Tire performance prediction device, performance prediction method, and data set creation method

Abstract

To provide a device capable of predicting performance from variables related to tire design. [Solution] A tire performance prediction device includes a trained model storage unit that extracts feature quantities (27) from data (21A) including variables (21A) related to tire design and stores trained model (24B) that has been machine-learned to output tire performance (22) from feature quantities (27). Feature quantities (27) can be restored to data (21A).

Description

[Technical Field]

[0001] The present invention relates to a tire performance prediction device, a performance prediction method, and a data set creation method. [Background technology]

[0002] Patent Document 1 listed below describes a tire image recognition method. This method involves inputting an image of the contact patch of a target tire to be recognized into a machine learning model that has learned the relationship between an image representing the tire contact patch and the contour of the tire contact patch, deriving an output, and estimating the contour of the contact patch of the target tire based on the derived output. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-048936 Summary of the Invention [Problem to be solved by the invention]

[0004] It is known that tire performance varies depending on the thickness of the rubber components that make up the tire, the structure of the carcass, etc. Therefore, if tire performance could be predicted from variables related to tire design that specify these thicknesses, structures, etc., there would be an advantage in that costs for tire prototyping, testing, etc. could be reduced. However, no specific method for realizing such prediction has been proposed.

[0005] The present invention has been devised in view of the above circumstances, and has as its main object to provide an apparatus capable of predicting tire performance from variables related to tire design. [Means for solving the problem]

[0006] The present invention is a tire performance prediction device that includes a trained model storage unit that extracts features from data including variables related to tire design and stores a trained model that has been machine-learned to output the tire performance from the features, and the features can be restored to the data. [Effects of the Invention]

[0007] By employing the above-described configuration, the tire performance prediction device of the present invention can predict performance from variables related to tire design. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram illustrating an example of a tire performance prediction device, a trained model generation device, and a dataset creation device. [Figure 2] 1 is a tire meridian cross-sectional view showing an example of a tire. [Figure 3] FIG. 2 is a planar development view showing an example of a carcass and a belt layer. [Figure 4] 1 is a flowchart illustrating an example of a processing procedure for a method for generating a trained model. [Figure 5] FIG. 10 is a diagram illustrating an example of a training dataset. [Figure 6] 10 is a flowchart showing an example of a processing procedure of a preparation step. [Figure 7] FIG. 1 is a conceptual diagram illustrating an example of a machine learning model (trained model). [Figure 8] 10 is a flowchart showing an example of a processing procedure of a learning step. [Figure 9] 1 is a flowchart showing an example of a processing procedure of a tire performance prediction method. [Figure 10] FIG. 10 is a diagram illustrating an example of a training dataset according to another embodiment of the present invention. [Figure 11] FIG. 10 is a conceptual diagram illustrating an example of a machine learning model (trained model) according to another embodiment of the present invention. [Figure 12]10 is a flowchart illustrating an example of a processing procedure of a data set creation method. [Figure 13] FIG. 10 is a diagram illustrating an example of a data set. [Figure 14] 10 is a flowchart showing an example of a processing procedure of a tire performance prediction method according to another embodiment of the present invention. [Figure 15] 10 is a flowchart illustrating an example of a processing procedure of an optimal solution acquisition step. [Figure 16] FIG. 10 is a diagram illustrating an example of a processing procedure of an optimal solution acquisition step. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be understood that the drawings include exaggerated representations and representations that differ from the dimensional ratios of actual structures in order to facilitate understanding of the contents of the invention. Furthermore, identical or common elements are designated by the same reference numerals throughout the embodiments, and redundant explanations will be omitted. Furthermore, the specific configurations shown in the embodiments and drawings are for the purpose of understanding the contents of the present invention, and the present invention is not limited to the specific configurations shown in the drawings.

[0010] [Tire performance prediction device] 1 is a block diagram showing an example of a tire performance prediction device 1A, a trained model generation device 1B, and a dataset creation device 1C. The tire performance prediction device (hereinafter sometimes referred to as the "prediction device") 1A is a device for predicting tire performance. This prediction device 1A executes a tire performance prediction method (hereinafter sometimes referred to as the "prediction method") described below.

[0011] The prediction device 1A of this embodiment is also configured as a trained model generation device (hereinafter sometimes referred to as a "generation device") 1B, and further configured as a dataset creation device (hereinafter sometimes referred to as a "creation device") 1C. Note that the prediction device 1A, the generation device 1B, and the creation device 1C may each be configured independently.

[0012] The generating device 1B of this embodiment is a device for generating a trained model that has been machine-learned to output tire performance. The generating device 1B executes a trained model generation method (hereinafter, sometimes referred to as a "generation method") described below. The creating device 1C of this embodiment is a device for creating a dataset to be input to the trained model. The creating device 1C executes a dataset generation method (hereinafter, sometimes referred to as a "creation method") described below.

[0013] The prediction device 1A (the generation device 1B and the creation device 1C) of this embodiment is configured as a general-purpose computer 1. Examples of the computer 1 include a desktop personal computer, a laptop personal computer, a tablet, a smartphone, and a cloud server.

[0014] The prediction device 1A (the generation device 1B and the creation device 1C) of this embodiment includes an input device 3, an output device 4, and a calculation processing device 5.

[0015] [Input section, output section, arithmetic processing unit] The input device 3 is configured as an input device. Examples of this input device include a keyboard and a mouse. The output device 4 is configured as an output device. Examples of this output device include a display device and a printer. The arithmetic processing device 5 of this embodiment is configured to include a processor (arithmetic unit) 5A that performs various calculations, a storage unit 5B that stores data, programs, etc., and a working memory 5C.

[0016] [Processor] The processor 5A in this embodiment is configured as a central processing unit (CPU), but is not particularly limited thereto and may be configured as, for example, a microprocessor or other processing unit. In this embodiment, the tire performance prediction method, the trained model generation method, and the dataset creation method are executed by one processor 5A, but may also be executed (parallel processing) by multiple processors 5A (not shown).

[0017] [Storage] The storage unit 5B is a non-volatile information storage device formed of, for example, a magnetic disk, an optical disk, an SSD, etc. The storage unit 5B is provided with a data unit 7 and a program unit 8.

[0018] [Data section] The data unit 7 of this embodiment is for storing data and the like necessary to execute the tire performance prediction method, the trained model generation method, and the dataset creation method. The data unit 7 of this embodiment includes a training dataset storage unit 7a, a trained model storage unit 7b, a data storage unit 7c, a feature storage unit 7d, a performance storage unit 7e, an input dataset storage unit 7f, and an optimal solution storage unit 7g. The data unit 7 is not limited to this configuration, and may include storage units capable of storing other data as needed, or some of these may be omitted. The data stored in each storage unit will be described in each step of the prediction method, generation method, and creation method, which will be described later.

[0019] [Program section] The program unit 8 of this embodiment is a program (application) required to execute the tire performance prediction method, the trained model generation method, and the dataset creation method. Execution of such program unit 8 by the processor (computing unit) 5A causes the computer 1 (prediction device 1A, generation device 1B, and creation device 1C) to function as specific means.

[0020] The program unit 8 of this embodiment includes an input unit 8a, an extraction unit 8b, an output unit 8c, a preparation unit 8d, a learning unit 8e, an evaluation unit 8f, a creation unit 8g, an optimal solution acquisition unit 8h, and a restoration unit 8i. Note that the program unit 8 is not limited to this configuration, and other programs may be included, or some of these may be omitted, as necessary. The functions of each program unit 8 will be explained in each step of the prediction method, generation method, and creation method described below.

[0021] [tire] 2 is a tire meridian cross-sectional view showing an example of a tire 11. The tire 11 of this embodiment is exemplified as a pneumatic tire mounted on an SUV or a passenger car, but is not limited to this. The tire 11 may also be a tire of another category, such as a heavy-duty tire for trucks, buses, etc.

[0022] The tire 11 of this embodiment includes a tread portion 12, a pair of sidewall portions 13, and a pair of bead portions 14. The bead portions 14 have, for example, an annularly extending bead core 18. Furthermore, the tire 11 of this embodiment is configured to include a rubber member 15, a carcass 16, and a belt layer 17.

[0023] [Rubber parts] The rubber member 15 includes a tread rubber 15a, a sidewall rubber 15b, a clinch rubber 15c, a bead apex rubber 15d, and an inner liner rubber 15e. However, the rubber member 15 is not limited to this configuration and may include, for example, other rubber members.

[0024] The tread rubber 15a is disposed radially outward of the belt layer 17 in the tread portion 12. The sidewall rubber 15b is disposed radially inward of the tread rubber 15a (in this example, in the sidewall portion 13, outward of the carcass 16 in the axial direction of the tire).

[0025] The clinch rubber 15c is disposed on the radially inner side of the sidewall rubber 15b (in this example, the bead portion 14). The bead apex rubber 15d extends radially outward from the bead core 18. The inner liner rubber 15e is disposed on the inner surface of the carcass 16.

[0026] The characteristics of these rubber members 15 can be specified by their thickness (maximum thickness) W1, physical property values, etc. Examples of physical property values ​​include elastic modulus and loss tangent. Such characteristics (thickness and physical property values) of the rubber members 15 can specify the rigidity, etc. of the tire 11, and therefore have a high correlation with the performance of the tire 11, which is affected by the rigidity, etc.

[0027] In the present embodiment, the elastic modulus is exemplified as a complex elastic modulus, but is not limited to this, and may be, for example, a storage elastic modulus or a loss tangent. These elastic moduli and the loss tangent described above are measured as appropriate, and can be measured, for example, in accordance with the provisions of JIS-K6394 using a viscoelasticity spectrometer under the following conditions. Initial strain: 10% Amplitude: ±2% Frequency: 10Hz Deformation mode: tension Temperature: 100℃ Viscoelasticity spectrometer: GABO "Iplexar (registered trademark)"

[0028] [Carcass] The carcass 16 extends between the pair of bead portions 14. The carcass 16 includes at least one carcass ply 16A (one in this example).

[0029] The carcass ply 16A includes, for example, a main body portion 16a and a turned-up portion 16b. The main body portion 16a extends, for example, between the two bead portions 14. The turned-up portion 16b is continuous with the main body portion 16a and is turned up around the bead core 18 from the inner side to the outer side in the axial direction of the tire. A bead apex rubber 15d is disposed between the main body portion 16a and the turned-up portion 16b.

[0030] 3 is a planar development view showing an example of the carcass 16 and the belt layer 17. The carcass ply 16A has a plurality of carcass cords (fiber material) 16c arranged in parallel. These carcass cords 16c may be made of organic fiber cords such as aramid or rayon.

[0031] The structure of the carcass 16 is specified by, for example, ends E1, which is the number of carcass cords 16c per unit ply width, and the angle θ1 of the carcass cords 16c with respect to the tire equator C. The unit ply width is the length measured in a direction perpendicular to the longitudinal direction of the carcass cords 16c in a normal state, and is set to 5 cm. The angle θ1 is set to 75 to 90 degrees. The structure of the carcass 16 (ends E1, angle θ1, etc.) specifies the rigidity and other properties of the tire 11, and therefore has a high correlation with the performance of the tire 11, which is affected by the rigidity and other properties.

[0032] The "normal state" refers to a state in which the tire 11 is mounted on a normal rim (not shown), inflated to a normal internal pressure, and no load is applied. In this specification, unless otherwise specified, the dimensions of each part of the tire 11 are values ​​specified in the normal state.

[0033] A "genuine rim" is a rim that is defined for each tire in a standard system that includes the standard on which the tire 11 is based. Therefore, a genuine rim is, for example, a "standard rim" for JATMA, a "design rim" for TRA, or a "measuring rim" for ETRTO.

[0034] The "normal internal pressure" is the air pressure determined for each tire by each standard in a standard system including the standard on which the tire 11 is based. Therefore, the normal internal pressure is, for example, the "maximum air pressure" in the case of JATMA, the maximum value listed in the table "TIRE LOAD LIMITS AT VARIOUS COLD INFLATION PRESSURES" in the case of TRA, and the "INFLATION PRESSURE" in the case of ETRTO.

[0035] [Belt layer] The belt layer 17 is disposed in the tread portion 12. The belt layer 17 includes at least one belt ply 17A, 17B, two in this embodiment. These belt plies 17A, 17B have a plurality of belt cords (fiber material) 17c arranged in parallel. Steel cords are used for these belt cords 17c, but highly elastic organic fiber cords such as aramid and rayon can also be used as needed.

[0036] The structure of the belt layer 17 is specified by, for example, ends E2, which is the number of belt cords 17c per unit ply width, and the angle θ2 of the belt cords 17c with respect to the tire equator C. The unit ply width is the length measured along the belt plies 17A, 17B in a meridian cross section of the tire in a normal state, and is set to 5 cm. The angle θ2 is set to 10 to 35 degrees. The rigidity and other properties of the tire 11 are specified by such a structure of the belt layer 17 (ends E2, angle θ2, etc.), and therefore there is a high correlation with the performance of the tire 11, which is affected by the rigidity and other properties.

[0037] As described above, the performance of the tire 11 is affected by the rigidity and other factors of the tire 11, and is therefore strongly correlated with the thickness (maximum thickness) W1 of the rubber member 15, which can specify the rigidity, the physical properties of the rubber member 15, the structure of the carcass 16, and the structure of the belt layer 17. These characteristics, structures, and other factors can be specified as variables related to the design of the tire 11 (hereinafter, sometimes referred to as "design variables") at the design stage of the tire 11 (i.e., the stage before prototyping). If the performance of the tire 11 could be predicted from these design variables, there would be an advantage in that costs for prototyping and testing the tire 11 could be reduced. However, no specific method has been proposed for realizing such predictions.

[0038] In the prediction method of this embodiment, feature quantities are extracted from data including variables (design variables) related to the design of the tire 11, and the performance of the tire 11 is output (predicted) from the feature quantities. This reduces the costs of prototyping and testing the tire 11, and can improve development efficiency. Furthermore, the feature quantities extracted from the data can be restored to the original data (design variables). As a result, for example, when good performance is output from a certain feature quantity, even if an operator or the like cannot understand the meaning indicated by the feature quantity, the feature quantity can be restored to the original data (design variables), and the design variables that can demonstrate that performance can be easily understood.

[0039] A trained model is used to predict the performance of the tire 11. Therefore, in this embodiment, a trained model generation method is performed prior to the execution of the prediction method. Note that if a trained model has already been generated when the prediction method is executed, the generation method may be omitted.

[0040] [Method for generating trained model (first embodiment)] In the generation method of this embodiment, a trained model is generated. The trained model of this embodiment is a model trained by machine learning to extract feature amounts from data including variables related to the design of the tire 11 and output the performance of the tire 11 from the feature amounts. In order to generate such a trained model, it is effective to train a machine learning model using multiple types of training datasets.

[0041] 4 is a flowchart showing an example of a processing procedure of a method for generating a trained model. Each step of the generation method of this embodiment is executed by a processor 5A included in the generation device 1B (computer 1) shown in FIG.

[0042] [Prepare the training dataset (preparation step)] In the generation method of this embodiment, first, a training dataset is prepared (preparation step S1). In the preparation step S1 of this embodiment, first, a preparation unit 8d included in the program unit 8 shown in FIG. 1 is loaded into the working memory 5C. The preparation unit 8d is a program for preparing the training dataset. When the preparation unit 8d is executed by the processor 5A, the computer 1 (generation device 1B) can function as a means for preparing the training dataset.

[0043] It is preferable that the learning dataset is acquired based on multiple types of tires 11. The categories of the multiple types of tires 11 are not particularly limited. For example, from the viewpoint of improving the prediction accuracy of the trained model (machine learning model), the categories of the multiple types of tires 11 may be the same. Furthermore, from the viewpoint of improving the versatility of the trained model (machine learning model), some of the categories of the multiple types of tires 11 may be different. It is preferable that the multiple types of tires 11 differ from each other in at least one of the characteristics of the rubber member 15 (maximum thickness W1 and physical property values), the structure of the carcass 16 (end E1 and angle θ1), and the structure of the belt layer 17 (end E2 and angle θ2), for example.

[0044] FIG. 5 is a diagram showing an example of the training dataset 23. FIG. 5 shows an example of one training dataset 23 acquired from one tire 11 (shown in FIGS. 2 and 3) as a representative example. The training dataset 23 of this embodiment is used for training the above-mentioned machine learning model. Therefore, the training dataset 23 of this embodiment includes data 21 including variables (design variables) 21A related to the design of the tire 11, and performance 22 of the tire 11. FIG. 6 is a flowchart showing an example of the processing procedure of the preparation step S1.

[0045] [Get data including tire design variables] In the preparation step S1 of this embodiment, first, as shown in FIG. 5, data 21 including variables (design variables) 21A related to the design of the tire 11 is acquired (step S11). In step S11 of this embodiment, data 21 (design variables 21A) is acquired for each of multiple types of tires 11. The data 21 may consist of only the design variables 21A, or may further include other data. The data 21 of this embodiment includes only the design variables 21A.

[0046] The design variables 21A in this embodiment preferably include at least one of the thickness (maximum thickness) W1 of the rubber member 15, the physical property value P of the rubber member 15, the structure 31 (ends E1 and angle θ1) of the carcass 16, and the structure 32 (ends E2 and angle θ2) of the belt layer 17. As described above, these design variables 21A have a strong correlation with the performance 22 of the tire 11. The design variables 21A in this embodiment include all of the thickness (maximum thickness in this example) W1 of the rubber member 15, the physical property value P of the rubber member 15, the structure 31 of the carcass 16, and the structure 32 of the belt layer 17, but are not particularly limited thereto and may include only one of these. The design variables 21A may also include other design variables (e.g., the structure of the bead core 18, the structure of the band layer, etc.) depending on the performance, etc. output from the trained model 24B.

[0047] In this embodiment, the thickness of the rubber member 15 includes the maximum thickness W1 of the tread rubber 15a. The physical property value P of the rubber member 15 includes the complex modulus of elasticity of the tread rubber 15a. The structure 31 of the carcass 16 includes the number of ends E1 (pieces / 5 cm) of the carcass cords 16c and the angle θ1 of the carcass cords 16c. The structure 32 of the belt layer 17 includes the number of ends E2 (pieces / 5 cm) of the belt cords 17c and the angle θ2 of the belt cords 17c. Note that the design variables are not limited to these embodiments, and for example, some of these may be omitted, or the design variables may further include the maximum thickness of the sidewall rubber 15b, the number of carcass plies 16A, and the number of belt plies 17A, 17B, etc.

[0048] Variables (design variables) 21A related to the design of the tire 11 can be acquired as needed. The design variables 21A may be acquired from design data (CAD data) of the tire 11, from a database of design variables, or directly input by an operator. The design variables 21A are stored in the learning dataset storage unit 7a shown in FIG. 1.

[0049] [Get tire performance] Next, in the preparation step S1 of this embodiment, the performance 22 of the tire 11 is acquired (step S12), as shown in Fig. 5. In step S12 of this embodiment, the performance 22 of each of a plurality of types of tires 11 is acquired.

[0050] The performance 22 is not particularly limited as long as it can be used to evaluate the tire 11. The performance 22 in this embodiment includes at least one of the rolling resistance coefficient, vertical spring constant, lateral spring constant, and air resistance value of the tire 11. These performances 22 are affected by the rigidity and the like of the tire 11, and therefore have a strong correlation with the thickness (maximum thickness) W1 of the rubber member 15, the physical property value P of the rubber member 15, the structure 31 of the carcass 16, and the structure 32 of the belt layer 17, which can identify the rigidity and the like.

[0051] The rolling resistance coefficient, longitudinal spring constant, and lateral spring constant can be obtained, for example, by using a known testing machine or the like. The air resistance value can be obtained, for example, by a wind tunnel test of the tire 11. These performances 22 may also be obtained by a simulation using a computer 1 (shown in FIG. 1). For such a simulation, it is preferable to use the tire model described above.

[0052] The performance 22 may also include distribution data (not shown) of physical quantities acting on the tread portion 12 when the tread portion 12 contacts the road surface, a contact profile (not shown) of the tire 11, etc. These distribution data and profiles can be identified, for example, when the tire 11 in a normal state is brought into contact with the road surface (not shown) under conditions of a normal load and a camber angle of 0°, and is driven at a predetermined traveling speed (for example, 60 km / h).

[0053] The "normal load" is the load determined for each tire by each standard in a standard system including the standard on which the tire 11 is based. Therefore, the normal load is, for example, "maximum load capacity" in the case of JATMA, the maximum value listed in the table "TIRE LOAD LIMITS AT VARIOUS COLD INFLATION PRESSURES" in the case of TRA, and "LOAD CAPACITY" in the case of ETRTO.

[0054] The distribution data includes physical quantities acting on the outer surface 12o of the tread portion 12 shown in FIG. 2 (hereinafter, sometimes referred to as "outer surface physical quantities") and physical quantities acting on the inside of the tread radially inward of the outer surface 12o (hereinafter, sometimes referred to as "internal physical quantities"). Examples of the outer surface physical quantities include wear energy, shear force, and slip amount. Examples of the internal physical quantities include strain and stress. These physical quantities are affected by the rigidity and other properties of the tire 11, and therefore have a strong correlation with the thickness (maximum thickness) W1 of the rubber member 15, the physical property value P of the rubber member 15, the structure 31 of the carcass 16, and the structure 32 of the belt layer 17, which can identify the rigidity and other properties of the tire 11.

[0055] The distribution data and profile (not shown) may be measured using, for example, a known measuring device (not shown), or may be determined by performing a simulation using a computer 1 (shown in FIG. 1). In the simulation, the distribution data may be calculated by running a tire model (not shown) that models the tire 11 on a road surface model (not shown) that models the road surface (not shown) under the above conditions. Such a simulation may be performed as appropriate based on a known method (for example, the method described in JP 2023-084539 A).

[0056] The performance 22 may be at least one of the rolling resistance coefficient, vertical spring constant, lateral spring constant, air resistance value, and distribution data of the tire 11, or all of these may be acquired, or other performance data may be acquired in addition. In this embodiment, the rolling resistance coefficient 22A of the tire 11 is acquired as the performance 22. FIG. 5 shows a case where the rolling resistance coefficient 22A is "6.0". The performance 22 is stored in the learning dataset storage unit 7a shown in FIG. 1.

[0057] [Create a training dataset] Next, in the preparation step S1 of this embodiment, a training data set 23 (shown in FIG. 5) is created (step S13). In step S13 of this embodiment, data 21 (in this example, design variables 21A) and performance 22 (in this example, rolling resistance coefficient 22A) are combined for each of a plurality of types of tires 11. In this way, a plurality of training data sets 23 are created.

[0058] In this embodiment, training datasets 23 of multiple types of tires 11 are used to train a machine learning model in a training step S2, which will be described later. This makes it possible to extract, from data 21 (design variables 21A in this example) of a tire to be evaluated, feature quantities that can be restored to data 21, and to generate a trained model that can output performance 22 (rolling resistance coefficient 22A in this example) from the feature quantities. The multiple training datasets 23 are stored in the training dataset storage unit 7a shown in FIG. 1.

[0059] [Training the machine learning model (training step)] Next, in the generation method of this embodiment, learning of a machine learning model is performed using the learning dataset 23 shown in Fig. 5 (learning step S2). In the learning step S2, feature quantities are extracted from data 21 including variables (design variables) 21A related to the design of the tire 11, and learning of the machine learning model is performed so that performance 22 of the tire 11 is output from the feature quantities. Furthermore, the feature quantities extracted from the data 21 can be restored to the original data 21.

[0060] In the learning step S2 of this embodiment, first, the learning dataset 23 (shown in FIG. 5) stored in the learning dataset storage unit 7a shown in FIG. 1 and a learning unit 8e included in the program unit 8 are loaded into the working memory 5C. The learning unit 8e is a program for training the machine learning model using the learning dataset 23. When the learning unit 8e is executed by the processor 5A, the computer 1 (generation device 1B) can function as a means for training the machine learning model.

[0061] The machine learning model is not particularly limited as long as it can extract, from data 21 including variables (design variables) 21A related to the design of tire 11, feature amounts that can be restored to the data 21 and output performance 22 of tire 11 from the feature amounts. Fig. 7 is a conceptual diagram showing an example of machine learning model 24A (trained model 24B).

[0062] The machine learning model 24A of this embodiment includes a first model 25 and a second model 26. The first model 25 of this embodiment is for extracting feature quantities 27 from data 21 including variables (design variables) 21A related to the design of the tire 11. These feature quantities 27 can be restored to the original data 21 (design variables 21A). On the other hand, the second model 26 is for outputting performance 22 from the feature quantities 27 extracted by the first model 25. Note that the machine learning model 24A is not limited to an aspect including the first model 25 and the second model 26, and may be configured with only one of these models or may further include other models depending on, for example, the algorithm employed.

[0063] As described above, the first model 25 is used to extract, from the data 21 including variables (design variables) 21A related to the design of the tire 11, feature quantities 27 that can be restored to the data 21. Such a first model 25 is not particularly limited as long as it can extract feature quantities 27 that can be restored to the data 21. For example, it is preferable that the feature quantities 27 are extracted using at least one of principal component analysis, independent component analysis, singular value decomposition, Fourier transform, and autoencoder. While principal component analysis, independent component analysis, singular value decomposition, Fourier transform, and autoencoder are all well-known, using them to generate the first model 25 makes it possible to effectively extract feature quantities 27 for estimating the performance 22. Furthermore, the extracted feature quantities 27 can be restored to the original data 21 with high accuracy.

[0064] In this embodiment, the first model 25 uses principal component analysis. This principal component analysis is a statistical method for reducing multiple variables into fewer principal components (synthetic variables) than the multiple variables, and is a type of unsupervised learning. For example, the scikit-learn library of the well-known programming language Python is used for the principal component analysis.

[0065] In the first model 25 of this embodiment, data 21 including variables (design variables) 21A related to the design of the tire 11 is input, and the design variables 21A are contracted (dimensionally reduced) into multiple principal components. As a result, principal component scores (numerical data) 28 converted into each principal component (first principal component, second principal component, etc.) can be acquired. Note that the number of the multiple principal components is smaller than the number of design variables 21A.

[0066] A combination of the multiple principal component scores 28 is extracted as a feature 27 of the data 21 (design variable 21A). By performing an inverse transformation of the principal component analysis on the feature 27 (multiple principal component scores 28), it is possible to obtain data 21 (design variable 21A) in which the feature 27 has been restored to its original dimension. In this way, the first model 25 can extract the feature 27 so that the original data 21 can be restored, while compressing the dimension of the data 21.

[0067] The plurality of principal component scores 28 constituting the feature 27 can be handled (for example, edited) by the computer 1 shown in FIG. 1. Therefore, the feature 27 can be extracted in an editable manner. By editing the feature 27, it becomes possible to obtain the feature 27 extracted from the data 21 (design variables 21A) of the tire 11 in a pseudo manner, without having to separately design a tire 11 in which at least a part of the original data 21 (design variables 21A) is changed.

[0068] As described above, the second model 26 is for outputting the performance 22 from the feature quantities 27 extracted by the first model 25. Such a second model 26 is not particularly limited as long as it can output the performance 22 from the feature quantities 27, but it is preferable that the performance 22 be output based on at least one of a neural network, multiple regression, random forest regression, and deep learning, for example. These neural network, multiple regression, random forest regression, and deep learning are all well known, and by using them to generate the second model 26, it becomes possible to accurately estimate the performance 22 from the feature quantities 27 (plurality of principal component scores 28).

[0069] The second model 26 of this embodiment is based on a neural network and outputs the performance 22. The neural network can be defined as appropriate. The neural network (second model 26) of this embodiment is defined based on a radial basis function (RBF).

[0070] The second model (RBF network) 26 includes an input layer 43, an output layer 44, and an intermediate layer 45, and is defined as an approximate response surface expressed by superimposing Gaussian functions.

[0071] The input layer 43 of this embodiment receives input of feature quantities 27. As described above, the feature quantities 27 of this embodiment are composed of a plurality of principal component scores (numerical data) 28, and each of these principal component scores 28 is input to the input layer 43. The output layer 44 of this embodiment is capable of outputting the performance 22 of the tire 11 (in this example, the rolling resistance coefficient 22A). The intermediate layer 45 of this embodiment is a basis function (Gaussian function) and is generated by machine learning. By generating such a second model 26, it becomes possible to output the performance 22 from the feature quantities 27 extracted by the first model 25.

[0072] Next, a description will be given of an example of a machine learning procedure for the trained model 24B (the first model 25 and the second model 26). Fig. 8 is a flowchart showing an example of a procedure for the training step S2.

[0073] [Machine learning of the first model] 7, in the learning step S2 of the present embodiment, first, machine learning of the first model 25 is performed (step S21). In this step S21, machine learning of the first model 25 is performed so that feature quantities 27 that can be restored to the original data 21 are extracted from the data 21 including variables (design variables) 21A related to the design of the tire 11.

[0074] In step S21 of this embodiment, first, data 21 (design variables 21A in this example) included in one training data set 23 shown in FIG. 5 among a plurality of training data sets 23 (not shown) is input to a first model 25 shown in FIG. 7. As a result, features 27 (principal component scores 28) obtained by dimensionally compressing the data 21 are extracted. Furthermore, the extracted features 27 are input to the first model 25. As a result, data 21 (design variables 21A in this example) in which the features 27 have been restored to their original dimensions is output. Then, various parameters (e.g., principal components, etc.) of the first model 25 are updated so as to minimize the error between the output data (estimated data) 21 and the data (ground truth data) 21 of the training data set 23 shown in FIG. 5.

[0075] In step S21 of this embodiment, a series of processes from inputting data 21 to updating parameters (principal components) is performed using each of the data 21 in a plurality of training datasets 23 (not shown), thereby optimizing the first model 25. This allows the first model 25 to be generated that can extract features 27 that can be restored to the data 21 while compressing the dimensions of the data 21 including variables (design variables) 21A related to the design of the tire 11. The first model 25 is stored in the trained model storage unit 7b shown in FIG. 1.

[0076] [Implement machine learning for the second model] Next, in the learning step S2 of this embodiment, as shown in FIG. 7, machine learning of the second model 26 is performed so as to output the performance 22 of the tire 11 from the feature amount 27 (step S22).

[0077] In step S22 of this embodiment, first, the data 21 (design variable 21A in this example) included in one of a plurality of training data sets 23 (not shown) shown in FIG. 5 is input to the first model 25 shown in FIG. 7. In this step S22, the first model 25 that has been trained (generated) in the previous step S21 is used. This allows the dimensionality of the data 21 to be compressed, while accurately extracting feature quantities 27 that can be restored to the data 21.

[0078] Next, in step S22 of this embodiment, the extracted feature quantity 27 is input to the second model 26. As a result, the performance 22 (in this example, the tire rolling resistance coefficient 22A) estimated by the second model 26 can be output. Next, in step S22 of this embodiment, the basis functions of the intermediate layer 45 of the second model 26 are adjusted so as to minimize the error between the output performance (estimated data) 22 and the performance 22 (ground truth data) 22 included in the training dataset 23 shown in FIG. 5. For example, a gradient method or the like is used for this adjustment.

[0079] In step S22 of this embodiment, a series of processes from inputting the data 21 to adjusting the basis functions is performed using each of a plurality of training data sets 23 (not shown), thereby optimizing the second model 26. This generates the second model 26 that can output the performance 22 of the tire 11 from the feature quantities 27 extracted by the first model 25. The second model 26 is stored in the trained model storage unit 7b shown in FIG. 1.

[0080] As described above, the performance 22 of the tire 11 has a strong correlation with the design variables 21A of the tire 11. When the data 21 including such design variables 21A is input to the first model 25 of the trained model 24B, the feature 27 for estimating the performance 22 can be effectively extracted. Then, when the feature 27 extracted by the first model 25 is input to the second model 26 of the trained model 24B, the performance 22 can be estimated with high accuracy. The trained model 24B including the first model 25 and the second model 26 makes it possible to estimate the performance 22 from the data 21 without requiring the experience or intuition of an expert.

[0081] Furthermore, the first model 25 of this embodiment can extract feature quantities 27 that can be restored to the data 21. Therefore, for example, from feature quantities 27 that have resulted in good performance 22 being output by the second model 26, data 21 (design variables 21A) that can demonstrate the performance 22 can be restored. As a result, even if an operator or the like cannot understand the feature quantities 27, the feature quantities 27 can be restored to the original data 21 (design variables 21A), making it easy to understand the design variables 21A that can demonstrate the performance 22, which is useful for the design and development of the tire 11.

[0082] Furthermore, the first model 25 of this embodiment can extract feature quantities 27 obtained by dimensionally compressing the data 21 (design variables 21A) of the tire 11. By inputting these feature quantities 27 to the second model 26, the number of machine learning parameters of the second model 26 is reduced compared to, for example, when the data 21 before the feature quantities 27 are extracted is input directly to the second model 26. This allows the second model 26 to be made smaller.

[0083] [Tire performance prediction method (first embodiment)] Next, an example of a processing procedure for a tire performance prediction method is shown. The prediction method of this embodiment uses a trained model 24B (including a first model 25 and a second model 26 in this example) generated based on the generation method shown in Figures 4, 6, and 8.

[0084] 9 is a flowchart showing an example of a processing procedure of a tire performance prediction method. Each step of the prediction method of this embodiment is executed by a processor 5A included in the prediction device 1A (computer 1) shown in FIG.

[0085] [Enter data including tire design variables] In the prediction method of this embodiment, first, as shown in Fig. 7, data 21 including variables (design variables) 21A related to the design of the tire 11 is input (step S3). In step S3, the data 21 including the design variables 21A for the tire 11 to be evaluated is input to the prediction device 1A (computer 1) shown in Fig. 1.

[0086] In step S3 of this embodiment, first, the input unit 8a included in the program unit 8 shown in Fig. 1 is loaded into the working memory 5C. The input unit 8a is a program for inputting data 21 including the design variables 21A shown in Fig. 7 for the tire 11 to be evaluated shown in Figs. 2 and 3. Execution of this input unit 8a by the processor 5A allows the computer 1 (prediction device 1A) to function as a means for inputting the data 21.

[0087] In step S3 of this embodiment, the prediction device 1A (input unit 8a) shown in FIG. 1 acquires design variables 21A as data 21 of the tire 11 to be evaluated. In this embodiment, the design variables 21A of the tire 11 to be evaluated are acquired based on the processing procedure in step S11 of the preparation step S1 shown in FIG. 6. As described above, the design variables 21A of this embodiment include the maximum thickness W1 and physical property value (complex modulus) P of the rubber member 15 (tread rubber 15a), the structure 31 (ends E1 and angle θ1) of the carcass 16, and the structure 32 (ends E2 and angle θ2) of the belt layer 17. The acquired data 21 including the design variables 21A is stored in the data storage unit 7c shown in FIG. 1.

[0088] [Extracting features from data containing variables related to tire design] Next, in the prediction method of this embodiment, as shown in Fig. 7, feature quantities 27 that can be restored to data 21 are extracted from data 21 including variables (design variables 21A) related to the design of tire 11 (step S4). To extract feature quantities 27, a first model 25 included in trained model 24B is used.

[0089] In step S4 of this embodiment, first, data 21 including design variables 21A of the tire 11 to be evaluated, which is stored in the data storage unit 7c shown in FIG. 1, is loaded into the working memory 5C. Furthermore, a first model 25 (shown in FIG. 7) stored in the trained model storage unit 7b and an extraction unit 8b included in the program unit 8 are loaded into the working memory 5C. The extraction unit 8b is a program for inputting the data 21 including the design variables 21A into a trained model 24B (in this example, the first model 25) and extracting feature quantities 27 that can be restored to the data 21. Execution of this extraction unit 8b by the processor 5A causes the computer 1 (prediction device 1A) to function as a means for extracting feature quantities 27.

[0090] In step S4 of the present embodiment, the prediction device 1A (extraction unit 8b) inputs data 21 including design variables 21A of the tire 11 to be evaluated into the first model 25, as shown in Fig. 7. This allows the data 21 (design variables 21A) to be dimensionally compressed, and extracts feature quantities 27 that can be restored to the original data 21. The extracted feature quantities 27 are stored in the feature quantity storage unit 7d shown in Fig. 1.

[0091] [Output tire performance corresponding to feature values] Next, in the prediction method of this embodiment, the performance 22 of the tire 11 corresponding to the feature 27 is output (step S5), as shown in Fig. 7. To output the performance 22, a trained model 24B (in this example, the second model 26) that has been machine-trained to output the performance 22 of the tire 11 from the feature 27 is used.

[0092] In step S5 of this embodiment, first, the feature 27 stored in the feature storage unit 7d shown in FIG. 1 and the second model 26 (shown in FIG. 7) stored in the trained model storage unit 7b are loaded into the working memory 5C. Furthermore, the output unit 8c included in the program unit 8 is loaded into the working memory 5C. The output unit 8c is a program for outputting the performance 22 of the tire 11 corresponding to the feature 27. When the output unit 8c is executed by the processor 5A, the computer 1 (prediction device 1A) can function as a means for outputting the performance 22 of the tire 11 to be evaluated.

[0093] In step S5 of this embodiment, as shown in FIG. 7, the prediction device 1A (output unit 8c) inputs feature quantities 27 extracted from data 21 of the tire 11 to be evaluated to the input layer 43 of the second model 26. As a result, the performance 22 of the tire 11 to be evaluated (in this example, the rolling resistance coefficient 22A of the tire 11) is output from the output layer 44 of the second model 26. Therefore, the prediction method of this embodiment makes it possible to estimate the performance 22 of the tire 11 to be evaluated without requiring the experience or intuition of a skilled person.

[0094] The performance 22 output from the second model 26 is stored in the performance storage unit 7e shown in Fig. 1. In addition, in step S5, the output performance 22 may be output (displayed) to the output device 4 including, for example, a display device. This allows an operator or the like to grasp the performance 22 of the tire 11, and further enables evaluation of the performance 22 of the tire 11 to be evaluated.

[0095] [Evaluate the performance data of the target tires] Next, in the prediction method of this embodiment, the quality of the performance 22 (shown in FIG. 7) of the tire 11 is evaluated (step S6). The quality of the performance 22 may be evaluated by the prediction device 1A (computer 1) shown in FIG. 1, or may be evaluated by an operator or the like.

[0096] In step S6 of this embodiment, first, the performance 22 of the tire 11 (in this example, the tire rolling resistance coefficient 22A) stored in the performance storage unit 7e shown in FIG. 1 and an evaluation unit 8f included in the program unit 8 are read into the working memory 5C. The evaluation unit 8f is a program for determining whether the output performance 22 is good or not. Execution of the evaluation unit 8f by the processor 5A allows the computer 1 to function as a means for evaluating the performance 22.

[0097] The quality of the performance 22 can be evaluated as appropriate. In the present embodiment, when the performance 22 is the rolling resistance coefficient 22A of the tire, for example, if the rolling resistance coefficient 22A is less than a predetermined threshold, the rolling resistance performance can be determined to be excellent and good. The threshold can be set as appropriate according to the performance (rolling resistance performance, etc.) 22 required of the tire 11 to be evaluated shown in FIGS. 2 and 3 , for example.

[0098] If the performance 22 of the tire 11 to be evaluated is determined to be good ("Yes" in step S6), the tire 11 is manufactured based on the data 21 (in this example, the design variable 21A) input to the trained model 24B (first model 25) shown in FIG. 7 (step S7). As described above, the feature 27 in this embodiment is extracted so as to be reconstructed to the data 21 (in this example, the design variable 21A). Therefore, the original data 21 (design variable 21A) may be reconstructed from the feature 27 input to the second model 26, and the tire 11 may be manufactured based on the reconstructed data 21.

[0099] On the other hand, if it is determined that the performance 22 of the tire 11 to be evaluated is not good ("No" in step S6), at least a part of the design variables 21A of the tire 11 to be evaluated is changed (step S8), and steps S3 to S6 are performed again.

[0100] When the rolling resistance coefficient 22A is output as the tire performance 22 as in this embodiment, the design variables 21A of the tire 11 may be changed in step S8 so as to reduce the rolling resistance coefficient (so as to improve the performance 22). Such changes to the design variables 21A may be performed, for example, by an operator. Then, in steps S3 to S7, which are performed again, new feature quantities 27 may be extracted from the data 21 of the changed tire 11, and the performance 22 corresponding to the feature quantities 27 may be output, as shown in FIG. 7. Therefore, a tire 11 having desired performance (for example, rolling resistance performance) 22 may be reliably designed and manufactured.

[0101] As described above, the feature quantities 27 extracted from the data 21 are extracted so as to be arbitrarily editable. Therefore, in step S8, only the feature quantities 27 may be edited, and steps S5 and S6 may be performed again. This makes it possible to evaluate the performance 22 of the tire 11 in which the design variables 21A have been pseudo-changed, without specifically changing the design variables 21A of the tire 11 or extracting the feature quantities 27 from the data 21.

[0102] [Method for generating trained model (second embodiment)] In the above-described embodiments, the second model 26 is exemplified as being such that the performance 22 is output from the feature amount 27 extracted from the data 21, as shown in Fig. 7. However, the present invention is not limited to such an embodiment. The second model 26 may output the performance 22 from the feature amount 27 and conditions for evaluating the performance of the tire 11 (hereinafter, sometimes referred to as "evaluation conditions"), for example.

[0103] In the generation method of this embodiment, in step S11 (shown in FIG. 6) of acquiring data 21, the data 21 including the design variables 21A shown in FIG. 5 and evaluation conditions (not shown) are acquired. The design variables 21A can be acquired in the same procedure as in the previous embodiments.

[0104] Fig. 10 is a diagram showing an example of a training data set 23 according to another embodiment of the present invention. In Fig. 10, one training data set 23 acquired from one tire 11 is shown as a representative.

[0105] The evaluation conditions 46 are not particularly limited as long as they relate to conditions for evaluating tire performance. The evaluation conditions 46 in this embodiment include, for example, at least one of internal pressure, load, and running speed. These evaluation conditions 46 affect the rigidity and contact shape of the tread portion 12. Therefore, the evaluation conditions 46 have a strong correlation with the performance 22 (in this example, the tire rolling resistance coefficient 22A) of the tire 11, such as the rolling resistance coefficient, vertical spring constant, lateral spring constant, air resistance value, and distribution data.

[0106] The evaluation conditions 46 are composed of numerical data 47 that specify the internal pressure, load, and traveling speed. Therefore, the numerical data 47 of the evaluation conditions 46 can be treated in the same way as the principal component scores 28 of the features 27 shown in FIG. 7, and the number of the numerical data 47 is smaller than that of the design variables 21A. Therefore, unlike the design variables 21A, the evaluation conditions 46 do not require the extraction of reconstructible features 27, and therefore the extraction of features from the evaluation conditions 46 is omitted. This can shorten the time required to create the training dataset 23.

[0107] In step S11 of this embodiment, data 21 including design variables 21A and evaluation conditions 46 are acquired for multiple types of tires 11. The data 21 and evaluation conditions 46 are stored in the learning dataset storage unit 7a shown in FIG.

[0108] Next, in the generation method of this embodiment, in step S13 of the preparation step S1 shown in Fig. 6, the training data set 23 shown in Fig. 10 is created. In this step S13, the training data set 23 is created for each of a plurality of types of tires 11, combining data 21 including design variables 21A, evaluation conditions 46, and performance 22 (tire rolling resistance coefficient 22A).

[0109] FIG. 11 is a conceptual diagram showing an example of a machine learning model 24A (trained model 24B) according to another embodiment of the present invention.

[0110] Next, in the generation method of this embodiment, in step S21 of the learning step S2 shown in Fig. 8, machine learning of a first model 25 is performed so as to extract, from data 21 including design variables 21A, feature quantities 27 that can be restored to the data 21, as shown in Fig. 11. In step S21 of this embodiment, the first model 25 that can extract feature quantities 27 that can be restored to the design variables 21A is generated while compressing the dimensions of the design variables 21A.

[0111] Next, in the generation method of this embodiment, in step S22 of the learning step S2 shown in Fig. 8, machine learning of the second model 26 is performed so as to output the tire performance 22 from the feature quantities 27 extracted from the data 21 including the design variables 21A and the evaluation conditions 46. In this step S22, the second model 26 capable of outputting the tire performance 22 is generated from the feature quantities 27 extracted by the first model 25 and the evaluation conditions 46.

[0112] In this embodiment, principal component scores (numerical data) 28 of the feature quantities 27 extracted from the design variables 21A and numerical data 47 of the evaluation conditions 46 are input to the input layer 43 of the trained model 24B (second model 26). These design variables 21A and evaluation conditions 46 are related to each other in that they affect the rigidity and contact shape of the tread portion 12, and further, are strongly correlated with the performance 22 (in this example, the rolling resistance coefficient 22A of the tire) output from the second model 26. Therefore, a trained model 24B (second model 26) capable of accurately estimating the performance 22 of the tire 11 can be generated based on the feature quantities 27 extracted from the design variables 21A and the evaluation conditions 46.

[0113] The first model 25 of this embodiment can extract feature quantities 27 that can be restored to the design variables 21A. As a result, for example, the feature quantities 27 that have provided good performance 22 output by the second model 26 can be restored to the design variables 21A of the tire 11 that can demonstrate that performance 22. Furthermore, the first model 25 of this embodiment can extract feature quantities 27 that have been dimensionally compressed from the data 21 of the tire 11 (in this example, the design variables 21A), which allows the second model 26 to be made smaller.

[0114] Furthermore, unlike the design variables 21A, no restorable features are extracted from the evaluation conditions 46. Therefore, the time required to create the training dataset 23 and the time required to generate the trained model 24B (the first model 25 and the second model 26) can be reduced.

[0115] [Tire performance prediction method (second embodiment)] The prediction method of this embodiment uses the trained model 24B (first model 25 and second model 26) generated based on the generation method shown in FIGS.

[0116] In the prediction method of this embodiment, in step S3 shown in Fig. 9, data 21 including design variables 21A of the tire 11 to be evaluated and evaluation conditions 46 are input to the prediction device 1A (computer 1) shown in Fig. 1, as shown in Fig. 11. In this embodiment, the design variables 21A of the tire 11 to be evaluated and the evaluation conditions 46 are acquired based on the processing procedure in step S11 of the preparation step S1 shown in Fig. 6.

[0117] Next, in the prediction method of this embodiment, in step S4 shown in Fig. 9, feature quantities 27 that can be restored to the data 21 are extracted from the data 21 including the design variables 21A of the tire 11, as shown in Fig. 11. In this step S4, the prediction device 1A (extraction unit 8b) shown in Fig. 1 inputs the data 21 including the design variables 21A of the tire 11 to be evaluated into the first model 25. As a result, the feature quantities 27 that can be restored to the original data 21 can be extracted while compressing the dimensions of the data 21.

[0118] Next, in the prediction method of this embodiment, in step S5 shown in FIG. 9, the performance 22 of the tire 11 is output based on the feature 27 and the evaluation condition 46, as shown in FIG. 11. In step S5 of this embodiment, the prediction device 1A (output unit 8c) inputs the feature 27 extracted from the data 21 of the tire 11 to be evaluated and the evaluation condition 46 to the input layer 43 of the second model 26. As a result, the performance 22 of the tire 11 to be evaluated (in this example, the tire rolling resistance coefficient 22A) is output from the output layer 44 of the second model 26. Therefore, in the prediction method of this embodiment, as in the previous embodiments, it is possible to estimate the performance 22 of the tire 11 to be evaluated without requiring the experience or intuition of a skilled person.

[0119] Next, as shown in FIG. 9, if it is determined that the performance 22 of the tire 11 to be evaluated is good ("Yes" in step S6), the tire 11 is manufactured based on the design variables 21A and evaluation conditions 46 input into the first model 25 shown in FIG. 11 (step S7). On the other hand, if it is determined that the performance 22 of the tire 11 to be evaluated is not good ("No" in step S6), at least a part of the design variables 21A of the tire 11 to be evaluated and the evaluation conditions 46 shown in FIG. 11 are changed in step S8. Then, steps S3 to S6 are performed again. This allows the tire 11 to be reliably designed and manufactured having the desired performance (for example, rolling resistance performance) 22.

[0120] 11 is extracted so that it can be edited as desired. Therefore, in step S8, only the feature 27 and the evaluation conditions 46 may be edited, and steps S5 and S6 may be performed again. This allows evaluation of tire performance 22 in which the design variables 21A are changed in a simulated manner, without specifically changing the tire design variables 21A.

[0121] Furthermore, similar to the data 21 (design variables 21A), the evaluation conditions 46 may be extracted by extracting, for example, a feature that can be restored to the evaluation conditions 46 by the first model 25. This reduces the number of machine learning parameters of the second model 26, enabling further miniaturization of the second model 26.

[0122] [Dataset creation method] In the prediction method (prediction device 1A) of the above embodiment, the tire 11 (design variables 21A and evaluation conditions 46) are changed and new feature quantities 27 are extracted so that the performance 22 is improved, but the present invention is not limited to such an embodiment. For example, an optimal solution of the feature quantities 27 may be obtained so that the performance 22 satisfies a predetermined standard. By restoring such an optimal solution of the feature quantities 27 to the data 21 (design variables 21A), it is possible to easily obtain data 21 whose performance 22 satisfies the standard.

[0123] The optimal solution of the feature quantity 27 is obtained based on, for example, a known optimization method. Examples of the optimization method include a genetic algorithm (GA), Bayesian optimization (BO), and particle swarm optimization (PSO). The optimization method of this embodiment uses a genetic algorithm.

[0124] In genetic algorithms, genetic operations such as crossover are repeatedly performed on multiple chromosome information expressed by genes. This makes it possible to evolve chromosome information over time from a small number of samples, making it possible to efficiently obtain optimal solutions.

[0125] In this embodiment, the feature 27 shown in FIG. 7 is treated as chromosome information, and the principal component scores (numerical data) 28 constituting the feature 27 are treated as genes. As described above, in a genetic algorithm, genetic manipulation is performed on a plurality of chromosome information (in this example, feature 27). For this reason, it is preferable to create a dataset having a plurality of feature 27 with mutually different principal component scores 28. To create such a dataset, the dataset creation method described below is carried out.

[0126] In the dataset creation method (hereinafter sometimes referred to as the "creation method") of this embodiment, a dataset is created for input that is necessary for the trained model 24B (second model 26) that has been machine-learned to output the performance 22 of the tire 11 to output the performance 22. This dataset is made up of a plurality of feature quantities 27 (one feature quantity 27 is shown in FIG. 7), and is used to find an optimal solution for the feature quantity 27.

[0127] Fig. 12 is a flowchart showing an example of the processing procedure of a data set creation method. Each step of the creation method of this embodiment is executed by a processor 5A included in the creation device 1C (computer 1) shown in Fig. 1. Fig. 13 is a diagram showing an example of a data set 29.

[0128] [Enter data including tire design variables] In the prediction method of this embodiment, first, data 21 including variables (design variables 21A) related to the design of the tire 11 is input (step S31). In step S31, the data 21 including the design variables 21A for the tire 11 to be evaluated is input to the prediction device 1A (computer 1) shown in FIG.

[0129] In step S31 of this embodiment, first, the input unit 8a included in the program unit 8 shown in Fig. 1 is loaded into the working memory 5C. The input unit 8a is a program for inputting data 21 including design variables 21A for the tire 11 to be evaluated. When the input unit 8a is executed by the processor 5A, the computer 1 (prediction device 1A) can function as a means for inputting the data 21.

[0130] In step S31 of this embodiment, the prediction device 1A (input unit 8a) shown in Fig. 1 acquires the design variables 21A of the tire 11 to be evaluated. In this embodiment, the design variables 21A of the tire 11 to be evaluated are acquired based on the processing procedure in step S11 of the preparation step S1 shown in Fig. 6. The data 21 including the acquired design variables 21A is stored in the data storage unit 7c shown in Fig. 1.

[0131] [Extracting features from data containing variables related to tire design] Next, in the creation method of this embodiment, as shown in Fig. 13, feature quantities 27 that can be restored to the data 21 and can be arbitrarily edited are extracted from the data 21 including variables (design variables 21A) related to the design of the tire 11 (step S32). A first model 25 is used to extract the feature quantities 27.

[0132] In step S32 of this embodiment, first, data 21 including design variables 21A of the tire 11 to be evaluated, which is stored in the data storage unit 7c shown in FIG. 1, is loaded into the working memory 5C. Furthermore, a first model 25 (shown in FIG. 13) stored in the trained model storage unit 7b and an extraction unit 8b included in the program unit 8 are loaded into the working memory 5C. The extraction unit 8b is a program for inputting the data 21 including the design variables 21A into the trained model 24B (in this example, the first model 25) and extracting feature quantities 27 that can be restored to the data 21. Execution of this extraction unit 8b by the processor 5A causes the computer 1 (prediction device 1A) to function as a means for extracting feature quantities 27.

[0133] In step S32 of the present embodiment, the prediction device 1A (extraction unit 8b) inputs data 21 including design variables 21A of the tire 11 to be evaluated into the first model 25. As a result, the data 21 is dimensionally compressed, and feature quantities 27 that can be restored to the original data 21 can be extracted.

[0134] As described above, the plurality of principal component scores 28 constituting the feature 27 can be handled (edited, etc.) by the computer 1 shown in Fig. 1. Therefore, the feature 27 can be extracted in an editable manner.

[0135] In step S32 of this embodiment, one feature 27 is extracted by inputting one piece of data 21 (design variable 21A) into the first model 25. The extracted feature 27 is stored in the feature storage unit 7d shown in FIG.

[0136] [Creating a dataset with multiple distinct features] Next, in the creation method of this embodiment, as shown in Fig. 13, the extracted feature 27 is edited to create a data set 29 having a plurality of feature quantities 27 that are different from one another (step S33). In step S33 of this embodiment, one extracted feature quantity 27 is copied multiple times, and each of the copied feature quantities 27 is edited to create a data set 29 having a plurality of feature quantities 27 that are different from one another.

[0137] In step S33 of this embodiment, first, the feature 27 (shown in FIG. 13) stored in the feature storage unit 7d shown in FIG. 1 and a creation unit 8g included in the program unit 8 are loaded into the working memory 5C. The creation unit 8g is a program for creating a data set 29 having a plurality of feature values ​​27 that are different from one another by editing the feature values ​​27 shown in FIG. 13. When the creation unit 8g is executed by the processor 5A, the computer 1 (creation device 1C) can function as a means for creating the data set 29.

[0138] In step S33 of this embodiment, first, one feature 27 extracted in step S32 is copied multiple times. Next, for the multiple copied feature quantities 27, at least one principal component score 28 constituting each feature quantity 27 is changed. As a result, a data set 29 having multiple feature quantities 27 that are different from one another is created. These multiple feature quantities 27 are treated as pseudo-extracted feature quantities from the design variables (not shown) of a tire (not shown) different from the tire 11 of the design variable 21A shown in FIG. 13.

[0139] The number of feature quantities 27 constituting the data set 29 can be set appropriately in consideration of, for example, the efficiency of optimization, etc. The number of feature quantities 27 can be set to, for example, 30 to 100.

[0140] The principal component scores (numerical data) 28 that make up the feature quantities 27 can be edited as appropriate. For example, the principal component scores 28 that make up the feature quantities 27 may be edited based on the genetic manipulation (crossover or mutation) of a genetic algorithm. This can prevent bias in the principal component scores 28 that tends to occur when edited by an operator or the like, and can prevent convergence to a local optimum solution.

[0141] In this way, in the creation method of this embodiment, by editing the feature 27 extracted from the design variable 21A of one tire 11, a dataset 29 can be created that includes the feature 27 of multiple tires 11 having different design variables 21A. This eliminates, for example, the need to specifically design each of the multiple tires 11 and extract multiple feature 27 from the data 21 of those tires 11. Therefore, the dataset 29 including multiple feature 27 can be created easily and quickly. The dataset 29 is stored in the input dataset storage unit 7f shown in FIG. 1.

[0142] [Tire performance prediction method (third embodiment)] The prediction method of this embodiment uses the trained model 24B (first model 25 and second model 26) generated based on the generation method shown in FIGS.

[0143] 14 is a flowchart showing an example of a processing procedure of a tire performance prediction method according to another embodiment of the present invention. Each step of the prediction method according to this embodiment is executed by a processor 5A included in the prediction device 1A (computer 1) shown in FIG.

[0144] [Create dataset (creation step)] In the prediction method of this embodiment, first, an input dataset 29 necessary for causing the trained model 24B (second model 26) to output the performance 22 is created (creation step S41). In the creation step S41 of this embodiment, a dataset 29 having a plurality of mutually different feature quantities 27 is created based on the creation method shown in FIG. 12, as shown in FIG. 13. Note that if the dataset 29 has already been created, the creation step S41 may be omitted. The dataset 29 is stored in the input dataset storage unit 7f shown in FIG. 1.

[0145] [Find the optimal solution for features that meet the performance criteria (optimal solution acquisition step)] Next, in the generation method of this embodiment, an optimal solution of the feature 27 is obtained so that the performance 22 satisfies a predetermined standard (optimal solution obtaining step S42). In the optimal solution obtaining step S42 of this embodiment, the optimal solution of the feature 27 can be obtained based on the known optimization method described above (in this example, a genetic algorithm).

[0146] In the optimal solution acquisition step S42 of this embodiment, first, the dataset 29 (shown in FIG. 13) stored in the input dataset storage unit 7f shown in FIG. 1 is loaded into the working memory 5C. Furthermore, in the optimal solution acquisition step S42, the second model 26 (shown in FIG. 7) stored in the trained model storage unit 7b and an optimal solution acquisition unit 8h included in the program unit 8 are loaded into the working memory 5C. The optimal solution acquisition unit 8h is a program for obtaining an optimal solution of the feature quantity 27 so that the performance 22 satisfies a predetermined standard. When the optimal solution acquisition unit 8h is executed by the processor 5A, the computer 1 (prediction device 1A) can function as a means for obtaining an optimal solution of the feature quantity 27. FIG. 15 is a flowchart showing an example of the processing procedure of the optimal solution acquisition step S42. FIG. 16 is a diagram for explaining an example of the processing procedure of the optimal solution acquisition step S42.

[0147] [Output tire performance for each of multiple features] In the optimal solution acquisition step S42 of this embodiment, first, as shown in Fig. 16, for each of a plurality of feature quantities 27 included in the data set 29, the performance 22 of the tire 11 corresponding to each feature quantity 27 is output (step S51). The second model 26 included in the trained model 24B is used to output the performance 22.

[0148] In step S51 of this embodiment, the prediction device 1A (output unit 8c) shown in FIG. 1 inputs the plurality of feature quantities 27 included in the data set 29 to the input layer 43 of the second model 26, as shown in FIG. 16. As a result, the performance 22 of the tire 11 (in this example, the rolling resistance coefficient 22A of the tire 11) estimated for each of the plurality of feature quantities 27 is output from the output layer 44 of the second model 26. The output performance 22 is stored in the performance storage unit 7e shown in FIG. 1.

[0149] [Determine whether the tire performance output for each feature meets the criteria] Next, in the optimal solution acquisition step S42 of this embodiment, it is determined whether or not at least one of the performances 22 of the tire 11 output for each of the plurality of feature quantities 27 satisfies a predetermined criterion (step S52). The criterion is determined as appropriate depending on the performance 22 required of the tire 11. In the case where the performance 22 is the rolling resistance coefficient 22A of the tire as in this embodiment, for example, the rolling resistance coefficient 22A of the tire is determined to satisfy the criterion when it is less than a predetermined threshold value.

[0150] If it is determined that at least one of the performances 22 of the tire 11 output for each of the plurality of feature amounts 27 satisfies the criteria ("Yes" in step S52), the feature amount 27 that outputs the best performance 22 is selected as the optimum solution (step S53). The optimum solution (feature amount 27) is stored in the optimum solution storage unit 7g shown in Fig. 1. Then, the series of processes in the optimum solution acquisition step S42 is completed.

[0151] If it is determined that all of the performances 22 output for each of the plurality of feature quantities 27 do not satisfy the criteria ("No" in step S52), step S54 is performed to perform genetic manipulation on the plurality of feature quantities 27 included in the dataset 29. Then, steps S51 and S52 are performed again.

[0152] [Genetic manipulation of multiple features] Next, in the optimal solution acquisition step S42 of this embodiment, genetic manipulation is performed on the plurality of feature quantities 27 included in the data set 29 shown in Fig. 16 (step S54). In this embodiment, in step S54, genetic manipulation including selection, crossover, and mutation is performed on the plurality of feature quantities 27 included in the data set 29 based on a known genetic algorithm.

[0153] Selection is a genetic operation that selects high-performance features 27 or a specific number of features 27 from multiple features 27 included in a dataset 29. The selected features 27 are included in a new next-generation dataset 30. Crossover is a genetic operation that combines principal component scores (numeric data) 28 of multiple features 27 included in a dataset 29 to generate new features 27. The new features 27 are included in a new next-generation dataset 30. Mutation is a genetic operation that randomly changes the principal component scores (numeric data) 28 of features 27 included in a dataset 29 to generate new features 27. The new features 27 are included in a new next-generation dataset 30.

[0154] In step S54, genetic manipulation is performed on a plurality of features 27 included in the dataset 29, thereby creating a new dataset 30 including features 27 with evolved principal component scores (numerical data) 28 so that the performance 22 satisfies a standard. This new dataset 30 is then replaced with the dataset 29 for outputting the performance 22 in step S51, which is performed again. The new dataset 30 is stored in the input dataset storage unit 7f shown in FIG. 1.

[0155] In the optimal solution acquisition step S42 of this embodiment, after the genetic manipulation step S54 is performed, steps S51 and S52 are performed again. In the re-performed step S51, tire performance 22 corresponding to a plurality of feature quantities 27 is output for the dataset 29 replaced from the new dataset 30. Then, the genetic manipulation (optimal solution acquisition step S42) is performed until the performance 22 satisfies the criterion, and therefore the optimal solution for the feature quantities 27 whose performance 22 satisfies the criterion is reliably found.

[0156] [Restore the optimal solution to the data] Next, in the prediction method of this embodiment, the optimal solution of the feature 27 is restored to the data 21 (design variables 21A) (step S43), as shown in Figures 13 and 14. The first model 25 included in the trained model 24B is used to restore the data 21.

[0157] In step S43 of this embodiment, first, the optimal solution of the feature 27 stored in the optimal solution storage unit 7g shown in FIG. 1 and the first model 25 (shown in FIG. 13) stored in the trained model storage unit 7b are loaded into the working memory 5C. Furthermore, a restoration unit 8i included in the program unit 8 is loaded into the working memory 5C. The restoration unit 8i is a program for restoring the optimal solution of the feature 27 to the data 21. When the restoration unit 8i is executed by the processor 5A, the computer 1 (prediction device 1A) can function as a means for restoring the data 21.

[0158] In step S43, the feature 27 selected as the optimal solution is input to the first model 25 shown in Fig. 13. This makes it possible to acquire data 21 (design variables 21A) in which the feature 27 is restored to its original dimension. Therefore, the design variables 21A whose performance 22 satisfies the standard are acquired.

[0159] [Manufacturing tires] Next, in the prediction method of this embodiment, the tire 11 is manufactured based on the restored data 21 (design variables 21A) (step S44). The data 21 (in this example, the thickness (maximum thickness) W1 of the rubber member 15, the physical property value P of the rubber member 15, the structure 31 of the carcass 16, and the structure 32 of the belt layer 17) are restored to their original dimensions from the optimal solution of the feature quantity 27. By manufacturing the tire 11 based on such data 21, a new tire 11 having a desired performance 22 (for example, the rolling resistance coefficient 22A) can be reliably designed and manufactured without being influenced by the experience or intuition of a skilled person.

[0160] Although a particularly preferred embodiment of the present invention has been described in detail above, the present invention is not limited to the illustrated embodiment and can be modified and implemented in various ways.

[0161] [Note] The present invention includes the following aspects.

[0162] [Invention 1] A tire performance prediction device, a trained model storage unit that stores a trained model that has been machine-learned to extract feature amounts from data including variables related to tire design and output tire performance from the feature amounts; The feature amount can be restored to the data. Tire performance prediction device. [Invention 2] The tire performance prediction device according to the first aspect of the present invention, wherein the feature amount is arbitrarily editable. [Invention 3] 3. The tire performance prediction device according to claim 1, wherein the trained model includes a first model that extracts the feature amount by dimensionally compressing the data. [Invention 4] The tire performance prediction device according to aspect 3, wherein the first model extracts the feature amounts based on at least one of principal component analysis, independent component analysis, singular value decomposition, and autoencoder. [Invention 5] 5. The tire performance prediction device according to any one of claims 1 to 4, wherein the trained model includes a second model that outputs the performance from the feature amount. [Invention 6] The tire performance prediction device according to aspect 5, wherein the second model outputs the performance based on at least one of a neural network, multiple regression, random forest regression, and deep learning. [Invention 7] The tire has predetermined conditions for evaluating the performance, 7. The tire performance prediction device according to claim 5 or 6, wherein the second model outputs the performance based on the feature amount and the condition. [Invention 8] The tire includes at least one of a rubber member, a carcass, and a belt layer, The tire performance prediction device according to any one of the present inventions 1 to 7, wherein the variables include at least one of the thickness of the rubber member, the physical property value of the rubber member, the structure of the carcass, and the structure of the belt layer. [Invention 9] 9. The tire performance prediction device according to any one of aspects 1 to 8, wherein the performance includes distribution data of physical quantities acting on the tread portion when the tread portion comes into contact with the road surface. [Invention 10] 10. The tire performance prediction device according to any one of claims 1 to 9, wherein the performance includes at least one of the rolling resistance, vertical spring constant, lateral spring constant, and air resistance value of the tire. [Invention 11] an optimal solution acquisition unit that obtains an optimal solution for the feature quantity so that the performance satisfies a predetermined standard; 11. The tire performance prediction device according to any one of claims 1 to 10, further comprising: a restoration unit that restores the optimal solution to the data. [Invention 12] 1. A method for predicting tire performance executed by a processor, comprising: extracting features from data including variables related to tire design; and outputting the tire performance corresponding to the feature quantity using a trained model that has been machine-learned to output the tire performance from the feature quantity, The feature amount can be restored to the data. A method for predicting tire performance. [Invention 13] A method for creating an input dataset necessary for outputting tire performance to a trained model trained by machine learning to output the performance, comprising: extracting arbitrarily editable feature values ​​from data including variables related to tire design; and editing the feature values ​​to create a data set having a plurality of feature values ​​that are different from each other; The feature amount can be restored to the data. How to create the dataset. [Explanation of symbols]

[0163] 21 Data 21A Tire Design Variables 22 Performance 24B trained model 27 Features

Claims

1. A tire performance prediction device, a trained model storage unit that stores a trained model that has been machine-learned to extract feature amounts from data including variables related to tire design and output tire performance from the feature amounts; The feature amount can be restored to the data. Tire performance prediction device.

2. The tire performance prediction device according to claim 1 , wherein the feature amount is arbitrarily editable.

3. The tire performance prediction device according to claim 1 , wherein the trained model includes a first model that extracts the feature amount by dimensionally compressing the data.

4. The tire performance prediction device according to claim 3 , wherein the first model extracts the feature quantities based on at least one of principal component analysis, independent component analysis, singular value decomposition, and an autoencoder.

5. The tire performance prediction device according to claim 1 , wherein the trained model includes a second model that outputs the performance from the feature amount.

6. The tire performance prediction device according to claim 5 , wherein the second model outputs the performance based on at least one of a neural network, a multiple regression, a random forest regression, and a deep learning.

7. The tire has predetermined conditions for evaluating the performance, The tire performance prediction device according to claim 5 , wherein the second model outputs the performance based on the feature amount and the condition.

8. The tire includes at least one of a rubber member, a carcass, and a belt layer, The tire performance prediction device according to claim 1 , wherein the variables include at least one of a thickness of the rubber member, a physical property value of the rubber member, a structure of the carcass, and a structure of the belt layer.

9. The tire performance prediction device according to claim 1 , wherein the performance includes distribution data of physical quantities acting on the tread portion when the tread portion comes into contact with the road surface.

10. The tire performance prediction device according to claim 1 , wherein the performance includes at least one of rolling resistance, longitudinal spring constant, lateral spring constant, and air resistance value of the tire.

11. an optimal solution acquisition unit that obtains an optimal solution for the feature quantity so that the performance satisfies a predetermined standard; The tire performance prediction device according to claim 1 , further comprising: a restoration unit that restores the optimal solution to the data.

12. 1. A method for predicting tire performance executed by a processor, comprising: extracting features from data including variables related to tire design; and outputting the tire performance corresponding to the feature quantity using a trained model that has been machine-learned to output the tire performance from the feature quantity, The feature amount can be restored to the data. A method for predicting tire performance.

13. A method for creating an input dataset necessary for outputting tire performance to a trained model trained by machine learning to output the performance, comprising: extracting arbitrarily editable feature values ​​from data including variables related to tire design; and editing the feature values ​​to create a data set having a plurality of feature values ​​that are different from each other; The feature amount can be restored to the data. How to create the dataset.

Images