JP7456749B2 - Wear amount estimation system and calculation model generation system - Google Patents

Description

The present invention relates to a wear estimation system and arithmetic model generation system for estimating the wear amount of tires mounted on a vehicle.

In general, tires progress as wear progresses depending on driving conditions, distance traveled, and the like. Furthermore, in recent years, devices have been commercialized that attach sensors to tires to measure tire pressure and temperature and display the measured pressure and temperature.

Patent Document 1 describes a conventional tire wear estimating device. This tire wear estimating device has a vehicle speed detection means, calculates position data of the vehicle based on a signal from a satellite received by a GPS receiver, and detects a vehicle speed V from the position data. The tire wear estimating device also measures the wheel rotation speed using a wheel speed sensor, and converts it into a wheel rotation speed Vw corrected based on the tire internal pressure detected by the pressure sensor. A speed ratio R=(Vw/V), which is the ratio of the corrected wheel rotational speed to the vehicle speed, is calculated, and the amount of tire wear is estimated based on the speed ratio R.

Japanese Patent Application Publication No. 2008-143460

In the tire wear estimating device described in Patent Document 1, the speed ratio, which is the ratio of the wheel rotation speed to the vehicle speed, has a high correlation with the amount of tire wear. The inventor of the present invention considered that, for example, when the vehicle is traveling uphill or downhill, the load on the tires changes compared to when the vehicle is traveling on a flat road, so it is important to incorporate such factors. We realized that there is room for improvement to improve the estimation accuracy of tire wear amount. The inventor also considered that the accuracy of estimating the amount of tire wear could be further improved by incorporating factors such as braking on a downhill slope.

The present invention has been made in view of the above circumstances, and an object thereof is to provide a wear amount estimation system and a calculation model generation system that can accurately estimate tire wear amount.

A wear amount estimation system according to an aspect of the present invention includes a position information acquisition unit that acquires position data of a vehicle on which a tire is mounted, and a calculation model that calculates a tire wear amount based on information regarding the altitude of the vehicle. The tire includes a wear amount calculation unit that inputs altitude data in the position data and calculates a wear amount of the tire using the calculation model.

Another aspect of the present invention is a computational model generation system. The calculation model generation system includes a position information acquisition unit that acquires position data of a vehicle on which tires are mounted, and a calculation model that calculates tire wear amount based on information regarding the altitude of the vehicle, and includes a calculation model that calculates tire wear amount based on information regarding the altitude of the vehicle, a wear amount calculation unit that calculates the amount of wear of the tire using the calculation model by inputting the information, and compares the amount of wear measured on the tire with the amount of wear calculated by the wear amount calculation unit, and calculates the amount of wear of the tire using the calculation model. an arithmetic model update unit that updates the .

The present invention makes it possible to estimate tire wear with high accuracy.

1 is a block diagram showing a functional configuration of a calculation model generation system according to a first embodiment; FIG. FIG. 3 is a schematic diagram for explaining learning of a calculation model. 3 is a flowchart showing a procedure for generating an arithmetic model by the arithmetic model generation system. 3 is a graph showing changes in altitude of a vehicle over time. This is a graph showing an enlarged portion of the temporal change in the altitude of the vehicle. It is a graph further enlarging a part of the time change of the altitude of the vehicle. It is a graph plotting the latitude and longitude of a vehicle. FIG. 2 is a block diagram showing a functional configuration of a wear amount estimation system according to a second embodiment.

Hereinafter, the present invention will be explained based on a preferred embodiment with reference to FIGS. 1 to 8. Identical or equivalent components and members shown in each drawing are designated by the same reference numerals, and redundant explanations will be omitted as appropriate. Further, the dimensions of members in each drawing are shown enlarged or reduced as appropriate to facilitate understanding. Further, in each drawing, some members that are not important for explaining the embodiments are omitted.

(Embodiment 1)
FIG. 1 is a block diagram showing the functional configuration of a calculation model generation system 100 according to the first embodiment. The calculation model generation system 100 calculates the amount of tire wear based on the position information acquired by the position information acquisition unit 31 and tire physical quantities such as air pressure and temperature measured by the sensor 20 disposed on the tire 10. A calculation model 33b is generated.

The calculation model generation system 100 uses a learning model such as a neural network as a calculation model, uses the amount of tire wear actually measured in the tire 10 as training data, and repeats learning by performing calculations and updating the calculation model. The accuracy of the calculation model 33b is improved. The wear amount estimating device 30 functions as a device that estimates the amount of tire wear after the calculation model 33b is trained.

The calculation model generation system 100 can perform learning of a calculation model for a tire 10 having a certain specification by driving a vehicle equipped with the tire 10 (including wheels). Tire specifications include information about tire performance, such as manufacturer, product name, tire size, tire width, aspect ratio, tire strength, static stiffness, dynamic stiffness, tire outer diameter, load index, and manufacturing date. is included.

The calculation model generation system 100 uses the position information acquisition unit 31 to acquire vehicle position data. The calculation model generation system 100 estimates whether the vehicle is traveling uphill or downhill when traveling based on the altitude data, and inputs the estimation to the calculation model 33b. Furthermore, when the vehicle is traveling downhill, the calculation model generation system 100 inputs the slope and distance of the downhill slope to the calculation model 33b.

The computation model generation system 100 also estimates the number of braking events of the vehicle and inputs the estimated number of braking events to the computation model 33b. The computation model generation system 100 also estimates the number of turns of the vehicle and inputs the estimated number of turns to the computation model 33b.

A pressure sensor 21, a temperature sensor 22, and an acceleration sensor 23 are arranged on the tire 10 or wheel 15. The pressure sensor 21 and the temperature sensor 22 are installed, for example, by being attached to an air valve of the tire 10 or fixed to the wheel 15, and measure the air pressure and temperature of the tire 10, respectively. Moreover, the pressure sensor 21 and the temperature sensor 22 may be arranged on the inner liner of the tire 10 or the like.

The acceleration sensor 23 is disposed, for example, on the tire 10 or the wheel 15, and measures the acceleration occurring in the tire 10. Note that, in order to identify each tire, the tires 10 may be attached with, for example, an RFID or the like provided with unique identification information. In addition to the altitude data, the calculation model generation system 100 may use tire data measured on the tires, such as air pressure, temperature, and acceleration, as factors to be input into the calculation model 33b.

The wear amount estimating device 30 includes a position information acquisition section 31, a tire information acquisition section 32, a wear amount calculation section 33, and a calculation model updating section 34. The wear amount estimating device 30 is, for example, an information processing device such as a PC (personal computer). Each part of the wear amount estimating device 30 can be realized in terms of hardware by electronic elements such as the CPU of a computer, mechanical parts, etc., and can be realized by computer programs in terms of software, but here, those parts will be explained. It depicts functional blocks realized through collaboration. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by combining hardware and software.

The position information acquisition unit 31 acquires vehicle position data measured by the GPS receiver 50. The position data includes latitude, longitude, and altitude data. The altitude data is used to estimate whether the vehicle is traveling uphill or downhill. The latitude and longitude information is used to estimate the number of turns the vehicle has made, etc. The position information acquisition unit 31 outputs the acquired latitude, longitude, and altitude data to the wear amount calculation unit 33.

The tire information acquisition unit 32 acquires tire data including the air pressure, temperature, acceleration, and time of measurement measured in the tire 10 from the pressure sensor 21, temperature sensor 22, and acceleration sensor 23 by wireless communication or the like, and the wear amount calculation unit Output to 33.

The wear amount calculation section 33 includes a preprocessing section 33a and a calculation model 33b. The preprocessing unit 33a estimates whether the vehicle is traveling uphill or downhill based on the altitude data, and calculates the number of times the vehicle is traveling uphill and the number of times traveling downhill is traveling downhill. Calculate the number of trips. Further, the preprocessing unit 33a calculates the slope and distance of the downhill slope when the vehicle is continuously traveling downhill.

Further, the preprocessing unit 33a may estimate the number of times of braking by determining a change in the position of the vehicle based on the position data. When the change in position of the vehicle is large, it is estimated that the vehicle is accelerating, and when the change in position is small, it is estimated that the vehicle is braking.

The preprocessing unit 33a also calculates the number of turns of the vehicle based on the latitude and longitude data. Note that the preprocessing unit 33a acquires position data from the position information acquisition unit 31 every moment, and calculates the travel distance based on the position data from the start of travel to the present, and calculates speed and turning radius based on time changes in the position data. and the turning speed can be determined.

In the preprocessing section 33a, in order to accurately determine the number of uphill and downhill runs, the slope of a downhill slope, the number of times of braking, the number of turns of the vehicle, etc., the sampling frequency in data acquisition by the GPS receiver 50 is set to at least 1 every 10 seconds. times, preferably once every second, more preferably once every 0.1 seconds. If real-time calculation processing is not required, the frequency of sampling during data acquisition by the GPS receiver 50 may be reduced, and the data may be supplemented using altitude data of map data or the like. For example, after one day's running, the number, slope, and distance of uphill and downhill slopes on the route may be derived from changes in position data and input into the calculation model 33b.

FIG. 2 is a schematic diagram for explaining learning of the calculation model 33b. Among the input data to the calculation model 33b, the inputs related to position data are the number of uphill runs, the number of downhill runs, the slope and distance of a downhill slope, the number of braking times, and the number of turns, which are calculated by the preprocessing unit 33a. Inputs related to tire data include air pressure, temperature, acceleration, and the like. In addition to these, the input data may also include weather data, data from a digital tachograph mounted on the vehicle, and information on road surface conditions.

Weather data, such as the temperature and precipitation in the driving area, are used as input data to calculation model 33b. Digital tachograph data, such as vehicle weight and speed data, are used as input data to calculation model 33b. Information on road surface conditions, such as the unevenness, temperature, and wet/dry conditions of the road surface on which the vehicle is driving, are used as input data to calculation model 33b.

The calculation model 33b uses a learning model such as a neural network, for example. The calculation model 33b inputs tire data, mileage, speed, turning radius, etc. to the nodes of the input layer, and executes calculations using a path from the input layer that is weighted to the intermediate layer. The calculation model 33b further performs calculations using a weighted path from the intermediate layer to the output layer, and outputs the amount of tire wear from the nodes of the output layer. In a learning model such as a neural network, in addition to linear calculations, nonlinear calculations may be performed using an activation function or the like.

The calculation model updating unit 34 updates the calculation model 33b by comparing the amount of tire wear as a calculation result with the teacher data. The calculation model update section 34 includes a wear amount comparison section 34a and an update processing section 34b. The wear comparison section 34a compares the tire wear amount calculated by the calculation model 33b with the tire wear amount as teacher data measured by the tire measuring device 40, and outputs the error to the update processing section 34b.

The update processing unit 34b updates the weighting of the paths on the calculation model based on the wear amount error calculated by the calculation model 33b. The accuracy of the calculation model is improved by repeatedly calculating the tire wear amount by the calculation model 33b, comparing it with the teacher data by the wear amount comparison unit 34a, and updating the calculation model by the update processing unit 34b.

The tire measuring device 40 directly measures the depth of grooves provided in the tread of the tire 10. An operator may measure the depth of each groove using a measuring instrument, a camera, visual inspection, etc., and the tire measuring device 40 may store measurement data input by the operator. Further, the tire measuring device 40 may be a dedicated device that measures and stores the groove depth using a mechanical or optical method.

Specifically, for example, when a tire has four grooves, the tire measuring device 40 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 120° intervals. measure. Thereby, uneven wear data in the width direction or circumferential direction of the tire is also stored in the tire measuring device 40. Note that the tire measuring device 40 may indirectly measure the depth of the groove by calculating from information on the mileage and the rotation speed/speed of the tire, since the diameter changes due to wear of the tire. In addition, a method that directly measures the groove depth may be used in combination with a method that predicts the depth by calculation based on the travel distance and the number of rotations and speed of the tire.

Next, the operation of the calculation model generation system 100 will be explained. FIG. 3 is a flowchart showing a procedure for generating a calculation model by the calculation model generation system 100. The wear amount estimating device 30 starts acquiring position data using the position information acquisition unit 31 (S1). Furthermore, the tire information acquisition unit 32 starts acquiring tire data including the air pressure, temperature, and acceleration measured in the tire 10 from the pressure sensor 21, temperature sensor 22, and acceleration sensor 23 (S2). The preprocessing unit 33a calculates the number of uphill trips and the number of downhill trips based on the position data acquired by the position information acquisition unit 31 (S3). In step S3, the preprocessing unit 33a may further calculate the slope and distance of the downhill, the number of times of braking, the number of turns, the turning radius, and the turning speed.

The preprocessing unit 33a accumulates data over a predetermined period (S4). The predetermined period may be, for example, one driving period of the vehicle, several days, or one week, but is not limited to these. After a predetermined period of time has elapsed, the preprocessing unit 33a inputs each data to the calculation model 33b and estimates the amount of tire wear (S5). The wear comparison unit 34a compares the tire wear amount calculated by the calculation model 33b with the tire wear amount as teacher data measured by the tire measuring device 40 (S6). The wear comparison unit 34a outputs the difference between the tire wear amount calculated by the calculation model 33b and the tire wear amount measured by the tire measurement device 40 as a result of the comparison to the update processing unit 34b.

The update processing unit 34b updates the calculation model based on the tire wear amount error input from the wear amount comparison unit 34a (S7), and ends the process. By repeating these processes, the wear amount estimating device 30 updates the calculation model and improves the accuracy of tire wear amount estimation.

FIG. 4 is a graph showing the temporal change in the altitude of the vehicle, and FIG. 5 is a graph in which a part of the temporal change in the vehicle altitude is enlarged. As shown in the circled areas a and b in FIG. 4, the altitude of the vehicle changes moment by moment while the vehicle is running. In FIG. 5, a portion where the vehicle is estimated to be traveling downhill is circled. The preprocessing unit 33a calculates the number of occurrences of a portion in which the vehicle is estimated to be traveling downhill as the number of times the vehicle travels downhill. Note that, in the same way as for downhills, the number of uphill runs is calculated from a graph showing changes in altitude over time.

The wear amount estimating device 30 constructs a calculation model 33b that takes into consideration the fact that the vehicle is traveling uphill or downhill by inputting the altitude data when the vehicle is running to the calculation model 33b, and performs calculations. The model 33b allows the amount of tire wear to be estimated with high accuracy. The wear amount estimating device 30 can improve the accuracy of estimating the amount of tire wear by using the number of uphill trips and the number of downhill trips as input to the calculation model 33b. The wear amount estimating device 30 can improve the accuracy of estimating the amount of tire wear by using the number of downhill trips as an input to the calculation model 33b.

In addition, when there are consecutive parts where it is estimated that the vehicle is traveling downhill, the wear amount estimating device 30 calculates the slope and distance of each downhill, and uses the calculated gradient and distance as input to the calculation model 33b. Furthermore, the accuracy of estimating the amount of tire wear can be improved.

FIG. 6 is a graph further enlarging a part of the temporal change in the altitude of the vehicle. The area where the vehicle is estimated to have braked is circled. In FIG. 6, arrows indicate changes in the position of the vehicle, and it is presumed that braking of the vehicle is occurring at locations where the length of the arrow changes. The wear amount estimating device 30 can further improve the accuracy of estimating the amount of tire wear by inputting the number of times of braking of the vehicle to the calculation model 33b.

FIG. 7 is a graph plotting the latitude and longitude of the vehicle. The preprocessing unit 33a can estimate the location of a turn from the latitude and longitude data of the vehicle, and calculates the number of turns of the vehicle. The wear amount estimating device 30 can further improve the accuracy of estimating the amount of tire wear by inputting the number of turns of the vehicle to the calculation model 33b. Furthermore, it can be estimated from the graph shown in FIG. 7 whether the vehicle has turned to the right or to the left, and the number of right turns and the number of left turns may be estimated and input to the calculation model 33b. Furthermore, it can also be estimated from the graph shown in FIG. 7 whether the vehicle has made a sharp turn or a slow turn, and it is also possible to estimate whether the vehicle has made a sharp turn or a slow turn, respectively, and input the estimates to the calculation model 33b. Further, based on a graph plotting the latitude and longitude of the vehicle, the preprocessing unit 33a calculates at least one or both of the turning radius and turning speed of the vehicle, and inputs the calculated turning radius and turning speed to the calculation model 33b. The accuracy of quantity estimation can be further improved.

In addition, the computation model generation system 100 can make the computation model 33b learn about uneven wear of the tires 10 by inputting the number of downhill runs and the number of turns into the computation model 33b. By estimating the amount of wear based on the computation model 33b generated by the computation model generation system 100, it is also possible to suggest rotation of the tires 10 according to the uneven wear condition of each tire of the vehicle.

(Embodiment 2)
FIG. 8 is a block diagram showing the functional configuration of the wear amount estimation system 110 according to the second embodiment. After the calculation model 33b for estimating tire wear amount is generated by the calculation model generation system 100 according to the first embodiment as described above, the wear amount estimating device 30 including the calculation model 33b can be configured. The wear estimation system 110 includes a GPS receiver 50, a sensor 20, and a wear estimation device 30, and uses the calculation model 33b generated by the calculation model generation system 100 to estimate the wear amount of the tires 10 mounted on a vehicle. Estimate with high accuracy.

The wear amount estimating device 30 includes a position information acquisition section 31, a tire information acquisition section 32, a wear amount calculation section 33, and a notification section 35, and can be used by being mounted on a vehicle. The position information acquisition unit 31 and the tire information acquisition unit 32 have the same configuration and operation as in the first embodiment, and their description will be omitted for the sake of brevity.

The wear amount calculation unit 33 uses the calculation model generated by the calculation model generation system 100 according to the first embodiment as the calculation model 33b. The wear amount calculation unit 33 may calculate the tire wear amount after accumulating each data acquired by the position information acquisition unit 31 and the tire information acquisition unit 32 for a predetermined period, or may calculate the tire wear amount moment by moment at the acquired timing. may be calculated.

The preprocessing unit 33a has the same configuration and operation as in the first embodiment, and calculates the number of uphill trips, the number of downhill trips, the downhill slope and distance, the number of braking times, the number of turns, the turning radius, and the turning speed from the position data. It is calculated and used as input data to the calculation model 33b. As explained in the first embodiment, the preprocessing unit 33a inputs the number of uphill runs, the number of downhill runs, the slope and distance of a downhill slope, and the number of braking cycles required as inputs in accordance with the inputs considered in generating the calculation model 33b. , calculate the number of turns, turning radius, and turning speed.

The calculation model 33b has the same configuration and function as in the first embodiment, and may use the number of uphill runs and the number of downhill runs, or the number of downhill runs, as input. As in the first embodiment, the calculation model 33b may also use the gradient and distance of the downhill slope, the number of braking events, the number of turns, the turning radius, and the turning speed as input. The wear amount estimation system 110 may provide a wear amount calculation section including the calculation model 33b in a server device or the like outside the vehicle connected via a communication network, and transmit information such as position data from the vehicle to the server device or the like to estimate the wear amount.

The notification unit 35 notifies passengers, such as the driver of the vehicle, of the amount of tire wear through display on the display device 51, audio output from the speaker 52, etc. in order to make the occupants of the vehicle, such as the driver, aware of the current amount of tire wear. Further, the notification unit 35 may notify a vehicle control device 53 mounted on the vehicle of the current amount of tire wear. The vehicle control device 53 can perform vehicle control such as automatic driving and collision avoidance based on the current amount of tire wear.

Next, features of the wear amount estimation system 110 and the calculation model generation system 100 according to each embodiment will be described.
The wear amount estimation system 110 includes a position information acquisition section 31 and a wear amount calculation section 33. The position information acquisition unit 31 acquires position data of a vehicle on which the tire 10 is mounted. The wear amount calculation unit 33 has a calculation model 33b that calculates the amount of tire wear based on information regarding the altitude of the vehicle, and calculates the amount of wear of the tire 10 by inputting the altitude data in the position data using the calculation model 33b. Thereby, the wear amount estimation system 110 constructs a calculation model 33b that takes into consideration that the vehicle is traveling uphill or downhill based on the altitude data, and estimates the tire wear amount with high accuracy using the calculation model 33b. be able to.

The wear amount calculation unit 33 also includes a preprocessing unit 33a that calculates the number of times the vehicle travels uphill and the number of times the vehicle travels downhill, based on the altitude data. The number of uphill trips and the number of downhill trips calculated by 33a are input to the calculation model 33b. Thereby, the wear amount estimation system 110 can improve the estimation accuracy of the tire wear amount.

The wear amount calculation unit 33 also includes a preprocessing unit 33a that calculates the number of times the vehicle travels downhill based on the altitude data, and calculates the number of times the vehicle travels downhill based on the altitude data. 33b. Thereby, the wear amount estimation system 110 can improve the estimation accuracy of the tire wear amount.

Furthermore, when the vehicle is continuously traveling downhill, the preprocessing unit 33a inputs the slope and distance of the downhill slope to the calculation model 33b. Thereby, the wear amount estimation system 110 can further improve the estimation accuracy of the tire wear amount.

Further, the preprocessing unit 33a estimates the number of times the vehicle is braked, and inputs the estimated number of times of braking into the calculation model 33b. Thereby, the wear amount estimation system 110 can further improve the estimation accuracy of the tire wear amount.

The preprocessing unit 33a also calculates the number of turns of the vehicle based on the position data, and inputs the calculated number of turns to the calculation model 33b. Thereby, the wear amount estimation system 110 can further improve the accuracy of estimating the amount of tire wear.

The pre-processing unit 33a also calculates at least one of the vehicle's turning radius and turning radius based on the position data, and inputs the calculated values to the calculation model 33b. This allows the wear amount estimation system 110 to further improve the accuracy of estimating the amount of tire wear.

The calculation model generation system 100 includes a position information acquisition section 31, a wear amount calculation section 33, and a calculation model update section 34. The position information acquisition unit 31 acquires position data of a vehicle on which the tire 10 is mounted. The wear amount calculation unit 33 has a calculation model 33b that calculates the amount of tire wear based on information regarding the altitude of the vehicle, and calculates the amount of wear of the tire 10 by inputting the altitude data in the position data using the calculation model 33b. The calculation model update unit 34 compares the amount of wear measured by the tire 10 with the amount of wear calculated by the wear amount calculation unit 33, and updates the calculation model 33b. As a result, the calculation model generation system 100 generates a calculation model 33b that takes into consideration that the vehicle is traveling uphill or downhill based on the altitude data, and accurately estimates the amount of tire wear using the calculation model 33b. be able to.

The above description has been based on the embodiments of the present invention. Those skilled in the art will understand that these embodiments are illustrative and that various modifications and changes are possible and within the scope of the claims of the present invention. It is about to be done. Accordingly, the description and drawings herein are to be regarded in an illustrative rather than a restrictive sense.

10 tire, 31 position information acquisition unit, 33 wear amount calculation unit,
33b calculation model, 34 calculation model update unit,
100 Arithmetic model generation system, 110 Wear amount estimation system.

Claims (5)

a tire information acquisition unit that acquires tire data including tire temperature and pressure;
a position information acquisition unit that travels on a road and acquires position data of a vehicle equipped with the tire;
It has a calculation model that calculates the amount of tire wear, and the tire data, the mileage calculated based on the position data, and the altitude data in the position data are input, and the calculation model calculates the amount of wear of the tires. Equipped with a wear amount calculation section,
The wear amount calculation section includes a preprocessing section that calculates the number of times the vehicle travels downhill based on the altitude data, and the number of downhill travels calculated by the preprocessing section is calculated based on the calculation model. As input,
The wear amount calculation unit further calculates at least one of the number of times of braking of the vehicle, the turning radius of the vehicle, and the turning speed of the vehicle based on the position data, using the preprocessing unit, and inputs the calculated value to the calculation model. A wear estimation system featuring: 2. The wear amount calculation unit further calculates the number of times the vehicle travels uphill based on the altitude data using the preprocessing unit, and inputs the calculated number of times the vehicle travels uphill. 1. The wear amount estimation system according to 1. The wear amount calculation unit is characterized in that, when the vehicle is continuously traveling downhill , the preprocessing unit further calculates the slope and distance of the downhill slope , and inputs the slope and distance of the downhill slope. The wear amount estimation system according to claim 1 or 2. 4. The wear amount calculation section further calculates the number of turns of the vehicle based on the position data by the preprocessing section , and uses the calculated number of turns as an input to the calculation model. Wear amount estimation system described in . a tire information acquisition unit that acquires tire data including tire temperature and pressure;
a position information acquisition unit that travels on a road and acquires position data of a vehicle equipped with the tire;
It has a calculation model that calculates the amount of tire wear, and the tire data, the mileage calculated based on the position data, and the altitude data in the position data are input, and the calculation model calculates the amount of wear of the tires. A wear amount calculation section,
a calculation model updating unit that compares the amount of wear measured by the tire with the amount of wear calculated by the wear amount calculation unit and updates the calculation model ;
The wear amount calculation section includes a preprocessing section that calculates the number of times the vehicle travels downhill based on the altitude data, and the number of downhill travels calculated by the preprocessing section is calculated based on the calculation model. As input,
The wear amount calculation unit further calculates at least one of the number of times the vehicle is braked, the turning radius, and the turning speed of the vehicle based on the position data, and inputs the calculated value to the calculation model. A computational model generation system featuring:

Images