JP2023095215A - Tire deterioration estimation system, tire deterioration estimation method, and tire deterioration diagnosis system - Google Patents

Abstract

To provide a tire deterioration estimation system, a tire deterioration estimation method, and a tire deterioration diagnosis system capable of improving accuracy of tire deterioration estimation.SOLUTION: A tire deterioration estimation system 100 includes a sensor 20 and a deterioration estimation unit 32. The sensor 20 is disposed in a tire 10 and measures a physical quantity related to deformation of the tire 10. The deterioration estimation unit 32 inputs the physical quantity measured by the sensor 20 into a learning type calculation model 32a to estimate a deterioration indicator value of the tire 10. The calculation model 32a includes a feature extraction unit that extracts a feature quantity of the physical quantity measured by the sensor 20.SELECTED DRAWING: Figure 1

Description

The present invention relates to a tire deterioration estimation system, a tire deterioration estimation method, and a tire deterioration diagnosis system.

It is known that the deterioration of tires progresses according to the driving environment and the passage of time, and the tires harden, which affects the braking and cornering motions of the vehicle. In recent years, techniques for estimating the progress of deterioration of tire physical properties have been developed.

Patent Literature 1 describes a conventional tire deterioration prediction system. The prediction system includes tire condition measuring means for measuring characteristic values including at least tire internal pressure information indicating tire conditions or vehicle running conditions, and at least one point in the case based on the characteristic values measured by the tire condition measuring means. temperature history estimating means for estimating the temperature history of, and at least one case constituent member that can deteriorate due to the air temperature in the tire based on the temperature history and tire internal pressure information estimated by the temperature history estimating means, member physical property estimation means for estimating at least one current physical property value; and predicting the travelable distance of the tire until the current physical property value estimated by the member physical property estimation means reaches a preset limit physical property value. and remaining travelable distance prediction means.

JP 2014-46879 A

The tire deterioration prediction system described in Patent Document 1 estimates tire physical property values based on tire internal pressure information and temperature history, and predicts the travelable distance until the limit physical property value is reached. The inventors of the present application have found that there is room for improvement in estimating tire deterioration because mechanical fatigue caused by deformation, such as expansion and contraction, associated with movement of the tire during running also advances tire deterioration.

SUMMARY OF THE INVENTION The present invention has been made in view of such circumstances, and aims to provide a tire deterioration estimation system, a tire deterioration estimation method, and a tire deterioration diagnosis system capable of improving the accuracy of tire deterioration estimation. to provide.

One aspect of the present invention is a tire deterioration estimation system. The tire deterioration estimation system is installed in the tire, and estimates the deterioration index value of the tire by inputting the physical quantity measured by the sensor that measures the physical quantity related to the deformation of the tire and the learning type arithmetic model. and a degradation estimating unit that performs the degradation estimation, and the computing model has a feature extracting unit that extracts a feature quantity of the physical quantity measured by the sensor.

Another aspect of the invention is a tire deterioration estimation method. A method for estimating tire deterioration includes an acquisition step of acquiring a physical quantity related to tire deformation from a sensor provided on the tire, and inputting the physical quantity acquired by the acquisition step into a learning-type arithmetic model to obtain a tire deterioration index value. and a degradation estimation step of estimating , wherein the computation model extracts the feature quantity of the physical quantity acquired in the acquisition step.

Yet another aspect of the present invention is a tire deterioration diagnostic system. A tire deterioration diagnosis system is installed in a tire, and estimates a tire deterioration index value by inputting a sensor that measures a physical quantity related to tire deformation and the physical quantity measured by the sensor into a learning-type arithmetic model. an accumulating unit for accumulating the tire deterioration index value estimated by the deterioration estimating unit; and a notification unit for notifying the tire deterioration index value accumulated by the accumulating unit, the arithmetic model has a feature extraction unit that extracts a feature amount of the physical quantity measured by the sensor.

ADVANTAGE OF THE INVENTION According to this invention, the precision of deterioration estimation of a tire can be improved.

1 is a block diagram showing the functional configuration of a tire deterioration estimation system according to an embodiment; FIG. It is a schematic diagram which shows the structure of an arithmetic model. 1 is a block diagram showing a functional configuration of an arithmetic model generation system; FIG. 4 is a flowchart showing a procedure of tire deterioration estimation processing by a tire deterioration estimation system; 4 is a chart showing an example of verification results of deterioration index value estimation by a tire deterioration estimation system; It is a block diagram which shows the functional structure of the tire deterioration diagnostic system which concerns on a modification.

BEST MODE FOR CARRYING OUT THE INVENTION The present invention will be described below based on preferred embodiments with reference to FIGS. 1 to 6. FIG. The same or equivalent constituent elements and members shown in each drawing are denoted by the same reference numerals, and duplication of description will be omitted as appropriate. In addition, the dimensions of the members in each drawing are appropriately enlarged or reduced for easy understanding. Also, in each drawing, some of the members that are not important for explaining the embodiments are omitted.

(embodiment)
FIG. 1 is a block diagram showing the functional configuration of a tire deterioration estimation system 100 according to an embodiment. The tire deterioration estimation system 100 includes a sensor 20 and a tire deterioration estimation device 30 arranged on the tire 10 . The sensor 20 measures physical quantities related to deformation of the tire 10 , such as acceleration and strain in the tire 10 and loads generated in the tire 10 , and outputs the measured data to the tire deterioration estimation device 30 .

The tire deterioration estimation device 30 estimates a deterioration index value such as the number of years of deterioration of the tire 10 based on the physical quantity related to the deformation of the tire 10 measured by the sensor 20 . The tire deterioration estimating device 30 may acquire information such as vehicle acceleration from the vehicle side and use it for calculations for estimating the deterioration index value of the tire 10 .

The sensor 20 has an acceleration sensor 21, a strain gauge 22, a piezoelectric sensor 23, and the like, and measures physical quantities in the tire 10. FIG. These sensors measure physical quantities related to deformation and movement of the tire 10 as physical quantities of the tire 10 .

Acceleration sensor 21 , strain gauge 22 , and piezoelectric sensor 23 move mechanically together with tire 10 , and measure the amount of acceleration and strain generated in tire 10 . The acceleration sensor 21 is disposed, for example, on the tread, side, bead, wheel, etc. of the tire 10 and measures acceleration in three axes of the circumferential direction, axial direction and radial direction of the tire 10 .

The strain gauges 22 are arranged on the tread, sides, beads, etc. of the tire 10 and measure the strain at the places where they are arranged. The piezoelectric sensor 23 is arranged on the tread, side, bead, etc. of the tire 10, measures the load generated at the arrangement location, converts it into an electric signal, and outputs it. In order to identify each tire, the tire 10 may be attached with, for example, an RFID 11 or the like provided with unique identification information.

The tire deterioration estimation device 30 has a data acquisition section 31 and a deterioration estimation section 32 . The tire deterioration estimation device 30 is, for example, an information processing device such as a PC (personal computer). Each part in the tire deterioration estimation device 30 can be realized by electronic elements such as a CPU of a computer, mechanical parts, etc. in terms of hardware, and realized by computer programs etc. in terms of software. It depicts the functional blocks realized by cooperation. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by combining hardware and software.

The data acquisition unit 31 acquires information on the acceleration and strain measured by the sensor 20 and the load generated inside the tire 10 by wireless communication or the like. The deterioration estimator 32 has an arithmetic model 32 a , inputs information from the data acquisition unit 31 to the arithmetic model 32 a , and estimates a deterioration index value such as the number of years of deterioration of the tire 10 .

The arithmetic model 32a uses a learning model such as a neural network. FIG. 2 is a schematic diagram showing the configuration of the computation model 32a. The computational model 32a is of the CNN (Convolutional Neural Network) type, and is a learning model equipped with convolutional computations and pooling computations used in its prototype, so-called LeNet. FIG. 2 shows an example in which acceleration data in three axial directions are used as input data to the computation model 32a, and the probability of years of deterioration Y1 to Yn is output.

The computational model 32 a includes an input layer 50 , a feature extraction section 51 , an intermediate layer 52 , a fully connected section 53 and an output layer 54 . The input layer 50 receives time-series data such as acceleration in three axial directions acquired by the data acquisition unit 31 . For example, the acceleration data is measured in time series by the sensor 20, and the data of a certain time interval is cut out by a window function and used as input data. Input data is, for example, 64 pieces of acceleration data included in a fixed time interval in each axial direction. The input data is data arranged in time series, cut out in a certain time interval, similarly when strain and load are measured by the sensor 20 .

The acceleration measured by the tire 10 has periodicity for each rotation of the tire 10 . The time interval of the input data cut out by the window function is preferably set to a time period corresponding to the rotation period of the tire 10, for example, so that the input data itself has periodicity. The window function may extract input data in a time interval shorter or longer than one rotation of the tire 10. If at least the extracted input data contains periodic information, the computation model 32a learning is possible.

The feature extraction unit 51 extracts a feature amount using a convolution operation 51a and a pooling operation 51b, and transmits the feature amount to each node of the intermediate layer 52. FIG. In the example of the feature extraction unit 51 shown in FIG. 3, the input data is subjected to the first convolution operation using 20 filters. The convolution operation 51a performs a convolution operation while moving a filter with respect to time-series input data such as acceleration data. The convolution operation 51a is executed for each of the acceleration data in the three axial directions, which is a plurality of pieces of input data.

In the convolution operation 51a, the filter length is set to 5, but it may be set to a size of about 1 to 5 as appropriate. Note that the convolution operation is obtained by multiplying the continuous filter length data (for example, A1, A2, A3) in the time-series input data by each value (f1, f2, f3) in the filter. Add the obtained values to obtain A1×f1+A2×f2+A3×f3. It should be noted that the convolution operation may be performed by performing zero padding to add "0 (zero)" data to the ends of the input data. In addition, the amount of movement of the filter in the convolution operation is normally assumed to be one input data, but can be changed as appropriate in order to reduce the size of the computation model 32a.

The pooling operation 51b executes the first maximum value pooling operation on the data after the first convolution operation. For example, the pooling operation 51b selects the larger value from the two values arranged in chronological order.

The second convolution operation 51c performs a convolution operation on the data after the pooling operation 51b using, for example, 50 filters. The filter length in the convolution operation 51c may be the same as that in the convolution operation 51a, or may be different. For the convolution operation 51c as well, the scale of operation can be reduced by using the same filter for each axial direction and making it common.

The pooling operation 51d executes the second maximum value pooling operation on the data after the convolution operation 51c. Similarly to the pooling operation 51b, the pooling operation 51d selects, for example, the larger value from the two values arranged in time series. The feature extraction unit 51 acquires 64 data as a calculation result by convolution calculation and pooling calculation, and outputs it to each node of the intermediate layer 52 .

The full linking unit 53 fully links the data from each node of the intermediate layer 52 in two layers, and outputs the probability of deterioration years Y1 to Yn as deterioration index values to each node of the output layer 54 . The fully-connected unit 53 executes calculations by fully-connected paths that perform linear calculations using weighting, etc. However, in addition to linear calculations, non-linear calculations using activation functions and the like may also be performed. good.

FIG. 3 is a block diagram showing the functional configuration of the computational model generation system 110. As shown in FIG. The computational model generation system 110 includes a computational model generation device 70 having a learning processing unit 71 . The arithmetic model generating device 70 has a learning processing section 71 in addition to each component of the tire deterioration estimating device 30 . Parts corresponding to each component of the tire deterioration estimating device 30 in the arithmetic model generating device 70 have functions equivalent to those of the tire deterioration estimating device 30, but the arithmetic model 32a is before or during learning.

The learning processing unit 71 uses the number of years of deterioration of the tire 10 used during learning as teacher data to allow the computation model 32a to learn. The age of deterioration of the tire 10 indicates, for example, a deterioration index value that deteriorates due to exposure of the rubber material of the tire 10 to air. Specifically, prepare new tires that have been exposed to air for less than one year immediately after manufacture, two-year-old tires that are one to two years old, and three-year-old tires that are two to three years old. Correspond with deterioration years F1, F2, . . . , Fn.

For example, in learning using a new tire, the learning processing unit 71 uses teacher data with a probability of 1 for the number of years of deterioration F1 and a probability of 0 for the years of deterioration F2 to Fn, and compares the result of estimation by the computation model 32a with the teacher data. , to learn the arithmetic model 32a. Further, the learning processing unit 71 learns the arithmetic model 32a by using teacher data in which the probability of the deterioration years F2 is 1 and the probability of the other deterioration years is 0 in the learning with the two-year-old tire. Similarly, the learning processing unit 71 can learn the arithmetic model 32a using 3-year-old tires, 4-year-old tires, and the like.

The learning processing unit 71 compares the deterioration index value of the tire 10 estimated by the arithmetic model 32a with the teacher data, newly sets various coefficients in the arithmetic process such as weighting in the arithmetic model 32a, and repeats updating of the model. learn by doing. The tire deterioration estimation system 100 estimates the deterioration index value of the tire 10 using the arithmetic model 32 a that has been learned by the arithmetic model generation system 110 .

The arithmetic model 32a can perform learning of the arithmetic model 32a in a rotation test with tires 10 (including wheels) of each specification. However, there is no need to perform learning of the arithmetic model 32a for each specification of the tire 10 strictly. The calculation model 32a may be constructed for each type of tire, such as passenger car tires and truck tires, based on the assumption that the deterioration index value of the estimation result can be estimated within a certain error range, or based on the tire material. You may divide a type and construct it separately for each type. The calculation model 32a may share one calculation model 32a for tires 10 included in a plurality of specifications, thereby reducing the number of calculation models.

The learning processing unit 71 can also execute the learning of the computational model 32a by running a test run of a vehicle on which the tires 10 are actually mounted. The specifications of the tire 10 include information on tire performance such as tire size, tire width, aspect ratio, tire strength, tire outer diameter, load index, date of manufacture, and the like.

Next, the operation of tire deterioration estimation system 100 will be described. FIG. 4 is a flowchart showing a procedure of tire deterioration estimation processing by the tire deterioration estimation system 100. As shown in FIG. The data acquisition unit 31 of the tire deterioration estimation device 30 acquires physical quantities such as the acceleration and strain in the tire 10 measured by the sensor 20 and the load generated in the tire 10 as time-series data (S1).

The deterioration estimating unit 32 extracts input data in a certain time interval from the data acquired by the data acquiring unit 31 (S2). In estimating the deterioration index value of the tire 10, at least one of the acceleration and strain in the tire 10 and the load generated in the tire 10 is used as input data to the computation model 32a. Further, in estimating the deterioration index value of the tire 10, the above-mentioned acceleration, strain and load are used as input data in a uniaxial direction, in an arbitrary combination in a biaxial direction, or in a triaxial direction.

The feature extraction unit 51 of the computation model 32a executes processing for extracting feature amounts by convolution and pooling operations on the input data (S3). The full connection unit 53 of the computation model 32a performs a full connection operation on the feature amounts extracted by the feature extraction unit 51 and input to each node of the intermediate layer 52 (S4). Parameters such as weights used in the fully-connected calculation are determined in the learning of the calculation model 32a. The deterioration estimator 32 calculates the probabilities of the deterioration years F1 to Fn, which are the deterioration index values, by the fully connected calculation of the calculation model 32a, outputs the deterioration index value with the highest probability (S5), and ends the process. do.

The deterioration estimating unit 32 of the tire deterioration estimating system 100 estimates the deterioration index value of the tire 10 using the arithmetic model 32a having the feature extracting unit 51 that extracts the feature amount by convolution operation, thereby estimating the deterioration of the tire 10. Accuracy can be improved. For example, when the hardness of the rubber material of the tire 10 increases due to deterioration over time, the physical quantity data related to the deformation of the tire 10 changes according to the change in hardness. It is considered that the tire deterioration estimation system 100 can estimate a deterioration index value such as the number of years of deterioration of the tire 10 by extracting an influence such as a change in hardness as a characteristic amount by the characteristic extraction unit 51 .

Sensor 20 of tire deterioration estimation system 100 has at least one of acceleration sensor 21 , strain gauge 22 and piezoelectric sensor 23 . The data acquisition unit 31 acquires the acceleration and strain measured by the tire 10 and the load in the tire 10 measured by the piezoelectric sensor 23, and uses them as input data to the computation model 32a. As a result, the tire deterioration estimation system 100 can estimate the deterioration index value of the tire 10 based on the measurement data of the acceleration, strain, and load that are affected by deterioration factors such as changes in the hardness of the tire 10 .

The feature extraction unit 51 of the computational model 32a performs a convolution operation by moving a filter on time-series data relating to physical quantities such as acceleration, strain, and load measured by the sensor 20 . The tire deterioration estimation system 100 can also extract feature quantities for physical quantities such as acceleration, strain, and load by performing filter calculations on time-series data.

The deterioration estimating unit 32 of the tire deterioration estimating system 100 uses, as the output of the computational model 32a, the probabilities for the deterioration index values defined as multistage values to determine which stage of deterioration the tire 10 is in. can be estimated. The deterioration estimating unit 32 can present the estimation result on a user-friendly scale, such as a new tire or a two-year-old tire, by using, for example, the number of years of deterioration as the deterioration index value.

FIG. 5 is a chart showing an example of verification results of deterioration index value estimation by the tire deterioration estimation system 100. In FIG. In the example shown in FIG. 5, the deterioration estimating unit 32 gives a correct answer when using measurement data from the acceleration sensor 21, the strain gauge 22, and the piezoelectric sensor 23 for a new tire and a tire aged 2 to 5 years. The estimated probability (hereinafter referred to as correct answer rate) is shown. When the correct answer rate is 1, it means that all the answers were correct.

When the acceleration data measured by the acceleration sensor 21 is used as the input for the arithmetic model 32a, the correct answer rate of the deterioration estimator 32 is low at 0.9 for a tire aged 5 years, but the deterioration years of the tire are estimated with a high probability. I know you are. When the data measured by the strain gauge 22 and the piezoelectric sensor 23 are input to the computation model 32a, the correct answer rate of the deterioration estimator 32 is 1.00 in significant digits. is estimated.

For example, for acceleration data measured for a predetermined period (for example, several tens of minutes to several hours) by the acceleration sensor 21, a plurality of sets of input data extracted by a window function are prepared. to estimate The deterioration estimator 32 preferably uses the deterioration index value with the highest frequency among the deterioration index values estimated for each set of input data as the estimation result.

(Modification)
FIG. 6 is a block diagram showing the functional configuration of a tire deterioration diagnostic system 120 according to a modification. The tire deterioration diagnosis system 120 includes an accumulation unit 33 and a notification unit 34 in the tire deterioration estimation device 30, and provides the estimated deterioration index value of the tire 10 to the outside as a diagnosis result. The storage unit 33 has a storage device configured by, for example, an SSD (Solid State Drive), hard disk, CD-ROM, DVD, etc., and stores the deterioration index value of the tire 10 estimated by the deterioration estimation unit 32 .

The notification unit 34 includes a display device such as a liquid crystal display and an audio output device such as a speaker, and displays or outputs the information on the deterioration index value of the tire 10 accumulated in the accumulation unit 33 . Further, the notification unit 34 provides the deterioration index value of the tire 10 accumulated in the accumulation unit 33 to the vehicle control device 80 via CAN communication in the vehicle, for example. The notification unit 34 also provides the deterioration index value of the tire 10 accumulated in the accumulation unit 33 to the server device 81 connected by wireless or wired communication.

The vehicle control device 80 applies the deterioration index value of the tire 10 input from the tire deterioration estimation device 30, for example, to estimation of braking distance, application to vehicle control, and notification of information regarding safe driving of the vehicle to the driver. used for The vehicle control device 80 can also provide information regarding safe driving of the vehicle in the future using map information, weather information, and the like.

The server device 81 displays the deterioration index value of the tire 10 input from the tire deterioration estimating device 30 on, for example, a display device, and provides the user with information in planning such as tire replacement and tire rotation. The tire deterioration diagnosis system 120 notifies the estimated deterioration index value of the tire 10 to the outside by the notification unit 34, thereby providing useful information for use in vehicle control and planning for tire replacement by the user. can be done.

In the above embodiments and modifications, the computational model 32a uses a CNN-type LeNet model, but a model structure such as a so-called DenseNet model, ResNet model, MobileNet model, or PeleelNet model may also be used. Also, a model may be constructed by incorporating module structures such as Dense Block, Residual Block, and Stem Block into the computation model 32a.

Next, features of the tire deterioration estimation system 100, the tire deterioration estimation method, and the tire deterioration diagnosis system according to the embodiment will be described.
A tire deterioration estimation system 100 according to the embodiment includes a sensor 20 and a deterioration estimation unit 32 . The sensor 20 is arranged on the tire 10 and measures a physical quantity related to deformation of the tire 10 . The deterioration estimator 32 inputs the physical quantity measured by the sensor 20 into the learning-type arithmetic model 32a to estimate the deterioration index value of the tire 10 . The computational model 32 a has a feature extractor 51 that extracts the feature quantity of the physical quantity measured by the sensor 20 . Thereby, the tire deterioration estimation system 100 can improve the accuracy of deterioration estimation of the tire 10 .

Also, the sensor 20 has at least one of an acceleration sensor 21 , a strain gauge 22 and a piezoelectric sensor 23 . Thereby, the tire deterioration estimation system 100 can estimate the deterioration index value of the tire 10 based on the acceleration, strain and load measurement data.

Further, the feature extracting unit 51 performs calculations by moving a filter on data arranged in time series of physical quantities measured by the sensor 20 . As a result, the tire deterioration estimation system 100 can extract feature quantities for physical quantities such as acceleration, strain, and load by performing filter calculations on time-series data.

Further, the deterioration index value is a multi-level value, and the computation model 32a outputs the probability of each stage of the deterioration index value. Thereby, the tire deterioration estimation system 100 can estimate which stage of deterioration the tire 10 is in.

The deterioration index value is the number of years of deterioration. As a result, the tire deterioration estimation system 100 can present the estimation results on a user-friendly scale.

The tire deterioration estimation method comprises an acquisition step and a deterioration estimation step. The acquisition step acquires a physical quantity related to deformation of the tire 10 from the sensor 20 arranged on the tire 10 . The deterioration estimation step estimates the deterioration index value of the tire 10 by inputting the physical quantity acquired in the acquisition step into the learning-type arithmetic model 32a. The computational model 32a extracts the feature quantity of the physical quantity acquired in the acquisition step. According to this tire deterioration estimation method, the accuracy of deterioration estimation of the tire 10 can be improved.

The tire deterioration diagnosis system 120 includes a sensor 20, a deterioration estimation section 32, an accumulation section 33 and a notification section . The sensor 20 is arranged on the tire 10 and measures a physical quantity related to deformation of the tire 10 . The deterioration estimator 32 inputs the physical quantity measured by the sensor 20 into the learning-type arithmetic model 32a to estimate the deterioration index value of the tire 10 . The accumulation unit 33 accumulates the deterioration index values of the tire 10 estimated by the deterioration estimation unit 32 . The notification unit 34 notifies the deterioration index value of the tire 10 accumulated by the accumulation unit 33 . The computational model 32 a has a feature extractor 51 that extracts the feature quantity of the physical quantity measured by the sensor 20 . As a result, the tire deterioration diagnosis system 120 notifies the estimated deterioration index value of the tire 10 to the outside by the notification unit 34, thereby providing useful information for use in vehicle control and planning for tire replacement by the user. can provide.

The above has been described based on the embodiments of the present invention. Those skilled in the art will appreciate that these embodiments are illustrative and that various variations and modifications are possible within the scope of the claims of the present invention, and that such variations and modifications also fall 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 tires, 20 sensors, 21 acceleration sensors, 22 strain gauges,
23 Piezoelectric sensor 32 Degradation estimator 32a Calculation model 33 Accumulator
34 reporting unit, 51 feature extraction unit, 100 tire deterioration estimation system,
120 tire deterioration diagnosis system;

Claims (7)

A sensor that is arranged on the tire and measures a physical quantity related to deformation of the tire;
a deterioration estimating unit that inputs the physical quantity measured by the sensor into a learning-type arithmetic model to estimate a deterioration index value of the tire,
The tire deterioration estimation system, wherein the arithmetic model has a feature extraction unit that extracts a feature quantity of the physical quantity measured by the sensor. 2. The tire deterioration estimation system according to claim 1, wherein the sensor has at least one of an acceleration sensor, a strain gauge and a piezoelectric sensor. 3. The tire deterioration estimation system according to claim 1, wherein the feature extracting unit performs calculations by moving a filter for the time-series data of the physical quantities measured by the sensor. The deterioration index value is a multistage value,
The tire deterioration estimation system according to any one of claims 1 to 3, wherein the arithmetic model outputs a probability at each stage of the deterioration index value. 5. The tire deterioration estimation system according to claim 4, wherein the deterioration index value is the number of years of deterioration. an acquisition step of acquiring a physical quantity related to tire deformation from a sensor disposed on the tire;
a degradation estimation step of estimating a tire degradation index value by inputting the physical quantity acquired in the acquisition step into a learning-type arithmetic model;
A method for estimating tire deterioration, wherein the arithmetic model extracts the feature quantity of the physical quantity obtained in the obtaining step. A sensor that is arranged on the tire and measures a physical quantity related to deformation of the tire;
a deterioration estimating unit that inputs the physical quantity measured by the sensor into a learning-type arithmetic model to estimate a tire deterioration index value;
an accumulation unit that accumulates the tire deterioration index value estimated by the deterioration estimation unit;
a notification unit that notifies the deterioration index value of the tire accumulated by the accumulation unit;
with
The tire deterioration diagnosis system, wherein the arithmetic model has a feature extraction unit that extracts a feature quantity of the physical quantity measured by the sensor.

Images