Tread pattern estimation system, tread pattern estimation method, tire performance prediction system, tire performance prediction method, and program

The system estimates tire tread patterns and predicts performance by using a target value and machine learning, addressing inaccuracies in conventional methods by optimizing tread patterns for desired tire performance.

JP2024164578APending Publication Date: 2024-11-27SUMITOMO RUBBER INDUSTRIES LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2023080170
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-15
Publication Date
2024-11-27

AI Technical Summary

Technical Problem

Conventional tire performance prediction systems rely on ground contact surface images, which are influenced by varying measurement conditions, leading to inaccurate performance predictions due to deformation of the tire contact patch.

Method used

A system and method that estimates a tire tread pattern based on a target tire performance value and predicts tire performance using a trained prediction model, incorporating optimization and machine learning algorithms to determine an optimal tread pattern that achieves the desired performance.

Benefits of technology

Enables accurate estimation of tire tread patterns and prediction of tire performance values, allowing for improved tire development and evaluation by ensuring the predicted performance aligns with predefined targets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024164578000001_ABST
    Figure 2024164578000001_ABST
Patent Text Reader

Abstract

To provide a tread pattern estimation system, a tread pattern estimation method, and a program for estimating a tread pattern of a tire based on target values of tire performances required for the tire.SOLUTION: In an estimation system, when a target value of a specific tire performance is acquired by an acquiring processing unit (S13), a tread pattern of a tire capable of achieving the target value is estimated by a pattern estimating unit on the basis of the target value (S15, S16).SELECTED DRAWING: Figure 10
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a technique for estimating a tire tread pattern or predicting tire performance. [Background technology]

[0002] Conventionally, there is known a tire performance prediction system that predicts tire performance values ​​based on a contact patch image of a tire mounted on an automobile (see Patent Documents 1 and 2). The prediction system extracts image features from the contact patch image that represents the tire contact patch shape, inputs the features to a trained prediction model, and causes the prediction model to output a predicted value of tire performance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-195038 [Patent Document 2] JP 2022-090349 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional prediction system predicts tire performance values ​​based on the contact patch image, and does not estimate the tire tread pattern.

[0005] Furthermore, conventional prediction systems predict tire performance using a contact patch image in a state where the tire is loaded with a vehicle load. The shape of the tire's contact patch depends on various measurement conditions, such as the tire air pressure, tire rubber hardness, ambient temperature (air temperature), vehicle weight, and time left standing. If any one of these measurement conditions is different, the shape of the contact patch will be distorted, making it difficult to predict tire performance values ​​with high accuracy.

[0006] An object of the present disclosure is to provide a tread pattern estimation system, a tread pattern estimation method, and a program that estimate a tire tread pattern based on target values ​​of tire performance desired for the tire.

[0007] Another object of the present disclosure is to provide a tire performance prediction system, a tire performance prediction method, and a program for predicting a tire performance value based on a tire tread pattern. [Means for solving the problem]

[0008] A tread pattern estimation system according to one aspect of the present disclosure includes a target value acquisition unit that acquires a target value of tire performance, a pattern estimation unit that estimates a tire tread pattern capable of achieving the target value based on the tire performance and the target value, and a pattern display processing unit that displays the estimated pattern estimated by the pattern estimation unit on a predetermined display unit.

[0009] A tire performance prediction system according to another aspect of the present disclosure includes a pattern information acquisition unit that acquires pattern information including features of a tire tread pattern, a performance prediction unit that predicts a tire performance value based on the pattern information, and a performance display processing unit that displays the tire performance predicted value predicted by the performance prediction unit on a predetermined display unit. Effect of the Invention

[0010] According to the present disclosure, it is possible to estimate a tire tread pattern based on target values ​​of tire performance desired for the tire.

[0011] Furthermore, according to the present disclosure, it is possible to predict with high accuracy a tire performance value corresponding to the tread pattern of a tire based on the tread pattern of the tire. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing a configuration of an estimation system according to a first embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram showing a configuration of an estimation device included in the estimation system. [Figure 3A] FIG. 3A is a block diagram showing a pattern estimation unit that estimates a tread pattern. [Figure 3B] FIG. 3B is a block diagram showing a performance predicting unit that predicts tire performance values. [Figure 4] FIG. 4 is a block diagram showing a configuration of an information terminal included in the estimation system. [Diagram 5] FIG. 5 shows a tire information input screen, which is an example of a screen displayed on the information terminal of the estimation system. [Figure 6] FIG. 6 shows a performance information input screen, which is an example of a screen displayed on an information terminal of the estimation system. [Figure 7] FIG. 7 shows a target value input screen, which is an example of a screen displayed on an information terminal of the estimation system. [Figure 8] FIG. 8 shows an estimated pattern screen, which is an example of a screen displayed on an information terminal of the estimation system. [Figure 9] FIG. 9 shows a predicted performance graph screen, which is an example of a screen displayed on an information terminal of the estimation system. [Figure 10] FIG. 10 is a flowchart illustrating an example of a procedure of a pattern estimation process executed in the estimation system. [Figure 11] FIG. 11 is a diagram illustrating a configuration of a prediction system according to the second embodiment of the present disclosure. [Figure 12] FIG. 12 is a block diagram showing a configuration of a prediction device included in the prediction system. [Figure 13] FIG. 13 is a block diagram showing a configuration of an information terminal included in the prediction system. [Figure 14] FIG. 14 shows a predicted performance display screen, which is an example of a screen displayed on an information terminal of the prediction system. [Figure 15] FIG. 15 shows a feature display screen, which is an example of a screen displayed on an information terminal of the prediction system. [Figure 16]FIG. 16 is a flowchart illustrating an example of a procedure of a performance prediction process executed in the prediction system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. Note that the following embodiments are examples of the present disclosure and are not intended to limit the technical scope of the present disclosure.

[0014] [First embodiment] 1 is a diagram showing a configuration of an estimation system 100 according to a first embodiment of the present disclosure. The estimation system 100 of the present embodiment is mainly composed of an estimation device 10, an information terminal 20, and a database 30. The estimation system 100 is an example of a pattern estimation system of the present disclosure.

[0015] The estimation system 100 is a system that estimates a tread pattern in which a specific tire performance value (tire performance value) achieves a predetermined target value. In this embodiment, the estimation system 100 is configured to be able to estimate, based on the predetermined target value, a tire tread pattern having tire performance equivalent to the target value. The estimation result by the estimation system 100 is used for the development of the tire, performance testing of the tire, performance evaluation of the tire, etc.

[0016] The tire is mounted on vehicles such as passenger cars, large vehicles such as trucks and buses, motorcycles, racing vehicles, industrial vehicles, special vehicles, and load-bearing vehicles such as trailers and dollies, and rolls when a rotational force is transmitted from the vehicle to move the vehicle in a predetermined traveling direction. Note that the tire may be any type of tire as long as it has a tread portion in the part that comes into contact with the road surface, and may be, for example, a pneumatic tire filled with compressed air or a non-pneumatic tire not filled with compressed air.

[0017] The tread pattern, which is closely related to tire performance, is formed on the contact surface of the tire, that is, the surface of the tread portion of the tire. The tread pattern is a groove pattern formed on the tread portion, and its shape is designed based on various factors such as the direction and angle of the grooves, the length of the grooves, the depth of the grooves, the width of the grooves, the spacing between the grooves, and the state of connection between the grooves. The tread pattern has four main functions. Specifically, the tread pattern has a function of transmitting the driving force and braking force of the vehicle to the road surface, a function of draining water transmitted from the road surface, a function of stabilizing the running of the vehicle by suppressing slippage on the road surface, and a function of improving the ride comfort and quietness of the vehicle.

[0018] The inventors of the present disclosure have focused on specific tire performance (hereinafter referred to as "specific tire performance") such as fuel economy performance, wet grip performance, dry grip performance, and wear resistance performance related to the tread pattern as tire performance for which each of these functions can be evaluated, and developed an estimation system 100 that estimates a tread pattern capable of achieving the target values ​​of each of these tire performances using the target values ​​of each of these tire performances. Note that the tire performances described above are merely examples, and the estimation system 100 may estimate a tread pattern capable of achieving the target values ​​of other tire performances.

[0019] [Configuration of estimation system 100] 1, the estimation system 100 includes an estimation device 10, an information terminal 20, and a database 30, which are communicatively connected to each other via a network N1. The network N1 is, for example, a wired communication network connected by a LAN or the like, or a wireless communication network such as a dedicated line or a public line.

[0020] In this embodiment, a configuration in which the database 30 is connected to the network N1 is illustrated, but for example, the database 30 may be provided in the estimation device 10 or the information terminal 20. In addition, in this embodiment, a configuration in which the information terminal 20 is connected to the network N1 is illustrated, but each component and each function provided in the information terminal 20 may be installed in the estimation device 10.

[0021] The estimation device 10 acquires a target value of tire performance transmitted from the information terminal 20, and performs a process of estimating a tire tread pattern capable of achieving the target value based on the acquired target value. Specifically, a pattern estimation unit 111 (see FIG. 2) of the estimation device 10 estimates a tread pattern (groove shape) of the tire to be estimated, using input information including the target value transmitted from the information terminal 20, an optimization model 121 and a prediction model 122 (see FIGS. 3A and 3B) that are constructed in advance, which will be described later. In the estimation device 10, a performance prediction unit 112 (see FIG. 2) (to be described later) predicts a tire performance value corresponding to the tread pattern estimated by the pattern estimation unit 111 (hereinafter referred to as an "estimated pattern"), using various information such as the input information transmitted from the information terminal 20, and a prediction model 122 (see FIGS. 3 and 3B) (to be described later). The estimation result (estimated pattern) by the pattern estimation unit 111 and the prediction result (predicted performance value) by the performance prediction unit 112 are output to the information terminal 20 and displayed on the display unit 23 of the information terminal 20.

[0022] The estimation device 10 is an information processing device capable of executing various types of arithmetic processing, and is, for example, a server computer, a cloud server, or a personal computer connected to a network N1. Note that the estimation device 10 is not limited to a single computer, and may be a computer system in which multiple computers work in cooperation, or a cloud computing system. Furthermore, various types of processing executed by the estimation device 10 may be executed in a distributed manner by one or multiple processors. A program or computer software for operating the estimation system 100 is installed in the estimation device 10.

[0023] The information terminal 20 is an information processing device or terminal device used by a user. The information terminal 20 is a so-called desktop personal computer or notebook computer, or a portable terminal such as a smartphone or tablet terminal that can be carried around. A user inputs various information used in various arithmetic processes such as a pattern estimation process (see FIG. 9) executed in the estimation device 10 to the information terminal 20. Therefore, a program or computer software is installed in the information terminal 20 for transmitting the various information and control signals to the estimation device 10 in cooperation with the estimation system 100 and displaying the estimation result and the prediction result on a display screen.

[0024] The database 30 is a data group in which various data handled in the estimation system 100 is stored in a storage medium based on a predetermined data management method. The database 30 is managed in various forms, such as a storage device, an information processing device, a cloud server, or a data server communicably connected to the network N1. The database 30 includes reference data 30A used in an optimization model 121 (see FIG. 2) described below, and teacher data 30B used for generating or learning a prediction model 122 (see FIG. 2) described below.

[0025] The reference data 30A is data that is referred to when the estimation device 10 executes an optimization process using the optimization model 121. The reference data 30A is referred to when the optimization model 121 (see FIG. 2 ), which will be described later, determines design variables (pattern information) to be input to the prediction model 122. The reference data 30A includes information (pattern information) that indicates all tread patterns that can be applied to a tire. Specifically, the reference data 30A includes, for example, the pattern information of all tires available on the market, and information that indicates tire performance based on each tread pattern. The reference data 30A may include the pattern information of many prototype tires manufactured during past research and experiments.

[0026] The pattern information is, for example, a feature of a tread pattern, and includes, for example, a feature (first feature) based on groove shapes such as groove angle, groove width, groove depth, and groove length, a feature (second feature) such as a composition ratio of each groove shape and a ratio of a groove area to a tread surface, and a feature (third feature) such as an evaluation value (connectivity) of a connection state of each groove. The pattern information may be image data itself showing the tread pattern.

[0027] The teacher data 30B is a data set for generating or learning a prediction model 122 (see FIG. 2) used in a performance prediction process by a performance prediction unit 112 described later in the estimation device 10. The teacher data 30B is information used for generating various functions (hereinafter referred to as "prediction functions") included in the prediction model 122 described later. Specifically, the teacher data 30B is a data set including tire information (explanatory variables) on a large number of sample tires, pattern information (explanatory variables) indicating actual tread patterns of a large number of sample tires, actual measurement values ​​(objective variables) of a plurality of tire performances including the specific tire performance of each sample tire, and the like.

[0028] The tire information includes, for example, tire size information (tire width, aspect ratio, rim diameter, tire outer diameter, etc.), tire use (snow tire, summer tire, etc.), tire structure symbol, load index, maximum speed (maximum speed based on speed symbol), tire strength (ply rating), etc.

[0029] The sample tires may be tires that have been manufactured as products, or prototype tires manufactured during research and experiments for the development of the tires.

[0030] [Estimation device 10] The configuration of the estimation device 10 will be described below with reference to Fig. 2. Fig. 2 is a block diagram showing the configuration of the estimation device 10.

[0031] The estimation device 10 is for realizing the estimation system 100 of this embodiment, and estimates the estimation pattern using an optimization model 121 and a prediction model 122 described below, and also predicts the performance prediction value using the prediction model 122 described below.

[0032] As shown in FIG. 2, the estimation device 10 includes a control unit 11, a storage unit 12, a communication unit 13, a display unit 14, and an operation unit 15.

[0033] The communication unit 13 is a communication interface for connecting the estimation device 10 to the network N1 and performing data communication with each device connected to the network N1 in accordance with a predetermined communication protocol. Specifically, the communication unit 13 performs data communication with the information terminal 20 and the database 30 through the network N1.

[0034] The storage unit 12 is a non-volatile storage medium such as an HDD, an SSD, or a flash memory that stores various information and data. The storage unit 12 stores a control program 120, an optimization model 121, and a prediction model 122. The optimization model 121 and the prediction model 122 may be realized as electronic circuits having memories in which they are stored.

[0035] The control program 120 is non-temporarily recorded on a computer-readable recording medium such as a CD or a DVD, and is read from the recording medium by a reading device (not shown) such as a CD drive or a DVD drive electrically connected to the estimation device 10 and copied to the storage unit 12. Note that the control program 120 may be read from an external storage connected to the network N1, input via the communication unit 13, and copied to the storage unit 12.

[0036] The control program 120 is a program for executing a pattern estimation process (see FIG. 10) described later using an optimization model 121, a prediction model 122, etc. Instead of the control program 120, a program for causing the control unit 11 to execute the pattern estimation process may be stored in the storage unit 12.

[0037] 3A and 3B are block diagrams showing an optimization model 121 and a prediction model 122 used in the pattern estimation process (see FIG. 10).

[0038] The optimization model 121 is used in the estimation process (see step S14 in FIG. 10) by the pattern estimation unit 111 described later, and searches for the unknown pattern information so that the predicted value by the trained prediction model 122 becomes the predetermined target value or falls within the allowable range of the target value. As shown in FIG. 3, when a predetermined initial input value (initial pattern information) is input to the prediction model 122 by the control unit 11 (see FIG. 2), the optimization model 121 judges whether the predicted value output from the prediction model 122 is optimal. If the predicted value output from the prediction model 122 is not optimal, the optimization model 121 determines a new design variable (new pattern information) and inputs the design variable to the prediction model 122 as a new input value, and judges again whether the predicted value predicted by the prediction model 122 is optimal. In this way, a search for the desired pattern information is performed. This search is repeated until the predicted value output from the prediction model 122 becomes an optimal solution. In other words, the optimization model 121 optimizes the design variables (i.e., pattern information) so that the difference between the predicted value by the prediction model 122 and the target value is minimized, or so that the predicted value is within an allowable range of the target value. When the predicted value output from the prediction model 122 is determined to be an optimal solution, the design variables (pattern information) input at the time of the prediction are output as the estimated pattern.

[0039] As a first optimization method by the optimization model 121, a method of determining that a predetermined calculated value of an objective function is optimal when it reaches a minimum value is applicable. In this first optimization method, the optimization model 121 repeatedly executes an optimization process until the calculated value of the objective function reaches the minimum value. Then, the optimization model 121 outputs the design variables (pattern information) when the calculated value of the objective function reaches the minimum value as an optimal solution. The minimum value is determined to be between 0 and a predetermined allowable value.

[0040] The objective function used in the optimization model 121 in the first optimization method is expressed by the following formula (1). In this case, the optimization model 121 uses the objective function f(v 1 ,v N A search is then performed for the design variable for which the calculated value of (i) is smaller than the calculated value in the previous search.

[0041]

number

[0042] Here, v in equation (1) i is the predicted value of the i-th tire performance when there are N types of tire performance predicted by the prediction model 122. i is the target value of the i-th tire performance, c i is the weighting coefficient for the i-th tire performance. Also, {(v i -t i ) / t i} 2 is the predicted value v i and the target value t i Difference with (=v i -t i ) to the target value t i That is, the objective function f(v i, ,v N ) is given as the sum of the squares of the difference ratios. Note that the weight c i can be arbitrarily determined for each of the corresponding tire performances.

[0043] The optimization model 121 is preferably implemented, for example, by a genetic algorithm (GA) list search, particle swarm optimization (PSO), or response surface methodology (RSM). In this embodiment, the optimization model 121 includes the above-mentioned multiple algorithms, and each time a predicted value is output from the prediction model 122, the optimization model 121 extracts features of an optimization problem based on the predicted value, narrows down the design variables (pattern information) to be input to the prediction model 122 based on the features, and selects an appropriate optimization algorithm to perform optimization calculation based on the objective function. The optimization model 121 may be implemented using one of the above-mentioned algorithms.

[0044] The prediction model 122 is a trained model used in the estimation process by the pattern estimation unit 111 described below. The prediction model 122 is also a trained model used in the performance prediction process (see step S17 in FIG. 10) by the performance prediction unit 112. The prediction model 122 predicts tire performance according to the pattern information related to the input tread pattern.

[0045] As shown in FIG. 3A, when new input values ​​(pattern information) output from the optimization model 121 are input to the input section as explanatory variables, the prediction model 122 predicts numerical values ​​of tire performance corresponding to the new input values, and outputs the prediction results (performance prediction values) from the output section as objective variables.

[0046] Furthermore, as shown in FIG. 3B, when the pattern information (feature of the estimated pattern) of the estimated pattern (estimated result) as the optimal solution output from the optimization model 121 is input to the input section as an explanatory variable, the prediction model 122 predicts a numerical value of tire performance corresponding to the estimated pattern, and outputs the prediction result (performance prediction value) from the output section as a target variable.

[0047] The input data input to the prediction model 122 includes the performance information and the tire information.

[0048] The prediction model 122 may include a known function (prediction function) that returns a predicted value (output data) for an input value (input data). Furthermore, the performance prediction unit 112 described below may be configured as a performance prediction value calculation unit that outputs the performance prediction value by the prediction function without using the prediction model 122.

[0049] The prediction model 122 is generated by machine learning by the control unit 11 based on the teacher data 30B stored in the database 30 and a predetermined algorithm. Note that, whenever the contents of the teacher data 30B are updated, the control unit 11 re-learns the prediction model 122 to update the prediction model 122. Note that the prediction model 122 may be generated or learned by a control unit other than the control unit 11, transferred from the outside, and stored in the storage unit 12.

[0050] The prediction model 122 can be constructed by various methods. For example, as an algorithm required for constructing the prediction model 122, multiple regression, generalized linear regression, principal component regression, ridge regression, lasso regression, kernel regression, random forest regression, Gaussian process regression, multi-layer neural network, clustering, support vector machine, RBF network defined by radial basis function, etc. are preferably used. In addition, the prediction model 122 may be constructed by deep learning that multi-layers the intermediate layer of the neural network. Note that the prediction model 122 may be constructed using one of the above-mentioned algorithms, or may be constructed using a plurality of algorithms.

[0051] The optimization model 121 and the prediction model 122 can be constructed by using commercially available computer software (for example, MATLAB (registered trademark) manufactured by The MathWorks, Inc., modeFRONTIER manufactured by ESTECO, Inc., etc.), open source software such as Python, etc.

[0052] 2, the display unit 14 is a display device such as a liquid crystal display or an organic EL display that displays various information. The operation unit 15 is an input device such as a mouse, a keyboard, or a touch panel that accepts user operations.

[0053] The control unit 11 controls the operation of each part of the estimation device 10. The control unit 11 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that executes various arithmetic processing. The ROM is a non-volatile storage medium in which control programs such as a BIOS and an OS for causing the CPU to execute various arithmetic processing are stored in advance. The RAM is a volatile or non-volatile storage medium that stores various information, and is used as a temporary storage memory (work area) for various arithmetic processing executed by the CPU. The control unit 11 controls the estimation device 10 by the CPU executing various control programs stored in advance in the ROM or the storage unit 12.

[0054] As shown in FIG. 2, the control unit 11 includes various processing units such as an acquisition processing unit 110, a pattern estimation unit 111 (an example of a pattern estimation unit of the present disclosure), a performance prediction unit 112 (an example of a performance prediction unit of the present disclosure), an output processing unit 113 (an example of an output processing unit of the present disclosure), a teacher data update unit 114, and a model learning unit 115.

[0055] The control unit 11 functions as the various processing units by the CPU executing various arithmetic processing in accordance with the control program. The control unit 11 or the CPU is an example of a computer that executes the control program. Some or all of the processing units included in the control unit 11 may be configured with electronic circuits. The control program may also be a program for causing a plurality of processors to function as the various processing units. The control program may also be a program for causing a graphics processing unit (GPU) to function as the various processing units (such as the pattern estimation unit 111 and the performance prediction unit 112).

[0056] The acquisition processing unit 110 is an example of a target value acquisition unit and a tire information acquisition unit of the present disclosure, and receives information set or input in the information terminal 20 when the information is transferred from the information terminal 20.

[0057] In this embodiment, the acquisition processing unit 110 performs a process of acquiring the target value of the specific tire performance used in the pattern estimation process (see FIG. 10) performed in the estimation device 10. Specifically, when the target value input by the user at the information terminal 20 is transmitted from the information terminal 50 to the estimation device 10 through the network N1, the acquisition processing unit 110 acquires information indicating the target value. The target value is set to an arbitrary value by the user.

[0058] The acquisition processing unit 110 also performs a process of acquiring tire information used in the pattern estimation process. Specifically, when the tire information input by a user at the information terminal 20 is transmitted from the information terminal 50 to the estimation device 10 via the network N1, the acquisition processing unit 110 acquires the tire information.

[0059] The tire information is information about a tire whose tread pattern is to be estimated by the pattern estimation process, such as tire size information, tire use (snow tire, summer tire, etc.), tire structure symbol, load index, maximum speed (maximum speed based on speed symbol), tire strength (ply rating), etc. The size information includes, for example, tire width, aspect ratio, rim diameter, tire outer diameter, etc.

[0060] The pattern estimation unit 111 performs processing for estimating a tire tread pattern capable of achieving the target value based on the target value acquired by the acquisition processing unit 110.

[0061] When the target value of the specific tire performance is acquired from the information terminal 20 together with a predetermined estimation request signal or a re-estimation request signal, the pattern estimation unit 111 estimates a tread pattern capable of achieving the target value, using the acquired target value, the optimization model 121, and the prediction model 122. In this embodiment, the pattern estimation unit 111 estimates the pattern information (feature amount) of a tread pattern capable of achieving the target value.

[0062] In this embodiment, the pattern estimation unit 111 calculates the pattern information for achieving the target value by optimizing input data including the pattern information used for prediction by the prediction model 122. In detail, the pattern information of the input data is optimized so that each predicted value indicating a physical property value of each of a plurality of tire performances predicted by the prediction model 122 falls within the allowable range of the preset target value. In this embodiment, when a predetermined estimation request signal or a re-estimation request signal is input, the pattern estimation unit 111 enables the optimization model 121 and inputs the initial input value to the input unit of the prediction model 122 to cause the optimization model 121 to search for an optimal solution. By repeating this search, a design variable that minimizes the calculated value of the objective function is identified. That is, the pattern information that achieves the target value is identified.

[0063] In addition, the pattern estimation unit 111 inputs the target value acquired by the acquisition processing unit 110 to the input unit of the optimization model 121, and sets the target value and its allowable range used during optimization by the optimization model 121.

[0064] In this embodiment, each target value of two or more of the specific tire performances is input to the input section of the optimization model 121. Then, the pattern estimation section 111 estimates a tread pattern capable of achieving all of the input target values.

[0065] Furthermore, the pattern estimation unit 111 optimizes the pattern information of the input data input to the prediction model 122 so as to satisfy a predetermined constraint condition set for the pattern information. This improves the accuracy of optimization. The constraint condition is, for example, the performance information and the tire information.

[0066] The estimated pattern estimated by the pattern estimation unit 111 is transmitted by the output processing unit 113 to the information terminal 20 via the communication unit 13 so as to be displayed on the display unit 23 of the information terminal 20 .

[0067] The performance prediction unit 112 predicts a tire performance value (performance value) corresponding to the estimated pattern based on the feature amount of the estimated pattern estimated by the pattern estimation unit 111. The tire performance predicted by the performance prediction unit 112 is a tire performance value of a tire having a tread pattern of the estimated pattern, and in particular, is a performance value of the specific tire performance closely related to the tread pattern.

[0068] Specifically, the performance prediction unit 112 inputs the pattern information (feature values) of the estimated pattern output as an optimal solution from the output unit of the optimization model 121 into the input unit of the prediction model 122, causes the prediction model 122 to predict a performance value of the tire performance according to the pattern information, and obtains the performance prediction value output from the output unit of the prediction model 122 as a prediction result.

[0069] The performance prediction value predicted by the performance prediction unit 112 is transmitted by the output processing unit 113 through the communication unit 13 to the information terminal 20 so as to be displayed on the display unit 23 of the information terminal 20 .

[0070] When the performance prediction value corresponding to the estimated pattern is predicted, the control unit 11 adds the performance prediction value, the tire information, and the estimated pattern to the teacher data 30B, and updates the contents of the teacher data 30B. The control unit 11 that performs such an update process functions as a teacher data update unit 114 in this embodiment.

[0071] Then, after the contents of the teacher data 30B are updated, the control unit 11 uses the updated teacher data 30B to train the prediction model 122. The control unit 11 that performs this process functions as the model training unit 115 in this embodiment.

[0072] The output processing unit 113 outputs the estimation result by the pattern estimation unit 111 and the prediction result by the performance prediction unit 112 to an external device via the communication unit 13. In this embodiment, the estimation result and the prediction result are transmitted to the information terminal 20. The information terminal 20 displays the estimation result and the prediction result on the display unit 23.

[0073] [Information terminal 20] The configuration of the information terminal 20 will be described below with reference to Fig. 4. Here, Fig. 4 is a block diagram showing the configuration of the information terminal 20.

[0074] As shown in Fig. 4, the information terminal 20 includes a control unit 21, a storage unit 22, a display unit 23, an operation unit 24, a communication unit 25, etc. The information terminal 20 is an information processing device or a terminal device used by a user. The user can input various information such as the tire information, the performance information, and the target values ​​used in the pattern estimation process by the estimation device 10 to the information terminal 20. The user can also input to the information terminal 20 the allowable range of the performance values ​​used in the pattern estimation process (see Fig. 10) by the estimation device 10.

[0075] The communication unit 25 is a communication interface for connecting the information terminal 20 to the network N1 and for executing data communication with the estimating device 10 through the network N1 in accordance with a predetermined communication protocol.

[0076] The storage unit 22 is a non-volatile storage medium such as a flash memory that stores various information. The storage unit 22 stores a control program 221 for causing the control unit 21 to execute various arithmetic processing, data used in the various arithmetic processing, and the like.

[0077] The display unit 23 is a display device such as a liquid crystal display or an organic EL display that displays various information. In response to an input request from a user, screens 230 to 234 showing various information are displayed on the display unit 23 by a display processing unit 213 described later. The operation unit 24 is an input device such as a mouse, a keyboard, or a touch panel that accepts an input operation by a user.

[0078] The control unit 21 controls the operation of each part of the information terminal 20. The control unit 21 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that executes various arithmetic processing. The ROM is a non-volatile storage medium in which control programs such as a BIOS and an OS for causing the CPU to execute various arithmetic processing are stored in advance. The RAM is a volatile or non-volatile storage medium that stores various information, and is used as a temporary storage memory (work area) for various arithmetic processing executed by the CPU. The control unit 21 controls the information terminal 20 by executing various control programs stored in advance in the ROM or the storage unit 22 by the CPU.

[0079] As shown in FIG. 4, the control unit 21 includes various processing units such as a tire information receiving unit 210, a performance information receiving unit 211, a target value receiving unit 212, a display processing unit 213, and a target value changing unit 216 (an example of a target value changing unit of the present disclosure). The control unit 21 functions as the various processing units by the CPU executing various arithmetic processing in accordance with the control program. The control unit 21 or the CPU is an example of a computer that executes the control program. Note that some or all of the processing units included in the control unit 21 may be configured with electronic circuits. The control program may also be a program for causing a plurality of processors to function as the various processing units.

[0080] The tire information receiving unit 210 performs a process of receiving the input of the tire information. Specifically, the tire information receiving unit 210 acquires information inputted to a tire information input screen 230 (see FIG. 5) displayed on the display unit 23.

[0081] 5, the tire information input screen 230 is an input screen for inputting specific numerical values ​​or evaluation values ​​of the tire information. The tire information input screen 230 has a plurality of input boxes corresponding to each piece of tire information. In each input box, the user can select a pull-down key using the operation unit 24, thereby specifying any of the numerical values ​​or evaluation values ​​from a pull-down menu.

[0082] When the next key 33 is pressed after the tire information is input on the tire information input screen 230, the input information is stored in the storage unit 22. Thereafter, the screen displayed on the display unit 23 is switched to the next performance information input screen 231 (see FIG. 6).

[0083] The performance information receiving unit 211 performs a process of receiving input of one or more tire performance values ​​of the tire and input of the allowable range of the performance values. Specifically, the performance information receiving unit 211 acquires information input to a performance information input screen 231 (see FIG. 6) displayed on the display unit 23.

[0084] As shown in Fig. 6, the performance information input screen 231 is an input screen for inputting performance information related to tire performance, specifically, tire performance and the allowable range of the performance value. The performance information input screen 231 has a display frame 43 including an input frame 43A for inputting the tire performance and an input frame 43B for inputting the allowable range (lower limit value and upper limit value) of each tire performance. In the input frame 43A, the user can select the pull-down key 42 by the operation unit 24 to specify any of the tire performances from a pull-down menu. In the input frame 43B, the allowable range (lower limit value and upper limit value) of the specified tire performance can be arbitrarily input.

[0085] The tire performance that can be specified in the input box 43A is, for example, fuel economy performance, wet grip performance, dry grip performance, wear resistance performance, etc. All of these tire performances may be input in advance in the input box 43A, and the allowable ranges of all tire performances may be input in advance in the input box 43B.

[0086] When the next key 33 is pressed after the performance information is input on the performance information input screen 231, the input information is stored in the storage unit 22. Thereafter, the screen displayed on the display unit 23 is switched to the next target value input screen 232 (see FIG. 7).

[0087] The target value receiving unit 212 performs a process of receiving an input of a target value of the specific tire performance that the tire is desired to have. Specifically, the target value receiving unit 212 acquires information input to a target value input screen 232 (see FIG. 7) displayed on the display unit 23.

[0088] As shown in FIG. 7, the target value input screen 232 has an input frame 44 for inputting and displaying the target value for each of the plurality of tire performances. The input frame 44 has an input frame 45 (enclosed by a dashed line) for inputting and displaying the target value. The user can input any numerical target value into the input frame 45 corresponding to any specific tire performance that the user wants the tire to have by operating the operation unit 24. The user needs to input the target value for at least one tire performance out of the plurality of tire performances. Of course, the user may input the target values ​​for all tire performances. The specific tire performance refers to the tire performance for which the target value has been input.

[0089] When the registration key 32 is pressed after the target value is input on the target value input screen 232, information on the input target value is stored in the memory unit 22. Thereafter, the allowable range of tire performance and information on the target value are transmitted to the estimation device 10 together with a tread pattern estimation request signal.

[0090] The display processing unit 213 performs processing for displaying, on the display unit 23, information on the estimated pattern estimated by the pattern estimation unit 111 and information on the performance prediction value predicted by the performance prediction unit 112.

[0091] Specifically, when the display processing unit 213 receives the estimated pattern transmitted from the estimation device 10, it displays on the display unit 23 an estimated pattern screen 233 (see FIG. 8) including image data of the estimated pattern.

[0092] Furthermore, when the display processing unit 213 receives the performance prediction value transmitted from the estimation device 10 , it displays the performance prediction value on the estimated pattern screen 233 .

[0093] As shown in FIG. 8, the estimated pattern screen 233 has a display frame 46 for displaying information related to the estimated pattern, and a display frame 47 for displaying the performance prediction value.

[0094] An estimated pattern image (two-dimensional image or three-dimensional image) diagrammed from the pattern information (feature amount) indicating the estimated pattern is displayed in a display frame 46. Also, a display frame 47 displays the tire performance inputted in the input frame 43A of the performance information input screen 231, its performance predicted value, and the target value.

[0095] Furthermore, the display processing unit 213 performs processing for displaying, on the display unit 23, a graph indicating the performance predicted value for each tire performance input in the input frame 43A of the performance information input screen 231. Specifically, the display processing unit 213 displays, on the display unit 23, a predicted performance graph screen 234 (see FIG. 9 ) including the above-mentioned display frame 47 and a display frame 48 for displaying a radar chart 49 (one example of a graph of the present disclosure).

[0096] 9 shows a radar chart 49 including numbers corresponding to the nine tire performances and predicted performance values ​​corresponding to each number. The radar chart 49 is a polygonal graph showing the predicted values ​​of each tire performance, and each tire performance and its predicted performance values ​​are reflected in the graph. The radar chart 49 is displayed with five scales from 0 to 4, and the lower limit of the predetermined allowable range is set to 0, and the upper limit of the allowable range is set to 4, and the scale positions of the predicted performance values ​​are determined based on this range. When the next key 33 on the estimated pattern screen 233 is pressed, the screen displayed on the display unit 23 is then switched to a predicted performance graph screen 234 (see FIG. 9).

[0097] In this embodiment, the display frame 47 of the estimated pattern screen 233 or the predicted performance graph screen 234 is configured so that the numerical value of the displayed content can be changed. If a target value has already been input, the numerical value of the target value can be changed. If a target value has not been input, a new numerical value can be input in the blank space for the target value. The user can change the display content of the target value in the display frame 47 within the allowable range by operating the operation unit 24.

[0098] After the estimated pattern is estimated, the target value change unit 216 performs a process of changing the target value used in estimating the estimated pattern. Specifically, when the numerical value of the target value in the display frame 47 is changed, the target value change unit 216 accepts an input of the changed target value and stores it in the storage unit 22. Furthermore, when the target value change key 35 is pressed after the numerical value of the target value is changed, the target value change unit 216 transmits information on the changed target value together with a tread pattern re-estimation request signal to the estimation device 10.

[0099] [Pattern estimation process] Hereinafter, the pattern estimation method of the present disclosure will be described with reference to an example of the procedure of the pattern estimation process executed in the estimation system 100, with reference to the flowchart in Fig. 10. Note that one or more steps included in the pattern estimation process may be omitted as appropriate, and the steps may be executed in a different order as long as the same operational effect is achieved.

[0100] First, in step S11, the control unit 21 of the information terminal 20 determines whether the tire information, the performance information, and the target value have been input. When the tire information and the target value have been input, the control unit 21 transmits an estimation request signal together with the tire information, the performance information, and the target value to the estimation device 10 (S12).

[0101] In the next step S13, when the control unit 11 of the estimation device 10 receives the estimation request signal, the control unit 11 acquires the tire information, the performance information, and the target value transmitted together with the estimation request signal. Note that step S13 is an example of a target value acquisition step of the present disclosure.

[0102] Upon receiving the estimation request signal, the control unit 11 of the estimation device 10 enables the optimization model 121 and the prediction model 122 to be operable, and outputs an estimation execution signal to the pattern estimation unit 111 to execute the estimation process (S14). In this case, the pattern estimation unit 111 inputs the target value transmitted from the information terminal 20 to the input unit of the optimization model 121 as minimum information required for the estimation process, and also inputs the initial input value to the input unit of the prediction model 122, causing the optimization model 121 and the prediction model 122 to execute a search for an optimal solution (S15). In this embodiment, the control unit 11 inputs the performance information and the tire information transmitted from the information terminal 20 to the input unit of the optimization model 121 as constraint conditions, in addition to the target value.

[0103] In the next step S16, the control unit 11 judges whether or not the estimated pattern has been output from the output unit of the optimization model 121 within a predetermined time. If the estimated pattern has not been output even after the predetermined time has elapsed, an error signal is output to the information terminal 20 (S23). On the other hand, if the estimated pattern has been output from the output unit of the optimization model 121 as an optimal solution, the process proceeds to the next step S17.

[0104] In step S17, the control unit 11 outputs a prediction execution signal to the performance prediction unit 112 to execute the performance prediction process. Specifically, the control unit 11 inputs, to an input unit of the prediction model 122, pattern information indicating the estimated pattern (estimated pattern information) output from the output unit of the optimization model 121 and the tire information used in the estimation process, and causes the prediction model 122 to perform normal prediction processing.

[0105] In the next step S18, the control unit 11 judges whether or not the performance prediction value has been output from the output unit of the prediction model 122 within a predetermined time. If the performance prediction value has not been output even after the predetermined time has elapsed, an error signal is output to the information terminal 20 (S23). On the other hand, if the performance prediction value has been output from the output unit of the prediction model 122, the process proceeds to the next step S19, where the control unit 11 transmits the estimated pattern and the performance prediction value to the information terminal 20.

[0106] When the control unit 21 of the information terminal 20 receives the estimated pattern and the predicted performance value from the estimation device 10, in step S20, the control unit 21 displays the estimated pattern and the predicted performance value on the display unit 23. Specifically, the control unit 21 displays an estimated pattern screen 233 (see FIG. 8) including the estimated pattern image (two-dimensional image or three-dimensional image) and the predicted performance value corresponding to the estimated pattern on the display unit 23. Then, on condition that the next key 33 is pressed, a predicted performance graph screen 234 (see FIG. 9) including the predicted performance value and a graph thereof is displayed on the display unit 23.

[0107] In the next step S21, the control unit 21 determines whether or not the numerical value of the target value displayed in the display frame 47 of the estimated pattern screen 233 or the predicted performance graph screen 234 has been changed. If the target value has not been changed, the series of processes ends.

[0108] When it is determined in step S21 that the target value has been changed, the control unit 21 transmits a re-estimation request signal together with the changed target value to the estimation device 10 (S22). When the estimation device 10 receives the re-estimation request signal, the control unit 11 repeatedly executes the processes from step S14 onward.

[0109] In this manner, in the estimation system 100 of this embodiment, when the target value of the specific tire performance is acquired by the acquisition processing unit 110, a tire tread pattern capable of achieving the target value is estimated by the pattern estimation unit 111 based on the target value. Therefore, as long as the target value of the specific tire performance of the tire to be developed is determined, the user can input the target value into the information terminal 20 to obtain information on the tread pattern (estimated pattern) that will achieve the target value.

[0110] Furthermore, in this embodiment, if the target value is changed after the pattern estimation unit 111 estimates the estimated pattern, the pattern estimation unit 111 estimates the tread pattern again based on the changed target value. Therefore, if the estimated pattern of the tire to be developed is not a desired shape, the user can have the pattern estimation unit 111 estimate the tread pattern again simply by changing the target value or additionally inputting a target value that was not set.

[0111] In the present embodiment, the tread pattern is estimated based on the target value and tire information of the tire that is the estimation target, so that the tread pattern can be estimated more accurately.

[0112] Moreover, the pattern estimation unit 111 is configured to use the optimization model 121 to search for pattern information to be input to the prediction model 122. Therefore, it is possible to easily obtain a highly accurate estimation result (estimated pattern).

[0113] Furthermore, the estimation system 100 of this embodiment includes not only the pattern estimation unit 111 but also a performance prediction unit 112 that predicts a tire performance value corresponding to the estimated pattern based on the feature amount of the estimated pattern. Therefore, the user can grasp not only the estimated pattern but also the predicted performance value of a tire having a tread pattern of the estimated pattern.

[0114] Furthermore, the estimated pattern and a radar chart 49 showing the performance prediction values ​​are displayed on the information terminal 20. This allows the user to easily grasp the balance of the performance prediction values ​​for each tire performance and easily compare the performance prediction values. Note that, although an example in which the radar chart 49 showing the performance prediction values ​​is displayed on the display unit 23 has been described in the present embodiment, the graph displayed on the display unit 23 is not limited to a radar chart and may be another graph such as a scatter plot or a broken line.

[0115] In the present embodiment, a processing example has been described in which, when target values ​​for two or more of the specific tire performance are input to the input section of the optimization model 121, the pattern estimation section 111 estimates a tread pattern capable of achieving all of the input target values. However, the present disclosure is not limited to such a processing example, and may be, for example, a processing example in which, even when target values ​​for a plurality of specific tire performance are input to the optimization model 121, a tread pattern capable of achieving at least one target value is estimated and output.

[0116] In the above embodiment, the estimation system 100 is illustrated as having a configuration in which the estimation device 10 is provided with the acquisition processing unit 110, the pattern estimation unit 111, the performance prediction unit 112, the output processing unit 113, the teacher data update unit 114, and the model learning unit 115, and the information terminal 20 is provided with the tire information reception unit 210, the target value reception unit 212, the display processing unit 213, and the target value change unit 216, but the present disclosure is not limited to this configuration. For example, at least one or more of the components provided in the information terminal 20 may be provided in the estimation device 10, and at least one or more of the components provided in the estimation device 10 may be provided in the information terminal 20.

[0117] [Second embodiment] Hereinafter, a prediction system 200 according to a second embodiment of the present disclosure will be described with reference to Figs. 11 to 16. Note that the terms used in this embodiment have the same definitions or meanings as those used in the first embodiment. In addition, for configurations or parts in this embodiment that are common to the first embodiment, please refer to the description in the first embodiment. In addition, for configurations or parts that are common to the first embodiment, the same reference numerals as those used in the description of the first embodiment are used in each drawing, and the description thereof will be omitted.

[0118] 11 is a diagram showing a configuration of a prediction system 200 according to a second embodiment of the present disclosure. The prediction system 200 of the present embodiment is mainly composed of a prediction device 40, an information terminal 50, and a database 30. The prediction system 200 is an example of a tire performance prediction system according to the present disclosure.

[0119] The prediction system 200 is a system that predicts a tire performance value (performance value) corresponding to the tread pattern of an existing tire based on the pattern information indicating the tread pattern of the tire. In this embodiment, the prediction system 200 is configured to be able to predict a tire performance value corresponding to the tread pattern based on the pattern information including the feature amount of the tread pattern. The prediction result by the prediction system 200 is used for the development of the tire, performance testing of the tire, performance evaluation of the tire, etc.

[0120] [Configuration of prediction system 200] As shown in FIG. 11, the prediction system 200 includes a prediction device 40, an information terminal 50, and a database 30, which are communicatively connected to each other via a network N1.

[0121] The database 30 may be provided in the prediction device 40 or the information terminal 50. In the present embodiment, a configuration in which the information terminal 50 is connected to the network N1 is illustrated, but each component and each function of the information terminal 50 may be installed in the prediction device 40.

[0122] The prediction device 40 acquires the pattern information of the tire that is the prediction target transmitted from the information terminal 50, and performs a process of predicting the tire performance value corresponding to the tread pattern of the tire based on the acquired pattern information. Specifically, the prediction device 40 predicts a tire performance value corresponding to the tread pattern of the existing tire using various information such as the pattern information transmitted from the information terminal 50, the above-mentioned prediction model 122 (see FIG. 3) that is constructed in advance, and the like. The prediction result (performance prediction value) by the prediction model 122 is output to the information terminal 50 and displayed on a display unit 53 of the information terminal 50.

[0123] The prediction device 40 is a hardware similar to that of the above-mentioned estimation device 10, and is an information processing device capable of executing various arithmetic processing, such as a server computer, a cloud server, or a personal computer connected to the network N1. A program or computer software for operating the prediction system 200 is installed in the prediction device 40.

[0124] The information terminal 50 is the same hardware as the above-mentioned information terminal 20, and is an information processing device or terminal device used by a user. The user inputs various information used in various arithmetic processing such as the performance prediction processing (see FIG. 16) executed in the prediction device 40 to the information terminal 50. Therefore, a program or computer software is installed in the information terminal 50 for transmitting the various information and control signals to the prediction device 40 in cooperation with the prediction system 200 and displaying the prediction result on a display screen.

[0125] [Prediction Device 40] The configuration of the prediction device 40 will be described below with reference to Fig. 12. Here, Fig. 2 is a block diagram showing the configuration of the prediction device 40.

[0126] The prediction device 40 is for realizing the prediction system 200 of this embodiment, and predicts the performance prediction value of the tire performance corresponding to the tread pattern of the tire to be predicted using the above-mentioned prediction model 122 (see FIG. 3).

[0127] As shown in FIG. 12, the prediction device 40 includes a control unit 41, a storage unit 12, a communication unit 13, a display unit 14, and an operation unit 15.

[0128] The communication unit 13 is a communication interface for connecting the prediction device 40 to the network N1 and for executing data communication with the information terminal 50 and the database 30 through the network N1.

[0129] The storage unit 12 is a non-volatile storage medium, and stores a control program 420 and a prediction model 122. Note that the prediction model 122 may be realized as an electronic circuit having a memory in which the prediction model 122 is stored.

[0130] The control program 420 is non-temporarily recorded on a computer-readable recording medium such as a CD or a DVD, and is read from the recording medium by a reading device (not shown) such as a CD drive or a DVD drive electrically connected to the prediction device 40 and copied to the storage unit 12. Note that the control program 420 may be read from an external storage connected to the network N1, input via the communication unit 13, and copied to the storage unit 12.

[0131] The control program 420 is a program for executing a performance prediction process (see FIG. 16) described later using the prediction model 122. Note that instead of the control program 420, a program for causing the control unit 41 to execute the performance prediction process (FIG. 16) may be stored in the storage unit 12.

[0132] The prediction model 122 is the same as the trained model used in the performance prediction process (see step S17 in FIG. 10) by the performance prediction unit 112 described in the first embodiment. In this embodiment, a performance prediction unit 412, which will be described later, provided in the control unit 41 of the prediction device 40 predicts numerical values ​​of tire performance according to the tread pattern of the tire to be predicted using the prediction model 122. When the pattern information (feature amount of the tread pattern) of the tire to be predicted acquired from the information terminal 50 is input to the input unit of the prediction model 122 as an explanatory variable, the prediction model 122 predicts numerical values ​​of tire performance according to the tread pattern of the tire to be predicted, and outputs the prediction result (performance prediction value) from the output unit as a response variable. The input data input to the prediction model 122 includes the tire information (explanatory variable) related to the tire to be predicted in addition to the pattern information.

[0133] It should be noted that when image data of the tread pattern of the tire to be predicted is acquired from the information terminal 50 instead of the pattern information, a performance prediction unit 412 described below extracts the pattern information (feature values) of the tread pattern from the image data, and the pattern information is input to the input unit of the prediction model 122.

[0134] In this embodiment, the prediction model 122 may also include a known function (prediction function) that returns a predicted value (output data) for an input value (input data). A performance prediction unit 412 described later may be configured as a performance prediction value calculation unit that outputs the performance prediction value by the prediction function without using the prediction model 122.

[0135] The control unit 41 controls the operation of each unit of the prediction device 40. The control unit 41 has the same configuration as the control unit 11 of the first embodiment, and includes control devices such as a CPU, a ROM, and a RAM. The control unit 41 controls the prediction device 40 by the CPU executing various control programs stored in advance in the ROM or the storage unit 12.

[0136] As shown in FIG. 12, the control unit 41 includes various processing units such as an acquisition processing unit 410 (an example of a pattern information acquisition unit of the present disclosure), a performance prediction unit 412 (an example of a performance prediction unit of the present disclosure), and a performance display processing unit 413 (an example of a performance display processing unit of the present disclosure).

[0137] The control unit 41 functions as the various processing units by the CPU executing various arithmetic processing in accordance with the control program. The control unit 41 or the CPU is an example of a computer that executes the control program. Some or all of the processing units included in the control unit 41 may be configured with electronic circuits. The control program may also be a program for causing a plurality of processors to function as the various processing units. The control program may also be a program for causing a graphics processing unit (GPU) to function as the various processing units (such as the performance prediction unit 412).

[0138] When information set or input on the information terminal 50 is transferred from the information terminal 50, the acquisition processing unit 410 receives the information.

[0139] In this embodiment, the acquisition processing unit 410 performs processing to acquire the pattern information of a tire to be predicted, which is used in the performance prediction processing (see FIG. 16) performed in the prediction device 40. Specifically, when the pattern information input to the information terminal 50 by a user is transmitted from the information terminal 50 to the prediction device 40 via the network N1, the acquisition processing unit 410 acquires the pattern information.

[0140] The acquisition processing unit 410 also performs a process of acquiring tire information used in the performance prediction process (see FIG. 16). Specifically, when the tire information input by a user at the information terminal 50 is transmitted from the information terminal 50 to the prediction device 40 via the network N1, the acquisition processing unit 410 acquires the tire information.

[0141] The tire information is information about an existing tire that is the prediction target, such as tire size information, tire usage (snow tire, summer tire, etc.), tire structure symbol, load index, maximum speed (maximum speed based on speed symbol), tire strength (ply rating), etc. The size information includes, for example, tire width, aspect ratio, rim diameter, tire outer diameter, etc.

[0142] The performance prediction unit 412 predicts a tire performance value (performance value) corresponding to the tread pattern of the tire that is the prediction target, based on the feature amount of the tread pattern of the tire.

[0143] When the performance prediction unit 412 acquires the pattern information (feature quantities) along with a predetermined prediction request signal or a re-prediction request signal from the information terminal 50, it predicts the tire performance value (performance value) corresponding to the tread pattern using the acquired pattern information and the prediction model 122.

[0144] Specifically, the performance prediction unit 412 inputs the pattern information (feature) acquired by the acquisition processing unit 410 to an input unit of the prediction model 122, causes the prediction model 122 to predict a performance value of the tire performance according to the pattern information, and acquires a performance prediction value output from an output unit of the prediction model 122 as a prediction result.

[0145] In this embodiment, the performance prediction unit 412 inputs not only the pattern information but also the tire information as explanatory variables to the input unit of the prediction model 122, and causes the prediction model 122 to predict tire performance values ​​(performance values) according to the tread pattern. This improves the prediction accuracy of tire performance.

[0146] In addition, when image data of the tread pattern of the tire to be predicted is acquired, the performance prediction unit 412 extracts the pattern information (feature values) of the tread pattern from the image data, and inputs the pattern information to the input unit of the prediction model 122.

[0147] The performance display processing unit 413 outputs the prediction result by the performance prediction unit 412 to an external device via the communication unit 13. In order to display the performance prediction value predicted by the performance prediction unit 412 on the display unit 23 of the information terminal 50, the performance display processing unit 413 transmits the performance prediction value to the information terminal 50 via the communication unit 13. In this embodiment, the performance display processing unit 413 also transmits the pattern information used in the prediction process to the information terminal 50 in order to display the pattern information together with the performance prediction value on the display unit 23. The information terminal 50 displays the performance prediction value and the pattern information on the display unit 23.

[0148] [Information terminal 50] The configuration of the information terminal 50 will be described below with reference to Fig. 13. Fig. 13 is a block diagram showing the configuration of the information terminal 50.

[0149] 13, the information terminal 50 includes a control unit 51, a storage unit 22, a display unit 23, an operation unit 24, and a communication unit 25. The information terminal 50 is an information processing device or a terminal device used by a user. The user can input various information such as the pattern information and the tire information used in the performance prediction process (see FIG. 16) executed by the prediction device 40 to the information terminal 50.

[0150] The communication unit 25 is a communication interface for connecting the information terminal 50 to the network N1 and for executing data communication with the prediction device 40 through the network N1.

[0151] The storage unit 22 is a non-volatile storage medium, and stores a control program 521, data used in various arithmetic processing, and the like.

[0152] The display unit 23 is a display device such as a liquid crystal display or an organic EL display that displays various information.

[0153] The control unit 51 controls the operation of each unit of the information terminal 50. The control unit 51 has a configuration similar to that of the control unit 21 of the first embodiment, and includes control devices such as a CPU, a ROM, and a RAM. The control unit 51 controls the information terminal 50 by executing various control programs stored in advance in the ROM or the storage unit 22 by the CPU.

[0154] As shown in FIG. 13, the control unit 51 includes various processing units such as a tire information receiving unit 210, a pattern information receiving unit 512, a display processing unit 513, and a feature amount changing unit 516 (an example of a feature amount changing unit in the present disclosure). The control unit 51 functions as the various processing units by the CPU executing various arithmetic processing in accordance with the control program. The control unit 51 or the CPU is an example of a computer that executes the control program. Note that some or all of the processing units included in the control unit 51 may be configured with electronic circuits. The control program may also be a program for causing a plurality of processors to function as the various processing units.

[0155] The tire information receiving unit 210 performs a process of receiving the input of the tire information. Specifically, the tire information receiving unit 210 acquires information inputted to a tire information input screen 230 (see FIG. 5) displayed on the display unit 23.

[0156] When the next key 33 is pressed after the tire information has been input on the tire information input screen 230, the input information is stored in the storage unit 22.

[0157] The pattern information receiving unit 512 performs a process of receiving input of the pattern information including the feature amount of the tread pattern of the tire to be predicted.

[0158] The pattern information is a feature of the tread pattern, and includes, for example, a feature (first feature) based on the groove shape such as a groove angle, a groove width, a groove depth, and a groove length, a feature (second feature) such as a composition ratio of each groove shape and a ratio of the groove area to the tread surface, and a feature (third feature) such as an evaluation value (connectivity) of the connection state of each groove. These feature amounts can be obtained, for example, by actually measuring the tread pattern of the tire to be predicted. Alternatively, these feature amounts may be obtained by analyzing an image of the tread pattern of the tire to be predicted. Alternatively, these feature amounts may be obtained from the pattern information downloaded from a tire manufacturer's website or the like. The pattern information is input to the information terminal 50 by a user, and then stored in the storage unit 22 and transmitted to the prediction device 40 for the performance prediction process by the prediction device 40.

[0159] The display processing unit 513 performs processing for displaying, on the display unit 23, information relating to the performance predicted value predicted by the performance predicting unit 412.

[0160] Specifically, when the display processing unit 513 receives the performance prediction value transmitted from the prediction device 40, it displays on the display unit 23 the predicted performance display screen 235 (see FIG. 14) including the performance prediction value.

[0161] 14, the predicted performance display screen 235 has a display frame 61 for displaying the predicted tire performance and its performance predicted value (prediction result). The display processing unit 513 displays the predicted tire performance and its performance predicted value in the display frame 61.

[0162] Further, the display processing unit 513 performs processing for displaying on the display unit 23 a graph showing the performance prediction value for each predicted tire performance.

[0163] The predicted performance display screen 235 has a display frame 62 for displaying the graph. The display processing unit 513 displays in the display frame 62 a radar chart 63 including the tire performance and its performance prediction values.

[0164] The predicted performance display screen 235 in Fig. 14 shows a radar chart 63 including numbers corresponding to the nine tire performance items and predicted performance values ​​corresponding to each number. The radar chart 63 is a polygonal graph showing the predicted values ​​of each tire performance item, and each tire performance item and its predicted performance value are reflected in the graph. The radar chart 63 is displayed with five scales ranging from 0 to 4, and for example, the lower limit of a predetermined allowable range is set to 0, and the upper limit of the allowable range is set to 4, and the scale positions of the predicted performance values ​​are determined based on this range.

[0165] Furthermore, the display processing unit 513 performs processing for displaying the feature amount used in the performance prediction processing on the display unit 23. Specifically, upon receiving the performance prediction value transmitted from the prediction device 40, the display processing unit 513 displays the feature amount display screen 236 (see FIG. 15 ) on the display unit 23.

[0166] 15, the feature amount display screen 236 has a display frame 64 for displaying the feature amounts used in the performance prediction process, and a display frame 62 for displaying a radar chart 63. The display processing unit 513 displays the name of each feature amount and the value of each feature amount (numeric value, level value, rank value, etc.) in the display frame 64 of the feature amount display screen 236.

[0167] In this embodiment, the display frame 64 of the feature display screen 236 is configured so that the value of the feature in the display frame 64 can be changed. If a feature value has been input, the value can be changed. Also, if there is a feature value that has a blank value, a new value can be input into the blank for that feature. The user can arbitrarily change the value of the feature in the display frame 64 by operating the operation unit 24.

[0168] When the next key 33 is pressed on the predicted performance display screen 235, the screen displayed on the display unit 23 is switched to a feature display screen 236 (see FIG. 15).

[0169] After the performance prediction value is predicted, the feature quantity change unit 516 performs a process of changing the value of the feature quantity used in the performance prediction process. Specifically, when the value of the feature quantity in the display frame 64 is changed, the feature quantity change unit 516 accepts an input of the changed value and stores it in the storage unit 22. Furthermore, when the feature quantity change key 36 is pressed after the value of the feature quantity is changed, the feature quantity change unit 516 transmits to the prediction device 40 the value information of the changed feature quantity together with a re-prediction request signal for re-predicting tire performance.

[0170] [Performance prediction processing] 16, the performance prediction method of the present disclosure will be described along with an example of the procedure of the performance prediction process executed in the prediction system 200. Note that one or more steps included in the performance prediction process may be omitted as appropriate, and the steps may be executed in a different order as long as the same action and effect is achieved.

[0171] First, in step S31, the control unit 51 of the information terminal 50 determines whether or not the tire information and the pattern information have been input. When the tire information and the pattern information have been input, the control unit 51 transmits a prediction request signal together with the tire information and the pattern information to the prediction device 40 (S32).

[0172] In the next step S33, when the control unit 41 of the prediction device 40 receives the prediction request signal, it acquires the tire information and the pattern information transmitted together with the prediction request signal. Note that step S33 is an example of a pattern information acquisition step of the present disclosure.

[0173] Upon receiving the prediction request signal, the control unit 41 of the prediction device 40 enables the prediction model 122 to be operable, and outputs a prediction execution signal to the performance prediction unit 112 to execute the prediction process (S34). Then, the control unit 41 inputs the feature amounts in the pattern information sent from the information terminal 50 to the input unit of the prediction model 122 as the minimum information required for the prediction process (S35). In this embodiment, the control unit 41 inputs the tire information sent from the information terminal 50 to the input unit of the prediction model 122 in addition to the feature amounts.

[0174] In the next step S36, the control unit 41 determines whether or not the performance prediction value has been output from the output unit of the prediction model 122 within a predetermined time. If the performance prediction value has not been output even after the predetermined time has elapsed, an error signal is output to the information terminal 50 (S43).

[0175] On the other hand, if the performance prediction value is output from the output section of the prediction model 122, in the next step S37, the control section 41 transmits the performance prediction value and the feature amount used in the performance prediction process to the information terminal 50.

[0176] When the control unit 51 of the information terminal 50 receives the performance prediction value and the feature amount from the prediction device 40, in step S38, the control unit 51 displays the performance prediction value and the feature amount on the display unit 23. Specifically, the control unit 51 displays a predicted performance display screen 235 (see FIG. 14) including the performance prediction value on the display unit 23. Then, on condition that the next key 33 is pressed, the control unit 51 displays a feature amount display screen 236 (see FIG. 15) including the feature amount on the display unit 23.

[0177] In the next step S39, the control unit 51 determines whether or not the value of the feature amount displayed in the display frame 61 of the feature amount display screen 236 has been changed. If the value of the feature amount has not been changed, the series of processes ends.

[0178] When it is determined in step S39 that the value of the feature has been changed, the control unit 51 transmits a re-prediction request signal together with the changed value of the feature to the prediction device 40 (S40). When the prediction device 40 receives the re-prediction request signal, the control unit 41 repeatedly executes the processes from step S34 onward.

[0179] In this way, in the prediction system 200 of this embodiment, when the pattern information of a tire to be predicted is acquired by the acquisition processing unit 410, the tire performance value of the tire to be predicted is predicted by the performance prediction unit 412 based on the feature amount included in the pattern information. Therefore, if the user knows information on the tread pattern of a tire whose tire performance is unknown, the user can input the pattern information of the tire into the information terminal 50 to obtain a predicted value of the tire performance of the tire to be predicted (performance predicted value).

[0180] In this embodiment, if the feature quantity is changed after the performance prediction value is predicted by the performance prediction unit 412, the performance prediction unit 412 predicts the tire performance values ​​again based on the changed feature quantity values. Therefore, the user can easily understand how the predicted tire performance values ​​will change depending on how the feature quantities of the tire tread pattern are changed.

[0181] In the present embodiment, the performance prediction value is predicted based on the values ​​of the feature quantities and tire information of the tire to be predicted, so that the performance of the tire to be predicted can be predicted more accurately.

[0182] Moreover, the performance prediction unit 412 is configured to cause the prediction model 122, which has been trained to output the performance prediction value, to output the performance prediction value. Therefore, by simply increasing the learning degree of the prediction model 122, a highly accurate prediction result (performance prediction value) can be easily obtained.

[0183] Furthermore, the performance prediction values ​​and a radar chart 49 showing the performance prediction values ​​are displayed on the information terminal 50. This allows the user to easily grasp the balance of the performance prediction values ​​for each tire performance and easily compare the performance prediction values. Note that, although an example in which the radar chart 49 showing the performance prediction values ​​is displayed on the display unit 23 has been described in the present embodiment, the graph displayed on the display unit 23 is not limited to a radar chart and may be another graph such as a scatter plot or a broken line.

[0184] In the above embodiment, the prediction system 200 is exemplified in a configuration in which the prediction device 40 is provided with the acquisition processing unit 410, the performance prediction unit 412, the performance display processing unit 413, etc., and the information terminal 50 is provided with the tire information receiving unit 210, the pattern information receiving unit 512, the display processing unit 513, the feature amount changing unit 516, etc., but the present disclosure is not limited to this configuration. For example, at least one or more of the components provided in the information terminal 50 may be provided in the prediction device 40, and at least one or more of the components provided in the prediction device 40 may be provided in the information terminal 50.

[0185] The above-described embodiments of the present disclosure include the following disclosure items (1) to (15).

[0186] The tread pattern estimation system according to disclosed item (1) includes a target value acquisition unit that acquires a target value of tire performance, a pattern estimation unit that estimates a tire tread pattern capable of achieving the target value based on the target value, and an output processing unit that outputs the estimated pattern estimated by the pattern estimation unit.

[0187] Disclosure (2) is the tread pattern estimation system according to disclosure (1), further comprising a target value modification unit that modifies the target value after estimation by the pattern estimation unit, and when the target value is modified by the target value modification unit, the pattern estimation unit re-estimates the tread pattern based on the modified target value.

[0188] Disclosed item (3) is a tread pattern estimation system according to disclosed item (1) or (2), further comprising a tire information acquisition unit that acquires tire information regarding the tire, and the pattern estimation unit estimates the tread pattern based on the target value and the tire information.

[0189] Disclosed item (4) is a tread pattern estimation system according to any one of disclosed items (1) to (3), wherein the pattern estimation unit includes a prediction model trained by machine learning to output a predicted value of the tire performance based on pattern information including features of a tread pattern of the tire, and an optimization model that optimizes the pattern information so that the predicted value by the prediction model falls within an acceptable range of the target value, and estimates a tread pattern identified by the pattern information optimized by the optimization model as a tread pattern that can achieve the target value.

[0190] Disclosed item (5) is a tread pattern estimation system according to any one of disclosed items (1) to (4), further comprising a performance prediction unit that predicts a value of the tire performance corresponding to the estimated pattern based on features of the estimated pattern estimated by the pattern estimation unit, and the output processing unit displays the estimated pattern and the predicted value predicted by the performance prediction unit on a predetermined display unit.

[0191] Disclosed item (6) is the tread pattern estimation system of disclosed item (5), wherein the output processing unit outputs a graph showing the predicted value for each tire performance to the display unit.

[0192] Disclosed item (7) is a tread pattern estimation system according to any one of disclosed items (1) to (6), wherein the tire performance includes at least two of fuel economy performance, wet grip performance, dry grip performance, and wear resistance performance, and the pattern estimation unit estimates the tread pattern capable of achieving any one or more of target values ​​for each of the plurality of tire performances.

[0193] The tread pattern estimation method of disclosed item (8) is a method executed by one or more processors, comprising: a target value acquisition step of acquiring a target value of tire performance; and an estimation step of estimating, based on the target value, a tire tread pattern that can achieve the target value.

[0194] The program related to disclosed item (9) is a program for causing one or more processors to execute a target value acquisition step of acquiring a target value of tire performance, and an estimation step of estimating a tire tread pattern capable of achieving the target value based on the tire performance and the target value.

[0195] The tire performance prediction system according to disclosed item (10) includes a pattern information acquisition unit that acquires pattern information including features of a tire tread pattern, a performance prediction unit that predicts a tire performance value based on the pattern information, and a performance display processing unit that displays the tire performance predicted value by the performance prediction unit on a specified display unit.

[0196] Disclosure (11) provides the tire performance prediction system according to disclosure (10), wherein the performance display processing unit displays the predicted value and the feature on the display unit and further includes a feature change unit that changes the feature displayed on the display unit, and when the feature is changed by the feature change unit, the performance prediction unit re-predicts a value of the tire performance based on the pattern information including the feature after the change.

[0197] Disclosure (12) is the tire performance prediction system according to disclosure (10) or (11), wherein the performance display processing unit displays a graph showing the predicted value on the display unit.

[0198] Disclosed item (13) is a tire performance prediction system according to any one of disclosed items (10) to (12), wherein the performance prediction unit inputs the pattern information to a prediction model that has been machine-trained to output the predicted value, thereby causing the prediction model to output the predicted value.

[0199] The tire performance prediction method according to disclosed item (14) is a method executed by one or more processors, which includes a pattern information acquisition step of acquiring pattern information including features of a tire tread pattern, and a prediction step of predicting a tire performance value based on the pattern information.

[0200] The program related to disclosed item (15) is a program for causing one or more processors to execute a pattern information acquisition step of acquiring pattern information including features of a tire tread pattern, and a prediction step of predicting a tire performance value based on the pattern information. [Explanation of symbols]

[0201] 10: Estimation device 11: Control section 20: Information terminal 21: Control section 30: Database 30A: Reference Data 30B: Teacher data 100: Estimation system 110: Acquisition processing unit 111: Pattern estimation unit 112: Performance Prediction Department 113: Output processing section 114: Teacher data update unit 115: Model Learning Department 121: Optimization Model 122: Predictive Model 210: Tire Information Reception Department 211: Performance information reception department 212: Target value reception unit 213: Display processing unit 216: Target value change unit 200: Prediction system 410: Acquisition processing unit 412: Performance Prediction Department 413: Performance display processing unit 512: Pattern information reception unit 513: Display processing unit 516: Feature modification unit

Claims

1. a target value acquisition unit that acquires a target value of tire performance; a pattern estimation unit that estimates a tire tread pattern that can achieve the target value based on the target value; an output processing unit that outputs an estimated pattern estimated by the pattern estimation unit; A tread pattern estimation system comprising:

2. A target value change unit that changes the target value after the estimation by the pattern estimation unit, the pattern estimation unit, when the target value is changed by the target value changing unit, re-estimating the tread pattern based on the changed target value. The tread pattern estimation system according to claim 1 .

3. A tire information acquisition unit that acquires tire information related to the tire is further provided, The pattern estimation unit estimates the tread pattern based on the target value and the tire information. The tread pattern estimation system according to claim 1 or 2.

4. The pattern estimation unit A prediction model trained by machine learning to output a prediction value of the tire performance based on pattern information including a feature amount of a tread pattern of the tire; an optimization model that optimizes the pattern information so that the predicted value by the prediction model falls within an allowable range of the target value, estimating a tread pattern specified by the pattern information optimized by the optimization model as a tread pattern capable of achieving the target value; The tread pattern estimation system according to claim 1 or 2.

5. a performance prediction unit that predicts a value of the tire performance corresponding to the estimated pattern based on the feature amount of the estimated pattern estimated by the pattern estimation unit, The output processing unit displays the estimated pattern and the predicted value predicted by the performance prediction unit on a predetermined display unit. The tread pattern estimation system according to claim 1 or 2.

6. The output processing unit outputs a graph indicating the predicted value for each tire performance to the display unit. The tread pattern estimation system according to claim 5 .

7. The tire performance includes at least two of fuel economy performance, wet grip performance, dry grip performance, and wear resistance performance, The pattern estimation unit estimates the tread pattern capable of achieving any one or more of the target values ​​of the tire performances. The tread pattern estimation system according to claim 1 or 2.

8. a target value acquisition step of acquiring a target value of tire performance; an estimation step of estimating a tire tread pattern capable of achieving the target value based on the target value; The tread pattern estimation method is executed by one or more processors.

9. a target value acquisition step of acquiring a target value of tire performance; an estimation step of estimating a tire tread pattern capable of achieving the target value based on the tire performance and the target value; A program for causing one or more processors to execute the above.

10. A pattern information acquisition unit that acquires pattern information including a feature amount of a tire tread pattern; a performance prediction unit for predicting tire performance values ​​based on the pattern information; a performance display processing unit that displays a predicted value of the tire performance predicted by the performance prediction unit on a predetermined display unit; A tire performance prediction system comprising:

11. the performance display processing unit displays the predicted value and the feature amount on the display unit; a feature amount changing unit that changes the feature amount displayed on the display unit, the performance prediction unit, when the feature amount is changed by the feature amount change unit, re-predicts the tire performance value based on the pattern information including the changed feature amount. The tire performance prediction system according to claim 10.

12. the performance display processing unit displays a graph indicating the predicted value on the display unit. The tire performance prediction system according to claim 10 or 11.

13. the performance prediction unit inputs the pattern information into a prediction model that has been machine-learned to output the predicted value, thereby causing the prediction model to output the predicted value. The tire performance prediction system according to claim 10 or 11.

14. A pattern information acquisition step of acquiring pattern information including a feature amount of a tire tread pattern; a prediction step of predicting a tire performance value based on the pattern information; The tire performance prediction method is executed by one or more processors.

15. A pattern information acquisition step of acquiring pattern information including a feature amount of a tire tread pattern; a prediction step of predicting a tire performance value based on the pattern information; A program for causing one or more processors to execute the above.

Citation Information

Patent Citations

  • Method for learning tire performance prediction model, method for predicting tire performance, system and program

    JP2021195038A

  • Method for learning tire performance prediction model, method for predicting tire performance, system and program

    JP2022090349A