 in addition to the new groove depth and the starting groove depth. The wear estimation unit 15 estimates the wear state of the tire 7 by the calculation model 15a based on the input data including the elapsed information.

[0078] The groove information management unit 14 calculates the number of days elapsed from the measurement date of the groove depth of the tire 7 to the time that is the starting point of wear estimation of the tire 7 as elapsed information, and updates the tire groove data 16b. The tire wear estimation system 100 can estimate the wear state of the tire 7 in consideration of the number of days elapsed from the time when the groove depth of the tire 7 was measured to the time that is the starting point of wear estimation of the tire 7 by using the elapsed information.

[0079] Generalizing the technical idea embodied by the above embodiments and modification examples, it can be said that the technical idea described in the following items is also included.

[0080] The first item is a tire wear estimation system including a vehicle information acquisition unit that acquires information including the travel distance and travel speed of a vehicle, a tire severity generation unit that generates, as severity information for tire wear, a value calculated based on the distribution of the travel speed acquired by the vehicle information acquisition unit, and an arithmetic model that calculates the wear state of a tire based on the input information, and inputs the travel distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the arithmetic model to estimate the wear state of the tire.

[0081] The second item is the tire wear estimation system according to the first item, wherein the tire severity generation unit divides the travel speed of the vehicle into a plurality of speed ranges, and for each speed range, generates the severity information as a value obtained by calculating the frequency of the travel speed acquired by the vehicle information acquisition unit within a period for estimating the wear state.

[0082] The third item is the tire wear estimation system according to the first or second item, wherein the vehicle information acquisition unit further acquires information on the acceleration of the vehicle, and the tire severity generation unit generates the severity information including the sum of the squares of the accelerations acquired by the vehicle information acquisition unit.

[0083] The fourth item is the tire wear estimation system according to any one of the first to third items, wherein the wear estimation unit estimates the wear state for each of a plurality of grooves of the tire.

[0084] The fifth item is a tire wear estimation method comprising a vehicle information acquisition step of acquiring information including the traveling distance and traveling speed of a vehicle, a tire severity generation step of generating, as severity information for tire wear, a value calculated based on the distribution of the traveling speed acquired in the vehicle information acquisition step, and a wear estimation step of inputting the traveling distance acquired in the vehicle information acquisition step and the severity information generated in the tire severity generation step into an arithmetic model that calculates the wear state of the tire based on the input information and estimating the wear state of the tire.

[0085] The sixth item is an arithmetic model generation system comprising a vehicle information acquisition unit that acquires information including the traveling distance and traveling speed of a vehicle, a tire severity generation unit that generates, as severity information for tire wear, a value calculated based on the distribution of the traveling speed acquired by the vehicle information acquisition unit, a wear estimation unit that has an arithmetic model that calculates the wear state of the tire based on the input information, inputs the traveling distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the arithmetic model, and estimates the wear state of the tire, and a learning processing unit that causes the arithmetic model to learn using the wear state measured for the tire as teacher data.

[0086] As described above, the embodiments of the present invention have been described based on the embodiments. These embodiments are examples, and it is 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 such modifications and changes are also within the scope of the claims of the present invention. Therefore, the description and drawings in this specification should be treated as illustrative rather than restrictive.

Explanation of Reference Numerals

[0087] 7 Tire, 12 Vehicle information acquisition unit, 121 Tire severity generation unit, 15 Wear estimation unit, 15a Arithmetic model, 21 Learning processing unit, 100 Tire wear estimation system, 110 Arithmetic model generation system.

Claims

1. a vehicle information acquisition unit that acquires information including a travel distance and a travel speed of the vehicle; a tire severity generating unit that generates a value calculated based on the distribution of the traveling speed acquired by the vehicle information acquiring unit as severity information on tire wear; a wear estimation unit having a calculation model for calculating a tire wear state based on input information, the wear estimation unit inputting the travel distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the calculation model to estimate the tire wear state; A tire wear estimation system comprising:

2. The tire wear estimation system of claim 1, wherein the tire severity generation unit divides the vehicle's driving speed into a plurality of speed ranges, and for each speed range, generates as the severity information a value calculated by calculating the frequency with which the driving speed acquired by the vehicle information acquisition unit is included within the period for which the wear state is estimated.

3. The vehicle information acquisition unit further acquires information on the acceleration of the vehicle, The tire wear estimation system according to claim 1 , wherein the tire severity generation unit generates the severity information including a sum of squares of accelerations acquired by the vehicle information acquisition unit.

4. The tire wear estimation system according to claim 1 , wherein the wear estimation unit estimates a wear state for each of a plurality of grooves of the tire.

5. A vehicle information acquisition step of acquiring information including a travel distance and a travel speed of the vehicle; a tire severity generating step of generating, as severity information on tire wear, a value calculated based on the distribution of the traveling speed acquired in the vehicle information acquiring step; a wear estimation step of inputting the travel distance acquired in the vehicle information acquisition step and the severity information generated in the tire severity generation step into a calculation model that calculates a tire wear state based on the input information, and estimating a tire wear state; A tire wear estimation method comprising:

6. a vehicle information acquisition unit that acquires information including a travel distance and a travel speed of the vehicle; a tire severity generating unit that generates a value calculated based on the distribution of the traveling speed acquired by the vehicle information acquiring unit as severity information on tire wear; a wear estimation unit having a calculation model for calculating a tire wear state based on input information, the wear estimation unit inputting the travel distance acquired by the vehicle information acquisition unit and the severity information generated by the tire severity generation unit into the calculation model to estimate the tire wear state; a learning processing unit that learns the calculation model using a wear state measured for the tire as training data; A computational model generation system comprising:

Images