JP2024035288A - Method for evaluating tire performance - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for evaluating tire performance, an evaluation device, an evaluation program, and the like.

SOLUTION: A method for evaluating tire performance includes the steps of: acquiring one or more measurement values for an evaluation target tire serving as an evaluation target; inputting the acquired one or more measurement values to a prediction model; and deriving output from the prediction model. The output derived from the prediction model corresponds to an evaluation result obtained by a driver evaluating at least one of the ride comfort and the steering stability of the vehicle on which the evaluation target tire is mounted with reference to at least one of the ride comfort and the steering stability of the vehicle on which the reference tire is mounted.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present invention relates to a method for evaluating tire performance, an evaluation device, an evaluation program, and a method for generating a trained model.

Patent Document 1 discloses a method of predicting tire performance values using a machine learning model based on an image representing a tire contact surface shape. According to Patent Document 1, tire performance values to be predicted are, for example, CP (cornering power), CFmax (maximum cornering force), and SAT (self-aligning torque).

JP 2021-195038 Publication

By the way, at least some of the mechanically measurable tire performance values as described above are considered to have a correlation with the ride comfort and steering stability of the vehicle on which the tire is installed. However, evaluation of vehicle ride comfort and handling stability is currently based at least in part on sensory evaluation by the driver. No systematic method for evaluating (tire performance) was provided.

An object of the present invention is to provide a method for evaluating tire performance, an evaluation device, an evaluation program, and a method for generating a trained model.

The tire performance evaluation method according to the first aspect includes acquiring one or more measured values of the tire to be evaluated, and inputting the acquired one or more measured values into a prediction model. and deriving an output from the predictive model. The output derived from the prediction model allows the driver to evaluate at least one of the ride comfort and handling stability of the vehicle equipped with the evaluation target tire and the ride comfort and handling stability of the vehicle equipped with the reference tire. It corresponds to the evaluation result evaluated based on at least one of the criteria.

The tire performance evaluation method according to the second aspect is the tire performance evaluation method according to the first aspect, and the prediction model is a trained machine learning model.

The tire performance evaluation method according to the third aspect is the tire performance evaluation method according to the first aspect or the second aspect, comprising one or more measured values for the reference tire and one or more measured values for the learning tire. Alternatively, preparing a learning data set that combines a plurality of measured values and correct data, and inputting data corresponding to the one or more measured values using the learning data set, The method further includes adjusting parameters defining the machine learning model so as to output data corresponding to correct data. The correct answer data may be such that the driver determines at least one of the ride comfort and handling stability of the vehicle on which the learning tires are installed, and at least one of the ride comfort and handling stability of the vehicle on which the reference tires are installed. Includes evaluation results based on the criteria.

The tire performance evaluation method according to the fourth aspect is the tire performance evaluation method according to any one of the first to third aspects, and the evaluation result is obtained from the vehicle on which the evaluation target tire is mounted. The one or more measured values include at least one of a lateral spring constant, a longitudinal spring constant, and a dynamic spring constant.

The tire performance evaluation method according to the fifth aspect is the tire performance evaluation method according to any one of the first to fourth aspects, and the evaluation result is obtained from the vehicle on which the evaluation target tire is mounted. The one or more measured values include at least one of dynamic spring constant, cornering power, maximum cornering force, and self-aligning torque.

The tire performance evaluation method according to the sixth aspect is the tire performance evaluation method according to any one of the first to fifth aspects, wherein the driver drives the vehicle equipped with the tire to be evaluated. obtaining an evaluation result in which at least one of ride comfort and handling stability is evaluated based on at least one of ride comfort and handling stability of the vehicle to which the reference tire is installed; and the evaluation result and the prediction. and comparing outputs derived from the model.

The tire performance evaluation method according to the seventh aspect is the tire performance evaluation method according to any of the first to sixth aspects, in which the driver The method further includes specifying the one or more measured values for bringing an evaluation result of at least one of ride comfort and handling stability of the vehicle equipped with the evaluation target tire closer to a target.

The tire performance evaluation device according to the eighth aspect includes an acquisition section, a storage section, and a derivation section. The acquisition unit acquires one or more measured values for the evaluation target tire that is the evaluation target. The storage unit stores parameters that define the prediction model. The derivation unit inputs the acquired one or more measured values into the prediction model and derives an output from the prediction model. The output derived from the prediction model allows the driver to evaluate at least one of the ride comfort and handling stability of the vehicle equipped with the evaluation target tire and the ride comfort and handling stability of the vehicle equipped with the reference tire. It corresponds to the evaluation result evaluated based on at least one of the criteria.

The tire performance evaluation program according to the ninth aspect causes one or more processors to execute the following.
- Obtaining one or more measured values for the tire to be evaluated that is the subject of evaluation - Inputting the obtained one or more measured values into a prediction model - Deriving an output from the prediction model The prediction model The output derived from the above is the output that allows the driver to evaluate at least one of the ride comfort and handling stability of the vehicle on which the evaluation target tire is installed, and at least one of the ride comfort and handling stability of the vehicle on which the reference tire is installed. Corresponds to the evaluation results evaluated as a standard.

The method for generating a trained model according to the tenth aspect includes the following.
- Preparing a learning data set that combines one or more measured values for the reference tire and one or more measured values for the learning tire, and correct data. - Using the learning data set. , adjusting parameters defining a machine learning model so that when data corresponding to the one or more measured values is input, data corresponding to the correct data is output; includes an evaluation result of evaluating at least one of the ride comfort and steering stability of a vehicle equipped with the standard tire based on at least one of the ride comfort and steering stability of the vehicle equipped with the reference tire.

According to the present invention, the senses of a driver who performs a sensory evaluation of tire performance, such as ride comfort and handling stability, are modeled as a predictive model that uses tire measurement values as input. As a result, knowledge for realizing the target tire performance can be efficiently obtained.

FIG. 1 is a block diagram showing an electrical configuration of a tire performance evaluation device according to an embodiment. 1 is a flowchart showing a method for evaluating tire performance using a predictive model. Flowchart showing a method for generating a predictive model.

Hereinafter, a method for evaluating tire performance, an evaluation device, an evaluation program, and a method for generating a trained model according to an embodiment of the present invention will be described.

<1. Overview＞
FIG. 1 is a block diagram showing the electrical configuration of an evaluation device 1 according to an embodiment of the present invention. Evaluation device 1 is mainly used in the design and development of tires, particularly in the design and development of tires to achieve the target ride comfort and handling stability (hereinafter collectively referred to as "tire performance"). support. In the development of such tires, tires that achieve target performance are often developed based on the performance of a tire called a control tire (hereinafter also referred to as a "reference tire"). The tire performance evaluation as described above is performed by one or more specialized testers (hereinafter also referred to as "drivers"). Drivers compare the sensations they get when driving a vehicle equipped with standard tires with the sensations they get when driving the same vehicle equipped with prototype tires (hereinafter also referred to as "evaluation tires"). Evaluate. That is, the driver evaluates at least one of the ride comfort and steering stability of the vehicle equipped with the evaluation target tire, based on the result of evaluating at least one of the ride comfort and steering stability of the vehicle equipped with the reference tire. do.

The evaluation of tire performance in the sensory evaluation described above may vary depending on the driver, or may vary depending on the physical condition of the same driver. In addition, the quantitative correlation between tire measurements and tire performance is still under investigation. As a result, in order to achieve a targeted evaluation of a specific performance, it is necessary to repeatedly produce tire prototypes relying on human intuition, which hinders efficient development. In view of the current situation, the evaluation device 1 uses a predictive model that predicts the evaluation of the tire to be evaluated by a specific driver based on one or more measured values of the tire to be evaluated, to compare the measured values of the tire with the sensory evaluation. Deepen your knowledge of correlations and support efficient development.

<2. Configuration of evaluation device>
The evaluation device 1 is a general-purpose computer as hardware, and is realized as, for example, a desktop computer, a laptop computer, a tablet, or a smartphone. The evaluation device 1 is manufactured by installing the program 132 into a general-purpose computer from a computer-readable recording medium 133 such as a CD-ROM or USB memory, or via a network. The program 132 causes the evaluation device 1 to perform operations described below.

The evaluation device 1 includes a control section 10, a display section 11, an input section 12, a storage section 13, and a communication section 14. These units 10 to 14 are connected to each other via a bus line 15 and can communicate with each other. The display unit 11 can be configured with a liquid crystal display, an organic EL display, a plasma display, a touch panel display, etc., and displays errors in the machine learning process of the prediction model, which will be described later, and output results derived from the prediction model. The input unit 12 can be configured with a mouse, a keyboard, a touch panel, etc., and accepts operations on the evaluation device 1. The display unit 11 and the input unit 12 may both be configured with the same touch panel display.

The storage unit 13 can be composed of a hard disk and a nonvolatile memory such as a flash memory. In addition to storing a program 132, the storage unit 13 stores parameters that define a trained machine learning model 131A constructed by machine learning to be described later. The machine learning model 131A is an example of a "prediction model."

The control unit 10 can be configured with a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a ROM, a RAM, and the like. The control unit 10 reads and executes the program 132 in the storage unit 13, thereby virtually operating as an acquisition unit 10A, a derivation unit 10B, a screen generation unit 10C, a verification unit 10D, and a learning unit 10E. The acquisition unit 10A acquires the measured value of the tire to be evaluated via the input unit 12, the communication unit 14, and the like. The derivation unit 10B inputs the measured values of the tire into the prediction model and derives the output from the prediction model. The screen generation unit 10C generates a screen that displays the (predicted) evaluation result of the performance of the tire to be evaluated based on the output derived by the derivation unit 10B. The communication unit 14 functions as a communication interface that performs data communication via a network. The operations of the verification section 10D and the learning section 10E will be described later.

<3. Prediction model configuration>
The configuration of the prediction model will be explained below. As described above, the prediction model of this embodiment is the trained machine learning model 131A. The learned machine learning model 131A (hereinafter also simply referred to as "machine learning model 131A") is constructed for each predetermined one or more drivers. In other words, the machine learning model 131A is a general term for one or more machine learning models 131 that have a common layer configuration and are defined by parameters optimized for each driver. The parameters defining these machine learning models 131 are stored in the storage unit 13 in association with, for example, information for identifying a driver. Then, when evaluating the performance of the tire to be evaluated by predicting the evaluation result of a specific driver, the machine learning model 131 constructed for the driver is applied.

Input data to the machine learning model 131 is one or more measured values of the tire to be evaluated. Measured values are not particularly limited as long as they are data obtained by measuring a single tire to be evaluated, such as lateral spring constant, longitudinal spring constant, dynamic spring constant, cornering power (CP), maximum cornering force, and self-alignment. Examples include lining torque (SAT), CTP, H (α), and G (α). In particular, when predicting the evaluation of ride comfort, it is preferable that the input data include at least one measured value of a lateral spring constant, a longitudinal spring constant, and a dynamic spring constant, and when predicting the evaluation of handling stability. Preferably, the input data includes at least one measured value of a dynamic spring constant, CP, maximum cornering force, and self-aligning torque. These measured values can be measured using a known tire performance tester or the like that reproduces and measures the behavior of a vehicle on which the tire is mounted on a bench.

The machine learning model 131A of this embodiment is a model based on a neural network (NN), which receives one or more measured values of the tire to be evaluated or one or more values corresponding thereto, and receives one or more measured values or one or more values corresponding thereto. The value corresponding to the driver's evaluation result for the evaluation item is output. As described above, the layer structure of the model described below is the same regardless of the driver in this embodiment.

The machine learning model 131A includes an input layer, an intermediate layer, and an output layer each having a predetermined number of nodes. The input layer is a layer for reading input data, and has the same number of nodes as the number of input data. Each node of the input layer outputs the input value as is, and inputs it to each node of the first intermediate layer connected immediately after the input layer.

Each node of the first intermediate layer calculates a value obtained by multiplying the input by a weight w and adding a bias b. Then, the calculated value is converted by the activation function and the value is output to the subsequent intermediate layer node. The input here is one or more values read in the input layer. The weight w has been adjusted for each value passed from each node of the input layer to each node of the first intermediate layer by a learning process described later. That is, for each node of the first intermediate layer, the number of weights w corresponding to the number of values input thereto is optimized. In addition, the number of biases b corresponding to the number of nodes is also optimized by the learning process described later.

The activation function is a function for realizing nonlinear transformation. The activation function is not particularly limited, and known activation functions such as a tanh function, a sigmoid function, a ReLU function, a step function, an ELU function, and a Softmax function can be employed.

The values output from each node of the first intermediate layer are preferably input to each node of the subsequent intermediate layer. The subsequent intermediate layer also has a predetermined number of nodes, and for each node, the weight w and bias b are optimized by a learning process described later. Similar to the first intermediate layer, each node outputs a value calculated using the weight w and bias b corresponding to the input value, and the activation function. That is, in the middle layer, in principle, the same processing as in the first middle layer is repeated. However, in the last intermediate layer, linear transformation using the optimized weights w and bias b is performed on the input, but non-linear transformation using the activation function is not performed. That is, the values after linear transformation output from each node of the last succeeding intermediate layer become input to each node of the output layer. Note that the number of intermediate layers is preferably two or more, but is not particularly limited and can be set as appropriate.

The output layer has a number of nodes corresponding to the number of one or more evaluation items, and each node typically outputs the input value as is. The output from each node is a value representing the predicted tire performance evaluation for the corresponding evaluation item. This output value becomes the output of the machine learning model 131A. In other words, this output allows the driver to evaluate at least one of the ride comfort and steering stability of a vehicle equipped with the evaluation target tire, based on at least one of the ride comfort and steering stability of a vehicle equipped with the reference tire. Correspond to the evaluation results.

Evaluation items related to ride comfort include, for example, the type of vibration felt (fine vibrations, coarse vibrations, vibrations that resonate with the human body, etc.), and the feeling of thrusting. Evaluation items related to handling stability include convergence, feel, responsiveness, grip feeling, and hardness. In this embodiment, the evaluation of each evaluation item is performed using a stepwise numerical index based on the evaluation of the sensory test of the reference tire. For example, if the index for each evaluation item in the sensory test of a reference tire is set to "3", the upper limit of each evaluation item is set to "5", and the lower limit is set to "1", then the evaluation target tire's (relative Performance can be evaluated on a five-level scale by selecting a value from 1 to 5. It can also be said that the output data output by the machine learning model 131A is each predicted value of the driver's five-level evaluation result for one or more evaluation items.

As described above, the machine learning model 131A of this embodiment is configured to output predicted evaluation results corresponding to one or more evaluation items for input data. However, the configuration of the NN-based machine learning model 131A is not particularly limited to that of the above embodiment. For example, the machine learning model 131A may be configured to output the probability of an evaluation index for one or more evaluation items that is predicted to be selected by the driver, rather than the predicted value of the evaluation result itself (this In this case, for example, a softmax function can be used as the activation function of the output layer). In this case, the evaluation index with the highest probability among each evaluation item can be used as the predicted value of the evaluation index. In this way, the value that can be converted into the predicted value of the evaluation index is determined by the driver's evaluation of at least one of the ride comfort and handling stability of the vehicle equipped with the evaluation target tire, and the ride comfort and handling stability of the vehicle equipped with the standard tire. This is an example of an output corresponding to an evaluation result based on at least one of steering stability.

<4. Evaluation method>
Next, a method for evaluating a tire to be evaluated, including the operation of the evaluation device 1, will be described with reference to FIG. 2.

First, the acquisition unit 10A acquires one or more measured values of the tire to be evaluated (step S1). The measured value can be obtained using a known tire performance testing machine, as described above. Acquisition by the acquisition unit 10A may be performed, for example, by the user of the evaluation device 1 (typically, a tire development designer) via the input unit 12, or via a recording medium such as a CD-ROM or USB memory. Alternatively, it may be performed by reading data from a tire performance testing machine via a network. The acquisition unit 10A stores the acquired measurement values in the RAM or the storage unit 13.

Subsequently, the derivation unit 10B receives the selection of one machine learning model 131 from among the machine learning models 131 constructed for each driver via the input unit 12 (step S2). This selection may be made by selecting information that identifies the driver associated with each machine learning model 131.

Subsequently, the measured value obtained in step S1 is input to the machine learning model 131, and an output from the machine learning model 131 is derived (step S3). As described above, these outputs are predicted values of numerical indicators corresponding to each predetermined evaluation item regarding tire performance. Note that when the output of the machine learning model 131 is a value representing a probability, the evaluation index that is predicted to have the highest probability of being selected can be used as the predicted value of the numerical index.

Subsequently, the screen generation unit 10C generates a result screen that displays the output derived in step S3, and displays it via the display unit 11 (step S4). The result screen can include, for example, a display in which predetermined evaluation items are associated with predicted values of numerical indicators for each evaluation item.

Subsequently, the output derived in step S3, that is, the predicted value of the evaluation result, is verified by the verification unit 10D (step S5). The verification unit 10D obtains the evaluation results actually performed on the evaluation target tires by the driver selected in step S2, and compares them with the predicted values. The actual evaluation results may be obtained via the input unit 12, via the recording medium, or may be received from another computer via the network, similarly to the acquisition of the measured values. In addition, the verification unit 10D also acquires target performance evaluation data (hereinafter referred to as "target evaluation") for the evaluation target tire. The target evaluation is an index value determined based on a reference tire. The actual evaluation results and the target evaluation may be obtained at any timing.

The evaluation result and the predicted value can be compared, for example, by calculating the difference between the actual evaluation result and the predicted value for each evaluation item, and determining whether there is any evaluation item that exceeds a predetermined threshold. If there is no evaluation item that exceeds the predetermined threshold, the verification unit 10D determines that "there is no difference between the evaluation result and the predicted value (NO)", and step S6 is executed. If there is an evaluation item that exceeds a predetermined threshold, the verification unit 10D determines that "there is a difference between the evaluation result and the predicted value (YES)", and step S7 is executed.

In step S6, it is verified whether the tire to be evaluated has the target performance based on the driver's actual evaluation results. The verification unit 10D compares the actual evaluation result and the target evaluation, and determines whether the target performance is achieved. Similar to step S5, this comparison can be performed, for example, by calculating the difference between the actual evaluation result and the target evaluation for each evaluation item, and determining whether there is any evaluation item that exceeds a predetermined threshold. If there is no evaluation item that exceeds a predetermined threshold, the verification unit 10D determines that "target evaluation has been achieved (YES)". In this case, since it has been confirmed that the tire targeted for development has been produced, the development of the tire is ended. If there is an evaluation item that exceeds a predetermined threshold, the verification unit 10D determines that "objective evaluation has not been achieved (NO)". In this case, step S8 is executed.

In step S7, the screen generation unit 10C generates a screen that displays the verification results in step S6, and displays it on the display unit 11. The result screen can include, for example, a display that compares the actual evaluation results by the driver with the predicted values of numerical indicators for each evaluation item. After confirming this, the user can analyze the cause of the difference between the predicted value by the machine learning model 131 and the actual evaluation result, and consider countermeasures. Countermeasures include, for example, adjusting the hyperparameters of the machine learning model 131, changing the training dataset and training the machine learning model 131 again (the learning process will be described later), reviewing the evaluation index, and changing the driver's own behavior. It may be possible to take into account fluctuations in the evaluation due to the physical condition of the patient, but this is not limited to this.

In step S8, the screen generation unit 10C generates a screen that displays the difference between the target evaluation and the actual evaluation result, and displays it on the display unit 11. After confirming this, the user can identify the evaluation items for which the target evaluation has not been achieved and consider countermeasures. In this case, it has already been verified in step S5 that the prediction made by the machine learning model 131 matches the driver's evaluation result to some extent. Therefore, the user can, for example, create input data with specific measured values changed, input this to the machine learning model 131, derive the output again, and change the specific measured values to obtain driver evaluation results. can predict how it will change. That is, it is possible to specify one or more measured values for bringing the driver's evaluation results closer to the target. This operation makes it easy to consider which values among the measured values of the tire to be evaluated should be changed and to what extent in order to achieve the target evaluation. This study can be used as a clue for the next prototype tire to be evaluated.

<5. Learning method>
Hereinafter, with reference to FIG. 3, a method for generating the trained machine learning model 131A, that is, a method for learning the machine learning model executed by the learning unit 10E will be described.

As described above, the machine learning model 131A of this embodiment is generated for each driver. For this reason, a learning data set for the machine learning model 131A is also prepared for each driver, but performance evaluation items and measurement values are common to each learning data set. Therefore, below we will explain how to train a machine learning model related to a specific driver.

The learning data set is a large number of data sets in which one or more measured values for tires and correct data are combined. Here, the tires include a reference tire and a learning tire other than the reference tire. The learning tire is, for example, a prototype tire, and corresponds to the tire to be evaluated. The correct data represents the evaluation result of a specific driver's evaluation of at least one of ride comfort and steering stability of a vehicle to which the tire is installed. Note that the evaluation results of the learning tires are evaluation results based on at least one of the ride comfort and steering stability of the vehicle equipped with the reference tires. Therefore, the correct answer data of this embodiment includes the standard value of the evaluation result for each evaluation item (for example, a fixed value such as "3"), and the evaluation of each evaluation item expressed as a relative value with respect to the standard value. including the results.

The above-mentioned learning data set can be prepared based on data accumulated through sensory evaluation by drivers at the site of tire design and development (step S11). In this embodiment, the prepared learning data set is taken into the evaluation device 1 via a recording medium or a network, and is stored in the storage unit 13 as a learning data set 134 by the learning unit 10E. The learning unit 10E divides the learning data set 134 into a training data set for parameter adjustment and a test data set for accuracy verification and stores them in advance. The ratio between the two can be set as appropriate.

Subsequently, the learning unit 10E divides the training data set into a predetermined number of data sets to create a plurality of subsets (step S12). The predetermined number is the number of data to be input into the machine learning model each time in the next step S13, and can be set as appropriate.

Subsequently, the learning unit 10E selects one of the subsets, inputs the measured value data included in the selected subset into the machine learning model, and derives an output from the machine learning model (step S13). The output is data corresponding to correct answer data combined with the input measurement value data, and in this embodiment, is a predicted value of an evaluation index corresponding to a predetermined evaluation item.

Subsequently, the learning unit 10E adjusts the parameters so that the value of the error function between the output derived in step S13 and the correct data combined with the measurement value data input in step S13 is minimized. (Step S14). More specifically, the learning unit 10E adjusts and updates the weighting coefficients, biases, etc. in the intermediate layer of the machine learning model using the error backpropagation method.

Subsequently, the learning unit 10E determines whether one epoch of learning has been completed (step S14). In this embodiment, it is determined that one epoch of learning is completed when steps S13 and S14 have completed one cycle for each subset created in step S12. If it is determined that one epoch of learning is not completed (NO), the learning unit 10E repeats steps S13 and S14 using a subset that has not yet been used. On the other hand, if it is determined that one epoch of learning has been completed (YES), step S15 is executed.

In subsequent step S15, the learning unit 10E determines whether learning for all epochs has been completed. The total number of epochs is not particularly limited and can be set as appropriate. If it is determined that learning for all epochs is not completed (NO), the learning unit 10E repeats steps S13 and S14 while selecting subsets in the same order as the previous epoch. On the other hand, if it is determined that learning for all epochs has been completed (YES), the learning unit 10E stores the latest parameters in the storage unit 13 and uses them as parameters that define the learned machine learning model 131A. That is, the learned machine learning model 131A is generated by the above procedure.

In addition, every time one epoch of learning ends, the learning unit 10E inputs the test data to the machine learning model at that time, calculates the output and the error between the test data and the correct data, and displays the calculation result. It may be displayed in section 11. As a result, if it is considered that the error in the output of the machine learning model has converged within a predetermined range before learning for all epochs is completed, learning may be ended at that point.

<6. Features＞
According to the evaluation device 1 described above, the evaluation result for the measured value of the tire to be evaluated can be predicted by the machine learning model 131 that has learned the sensory evaluation characteristics of each driver. This is expected to yield more knowledge about the correlation between specific tire measurements and tire performance evaluation (ride comfort and handling stability). In particular, in the above embodiment, the prediction by the machine learning model 131 is compared with the actual evaluation result by the driver, and after the reliability of the prediction by the machine learning model 131 is confirmed, the measured value of the tire to be evaluated and the evaluation result are compared. Correlation with the results will be examined. This makes it easy to examine which measurement values affect or do not affect ride comfort and handling stability, and tire design and development can be carried out more efficiently.

Furthermore, by constructing the machine learning model 131 in relation to multiple drivers, more knowledge can be obtained regarding common trends among each driver, evaluation items that tend to vary depending on the driver, and the like. It is thought that this will further facilitate consideration of which measurement values do or do not affect ride comfort and handling stability.

<7. Modified example>
Although one embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various changes can be made without departing from the spirit thereof. The gist of the modifications shown below can be combined as appropriate.

(1)
In the above embodiment, a NN-based model is used as the machine learning model 131A, but machine learning models are not limited to this, and include support vector machine (SVM), convolutional neural network (CNN) model, K- Other machine learning models, such as models using NN models, clustering, k-means, decision trees, and logistic regression models, and models that combine these may also be used. Furthermore, even if the model is based on a NN, the layer structure etc. can be changed as appropriate. For example, the machine learning model 131A may be a model in which the intermediate layer and the subsequent layers are divided for each evaluation item. In this case, a plurality of output layers can be provided corresponding to each evaluation item. Furthermore, one machine learning model 131 may be constructed for each performance evaluation item. That is, one machine learning model 131 may output one value for one evaluation target tire. In addition, regardless of which model is adopted, the value output by the machine learning model 131 may be the predicted value of the evaluation index itself, or, for example, the probability that each of evaluation indexes 1 to 5 will be selected by the driver. It may be a value representing . The learning method of the machine learning model 131A is not limited to the above embodiment, and a known parameter optimization algorithm such as stochastic gradient descent can be applied, and the loss function is not particularly limited either, depending on the nature of the output data. It can be selected as appropriate.

(2)
As the "prediction model", the regression model 130A can be used in addition to or instead of the machine learning model 131A. The regression model 130A is a regression model that uses one or more measured values as an explanatory variable and an evaluation index of a specific evaluation item as an objective variable, and is defined by parameters (coefficients of explanatory variables) optimized for each driver. be done. That is, the regression model 130A is a general term for regression models 130 defined by parameters optimized for each driver and, if necessary, for each evaluation item. When using the regression model 130 as a prediction model, the parameters that define it can be determined using a known regression algorithm such as the method of least squares. Further, if it is determined that there is a difference between the driver's actual evaluation result and the predicted value, it is possible to examine which parameter has a greater influence and easily adjust the parameter. Even when the regression model 130A is used as a predictive model, it is easy to consider which measured value affects or does not affect ride comfort and handling stability, and it is easy to make a difference between the driver's actual evaluation results and the target evaluation. Even if there is a difference, it is possible to efficiently obtain guidelines for which measurement value to change and by how much.

(3)
In the above embodiment, a five-level index is used as a performance evaluation index, but the performance evaluation index is not limited to this and can be changed as appropriate.

(4)
In the above embodiment, the evaluation device 1 is configured as one device, but the functions of each of the units 10A to 10E and the storage unit 13 may be distributed among multiple devices. For example, the machine learning model may be trained using a service provided through a network, and the constructed machine learning model 131A may be stored in the evaluation device 1.

(5)
The control unit 10 of the evaluation device 1 may include a vector processor, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), and other chips dedicated to artificial intelligence, in addition to the CPU and GPU. Further, the operation of the control unit 10 may be executed by one or more processors.

1 Evaluation device 10 Control unit 10A Acquisition unit 10B Derivation unit 10C Screen generation unit 10D Verification units 130, 130A Regression model (prediction model)
131,131A Machine learning model (prediction model)

Claims (10)

Obtaining one or more measured values for the evaluation target tire to be evaluated;
inputting the obtained one or more measured values into a predictive model;
deriving an output from the predictive model;
The output derived from the predictive model is:
Based on the evaluation results obtained by the driver evaluating at least one of the ride comfort and steering stability of the vehicle on which the evaluation target tire is installed, based on at least one of the ride comfort and steering stability of the vehicle on which the reference tire is installed. handle,
How to evaluate tire performance. The prediction model is a trained machine learning model.
A method for evaluating the performance of a tire according to claim 1. preparing a learning data set that combines one or more measured values for the reference tire and one or more measured values for the learning tire and correct data;
Adjusting parameters defining the machine learning model so that when data corresponding to the one or more measured values is input using the learning data set, data corresponding to the correct data is output. further including;
The correct answer data may be such that the driver determines at least one of the ride comfort and handling stability of the vehicle on which the learning tires are installed, and at least one of the ride comfort and handling stability of the vehicle on which the reference tires are installed. including evaluation results based on
The method for evaluating tire performance according to claim 2. The evaluation result represents the result of the driver's evaluation of the ride comfort of the vehicle on which the evaluation target tire is installed,
The one or more measured values include at least one of a transverse spring constant, a longitudinal spring constant, and a dynamic spring constant.
A method for evaluating the performance of a tire according to claim 1 or 2. The evaluation result represents the result of the driver's evaluation of the steering stability of the vehicle on which the evaluation target tire is installed,
The one or more measured values include at least one of dynamic spring constant, cornering power, maximum cornering force, and self-aligning torque.
A method for evaluating the performance of a tire according to claim 1 or 2. The driver evaluated at least one of the ride comfort and steering stability of the vehicle equipped with the evaluation target tire, based on at least one of the ride comfort and steering stability of the vehicle equipped with the reference tire. Obtaining evaluation results;
further comprising comparing the evaluation result and an output derived from the prediction model;
A method for evaluating the performance of a tire according to claim 1 or 2. 1 for bringing the evaluation result of the driver's evaluation of at least one of ride comfort and handling stability of the vehicle on which the evaluation target tire is mounted closer to the target based on the output derived from the prediction model; or further comprising identifying multiple measurements;
A method for evaluating the performance of a tire according to claim 1 or 2. an acquisition unit that acquires one or more measured values for the evaluation target tire to be evaluated;
a storage unit that stores parameters that define the predictive model;
a derivation unit that inputs the acquired one or more measured values into the prediction model and derives an output from the prediction model,
The output derived from the predictive model is:
Based on the evaluation results obtained by the driver evaluating at least one of the ride comfort and steering stability of the vehicle on which the evaluation target tire is installed, based on at least one of the ride comfort and steering stability of the vehicle on which the reference tire is installed. handle,
Tire performance evaluation device. Obtaining one or more measured values for the evaluation target tire to be evaluated;
Inputting the obtained one or more measured values into a prediction model;
causing one or more processors to derive an output from the predictive model;
The output derived from the predictive model is
Based on the evaluation results obtained by the driver evaluating at least one of the ride comfort and steering stability of the vehicle on which the evaluation target tire is installed, based on at least one of the ride comfort and steering stability of the vehicle on which the reference tire is installed. handle,
Tire performance evaluation program. preparing a learning data set that combines one or more measured values for a reference tire, one or more measured values for a learning tire, and correct data;
Adjusting parameters defining a machine learning model so that when data corresponding to the one or more measured values is input using the learning data set, data corresponding to the correct data is output. including;
The correct data is based on at least one of the ride comfort and steering stability of the vehicle equipped with the learning tire, and the driver bases at least one of the ride comfort and steering stability of the vehicle equipped with the reference tire. including the evaluation results evaluated as
How to generate a trained model.