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

Abstract

This technology provides an improved accuracy in estimating the wear condition of tires. [Solution] The tire wear estimation system 100 comprises a vehicle information acquisition unit 12, a groove information acquisition unit 13, and a wear estimation unit 15. The vehicle information acquisition unit 12 acquires information about the vehicle, including driving conditions. The groove information acquisition unit 13 acquires the new groove depth, which is the groove depth of the tire 7 when it is new and mounted on the vehicle, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear. The wear estimation unit 15 estimates the wear state of the tire 7 based on a machine learning-prepared calculation model 15a that uses the driving conditions acquired by the vehicle information acquisition unit 12, as well as the new groove depth and starting groove depth acquired by the groove information acquisition unit 13, as input data.

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 a vehicle.

Background Art

[0002] Generally, tires wear out according to the driving state, driving distance, etc. In recent years, 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 underway.

[0003] Patent Document 1 describes a conventional generation system for a calculation model for estimating the wear amount of tires. In the conventional calculation model generation system, a tire information acquisition unit acquires tire data including the temperature and pressure of the tire. A position information acquisition unit acquires position data of the vehicle on which the tire is mounted. The wear amount calculation unit has a calculation model for calculating the tire wear amount based on the temperature, pressure, and position, and inputs the tire data and the position data corresponding to the tire data to calculate the tire wear amount by the calculation model. The calculation model update unit compares the wear amount measured by the tire with the wear amount calculated by the wear amount calculation unit, and updates the calculation model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The inventors believed that when constructing a machine learning-type computational model with, for example, the wear state of each tire groove as the objective variable and parameters including at least the vehicle's driving conditions as explanatory variables, there is room for improvement in the accuracy of estimating the tire wear state by appropriately setting the explanatory variables. Furthermore, the inventors believed that, considering that tires are sometimes removed and reinstalled during use due to summer / winter tire changes or tire rotation, ingenuity is needed in setting the explanatory variables.

[0006] This invention has been made in view of the above circumstances, and its objective is to provide a tire wear estimation system, a tire wear estimation method, and a calculation model generation system that can improve the accuracy of estimating the wear state of a tire. [Means for solving the problem]

[0007] A tire wear estimation system according to one aspect of the present invention comprises: a vehicle information acquisition unit that acquires information including the driving conditions of a vehicle; a groove information acquisition unit that acquires the new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and the starting groove depth, which is the groove depth at a point in time that serves as the starting point for estimating the wear of the tire; and a wear estimation unit that estimates the wear state of the tire based on a machine learning-prepared computational model that uses the driving conditions acquired by the vehicle information acquisition unit, and the new groove depth and the starting groove depth acquired by the groove information acquisition unit as input data.

[0008] Another aspect of the present invention is a tire wear estimation method. The tire wear estimation method comprises: a vehicle information acquisition step of acquiring information including driving conditions of a vehicle; a groove information acquisition step of acquiring a new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and a starting groove depth, which is the groove depth at a point in time that serves as the starting point for estimating the wear of the tire; and a wear estimation step of estimating the wear state of the tire based on a machine learning-prepared computational model that uses the driving conditions acquired in the vehicle information acquisition step, as well as the new groove depth and the starting groove depth acquired in the groove information acquisition step, as input data.

[0009] Another aspect of the present invention is a computational model generation system. The computational model generation system comprises: a vehicle information acquisition unit that acquires information including the driving conditions of a vehicle; a groove information acquisition unit that acquires the new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and the starting groove depth, which is the groove depth at a point in time that serves as the starting point for estimating the wear of the tire; a wear estimation unit that estimates the wear state of the tire based on a learning-type computational model that takes the driving conditions acquired by the vehicle information acquisition unit, and the new groove depth and the starting groove depth acquired by the groove information acquisition unit as input data; and a learning processing unit that trains the computational model using the measured wear state of the tire as training data. [Effects of the Invention]

[0010] According to the present invention, the accuracy of estimating the wear state of tires can be improved. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the functional configuration of the tire wear estimation system according to an embodiment. [Figure 2] This is a block diagram showing the functional configuration of an in-vehicle measurement device. [Figure 3] This is a schematic diagram illustrating wear estimation and learning of the computational model. [Figure 4] This is a block diagram showing the functional configuration of the computational model generation system. [Figure 5] This flowchart shows the procedure for tire wear estimation using the tire wear estimation system. [Figure 6] This flowchart shows the procedure for generating computational models using the computational model generation system. [Figure 7] This chart shows the accuracy of wear estimation relative to the amount of wear. [Figure 8] This is a schematic diagram illustrating the definition of the position of grooves formed in a tire. [Modes for carrying out the invention]

[0012] The present invention will be described below with reference to Figures 1 to 8, based on preferred embodiments. The same or equivalent components and members shown in each drawing are denoted by the same reference numerals, and redundant explanations are omitted as appropriate. Furthermore, the dimensions of the members in each drawing are enlarged or reduced as appropriate for ease of understanding. Also, some members that are not important for explaining the embodiments are omitted in each drawing.

[0013] (Embodiment) Figure 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 on-board measuring 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 vehicle speed, acceleration, and position information from an on-board measurement device 70 mounted on the vehicle via a communication network 9, such as the Internet. The wear estimation device 10 also acquires weather information from a weather information server device 80. Furthermore, the wear estimation device 10 acquires information on the groove depth of the tire 7 when it is new (hereinafter referred to as "new groove depth") and the groove depth at the point in time that serves as the starting point for estimating the wear state of the tire 7 (hereinafter referred to as "starting groove depth"). Based on the acquired information, the wear estimation device 10 performs calculations using a learning-type calculation model 15a 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 amount of wear and the wear rate of the tire 7. The wear state of the tire 7 may be, for example, the amount of wear (a value such as 1 mm), or the ratio of the amount of wear to the initial groove depth in the tire groove (a value such as 10%). Wear estimation refers to estimating the wear state of the tire 7, that is, information such as the amount of wear and the 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 hardware-wise by electronic elements such as a computer's CPU and mechanical parts, and software-wise 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 status 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, the left-right direction, and the 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 the air valve or the like of the tire 7 mounted on the vehicle, or are firmly wound around 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 mounted on 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 communicates and connects to the communication network 9 by wireless communication such as WiFi (registered trademark), etc., 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, air 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 groove information acquisition unit 13, a groove information management unit 14, a wear estimation unit 15, and a storage unit 16. Each part in the wear estimation device 10 can be realized hardware-wise by electronic elements such as a computer's CPU and mechanical parts, and software-wise by a computer program, etc. 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.

[0023] The communication unit 11 connects to the communication network 9 via wireless or wired communication and communicates with the communication unit 74 of the in-vehicle measuring 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 (driving speed, position information, acceleration, etc.) and tire measurement information (tire temperature, air pressure, etc.) transmitted from the on-board measuring device 70 mounted on the vehicle. The vehicle information acquisition unit 12 stores the acquired vehicle measurement information as vehicle measurement data 16a in the storage unit 16. The vehicle measurement data 16a is used to calculate driving conditions such as the vehicle's mileage, which is used for estimating tire wear of the tire 7. In addition, if the vehicle information acquisition unit 12 uses tire measurement information for estimating tire wear of the tire 7, it stores the acquired tire measurement information in the storage unit 16.

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

[0026] The vehicle information acquisition unit 12 does not need to calculate the mileage itself if information regarding the vehicle's mileage is provided by the vehicle or an external device for vehicle management, and may acquire the mileage information from the vehicle or an external device.

[0027] The vehicle information acquisition unit 12 outputs the acquired mileage to the wear estimation unit 15. If the vehicle information acquisition unit 12 uses tire measurement information (tire temperature and air pressure, etc.) to estimate tire wear of the tire 7, it outputs the acquired tire measurement information to the wear estimation unit 15. The vehicle information acquisition unit 12 may also output speed and acceleration information from the vehicle measurement data 16a to the wear estimation unit 15.

[0028] The vehicle information acquisition unit 12 also acquires data from the storage unit 16 that is used to estimate the wear state of the tire 7, from among the vehicle specification data 16c, tire specification data 16d, and 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 that has been provided in advance regarding the specifications of various vehicles and tires 7.

[0029] The vehicle specification data 16c includes information about the vehicle's performance, such as manufacturer, vehicle name, vehicle model, vehicle weight, drivetrain, overall length, vehicle width, vehicle height, and maximum load capacity. The tire specification data 16d includes information about the tire 7's performance, such as 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. The tire position data 16e includes information about the mounting position of the tire 7 on the vehicle for wear estimation, tire identification information, and the axle to which it is mounted. The tire identification information is a serial number, such as a manufacturing number, assigned to each tire to identify it. The tire identification information, tire mounting position, and axle information can be stored in the storage unit 16, for example, by an operator inputting the information when mounting the tire on the vehicle, or by reading an RFID tag.

[0030] The groove information acquisition unit 13 acquires tire groove data 16b from the storage unit 16 and outputs it to the wear estimation unit 15. The tire groove data 16b includes 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 whose wear is to be estimated. As described above, the new groove depth is the groove depth of the tire 7 in its new state, and the starting groove depth is the groove depth at the point in 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 to be, for example, the groove depth obtained by measuring the wear state at the point in time that serves as the starting point for wear estimation, and this is set as the starting groove depth. Also, when a new tire 7 is mounted on a vehicle and wear estimation is performed based on subsequent driving conditions, the new groove depth and the starting groove depth will be the same value.

[0031] The starting groove depth should be determined using the latest data actually measured for tire 7, or a value obtained by subtracting the amount of wear estimated in the past.

[0032] The tire tread data 16b also includes a first date and time information D1 representing the starting point for estimating tire wear 7, a second date and time information D2 representing the time for estimating the wear state of tire 7, and a third date and time information D3 representing the time when tire 7 was replaced (summer and winter tire replacement) or its mounting position was changed. Each date and time information may be just the date, or it may include both the date and time. The tread information acquisition unit 13 may output each date and time information included in the tire tread data 16b to the wear estimation unit 15 if it uses each date and time information as input data to the calculation model 15a, in addition to the new tread depth and starting tread depth.

[0033] The groove information management unit 14 updates the starting groove depth, first date and time information D1, second date and time information D2, and third date and time information D3, which are associated with the tire identification information of the tire 7, and stores them in the storage unit 16 as tire groove data 16b. The groove information management unit 14 acquires the measured groove depth of the tire 7 as the starting groove depth during periodic inspections, etc., and updates the tire groove data 16b. The tire wear estimation system 100 inputs data such as mileage, speed, and acceleration after the groove depth of the tire 7 has been measured into the calculation model 15a described later to estimate the wear state of the tire 7. The groove information management unit 14 may also acquire the measured groove depth of the tire 7 as the starting groove depth when summer and winter tires are changed, and update the tire groove data 16b.

[0034] The groove information management unit 14 calculates the starting groove depth based on the groove depth estimated in the previous month, for example, when wear estimation is performed every month. The vehicle information acquisition unit 12 calculates data such as mileage, speed, and acceleration as driving conditions from the time the wear condition was estimated in the previous month (first date and time information D1) to the time the wear estimation is performed (second date and time information D2), and outputs it to the wear estimation unit 15.

[0035] The vehicle information acquisition unit 12 acquires driving conditions using third date and time information D3, which represents the time when summer and winter tires were changed. For example, consider the case where winter tires used in the previous winter are used again this year. The vehicle information acquisition unit 12 reads vehicle measurement data 16a from the date and time when the groove depth (starting groove depth) of the winter tires was measured in the previous year (first date and time information D1) to the date and time when the winter tires were changed to summer tires (third date and time information D3), calculates the mileage, etc., and outputs it to the wear estimation unit 15 as driving conditions. The vehicle information acquisition unit 12 also acquires driving conditions using third date and time information D3, which represents the time when the mounting position was changed by tire rotation. If tire rotation is performed after the date on which the starting groove depth was measured, the time series will be: date and time information for the starting groove depth (first date and time information D1), date and time information for the tire rotation (third date and time information D3), and date and time information for estimating the tire wear state (second date and time information D2). The vehicle information acquisition unit 12 reads 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 mileage, etc., and outputs it to the wear estimation unit 15 as driving conditions, where the wear estimation unit 15 estimates the tire wear state. Furthermore, the vehicle information acquisition unit 12 reads 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 the tire rotation, calculates the mileage, etc., and outputs it to the wear estimation unit 15 as driving conditions, where the wear estimation unit 15 estimates the tire wear state.

[0036] The wear estimation unit 15 has a calculation model 15a and estimates the wear state of the tire 7. The calculation model 15a is a machine learning model that calculates the wear state of the tire 7 (information such as wear amount and wear rate) based on the input information. Figure 3 is a schematic diagram to explain the wear estimation and learning of the calculation model 15a. The input data to the calculation model 15a is generally classified into vehicle measurement information, tire tread information, and other information systems.

[0037] The input data related to vehicle measurement information includes the vehicle's speed, acceleration, and distance traveled. The distance traveled is acquired by the vehicle information acquisition unit 12 as described above. The input data related to tire tread information includes the new tread depth, starting tread depth, and date and time information (D1, D2, D3) of the tire tread data 16b. The date and time information is used as input data to the calculation model 15a in the tire wear estimation. If the temperature and air pressure of the tire 7 are used in the tire wear estimation, this information may also be included in the input data.

[0038] Other input data includes road surface conditions estimated based on weather information, temperature and precipitation, the maximum load capacity of the vehicle included in vehicle specification data 16c, and wear resistance performance included in tire specification data 16d. The wear resistance performance of tire 7 is determined using, for example, a tire wear index value that quantifies the wear resistance performance of various tread compounds based on the Lambourn wear test, with the standard compound set to 100. In addition, other input data includes the mounting position of tire 7 included in tire position data 16e, tire identification information, and axle information.

[0039] The computational model 15a uses a learning model such as a neural network. The computational model 15a is constructed using methods such as a Deep Neural Network (DNN) or a decision tree. Alternatively, the computational model 15a may be a multilinear regression model on input information, and the model may be generated through learning.

[0040] Figure 4 is a block diagram showing the functional configuration of the computational model generation system 110. In addition to the configuration of the tire wear estimation system 100, the computational model generation system 110 includes a tire wear measuring device 60 and a computational model generation device 20 having a learning processing unit 21, etc.

[0041] The tire wear measuring device 60 directly measures the depth of the grooves in the tread of the tire 7 and acquires information on the wear condition of the tire 7. Alternatively, the operator may measure or estimate the depth of each groove using measuring instruments or a camera, and the tire wear measuring device 60 may store the measurement data entered by the operator. In addition, the tire wear measuring 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 condition.

[0042] Specifically, the tire wear measuring device 60 measures at four points in the width direction if the tire has four grooves, and also measures at three points in the circumferential direction of the same groove, for example, at 120° intervals. This allows the tire wear measuring device 60 to store uneven wear data in the width direction or circumferential direction of the tire. Furthermore, since the diameter changes as the tire wears down, the tire wear measuring device 60 may indirectly measure the groove depth by calculation from the mileage and tire rotation speed / velocity information. In addition, a method that directly measures the groove depth may be used in combination with a method that predicts the groove depth by calculation from the mileage and tire rotation speed / velocity.

[0043] The computational model generation device 20 has a learning processing unit 21 in addition to the components of the wear estimation device 10. The parts of the computational model generation device 20 that correspond to the components of the wear estimation device 10 have the same functions as those of the wear estimation device 10, but the computational model 15a is either pre-training or in the process of training.

[0044] The learning processing unit 21 acquires information on the wear status of the tire 7 from the tire wear measuring device 60 via the communication unit 11. Referring to Figure 3, during the learning process of the calculation model 15a, the calculation model 15a estimates the wear status of the tire 7 (such as wear amount and wear rate) as output data based on the input information and compares it with the training data.

[0045] The learning processing unit 21 performs learning by repeatedly updating the model, setting various coefficients in the calculation process, such as weighting, for the calculation model 15a based on the comparison result between the wear state estimated by the calculation model 15a and the training data. The tire wear estimation system 100 estimates the wear state of the tire 7 using the calculation model 15a that has been trained by the calculation model generation system 110. In the learning process of the calculation model 15a, known learning methods such as gradient boosting can be used. In addition, known validation methods such as random data sampling and cross-validation can be used to validate the calculation model 15a.

[0046] Next, the operation of the tire wear estimation system 100 and the calculation model generation system 110 will be explained. Figure 5 is a flowchart showing the procedure for wear estimation processing by the tire wear estimation system 100. The vehicle information acquisition unit 12 reads vehicle measurement data 16a and acquires vehicle information such as vehicle measurement information (S1). In step S1, if the vehicle information acquisition unit 12 uses tire measurement information to estimate the wear of the tire 7, it acquires the tire measurement information stored in the storage unit 16. In step S1, the vehicle information acquisition unit 12 also reads other necessary information from the storage unit 16, such as vehicle specifications, tire specifications, tire position, maximum load capacity of the vehicle, and tire wear resistance performance. The vehicle information acquisition unit 12 reads tire tread data 16b and calculates the mileage 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).

[0047] The groove information acquisition unit 13 reads tire groove data 16b from the storage unit 16 and acquires new groove depth, starting groove depth, and date and time information (S3). The wear estimation unit 15 acquires input data from the vehicle information acquisition unit 12 and the groove information acquisition unit 13, estimates the wear state of the tire 7 using the calculation model 15a (S4), and terminates the process. The calculation model 15a uses a trained calculation model generated by the calculation model generation system 110.

[0048] Figure 6 is a flowchart showing the procedure for generating the calculation model 15a by the calculation model generation system 110. The processes from steps S11 to S13 shown in Figure 6 are equivalent to the processes from steps S1 to S3 shown in Figure 5, and for the sake of brevity, the explanation is omitted. The learning processing unit 21 of the calculation model generation device 20 acquires information on the wear status of each tire 7 from the tire wear measurement device 60 (S14).

[0049] The wear estimation unit 15 acquires input data from the vehicle information acquisition unit 12 and the groove information acquisition unit 13, and estimates the wear state of the tire 7 using the calculation model 15a (S15). When road surface conditions are used as input data for the calculation model 15a, a processing unit (not shown) for estimating road surface conditions is provided, and the estimated road surface conditions are input from this processing unit to the wear estimation unit 15.

[0050] The learning processing unit 21 compares the tire wear state estimated by the calculation model 15a with the measured tire wear state as training data (S16). Based on the comparison result in step S16, the learning processing unit 21 updates the calculation model 15a (S17) and terminates the process. The calculation model generation device 20 updates the calculation model 15a by repeating these processes, thereby improving the accuracy of the estimation of the tire wear state.

[0051] Figure 7 is a chart showing the accuracy of wear estimation for wear amounts. In Figure 7, the new groove depth of tire 7 is 18 mm, and the estimation error for wear amounts from 1 mm to 12 mm is calculated. A wear amount of 1 mm means that the tire 7 has worn down by 1 mm from an arbitrary starting groove depth, such as when the groove depth of tire 7 goes from 15 mm to 14 mm, or from 6 mm to 5 mm. In the example, the calculation model 15a was trained using the new groove depth and starting groove depth as input data according to this embodiment, and the wear state of tire 7 was estimated using the trained calculation model 15a with the new groove depth and starting groove depth as input data. In the comparative example, the calculation model 15a was trained without using the new groove depth and starting groove depth as input data, and the wear state of tire 7 was estimated using the trained calculation model 15a with the new groove depth and starting groove depth as input data. As shown in Figure 7, the estimation error in the example is better than that in the comparative example. Comparing the example with 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 a vehicle's mileage of approximately 3000 km, it can be said that the estimation error is sufficiently improved in the example compared to the comparative example.

[0052] The vehicle information acquisition unit 12 of the tire wear estimation system 100 acquires information about the vehicle, including its driving conditions. The groove information acquisition unit 13 acquires the new groove depth, which is the groove depth of the tire 7 when it is new, and the starting groove depth, which is the groove depth at the point in time when tire wear estimation begins. The wear estimation unit 15 estimates the wear state of the tire 7 based on a machine learning-prepared calculation model 15a that uses the driving condition vehicle information acquired by the vehicle information acquisition unit 12, and the new groove depth and starting groove depth acquired by the groove information acquisition unit 13 as input data. As a result, the tire wear estimation system 100 can estimate wear while considering which stage of wear progression the tire is in, and can improve the accuracy of estimating the wear state of the tire 7.

[0053] The groove information acquisition unit 13 acquires first date and time information D1, which represents the starting point for estimating tire wear 7, and second date and time information D2, which represents the time when the tire wear state of 7 is estimated. The wear estimation unit 15 inputs the vehicle's driving conditions, 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 tire wear state of 7. As a result, the tire wear estimation system 100 can estimate wear by considering the date and time of the starting point for wear estimation and the time when wear is estimated, thereby improving the accuracy of the tire wear state estimation.

[0054] The groove information acquisition unit 13 also acquires third date and time information D3, which represents the time when the tire 7 was replaced or its mounting position was changed. The wear estimation unit 15 inputs the vehicle's driving conditions, 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. As a result, the tire wear estimation system 100 can estimate wear considering the time when the tire 7 was replaced or its mounting position was changed, thereby improving the accuracy of the tire wear state estimation.

[0055] 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, if 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 for the current month is estimated. In this way, the tire wear estimation system 100 can calculate the starting groove depth in accordance with the period for which wear estimation is performed and estimate the wear state of the tire 7.

[0056] In the tire wear estimation system 100, the driving conditions include at least two of the vehicle's mileage, speed, and acceleration. This allows the tire wear estimation system 100 to estimate the wear state of the tire 7 by considering the driving conditions such as the vehicle's mileage, speed, and acceleration.

[0057] The calculation model 15a is generated by machine learning using the tire wear status measured on a vehicle in motion as training data. As a result, the tire wear estimation system 100 can estimate the wear status of the tire 7 using the calculation model 15a generated by machine learning.

[0058] The groove information acquisition unit 13 also acquires the starting groove depth for each of the multiple grooves provided in the tire 7. The wear estimation unit 15 estimates the wear state of the tire 7 for each groove using the calculation model 15a. As a result, 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 multiple grooves provided in the tire width direction.

[0059] The groove information management unit 14 of the tire wear estimation system 100 stores the starting groove depth in the storage unit 16 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. As a result, the tire wear estimation system 100 can manage the starting groove depth for each tire 7 based on the tire identification information and use it to estimate the wear state of the tire 7.

[0060] The tire wear estimation method of this embodiment comprises a vehicle information acquisition step, a groove information acquisition step, and a wear estimation step. The vehicle information acquisition step acquires information about the vehicle, including its driving conditions. The groove information acquisition step acquires the new groove depth, which is the groove depth of the tire 7 when it is new and mounted on the vehicle, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for tire wear estimation. The wear estimation step estimates the wear state of the tire 7 based on a machine learning-prepared computation model 15a that uses the driving conditions acquired in the vehicle information acquisition step, as well as the new groove depth and starting groove depth acquired in the groove information acquisition step, as input data. This tire wear estimation method allows for wear estimation while considering which stage of wear progression the tire is in, thereby improving the accuracy of estimating the wear state of the tire 7.

[0061] The calculation model generation system 110 comprises a vehicle information acquisition unit 12, a groove information acquisition unit 13, a wear estimation unit 15, and a learning processing unit 21. The vehicle information acquisition unit 12 acquires information about the vehicle, including its driving conditions. The groove information acquisition unit 13 acquires the new groove depth, which is the groove depth of the tire 7 when it is new, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating the wear of the tire 7. The wear estimation unit 15 estimates the wear state of the tire 7 based on a learning-type calculation model 15a that uses the driving conditions acquired by the vehicle information acquisition unit 12, as well as the new groove depth and starting groove depth acquired by the groove information acquisition unit 13, as input data. The learning processing unit 21 trains the calculation model 15a using the wear state measured for each groove of the tire 7 as training data, as the vehicle to which the tire 7 is attached drives on ordinary roads and highways, from the start of use to the end of wear.

[0062] Figure 8 is a schematic diagram illustrating the definition of the position of grooves formed on the tire 7. Multiple grooves formed on the tire 7 can be identified, for example, by assigning groove identification information such as a to d based on the serial surface S of the tire 7. The serial surface has the tire model number and manufacturing code engraved on it, and the serial surface and the opposite surface can be identified by the tire alone. When the tire is mounted on the vehicle's axle, the serial surface of the tire 7 faces either inward (towards the center of the axle) or outward. The groove positions are identified by assigning symbols 1 to 4 in order from the outside of the vehicle. When the serial surface faces outward, groove identification information a, b, c, and d correspond to groove positions 1, 2, 3, and 4, respectively. When the serial surface faces inward, groove identification information a, b, c, and d correspond to groove positions 4, 3, 2, and 1, respectively.

[0063] The groove information management unit 14 stores the correspondence between groove identification information and groove position in the tire groove data 16b in the storage unit 16. For example, when the correspondence between groove identification information and groove position changes during tire rotation or tire replacement, the groove information management unit 14 stores the changed correspondence between groove identification information and groove position in the tire groove data 16b in the storage unit 16.

[0064] The groove information acquisition unit 13 may read groove identification information and the corresponding relationship between grooves, in addition to the new groove depth and starting groove depth, from the tire groove data 16b and output it to the wear estimation unit 15. The calculation model 15a may include the corresponding relationship between groove identification information and grooves in the input data. The wear estimation unit 15 estimates the wear state of the tire 7 using the calculation model 15a which includes the corresponding relationship between groove identification information and grooves in the input data. As a result, the tire wear estimation system 100 can estimate the wear state of the tire 7 considering the orientation of the tire 7 when it is mounted on the axle, and in particular can improve the accuracy of estimating uneven wear. Furthermore, the calculation model generation system 110 can generate a calculation model 15a that considers the orientation of the tire 7 by generating a calculation model 15a which includes the corresponding relationship between groove identification information and grooves in the input data, and can improve the accuracy of estimating uneven wear by the calculation model 15a.

[0065] (modified version) The tire tread data 16b may include elapsed time information indicating the number of days that have passed from the time the tread depth of the tire 7 was measured to the starting point for estimating the wear of the tire 7. The elapsed time information may include only the number of days, or it may include both the number of days and time. The tread information acquisition unit 13 outputs the new tread depth and the starting tread depth, as well as the elapsed time information contained in the tire tread data 16b, to the wear estimation unit 15. The wear estimation unit 15 estimates the wear state of the tire 7 using the calculation model 15a based on the input data including the elapsed time information.

[0066] The groove information management unit 14 calculates the number of days that have elapsed from the date the groove depth of the tire 7 was measured to the starting point for estimating the wear of the tire 7, uses this as elapsed information, and updates the tire groove data 16b. By using this elapsed information, the tire wear estimation system 100 can estimate the wear state of the tire 7 by considering the number of days that have elapsed from the date the groove depth of the tire 7 was measured to the starting point for estimating the wear of the tire 7.

[0067] The technical ideas embodied in the above embodiments and variations can be generalized to include the technical ideas described in the following items.

[0068] The first item is a tire wear estimation system comprising: a vehicle information acquisition unit that acquires information including the driving conditions of a vehicle; a groove information acquisition unit that acquires the new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear; and a wear estimation unit that estimates the wear state of the tire based on a machine learning-prepared calculation model that uses the driving conditions acquired by the vehicle information acquisition unit, as well as the new groove depth and the starting groove depth acquired by the groove information acquisition unit, as input data.

[0069] The second item is a tire wear estimation system as described in the first item, wherein the groove information acquisition unit acquires first date and time information representing the starting point for estimating tire wear, and second date and time information representing the time for estimating the tire wear state, and the wear estimation unit inputs the vehicle's driving conditions, calculated based on the first date and time information and the second date and time information, into the calculation model to estimate the tire wear state.

[0070] The third item is a tire wear estimation system as described in the first or second item, wherein the groove information acquisition unit acquires third date and time information representing the time when the tire was replaced or its mounting position was changed, and the wear estimation unit inputs the vehicle's driving conditions, calculated based on the first date and time information, the second date and time information, and the third date and time information, into the calculation model to estimate the tire's wear state.

[0071] The fourth item is a tire wear estimation system described in any one of the first to third items, wherein the starting groove depth is calculated based on the wear state estimated by the wear estimation unit.

[0072] The fifth item is a tire wear estimation system described in any one of the first to fourth items, wherein the driving conditions include at least two of the vehicle's mileage, speed, and acceleration.

[0073] The sixth item is a tire wear estimation system described in any one of the first to fifth items, in which the calculation model is generated by machine learning using the tire wear state measured on a vehicle in motion as training data.

[0074] The seventh item is a tire wear estimation system according to any one of the first to sixth items, further comprising a groove information management unit that stores the starting groove depth in a storage unit in association with tire identification information attached to the tire, and the groove information acquisition unit reads and acquires the starting groove depth corresponding to the tire identification information from the storage unit.

[0075] The eighth item is a tire wear estimation system described in any one of the first to seventh items, wherein the groove information acquisition unit acquires the starting groove depth for each of the multiple grooves provided in the tire, and the wear estimation unit estimates the wear state for each groove.

[0076] The ninth item is a tire wear estimation method comprising: a vehicle information acquisition step of acquiring information including the driving conditions of a vehicle; a groove information acquisition step of acquiring the new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and the starting groove depth, which is the groove depth at a point in time that serves as the starting point for estimating tire wear; and a wear estimation step of estimating the tire wear state based on a machine learning-prepared computational model that uses the driving conditions acquired in the vehicle information acquisition step, as well as the new groove depth and the starting groove depth acquired in the groove information acquisition step, as input data.

[0077] The tenth item is a calculation model generation system comprising: a vehicle information acquisition unit that acquires information including the driving conditions of a vehicle; a groove information acquisition unit that acquires the new groove depth, which is the groove depth of a tire mounted on the vehicle when it is new, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear; a wear estimation unit that estimates the wear state of the tire based on a learning-type calculation model that takes the driving conditions acquired by the vehicle information acquisition unit, and the new groove depth and starting groove depth acquired by the groove information acquisition unit as input data; and a learning processing unit that trains the calculation model using the measured wear state of the tire as training data.

[0078] The embodiments of the present invention have been described above. These embodiments are illustrative, 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 are also within the scope of the claims of the present invention. Accordingly, the descriptions and drawings herein should be treated as illustrative rather than limiting. [Explanation of Symbols]

[0079] 7 Tire, 12 Vehicle information acquisition unit, 13 Groove information acquisition unit, 14 Groove information management unit, 15 Wear estimation unit, 15a Calculation model, 21 Learning processing unit, 100 Tire wear estimation system, 110 Computation model generation system.

Claims

1. A vehicle information acquisition unit that acquires information including the driving status of the vehicle, A groove information acquisition unit that acquires the new groove depth, which is the groove depth of the tire when it is new, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear. A wear estimation unit estimates the tire wear state based on a machine learning-based calculation model that uses the driving conditions acquired by the vehicle information acquisition unit and the new groove depth and starting groove depth acquired by the groove information acquisition unit as input data. A tire wear estimation system equipped with the following features.

2. The groove information acquisition unit acquires first date and time information representing the starting point for estimating tire wear, and second date and time information representing the time for estimating the tire wear state. The tire wear estimation system according to claim 1, wherein the wear estimation unit inputs the vehicle's driving conditions, calculated based on the first date and time information and the second date and time information, into the calculation model to estimate the tire wear state.

3. The groove information acquisition unit acquires a third date and time information representing the time when the tire was replaced or its mounting position was changed. The tire wear estimation system according to claim 2, wherein the wear estimation unit inputs the vehicle's driving conditions, calculated based on the first date and time information, the second date and time information, and the third date and time information, into the calculation model to estimate the tire wear state.

4. The tire wear estimation system according to claim 1, wherein the starting groove depth is calculated based on the wear state estimated by the wear estimation unit.

5. The tire wear estimation system according to claim 1, wherein the driving conditions include at least two of the vehicle's mileage, speed, and acceleration.

6. The tire wear estimation system according to claim 1, wherein the calculation model is generated by machine learning using the tire wear state measured on a running vehicle as training data.

7. The system further includes a groove information management unit that stores the starting groove depth in a storage unit in correspondence with the tire identification information attached to the tire, The tire wear estimation system according to claim 1, wherein the groove information acquisition unit reads and acquires the starting groove depth corresponding to the tire identification information from the storage unit.

8. The groove information acquisition unit acquires the starting groove depth for each of the plurality of grooves provided in the tire, The tire wear estimation system according to claim 1, wherein the wear estimation unit estimates the wear state for each groove.

9. A vehicle information acquisition step that acquires information including the driving status of the vehicle, A groove information acquisition step that acquires the groove depth of the tire when it is new, which is the groove depth of the tire mounted on the vehicle, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear. A wear estimation step estimates the tire wear state based on a machine learning-based computational model that uses the driving conditions obtained in the vehicle information acquisition step and the new groove depth and starting groove depth obtained in the groove information acquisition step as input data. A tire wear estimation method comprising the following features.

10. A vehicle information acquisition unit that acquires information including the driving status of the vehicle, A groove information acquisition unit that acquires the new groove depth, which is the groove depth of the tire when it is new, and the starting groove depth, which is the groove depth at the point in time that serves as the starting point for estimating tire wear. A wear estimation unit estimates the tire wear state based on a learning-type calculation model that uses the driving conditions acquired by the vehicle information acquisition unit and the new groove depth and starting groove depth acquired by the groove information acquisition unit as input data. A learning processing unit that trains the calculation model using the measured wear state of the tire as training data, A computational model generation system equipped with the following features.

Images