Tire wear amount estimation system and arithmetic model operation method

Abstract

To provide a tire wear-amount estimation system and a computation model operation model that select a computation mode when operating, and can maintain the provision of wear-amount estimation data.SOLUTION: In a tire wear-amount estimation system 100, a data acquisition unit 12 acquires data of an explanatory variable including a numerical variable and a category variable about a vehicle and a tire 7 mounted to the vehicle. A wear-amount calculation unit 14 has a missing value corresponding computation model 14a and a missing value non-corresponding computation model 14b to which the data acquired by the data acquisition unit 12 is input, and is configured to calculate a tire wear-amount. A determination unit 13 is configured to determine whether or not a non-learning category variable is included in the data acquired by the data acquisition unit 12. The wear-amount calculation unit 14 is configured to calculate the tire wear-amount using one of the missing value corresponding computation model 14a and the missing value non-corresponding computation model 14b on the basis of a determination result by the determination unit 13.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a tire wear amount estimation system for estimating the wear amount of tires mounted on a vehicle and a method for operating an arithmetic model.

Background Art

[0002] Generally, tires wear as they are used, depending on the driving conditions and the driving distance. Recently, sensors for measuring the pressure and temperature of tires have been mounted on tires, and devices for displaying the measured pressure and temperature have been commercialized.

[0003] Patent Document 1 describes a conventional wear amount estimation system for estimating the wear amount of tires. This wear amount estimation system includes a tire information acquisition unit, a tire severity calculation unit, and a wear amount calculation unit. The tire information acquisition unit acquires air pressure data and temperature data of tires mounted on a vehicle. The tire severity calculation unit calculates a tire severity indicating the degree of load on the tire from at least one of the air pressure data and temperature data acquired by the tire information acquisition unit. The wear amount calculation unit has an arithmetic model for calculating the tire wear amount based on the severity information for the tire, and inputs the tire severity and calculates the tire wear amount by the arithmetic model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The tire wear amount estimation system described in Patent Document 1 estimates the tire wear amount based on a pre-learned arithmetic model. The inventor of the present invention has found that, even when estimating the tire wear amount using an arithmetic model for a vehicle or tire for which learning of the learning-type arithmetic model has not been performed, although the estimation accuracy is not necessarily good at the initial stage, it is possible to proceed with learning through the running of the vehicle, and there is room for improvement in the operation of the learning-type arithmetic model.

[0006] The present invention has been made in view of such circumstances, and an object thereof is to provide a tire wear amount estimation system and an arithmetic model operation method capable of selecting an arithmetic model during operation and maintaining the provision of wear amount estimation data.

Means for Solving the Problems

[0007] A tire wear amount estimation system according to an aspect of the present invention includes a data acquisition unit that acquires data of explanatory variables including numerical variables and categorical variables related to a vehicle and tires mounted on the vehicle, a wear amount calculation unit that has a missing value corresponding arithmetic model and a missing value non-corresponding arithmetic model that input the data acquired by the data acquisition unit and calculates the tire wear amount, and a determination unit that determines whether an unlearned categorical variable is included in the data acquired by the data acquisition unit. The wear amount calculation unit calculates the tire wear amount using one of the missing value corresponding arithmetic model and the missing value non-corresponding arithmetic model based on the determination result by the determination unit.

[0008] Another aspect of the present invention is an operation method for an arithmetic model. The operation method for the arithmetic model includes a data acquisition step of acquiring data of explanatory variables including numerical variables and categorical variables related to a vehicle and tires mounted on the vehicle, a wear amount calculation step of calculating a tire wear amount using a missing value-corresponding arithmetic model and a missing value-non-corresponding arithmetic model into which the data acquired in the data acquisition step is input, and a determination step of determining whether unlearned categorical variables are included in the data acquired in the data acquisition step. The wear amount calculation step calculates the tire wear amount using one of the missing value-corresponding arithmetic model and the missing value-non-corresponding arithmetic model based on the determination result by the determination step.

Advantages of the Invention

[0009] According to the present invention, an arithmetic model can be selected during operation to maintain the provision of wear amount estimation data.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0011] Hereinafter, the present invention will be described with reference to FIGS. 1 to 4 based on preferred embodiments. 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 shown enlarged or reduced as appropriate 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.

[0012] (Embodiment) FIG. 1 is a block diagram showing the functional configuration of a tire wear amount estimation system 100 according to an embodiment. The tire wear amount estimation system 100 includes a tire wear amount measuring device 60, an in-vehicle measuring device 70, a weather information server device 80, and a wear amount estimation device 10, and estimates the wear amount of the tire 7. The tire wear amount estimation system 100 can be applied to vehicles and tires for which learning of a learning-type calculation model has not been performed, and can select a calculation model during operation and maintain the provision of wear amount estimation data.

[0013] During operation of driving the vehicle, the tire wear amount measuring device 60 directly measures the depth of the grooves provided in the tread of the tire 7, for example, a plurality of times at regular intervals, and obtains the wear amount of the tire 7. The regular period is, for example, several weeks to several months, but is not limited thereto. The tire wear amount measuring device 60 transmits the measured tire 7 wear amount data to the wear amount estimation device 10 via the communication network 9. The operator may measure the depth of each groove using a measuring instrument, a camera, visual inspection, etc., and the tire wear amount measuring device 60 may store the measurement data input by the operator. Also, the tire wear amount measuring device 60 may be a dedicated device that measures the groove depth by a mechanical or optical method and stores the wear amount.

[0014] Specifically, for example, when the tire has four grooves, the tire wear measurement device 60 measures at four locations in the width direction, and further measures at three locations in the circumferential direction of the same groove, for example, at intervals of 120°. As a result, the uneven wear data in the width direction or the 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 groove depth by calculation from the information on the running distance and the rotation speed / speed of the tire. In addition, a device that directly measures the groove depth and a device that predicts by calculation from the running distance and the rotation speed / speed of the tire may be used in combination.

[0015] 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 part in the in-vehicle measurement device 70 can be realized by electronic elements such as a computer CPU and mechanical parts in terms of hardware, and can be realized by a computer program or the like in terms of software. 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 a combination of hardware and software.

[0016] The vehicle measurement unit 71 includes a speedometer 71a, a GPS receiver 71b, and an acceleration sensor 71c mounted on the vehicle. The speedometer 71a measures the 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 of the vehicle in three axial directions.

[0017] The tire measurement unit 72 includes a temperature sensor 72a and a pressure sensor 72b. The temperature sensor 72a and the pressure sensor 72b are arranged at the air valve or the like of the tire 7 mounted on the vehicle, or are firmly wound around 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 arranged at the inner liner or the like of the tire 7.

[0018] The information acquisition unit 73 acquires vehicle measurement information (such as speed, position information, acceleration, etc.) measured by the vehicle measurement unit 71 and tire measurement information (such as tire temperature and air pressure, etc.) measured by the tire measurement unit 72. The information acquisition unit 73 associates the measurement time information measured 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 amount estimation device 10.

[0019] When a device such as a digital tachometer is installed in the vehicle, the information acquisition unit 73 may acquire the 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 amount estimation device 10 via the communication network 9.

[0020] 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, snow accumulation, snowfall, temperature, sunshine duration, etc. at each location. The wear amount estimation device 10 acquires the weather information at the location where the vehicle is traveling from the weather information server device 80.

[0021] The wear amount estimation device 10 includes a communication unit 11, a data acquisition unit 12, a determination unit 13, a wear amount calculation unit 14, a storage unit 15, and a learning processing unit 16. Each unit in the wear amount estimation device 10 can be realized in terms of hardware by electronic elements such as a computer's CPU and mechanical parts, and can be realized in terms of software 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.

[0022] 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.

[0023] The data acquisition unit 12 acquires vehicle measurement information (speed, position information, acceleration, etc.) and tire measurement information (tire temperature, air pressure, etc.) transmitted from the in-vehicle measurement device 70 mounted on the vehicle. The data acquisition unit 12 calculates and acquires the travel distance of the vehicle based on the vehicle measurement information.

[0024] The data acquisition unit 12 can calculate and acquire the travel distance based on the position information of the vehicle measurement information. Also, the travel distance of the vehicle may be calculated based on the speed data in the vehicle measurement information and the time data associated with the data. That is, the travel 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.

[0025] If information regarding the travel distance of the vehicle is provided from the vehicle or an external device for vehicle management, etc., the data acquisition unit 12 does not need to calculate the travel distance itself and may acquire information regarding the travel distance from the vehicle or the external device.

[0026] The data acquisition unit 12 outputs the acquired travel distance to the wear amount calculation unit 14. The data acquisition unit 12 outputs the acquired tire measurement information (tire temperature, air pressure, etc.) to the wear amount calculation unit 14. When the wear amount calculation unit 14 estimates the tire wear amount based on an arithmetic model that uses the acceleration of the vehicle as an input element, the data acquisition unit 12 outputs the acceleration data in the vehicle measurement information to the wear amount calculation unit 14.

[0027] In addition, the data acquisition unit 12 acquires data used for estimating the wear amount of the tire 7 from among the vehicle specification data 15a and the tire specification data 15b from the storage unit 15, and outputs the data to the determination unit 13 and the wear amount calculation unit 14. The storage unit 15 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 the specifications of various vehicles and the tire 7.

[0028] The vehicle specification data 15a includes information regarding the performance of the vehicle, such as the manufacturer, vehicle type, vehicle name, vehicle model, vehicle body weight, drive train, overall length, vehicle width, vehicle height, maximum load capacity, etc. Further, the tire specification data 15b includes information regarding the performance of the tire 7, such as the manufacturer, product name, tire size, tire width, aspect ratio, wear resistance performance, tire strength, static rigidity, dynamic rigidity, tire outer diameter, load index, manufacturing date, etc. The vehicle specification data 15a and the tire specification data 15b correspond to the categorical variable part of the explanatory variables input to each calculation model described later.

[0029] The determination unit 13 determines whether the vehicle specification data 15a and the tire specification data 15b input from the data acquisition unit 12, that is, whether the categorical variable is unlearned in the missing value non-corresponding calculation model 14b of the wear amount calculation unit 14. The determination unit 13 outputs the determination result to the wear amount calculation unit 14.

[0030] The wear amount calculation unit 14 has a learning-type missing value corresponding calculation model 14a and a missing value non-corresponding calculation model 14b, selects one of the calculation models, and calculates the wear amount of the tire 7. The missing value corresponding calculation model 14a is, for example, a decision tree model, and is learned by a method such as gradient boosting. The missing value non-corresponding calculation model 14b is a neural network, has a multi-layer structure using, for example, convolutional operations such as CNN and fully connected operations, and determines the coupling coefficients between layers by learning.

[0031] Since the missing value - handling operation model 14a has the property of omitting the operation in the part of the categorical variable in the decision tree and outputting the result when an unlearned categorical variable is input, it is understood to be an operation model that can handle missing values. Since various coefficients in the operation process of the neural network are not learned for the categorical variable when the missing - value - non - handling operation model 14b receives an unlearned categorical variable as input, the output result does not necessarily have good estimation accuracy, and it is understood to be an operation model that does not handle missing values.

[0032] When the determination unit 13 determines that the categorical variable is a learned one, the wear amount calculation unit 14 calculates the tire wear amount using the operation model with higher wear amount estimation accuracy among the missing - value - handling operation model 14a and the missing - value - non - handling operation model 14b. When the determination unit 13 determines that the categorical variable is a learned one, if the missing - value - non - handling operation model 14b has higher tire wear amount estimation accuracy, the wear amount calculation unit 14 may calculate the tire wear amount using the missing - value - non - handling operation model 14b. Also, when the determination unit 13 determines that the categorical variable is a learned one, the wear amount calculation unit 14 may calculate the tire wear amount by an ensemble of the missing - value - handling operation model 14a and the missing - value - non - handling operation model 14b.

[0033] When the determination unit 13 determines that the categorical variable is an unlearned one, the wear amount calculation unit 14 calculates the tire wear amount using the missing - value - handling operation model 14a and causes the learning processing unit 16 to perform learning on the missing - value - non - handling operation model 14b. In this case, after the learning of the missing - value - non - handling operation model 14b is performed over a predetermined period (for example, several months), the wear amount calculation unit 14 switches from the missing - value - handling operation model 14a to the missing - value - non - handling operation model 14b and calculates the tire wear amount.

[0034] Also, when the learning of the missing value non-corresponding operation model 14b progresses and the estimated result of the tire wear amount by the missing value non-corresponding operation model 14b becomes better than the estimated result of the tire wear amount by the missing value corresponding operation model 14a, the wear amount calculation unit 14 switches from the missing value corresponding operation model 14a to the missing value non-corresponding operation model 14b to calculate the tire wear amount.

[0035] The learning processing unit 16 acquires the wear amount of the tire 7 from the tire wear amount measuring device 60 via the communication unit 11. FIG. 3 is a schematic diagram for explaining the wear amount estimation and learning of the missing value non-corresponding operation model 14b. In the learning process of the missing value non-corresponding operation model 14b, based on the input data, the tire wear amount as the output data is estimated by the missing value non-corresponding operation model 14b and compared with the teacher data. The teacher data uses the wear amount of the tire 7 measured by the tire wear amount measuring device 60.

[0036] The learning processing unit 16 compares the wear amount of the tire 7 estimated by the missing value non-corresponding operation model 14b with the teacher data, newly sets various coefficients in the calculation process such as weighting, and repeats the update of the operation model to execute learning. The input data to the missing value non-corresponding operation model 14b is generally classified into each system of vehicle measurement information, tire measurement information, and other information.

[0037] The input data related to vehicle measurement information and tire measurement information corresponds to the numerical variable part of the explanatory variables input to the operation model. The input data related to vehicle measurement information includes the acceleration and travel distance of the vehicle. The travel distance is acquired by the data acquisition unit 12 as described above. The input data related to tire measurement information includes the temperature and air pressure of the tire 7.

[0038] Input data based on other information includes the road surface condition estimated based on weather information, vehicle specification data 15a, tire specification data 15b, and the like. As described above, the vehicle specification data 15a and the tire specification data 15b correspond to the categorical variable part of the explanatory variables input to the calculation model. Among the vehicle specification data 15a, the vehicle name, drive train, etc. are categorical variables input to the calculation model. Also, among the tire specification data 15b, the product name, tire size, etc. are categorical variables input to the calculation model.

[0039] Next, the operation of the tire wear amount estimation system 100 will be described. FIG. 4 is a flowchart showing the procedure of the wear amount estimation process by the tire wear amount estimation system 100. The data acquisition unit 12 of the wear amount estimation device 10 acquires data of numerical variables and categorical variables regarding the vehicle and the tires mounted on the vehicle (S1). The determination unit 13 determines whether or not the data of the categorical variables acquired by the data acquisition unit 12 includes unlearned categorical variables (S2).

[0040] If it is determined in step S2 that unlearned categorical variables are included (S2: YES), the wear amount calculation unit 14 calculates the tire wear amount using the missing value corresponding calculation model 14a as the estimation result (S3). Also, the wear amount calculation unit 14 starts learning the missing value non-corresponding calculation model 14b (S4) and ends the process.

[0041] If it is determined in step S2 that unlearned categorical variables are not included (S2: NO), the wear amount calculation unit 14 calculates the tire wear amount using the missing value non-corresponding calculation model 14b as the estimation result (S5) and ends the process.

[0042] The missing value non-corresponding arithmetic model 14b started by step S4 is learned, for example, in a set predetermined period. The determination unit 13 determines that a category variable that was determined to be unlearned after the learning of the missing value non-corresponding arithmetic model 14b has been learned. Also, the learning of the missing value non-corresponding arithmetic model 14b may be regarded as learned when the estimation accuracy of the tire wear amount becomes better than the estimation accuracy of the tire wear amount using the missing value corresponding arithmetic model 14a.

[0043] The tire wear amount estimation system 100 determines whether a category variable is unlearned by the determination unit 13, and based on the determination result, estimates the tire wear amount using one of the missing value corresponding arithmetic model 14a and the missing value non-corresponding arithmetic model 14b. Thereby, the tire wear amount estimation system 100 can maintain the function of selecting an arithmetic model during operation and notifying the user of the estimated data of the tire wear amount even when the category variable is unlearned. The tire wear amount estimation system 100 estimates the tire wear amount using the missing value corresponding arithmetic model 14a even when the category variable is unlearned, and notifies the user, for example, by displaying the wear amount of each groove of the tire on a display screen such as a display.

[0044] When the tire wear amount estimation system 100 determines by the determination unit 13 that an unlearned category variable is included, the learning processing unit 16 learns the missing value non-corresponding arithmetic model 14b. Thereby, after the learning of the missing value non-corresponding arithmetic model 14b, the tire wear amount estimation system 100 can estimate and provide the tire wear amount using the missing value non-corresponding arithmetic model 14b.

[0045] The tire wear amount estimation system 100 can perform the learning of the missing value non-corresponding arithmetic model 14b by the learning processing unit 16 in a predetermined period (for example, several months), and thereafter, estimate and provide the tire wear amount using the missing value non-corresponding arithmetic model 14b.

[0046] Further, the tire wear amount estimation system 100 may perform learning of the missing value non-corresponding operation model 14b until the estimation result of the tire wear amount becomes better than the estimation result of the missing value corresponding operation model 14a. In this case, the tire wear amount estimation system 100 can provide an estimation result of the tire wear amount with higher estimation accuracy using the missing value non-corresponding operation model 14b with good estimation results. Note that the estimation accuracy of the tire wear amount in each operation model can be verified, for example, by calculating the RMSE (root mean square error) between the measured value and the estimated value of the tire wear amount acquired multiple times.

[0047] Further, the wear amount calculation unit 14 uses, for example, a decision tree model as the missing value corresponding operation model 14a and a neural network model as the missing value non-corresponding operation model 14b. Thereby, the tire wear amount estimation system 100 can easily construct each operation model according to a known operation model construction method.

[0048] The tire wear amount estimation system 100 described in this embodiment uses, for example, the missing value corresponding operation model 14a and the missing value non-corresponding operation model 14b learned in one vehicle having a certain vehicle name and the tires mounted on the vehicle. When this tire wear amount estimation system 100 is applied to another vehicle with the same vehicle name equipped with tires of the same specification (same product name and tire size, etc.), the category variables of the missing value corresponding operation model 14a and the missing value non-corresponding operation model 14b will be those that have been learned.

[0049] On the other hand, when this tire wear amount estimation system 100 is transferred to another vehicle with the same vehicle name or a different vehicle name equipped with tires of different specifications, the category variables of the missing value corresponding calculation model 14a and the missing value non-corresponding calculation model 14b will include those that have not been learned. Also, when transferred to another vehicle with a different vehicle name equipped with tires of the same specification, the category variables of the missing value corresponding calculation model 14a and the missing value non-corresponding calculation model 14b will include those that have not been learned. As described above, even when the tire wear amount estimation system 100 includes unlearned category variables, the missing value corresponding calculation model 14a can maintain the provision of estimated data on the tire wear amount.

[0050] Next, the features of the tire wear amount estimation system 100 and the calculation model operation method according to the embodiments and modification examples will be described. The tire wear amount estimation system 100 includes a data acquisition unit 12, a wear amount calculation unit 14, and a determination unit 13. The data acquisition unit 12 acquires data on explanatory variables including numerical variables and category variables related to the vehicle and the tire 7 mounted on the vehicle. The wear amount calculation unit 14 has a missing value corresponding calculation model 14a and a missing value non-corresponding calculation model 14b that input the data acquired by the data acquisition unit 12, and calculates the tire wear amount. The determination unit 13 determines whether the data acquired by the data acquisition unit 12 includes an unlearned category variable. The wear amount calculation unit 14 calculates the tire wear amount using one of the missing value corresponding calculation model 14a and the missing value non-corresponding calculation model 14b based on the determination result by the determination unit 13. Thereby, even when the tire wear amount estimation system 100 has not learned about the category variable, it can select a calculation model during operation and maintain the provision of estimated data on the tire wear amount.

[0051] When the determination unit 13 determines that an unlearned categorical variable is included, the learning processing unit 16 that learns the missing value non-corresponding operation model 14b is further provided. Thereby, after the learning of the missing value non-corresponding operation model 14b, the tire wear amount estimation system 100 can estimate and provide the tire wear amount using the missing value non-corresponding operation model 14b.

[0052] Further, after the learning by the learning processing unit 16 has elapsed for a predetermined period, the wear amount calculation unit 14 calculates the tire wear amount by the missing value non-corresponding operation model 14b. Thereby, the tire wear amount estimation system 100 can perform the learning of the missing value non-corresponding operation model 14b by the learning processing unit 16 in a predetermined period (for example, several months), and thereafter, can estimate and provide the tire wear amount using the missing value non-corresponding operation model 14b.

[0053] Further, after the estimation result by the missing value non-corresponding operation model 14b becomes better than the estimation result by the missing value corresponding operation model 14a, the wear amount calculation unit 14 calculates the tire wear amount by the missing value non-corresponding operation model 14b. Thereby, the tire wear amount estimation system 100 can provide an estimation result of the tire wear amount with higher estimation accuracy using the missing value non-corresponding operation model 14b with a good estimation result.

[0054] The missing value corresponding operation model 14a is a decision tree model, and the missing value non-corresponding operation model 14b is a neural network model. Thereby, the tire wear amount estimation system 100 can easily construct each operation model according to a known operation model construction method.

[0055] The operation method of the calculation model includes a data acquisition step, a wear amount estimation step, and a determination step. The data acquisition step acquires data of explanatory variables including numerical variables and categorical variables related to the vehicle and the tire 7 mounted on the vehicle. The wear amount calculation step calculates the tire wear amount using a missing value corresponding calculation model 14a and a non-missing value corresponding calculation model 14b that input the data acquired in the data acquisition step. The determination step determines whether an unlearned categorical variable is included in the data acquired in the data acquisition step. The wear amount calculation step calculates the tire wear amount using one of the missing value corresponding calculation model 14a and the non-missing value corresponding calculation model 14b based on the determination result of the determination step. According to this operation method of the calculation model, even when the categorical variable is not learned, the calculation model can be selected during operation to maintain the provision of the estimated data of the tire wear amount.

[0056] 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

[0057] 7 Tire, 12 Data acquisition unit, 13 Determination unit, 14 Wear amount calculation unit, 14a Missing value corresponding calculation model, 14b Non-missing value corresponding calculation model, 16 Learning processing unit, 100 Tire wear amount estimation system.

Claims

1. A data acquisition unit that acquires data of explanatory variables including numerical variables and categorical variables related to a vehicle and a tire mounted on the vehicle; A wear amount calculation unit that has a missing value corresponding calculation model and a missing value non-corresponding calculation model that input the data acquired by the data acquisition unit, and calculates a tire wear amount; A determination unit that determines whether unlearned categorical variables are included in the data acquired by the data acquisition unit; and The tire wear amount estimation system according to claim 1, wherein the wear amount calculation unit calculates a tire wear amount using one of the missing value corresponding calculation model and the missing value non-corresponding calculation model based on a determination result by the determination unit.

2. The tire wear amount estimation system according to claim 1, further comprising a learning processing unit that learns the missing value non-corresponding calculation model when the determination unit determines that unlearned categorical variables are included.

3. The tire wear amount estimation system according to claim 2, wherein the wear amount calculation unit calculates a tire wear amount by the missing value non-corresponding calculation model after a predetermined period has elapsed since the learning by the learning processing unit.

4. The tire wear amount estimation system according to claim 2, wherein the wear amount calculation unit calculates a tire wear amount by the missing value non-corresponding calculation model after an estimation result by the missing value non-corresponding calculation model becomes better than an estimation result by the missing value corresponding calculation model.

5. The tire wear amount estimation system according to any one of claims 1 to 4, wherein the missing value corresponding calculation model is a decision tree model, and the missing value non-corresponding calculation model is a neural network model.

6. A data acquisition step of acquiring data of explanatory variables including numerical variables and categorical variables related to a vehicle and a tire mounted on the vehicle; A wear amount calculation step of calculating a tire wear amount using a missing value corresponding calculation model and a missing value non-corresponding calculation model that input the data acquired by the data acquisition step; A determination step of determining whether unlearned categorical variables are included in the data acquired by the data acquisition step; and The wear amount calculation step calculates the tire wear amount using one of the missing value corresponding calculation model and the missing value non-corresponding calculation model based on the determination result of the determination step, which is a calculation model operation method.

Images