A method and system for predicting tire inflation performance

Abstract

The application relates to the technical field of tires, in particular to a tire inflation performance prediction method and system. The method comprises the following steps: generating a plurality of tire categories according to preset tire evaluation indexes, and generating pretreatment strategies of the tire categories; establishing an original geometric model according to scheme parameters of a tire to be predicted, and generating a target pretreatment strategy of the tire to be predicted; generating a simulation result of the tire to be predicted according to the target pretreatment strategy and the original geometric model; establishing a plurality of tire categories according to tire evaluation indexes, and setting corresponding pretreatment strategies; and generating optimal gradual prestress parameters and mesh division schemes of different categories of tires, so that the original geometric model of the tire to be predicted is accurately processed, the data processing efficiency is improved, and the accuracy of the simulation result is improved. The method realizes accurate prediction of the performance of the tire to be predicted, quickly completes design scheme optimization iteration, and shortens the research and development cycle.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of tires, in particular to a tire inflation performance prediction method and system. BACKGROUND

[0002] The crown strip, as an important component of the tire framework material, plays a crucial role in constraining the tire circumferential deformation and maintaining the tire size stability. The nylon aramid blended crown strip has been increasingly widely applied due to its advantages in tire high-speed performance and handling stability.

[0003] Due to the high modulus characteristics of the blended crown strip, there is a large difference between the finished product profile of the tire after vulcanization and the mold profile. If the inflation performance is directly analyzed according to the mold profile, the simulation accuracy will be seriously affected, and the tire performance prediction will be affected. SUMMARY

[0004] The purpose of the application is to solve the above technical problems, and the application provides a tire inflation performance prediction method and system, which aims to improve the optimization iteration efficiency of the design scheme by realizing the inflation performance prediction of the design scheme.

[0005] In some embodiments of the application, a plurality of tire categories are established according to tire evaluation indexes, and corresponding preprocessing strategies are set to generate the best gradual pre-stress parameters and mesh division schemes of different categories of tires, so as to accurately process the original geometric model of the tire to be predicted, improve the data processing efficiency and the accuracy of the simulation results.

[0006] In some embodiments of the application, the parameters of the tire to be predicted are obtained through the design scheme, so as to construct the corresponding original geometric model, and the original geometric model is processed according to the corresponding preprocessing strategy, and based on the technology of gradual pre-stress, the performance of the tire to be predicted is accurately predicted, the design scheme optimization iteration is quickly completed, and the research and development cycle is shortened.

[0007] Some embodiments of the application provide a tire inflation performance prediction method, which comprises:

[0008] A plurality of tire categories are generated according to preset tire evaluation indexes, and a preprocessing strategy of each tire category is generated;

[0009] An original geometric model is established according to the scheme parameters of the tire to be predicted, and a target preprocessing strategy of the tire to be predicted is generated;

[0010] A simulation result of the tire to be predicted is generated according to the target preprocessing strategy and the original geometric model;

[0011] When generating a plurality of tire categories, it comprises:

[0012] A tire category number sequence A is established, A=(a1, a2…ai…an), wherein ai is the i-th tire category; and n is the number of tire categories.

[0013] In some embodiments of the present application, when the pre-processing strategy of each tire category is generated, the following steps are included:

[0014] ai is sequentially set as a target tire category according to the tire category number sequence A;

[0015] A sample data packet of the target tire category is generated;

[0016] An initial processing strategy of the target tire category is generated, and a simulation deviation of the initial processing strategy is generated according to the sample data packet;

[0017] It is determined whether to iteratively optimize the initial processing strategy according to the simulation deviation;

[0018] The pre-processing strategy of the target tire category is generated according to the optimization result;

[0019] The pre-processing strategies of each tire category are sequentially generated;

[0020] A pre-processing strategy number sequence B is established, B=(b1, b2…bi…bn), wherein bi is the pre-processing strategy of the i-th tire category.

[0021] In some embodiments of the present application, when the target pre-processing strategy of the tire to be predicted is generated, the following steps are included:

[0022] Similar evaluation values of the tire to be predicted and each tire category are sequentially generated according to a preset evaluation model;

[0023] A similar evaluation value sequence F is generated, F=(f1, f2…fi…fn), wherein fi is the similar evaluation value of the tire to be predicted and the i-th tire category;

[0024] fi= µ r *(c r -c' ir ) 2 ]};

[0025] wherein k is the number of tire evaluation indexes; µ r is the influence factor of the r-th tire evaluation index; c r is the reference value of the r-th tire evaluation index in the scheme parameter of the tire to be predicted; c' ir is the reference value of the r-th tire evaluation index in the i-th tire category; and Q is a fixed coefficient;

[0026] The target pre-processing strategy is set according to the similar evaluation value sequence F.

[0027] In some embodiments of the present application, when the target preprocessing strategy is set according to the similar evaluation value sequence F, the method comprises:

[0028] a first preset similar evaluation value threshold F1 is set;

[0029] a maximum value fmax in the similar evaluation value sequence F is obtained;

[0030] if fmax>F1, the preprocessing strategy of the tire category corresponding to fmax is the target preprocessing strategy;

[0031] if fmax<F1, the preprocessing strategies of the tire categories corresponding to the two largest similar evaluation values in the similar evaluation value sequence F are selected, and the target preprocessing strategy of the tire to be predicted is set according to the fusion correction result of the two selected preprocessing strategies.

[0032] In some embodiments of the present application, when the simulation result of the tire to be predicted is generated, the method comprises:

[0033] the original geometric model is meshed according to the target preprocessing strategy;

[0034] an outer contour node set is established;

[0035] the mechanical properties of the rubber and the skeleton material are set;

[0036] a two-dimensional finite element model of the tire to be predicted is generated;

[0037] the rim rigid body parameters are imported into the two-dimensional finite element model;

[0038] the gradual prestress parameters of the tire to be predicted are generated according to the target preprocessing strategy, and the working condition parameters are generated according to the target preprocessing strategy;

[0039] the simulation result of the tire to be predicted is generated according to the two-dimensional finite element model, the gradual prestress parameters and the working condition parameters.

[0040] In some embodiments of the present application, the method further comprises:

[0041] a preset update period is set;

[0042] all the tire data to be predicted in the current update period are obtained according to a preset update time node;

[0043] a maximum similar evaluation value sequence H of the tire to be predicted is established, H=(h1, h2…hi…hm), wherein hi is the maximum similar evaluation value of the i-th tire to be predicted in the current update period, and m is the number of tires to be predicted in the current update period;

[0044] if hi<F1, a new tire category is generated according to the scheme parameters of the i-th tire to be predicted, and a preprocessing strategy of the new tire category is generated.

[0045] If hi > F1, no update instruction is generated.

[0046] In some embodiments of the present application, when generating the pretreatment strategy of the new tire category, the following steps are included:

[0047] Obtaining the actual scheme parameter of the simulation result of the to-be-predicted tire corresponding to the new tire category;

[0048] Generating a prediction deviation value g;

[0049] g = e1 * H1 + e2 * H2;

[0050] Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; H1 is a first reference value generated based on the inflated profile in the simulation result and the inflated profile in the actual scheme parameter; H2 is a second reference value generated based on the outer rim size in the simulation result and the outer rim size in the actual scheme parameter;

[0051] A preset first prediction deviation value threshold G1;

[0052] If g < G1, a first-level processing instruction is generated, and a pretreatment strategy of the new tire category is generated according to the first-level processing instruction;

[0053] If g > G1, a second-level processing instruction is generated, and a pretreatment strategy of the new tire category is generated according to the second-level processing instruction.

[0054] In some embodiments of the present application, a tire inflation performance prediction system is provided, comprising:

[0055] A first processing module, configured to generate a plurality of tire categories according to a preset tire evaluation index, and generate a pretreatment strategy for each tire category;

[0056] A second processing module, configured to establish an original geometric model according to a scheme parameter of a to-be-predicted tire;

[0057] A third processing module, configured to generate a target pretreatment strategy of the to-be-predicted tire;

[0058] A simulation module, configured to generate a simulation result of the to-be-predicted tire according to the target pretreatment strategy and the original geometric model;

[0059] The first processing module is further configured to:

[0060] According to the tire category sequence A, ai is sequentially set as a target tire category;

[0061] Generating a sample data packet of the target tire category;

[0062] generating an initial processing strategy of the target tire category, and generating a simulation deviation of the initial processing strategy according to the sample data packet;

[0063] determining whether to iteratively optimize the initial processing strategy according to the simulation deviation;

[0064] generating a pre-processing strategy of the target tire category according to the optimization result;

[0065] generating the pre-processing strategy of each tire category in sequence;

[0066] establishing a pre-processing strategy sequence B, B = (b1, b2…bi…bn), wherein bi is the pre-processing strategy of the i-th tire category.

[0067] In some embodiments of the application, the third processing module is further configured to:

[0068] generating a similarity evaluation value of the to-be-predicted tire and each tire category according to a preset evaluation model in sequence;

[0069] generating a similarity evaluation value sequence F, F = (f1, f2…fi…fn), wherein fi is a similarity evaluation value of the to-be-predicted tire and the i-th tire category;

[0070] fi= µ r *(c r -c' ir ) 2 ]};

[0071] wherein k is the number of tire evaluation indexes; µ r is an influence factor of the r-th tire evaluation index; c r is a reference value of the r-th tire evaluation index in the scheme parameter of the to-be-predicted tire; c' ir is a reference value of the r-th tire evaluation index in the i-th tire category; and Q is a fixed coefficient.

[0072] presetting a first similarity evaluation value threshold F1;

[0073] obtaining a maximum value fmax in the similarity evaluation value sequence F;

[0074] if fmax>F1, the pre-processing strategy of the tire category corresponding to fmax is the target pre-processing strategy;

[0075] if fmax<F1, selecting the pre-processing strategies of the tire categories corresponding to the two largest similarity evaluation values in the similarity evaluation value sequence F, and setting the target pre-processing strategy of the to-be-predicted tire according to the fusion correction result of the two selected pre-processing strategies.

[0076] In some embodiments of the application, the simulation module is further configured to:

[0077] Grid the original geometric model according to the target pretreatment strategy;

[0078] Establish an outer contour node set;

[0079] Set the mechanical properties of the rubber and the skeleton material;

[0080] Generate a two-dimensional finite element model of the tire to be predicted;

[0081] Import the rim rigid body parameters into the two-dimensional finite element model;

[0082] Generate the gradual prestress parameters of the tire to be predicted according to the target pretreatment strategy, and generate the working condition parameters according to the target pretreatment strategy;

[0083] Generate the simulation results of the tire to be predicted according to the two-dimensional finite element model, the gradual prestress parameters and the working condition parameters.

[0084] Compared with the prior art, the tire inflation performance prediction method and system of the embodiment of the present application has the beneficial effects that:

[0085] According to the tire evaluation index, a plurality of tire categories are established, and corresponding pretreatment strategies are set to generate the best gradual prestress parameters and grid division scheme of different categories of tires, so that the original geometric model of the tire to be predicted is accurately processed, and the data processing efficiency and the accuracy of the simulation results are improved.

[0086] By obtaining the tire to be predicted parameters through the design scheme, the corresponding original geometric model is constructed, and the original geometric model is processed according to the corresponding pretreatment strategy, and based on the technology of gradual prestress, the performance of the tire to be predicted is accurately predicted, the design scheme optimization iteration is quickly completed, and the research and development cycle is shortened. BRIEF DESCRIPTION OF DRAWINGS

[0087] Figure 1 is a flowchart of a tire inflation performance prediction method in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0088] The specific embodiments of the present application will be further described in detail below in combination with the drawings and examples. The following examples are used to illustrate the present application, but are not used to limit the scope of the present application.

[0089] In the description of the present application, it needs to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0090] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise stated, the meaning of "multiple" is two or more.

[0091] In the description of the present application, it needs to be explained that, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0092] As Figure 1 shown, a tire inflation performance prediction method of the preferred embodiment of the present application comprises:

[0093] S101: generating a plurality of tire categories according to preset tire evaluation indexes, and generating a pretreatment strategy for each tire category;

[0094] S102: establishing an original geometric model according to the scheme parameters of the tire to be predicted, and generating a target pretreatment strategy for the tire to be predicted;

[0095] S103: generating a simulation result of the tire to be predicted according to the target pretreatment strategy and the original geometric model;

[0096] Wherein, when generating a plurality of tire categories, it comprises:

[0097] A series of tire categories A is established, A=(a1, a2…ai…an), wherein ai is the i-th tire category; n is the number of tire categories.

[0098] Specifically, the tire evaluation indexes include but are not limited to rubber amount, tire wall thickness, tire size and other parameters affecting tire inflation performance, and a plurality of tire categories are generated according to different value ranges of each tire evaluation index.

[0099] Specifically, when generating the pretreatment strategy of each tire category, the following steps are included:

[0100] ai is set as the target tire category according to the tire category sequence A in turn;

[0101] A sample data packet of the target tire category is generated;

[0102] An initial processing strategy of the target tire category is generated, and a simulation deviation of the initial processing strategy is generated according to the sample data packet;

[0103] Whether to perform iterative optimization on the initial processing strategy is determined according to the simulation deviation;

[0104] The pretreatment strategy of the target tire category is generated according to the optimization result;

[0105] The pretreatment strategies of each tire category are generated in turn;

[0106] The pretreatment strategy sequence B is established, B=(b1, b2…bi…bn), wherein bi is the pretreatment strategy of the i th tire category.

[0107] Specifically, the initial processing strategy includes a grid division strategy for the original set model and how to define the gradual prestress parameters of the tire.

[0108] Specifically, the simulation deviation can be set according to the difference parameter between the simulation result corresponding to the initial processing strategy and the actual inflation performance of the tire in the sample data packet. The greater the simulation deviation, the lower the credibility of the current simulation result. The initial processing strategy is optimized in time, and simulation simulation is performed again. Through continuous iterative optimization, the best initial processing strategy corresponding to the target tire category is generated, and is set as the pretreatment strategy of the target tire category.

[0109] In the preferred embodiment of the present application, when generating the target pretreatment strategy of the tire to be predicted, the following steps are included:

[0110] The similarity evaluation values of the tire to be predicted and each tire category are generated in turn according to a preset evaluation model;

[0111] The similarity evaluation value sequence F is generated, F=(f1, f2…fi…fn), wherein fi is the similarity evaluation value of the tire to be predicted and the i th tire category;

[0112] fi= µ r *(c r -c' ir ) 2 ]};

[0113] wherein k is the number of tire evaluation indexes; µ r is the influence factor of the rth tire evaluation index; c r is the reference value of the rth tire evaluation index in the scheme parameter of the tire to be predicted; c' ir is the reference value of the rth tire evaluation index in the ith tire category; Q is a fixed coefficient;

[0114] a first similarity evaluation value threshold F1 is preset;

[0115] the maximum value fmax in the similarity evaluation value sequence F is obtained;

[0116] if fmax>F1, the pretreatment strategy of the tire category corresponding to fmax is the target pretreatment strategy;

[0117] if fmax<F1, the pretreatment strategies of the tire categories corresponding to the two largest similarity evaluation values in the similarity evaluation value sequence F are selected, and the target pretreatment strategy of the tire to be predicted is set according to the fusion correction result of the two selected pretreatment strategies.

[0118] Specifically, the corresponding similarity evaluation value is set according to the difference between the scheme parameter of the tire to be tested and the tire parameters corresponding to each tire category. The greater the similarity evaluation value, the closer the tire corresponding to the current design scheme is to the tire performance of the tire category. By calling the corresponding pretreatment strategy to process the original geometric model of the tire to be predicted, the data processing efficiency is improved.

[0119] It can be understood that in the above embodiments, a plurality of tire categories are established according to tire evaluation indexes, and corresponding pretreatment strategies are set to generate the best gradual prestress parameter and meshing scheme of different category tires, thereby accurately processing the original geometric model of the tire to be predicted and improving the data processing efficiency and the accuracy of the simulation result.

[0120] In the preferred embodiments of the present application, when generating the simulation result of the tire to be predicted, the following steps are included:

[0121] meshing the original geometric model according to the target pretreatment strategy;

[0122] establishing an outer contour node set;

[0123] setting the mechanical properties of the rubber and the skeleton material;

[0124] generating a two-dimensional finite element model of the tire to be predicted;

[0125] importing the rim rigid body parameters into the two-dimensional finite element model;

[0126] generating the gradual prestress parameter of the tire to be predicted according to the target pretreatment strategy, and generating the working condition parameter according to the target pretreatment strategy;

[0127] According to the two-dimensional finite element model, the simulation result of the to-be-predicted tire is generated according to the gradient prestress parameter and the working condition parameter.

[0128] Specifically, according to the design scheme of the to-be-predicted tire, the corresponding mechanical property parameters of the rubber compound and the skeleton material, and the rigid body parameters of the rim are extracted, and the simulation of the to-be-predicted tire is completed according to the method of the gradient prestress.

[0129] It can be understood that in the above embodiment, the parameters of the to-be-predicted tire are obtained according to the design scheme, so as to construct the corresponding original geometric model, and the original geometric model is processed according to the corresponding preprocessing strategy, and the performance of the to-be-predicted tire is accurately predicted based on the technology of the gradient prestress, so as to quickly complete the design scheme optimization iteration and shorten the research and development cycle.

[0130] In the preferred embodiment of the present application, the following is further included:

[0131] A preset update period;

[0132] According to the preset update time node, all to-be-predicted tire data in the current update period is obtained;

[0133] A maximum similarity evaluation value sequence H of the to-be-predicted tire is established, H=(h1, h2…hi…hm), wherein hi is the maximum similarity evaluation value of the i-th to-be-predicted tire in the current update period; and m is the number of to-be-predicted tires in the current update period;

[0134] If hi

[0135] If hi> F1, no update instruction is generated.

[0136] Specifically, when the preprocessing strategy of the new tire category is generated, the following is included:

[0137] The actual scheme parameters of the simulation result of the to-be-predicted tire corresponding to the new tire category are obtained;

[0138] A prediction deviation value g is generated;

[0139] g=e1*H1+e2*H2;

[0140] Wherein e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; H1 is a first reference value generated based on the inflated profile in the simulation result and the inflated profile in the actual scheme parameters; and H2 is a second reference value generated based on the outer edge size in the simulation result and the outer edge size in the actual scheme parameters;

[0141] A preset first prediction deviation value threshold G1 is set.

[0142] If g < G1, a first-level processing instruction is generated, and a pre-processing strategy of the new tire category is generated according to the first-level processing instruction;

[0143] If g > G1, a second-level processing instruction is generated, and a pre-processing strategy of the new tire category is generated according to the second-level processing instruction.

[0144] Specifically, the first-level processing instruction refers to setting the pre-processing strategy of the new tire category as the pre-processing strategy of the new tire category for the to-be-predicted tire in initial simulation. The second-level processing instruction refers to generating a sample data packet of the new tire category, and generating a corresponding pre-processing strategy according to the iterative optimization result.

[0145] It can be understood that in the above embodiments, the simulation processing efficiency and accuracy of the tire are improved by continuously updating and refining the tire category.

[0146] Based on the tire inflation performance prediction method in any of the above preferred embodiments, another preferred embodiment of the present application provides a tire inflation performance prediction system, comprising:

[0147] A first processing module is configured to generate a plurality of tire categories according to a preset tire evaluation index, and generate a pre-processing strategy for each tire category;

[0148] A second processing module is configured to establish an original geometric model according to a scheme parameter of a to-be-predicted tire;

[0149] A third processing module is configured to generate a target pre-processing strategy of the to-be-predicted tire;

[0150] A simulation module is configured to generate a simulation result of the to-be-predicted tire according to the target pre-processing strategy and the original geometric model;

[0151] The first processing module is further configured to:

[0152] Set ai as a target tire category in sequence according to the tire category sequence A;

[0153] Generate a sample data packet of the target tire category;

[0154] Generate an initial processing strategy of the target tire category, and generate a simulation deviation of the initial processing strategy according to the sample data packet;

[0155] Determine whether to perform iterative optimization on the initial processing strategy according to the simulation deviation;

[0156] Generate a pre-processing strategy of the target tire category according to the optimization result;

[0157] Generate the pre-processing strategy of each tire category in sequence;

[0158] A pre-processing strategy sequence B is established, B=(b1, b2…bi…bn), wherein bi is a pre-processing strategy of the i-th tire category.

[0159] In the preferred embodiment of the present application, the third processing module is further configured to:

[0160] generate a similarity evaluation value of the to-be-predicted tire and each tire category according to a preset evaluation model;

[0161] generate a similarity evaluation value sequence F, F=(f1, f2…fi…fn), wherein fi is a similarity evaluation value of the to-be-predicted tire and the i-th tire category;

[0162] fi= µ r *(c r -c' ir ) 2 ]};

[0163] wherein k is the number of tire evaluation indexes; µ r is an influence factor of the r-th tire evaluation index; c r is a reference value of the r-th tire evaluation index in the scheme parameter of the to-be-predicted tire; c' ir is a reference value of the r-th tire evaluation index in the i-th tire category; and Q is a fixed coefficient.

[0164] a first similarity evaluation value threshold F1 is preset;

[0165] obtain a maximum value fmax in the similarity evaluation value sequence F;

[0166] if fmax>F1, the pre-processing strategy of the tire category corresponding to fmax is the target pre-processing strategy;

[0167] if fmax<F1, the pre-processing strategies of the tire categories corresponding to the two largest similarity evaluation values in the similarity evaluation value sequence F are selected, and the target pre-processing strategy of the to-be-predicted tire is set according to the fusion and correction result of the two selected pre-processing strategies.

[0168] In the preferred embodiment of the present application, the simulation module is further configured to:

[0169] perform mesh division on the original geometric model according to the target pre-processing strategy;

[0170] establish an outer contour node set;

[0171] set the mechanical properties of the rubber and the skeleton material;

[0172] generate a two-dimensional finite element model of the to-be-predicted tire;

[0173] The rim rigid body parameters are introduced into the two-dimensional finite element model;

[0174] The gradient prestress parameters of the tire to be predicted are generated according to the target pretreatment strategy, and the working condition parameters are generated according to the target pretreatment strategy;

[0175] The simulation result of the tire to be predicted is generated according to the two-dimensional finite element model, the gradient prestress parameters and the working condition parameters.

[0176] According to the first concept of the present application, a plurality of tire categories are established according to tire evaluation indexes, and corresponding pretreatment strategies are set to generate the best gradient prestress parameters and mesh division scheme of different categories of tires, so as to accurately process the original geometric model of the tire to be predicted, and improve the data processing efficiency and the accuracy of the simulation result.

[0177] According to the second concept of the present application, the parameters of the tire to be predicted are obtained through the design scheme, so as to construct the corresponding original geometric model, and the original geometric model is processed according to the corresponding pretreatment strategy, and based on the technology of gradient prestress, the performance of the tire to be predicted is accurately predicted, the design scheme optimization iteration is quickly completed, and the research and development cycle is shortened.

[0178] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the technical principles of the present application, a number of improvements and substitutions can be made, and these improvements and substitutions should be considered as the protection scope of the present application.

Claims

1. A method for predicting tire inflation performance, characterized in that, It includes: Generate multiple tire categories according to preset tire evaluation indicators, and generate preprocessing strategies for each tire category; Establish an original geometric model based on the scheme parameters of the tire to be predicted, and generate the target preprocessing strategy for the tire to be predicted; Generate the simulation results of the tire to be predicted based on the target preprocessing strategy and the original geometric model; When generating multiple tire categories, it includes: Establish a tire category sequence A, A = (a1, a2... ai... an), where ai is the i-th tire category; n is the number of tire categories; When generating the target preprocessing strategy for the tire to be predicted, it includes: Generate the similarity evaluation values of the tire to be predicted and each tire category in sequence according to the preset evaluation model; Generate a similarity evaluation value sequence F, F = (f1, f2... fi... fn), where fi is the similarity evaluation value of the tire to be predicted and the i-th tire category; fi= µ r *(c r -c' ir ) 2 ]}; Where k is the number of tire evaluation indicators; µ r Let c be the influencing factor of the r-th tire evaluation index; r c' is the reference value for the r-th tire evaluation index in the scheme parameters of the tire to be predicted; ir is the reference value for the r-th tire evaluation index in the i-th tire category; Q is a fixed coefficient; Set the target preprocessing strategy according to the similarity evaluation value sequence F; Preset the first similarity evaluation value threshold F1; Obtain the maximum value fmax in the similarity evaluation value sequence F; If fmax > F1, the preprocessing strategy of the tire category corresponding to fmax is the target preprocessing strategy; If fmax < F1, select the preprocessing strategies of the tire categories corresponding to the two largest similarity evaluation values in the similarity evaluation value sequence F, and set the target preprocessing strategy of the tire to be predicted according to the fusion correction result of the two selected preprocessing strategies.

2. The tire inflation performance prediction method as described in claim 1, characterized in that, When generating the preprocessing strategies for each tire category, it includes: Set ai as the target tire category in sequence according to the tire category sequence A; Generate a sample data packet for the target tire category; Generate the initial processing strategy for the target tire category, and generate the simulation deviation amount of the initial processing strategy according to the sample data packet; Judge whether to perform iterative optimization on the initial processing strategy according to the simulation deviation amount; Generate the preprocessing strategy for the target tire category according to the optimization result; Generate the preprocessing strategies for each tire category in sequence; Establish a preprocessing strategy sequence B, B = (b1, b2... bi... bn), where bi is the preprocessing strategy of the i-th tire category.

3. The tire inflation performance prediction method as described in claim 2, characterized in that, When generating the simulation results of the tire to be predicted, it includes: Perform mesh division on the original geometric model according to the target preprocessing strategy; Establish an outer contour node set; Set the mechanical properties of the rubber material and the skeleton material; Generate a two-dimensional finite element model of the tire to be predicted; Import the rim rigid body parameters into the two-dimensional finite element model; Generate the gradual prestress parameters of the tire to be predicted according to the target preprocessing strategy, and generate the working condition parameters according to the target preprocessing strategy; Generate the simulation results of the tire to be predicted according to the two-dimensional finite element model, the gradual prestress parameters and the working condition parameters.

4. The tire inflation performance prediction method as described in claim 3, characterized in that, It also includes: Preset the update period; Obtain all the data of the tires to be predicted within the current update period according to the preset update time node; Establish a maximum similarity evaluation value sequence H for the tires to be predicted, H = (h1, h2... hi... hm), where hi is the maximum similarity evaluation value of the i-th tire to be predicted within the current update period; m is the number of tires to be predicted within the current update period; If hi < F1, generate a new tire category according to the scheme parameters of the i-th tire to be predicted, and generate the preprocessing strategy for the new tire category; If hi > F1, no update instruction is generated.

5. The tire inflation performance prediction method as described in claim 4, characterized in that, When generating the preprocessing strategy for adding a new tire category, it includes: Obtaining the actual scheme parameters of the simulation results of the tire to be predicted corresponding to the new tire category; Generating a prediction deviation value g; g = e1 * H1 + e2 * H2; Where, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; H1 is a first reference value generated based on the inflation profile in the simulation results and the inflation profile in the actual scheme parameters; H2 is a second reference value generated based on the outer edge dimensions in the simulation results and the outer edge dimensions in the actual scheme parameters; Presetting a first prediction deviation value threshold G1; If g < G1, generating a first-level processing instruction and generating a preprocessing strategy for the new tire category according to the first-level processing instruction; If g > G1, generating a second-level processing instruction and generating a preprocessing strategy for the new tire category according to the second-level processing instruction.

6. A tire inflation performance prediction system, employing the tire inflation performance prediction method according to any one of claims 1-5, characterized in that, It includes: The first processing module is used to generate multiple tire categories according to preset tire evaluation indicators and generate preprocessing strategies for each tire category; The second processing module is used to establish an original geometric model according to the scheme parameters of the tire to be predicted; The third processing module is used to generate the target preprocessing strategy of the tire to be predicted; The simulation module is used to generate the simulation results of the tire to be predicted according to the target preprocessing strategy and the original geometric model; The first processing module is also used for: Sequentially setting ai as the target tire category according to the tire category sequence A; Generating a sample data packet for the target tire category; Generating an initial processing strategy for the target tire category and generating a simulation deviation amount of the initial processing strategy according to the sample data packet; Judging whether to perform iterative optimization on the initial processing strategy according to the simulation deviation amount; Generating a preprocessing strategy for the target tire category according to the optimization result; Sequentially generating preprocessing strategies for each tire category; Establishing a preprocessing strategy sequence B, B = (b1, b2…bi…bn), where bi is the preprocessing strategy of the i-th tire category.

7. The tire inflation performance prediction system as described in claim 6, characterized in that, The third processing module is also used for: Sequentially generating similarity evaluation values between the tire to be predicted and each tire category according to a preset evaluation model; Generating a similarity evaluation value sequence F, F = (f1, f2…fi…fn), where fi is the similarity evaluation value between the tire to be predicted and the i-th tire category; fi= µ r *(c r -c' ir ) 2 ]}; Where k is the number of tire evaluation indicators; µ r Let c be the influencing factor of the r-th tire evaluation index; r c' is the reference value for the r-th tire evaluation index in the scheme parameters of the tire to be predicted; ir is the reference value for the r-th tire evaluation index in the i-th tire category; Q is a fixed coefficient; Presetting a first similarity evaluation value threshold F1; Obtaining the maximum value fmax in the similarity evaluation value sequence F; If fmax > F1, the preprocessing strategy of the tire category corresponding to fmax is the target preprocessing strategy; If fmax < F1, selecting the preprocessing strategies of the tire categories corresponding to the two largest similarity evaluation values in the similarity evaluation value sequence F and setting the target preprocessing strategy of the tire to be predicted according to the fusion correction result of the two selected preprocessing strategies.

8. The tire inflation performance prediction system as described in claim 7, characterized in that, The simulation module is also used for: Performing mesh division on the original geometric model according to the target preprocessing strategy; Establishing an outer contour node set; Setting the mechanical properties of the rubber material and the skeleton material; Generating a two-dimensional finite element model of the tire to be predicted; Importing the rim rigid body parameters into the two-dimensional finite element model; Generating the gradual prestress parameters of the tire to be predicted according to the target preprocessing strategy and generating working condition parameters according to the target preprocessing strategy; Based on the two-dimensional finite element model, the simulation results of the tire to be predicted are generated using the gradually varying prestress parameters and working condition parameters.

Images