Vehicle performance index optimization method, equipment and storage medium based on big data

Through big data and genetic algorithms, the vehicle performance indicators are optimized, combined with regional characteristics and environmental operating conditions distribution probability, the multi-objective optimization problem of vehicle performance indicators is solved, and performance improvement and cost savings are achieved in different environments.

CN118520786BActive Publication Date: 2024-11-08AUTOMOTIVE DATA OF CHINA (TIANJIN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410988876.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-08
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

While reducing energy consumption and increasing battery life, it is a challenge to achieve comprehensive optimization of vehicle performance indicators, especially in different geographical locations and climate conditions, the vehicle model parameter design and component selection requirements are higher.

Method used

Using the vehicle performance indicator optimization method based on big data, by obtaining the initial design parameters of the target vehicle model and the distribution probability of regional environmental conditions, combining genetic algorithms and deep learning models, the fitness function is constructed to optimize the design parameters and achieve multi-objective optimization. .

Benefits of technology

The comprehensive performance indicator optimization in most environmental conditions is achieved, the time and cost of experimental testing and model simulation are reduced, the high efficiency and low cost of the algorithm are ensured, and scientific and reasonable design parameters and performance indicators are obtained.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118520786B_ABST
    Figure CN118520786B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of electronic digital processing technology, and discloses a vehicle performance index optimization method, device and storage medium based on big data. The method obtains multiple initial design parameters of a target vehicle model and the target region where it is located, and determines the distribution probability of each environmental condition. Multiple groups of solution sets are generated according to the initial design parameters, and the multiple groups of solution sets are input into a genetic algorithm, and the multiple groups of solution sets are updated and screened by maximizing the fitness function; when the termination condition of the genetic algorithm is met, the current solution set and the performance indicators of the target vehicle model applying the current solution set are determined. The present invention realizes the high efficiency, accuracy and low cost of optimizing the performance indicators of the whole vehicle, and solves the multi-objective optimization problem in the design of vehicle indicators.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electronic digital processing technology, and in particular to a vehicle performance index optimization method, device and storage medium based on big data. Background Art

[0002] With the continuous advancement of automobile industry technology, vehicle performance indicators are constantly optimized, and vehicle indicators such as energy consumption, endurance, and power have become important references for users when choosing vehicles. However, there is often a mutual restriction between these indicators. For example, how to reduce energy consumption, increase endurance, and improve power to achieve comprehensive optimization of these indicators has become a major challenge facing all vehicle manufacturers. In addition, for consumers in different geographical locations and climates, different vehicle parameters often correspond to different vehicle parameters when the vehicle achieves optimal performance under various working conditions (such as normal temperature, high temperature, low temperature, low altitude, high altitude, etc.), which undoubtedly puts higher requirements on the parameter design of the vehicle and the selection of parts.

[0003] In view of this, the present invention is proposed. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a vehicle performance index optimization method, device and storage medium based on big data, so as to achieve high efficiency, accuracy and low cost optimization of vehicle performance indicators, and solve the multi-objective optimization problem in vehicle indicator design.

[0005] An embodiment of the present invention provides a vehicle performance index optimization method based on big data, the method comprising:

[0006] S110, obtaining a plurality of initial design parameters of a target vehicle model and a target region;

[0007] S120, determining the distribution probability of each environmental condition according to the target area;

[0008] S130, generating multiple sets of solutions according to the initial design parameters, inputting the multiple sets of solutions into a genetic algorithm, and updating and screening the multiple sets of solutions by maximizing a fitness function; wherein the fitness function of the genetic algorithm is as follows:

[0009]

[0010] in, Represents the weight of the i-th performance indicator under the j-th environmental condition; represents the i-th performance index of each solution set x applied to the target vehicle model under the j-th environmental condition; Represents the distribution probability of the jth environmental condition in the target area.

[0011] S140. When the termination condition of the genetic algorithm is met, determine the current solution set and the performance indicators of the target vehicle model applying the current solution set; wherein the current solution set includes a plurality of design parameters.

[0012] An embodiment of the present invention provides an electronic device, the electronic device comprising:

[0013] Processor and memory;

[0014] The processor is used to execute the steps of the vehicle performance index optimization method based on big data described in any embodiment by calling the program or instruction stored in the memory.

[0015] An embodiment of the present invention provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of the vehicle performance index optimization method based on big data described in any embodiment.

[0016] The embodiments of the present invention have the following technical effects:

[0017] (1) The present invention takes into account the regional characteristics of the target vehicle model and the distribution probability of environmental conditions, and applies the distribution probability of environmental conditions to the construction of the fitness function, thereby obtaining the optimal performance index and corresponding solution set of various environmental conditions, and finally achieving multi-objective optimization.

[0018] (2) The present invention combines the weight of the i-th performance indicator under the j-th environmental condition, the distribution probability of the performance indicator and the environmental condition to obtain the fitness function, thereby obtaining the current optimal solution set of the comprehensive performance indicator weight and the environmental condition distribution, making the solution set more scientific and reasonable, and having better performance for important performance indicators under most environmental conditions.

[0019] (3) The present invention optimizes multiple design parameters through genetic algorithms, eliminating the need for experimental testing or vehicle modeling and simulation, saving time and cost investment in experimental equipment operation and vehicle modeling and simulation, and ensuring high efficiency and low cost of the algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1It is a flow chart of a vehicle performance index optimization method based on big data provided by an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of a genetic algorithm provided by an embodiment of the present invention;

[0023] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0025] Example 1

[0026] The vehicle performance index optimization method based on big data provided by the embodiment of the present invention is mainly applicable to the case of optimizing the design parameters of the target vehicle model. The vehicle performance index optimization method based on big data provided by the embodiment of the present invention can be executed by an electronic device.

[0027] The target vehicle types are not limited to gasoline vehicles or new energy vehicles, but can be passenger vehicles or commercial vehicles.

[0028] Figure 1 is a flow chart of a vehicle performance index optimization method based on big data provided by an embodiment of the present invention. Figure 1 , the vehicle performance index optimization method based on big data specifically includes:

[0029] S110: Obtain multiple initial design parameters of a target vehicle model and a target region.

[0030] If the target vehicle model is a new model, the initial design parameters can be the first version of the initial design parameters given by the design department; if the target vehicle model is an old model that has been sold on the market, the initial design parameters are the design parameters of the old model. This embodiment aims to optimize the initial design parameters to improve the performance of the entire vehicle.

[0031] Optionally, the initial design parameters or the design parameters in the solution below are parameters that can affect the performance of the target vehicle model, including but not limited to engine parameters, battery parameters, suspension parameters, curb weight and motor parameters.

[0032] If the target vehicle model is a new model, the target area is the area where vehicles of the target vehicle model are expected to be sold; if the target vehicle model is an old model, the target area is the area where vehicles of the target vehicle model are traveling. The target area in this embodiment has certain environmental operating conditions characteristics, so the area can be divided according to the boundaries where the environmental operating conditions characteristics change.

[0033] For example, the country is divided into six major regions according to temperature and altitude, namely, Northeast China, North China, Northwest China, East China, South China and Southwest China. For old models, the positioning positions of each vehicle corresponding to the target model are collected; the positioning positions are clustered to obtain the target area where the target model is located. Specifically, in-service vehicles will upload the current positioning positions to the cloud, so that the cloud can summarize the positioning positions of each vehicle corresponding to the target model. Clustering is performed using a clustering algorithm to obtain at least one center point, and the target area where the center point is located is determined.

[0034] Clustering algorithms include but are not limited to K-Means clustering algorithm, density-based clustering algorithm and mean shift clustering algorithm. The target region where the target vehicle model is located can be 1, 2 or more.

[0035] S120: Determine the distribution probability of each environmental condition according to the target area.

[0036] The distribution probability of each temperature condition and the distribution probability of each altitude condition are determined according to the target region; the distribution probability of each temperature condition and the distribution probability of each altitude condition are combined in pairs to obtain the distribution probability of each environmental condition in the target region. It should be noted that the distribution probability of each environmental condition in each target region needs to be obtained here.

[0037] First, the temperature condition probabilities of the six target areas were sorted out based on the survey and statistical results. (Standard temperature), (high temperature), (Low Temperature) and Altitude Operating Condition Probability (Standard altitude), (High altitude). Specifically, the probability of standard temperature, high temperature and low temperature is determined according to the time distribution of different temperature values ​​in a target area in a year. The distribution area ratio of standard altitude and the distribution area ratio of high altitude are determined according to the distribution of different altitudes in a target area, which are used as the probability of standard altitude and the probability of high altitude respectively. Among them, the numerical range of each temperature condition and the numerical range of each altitude condition can be determined according to business needs.

[0038] By arranging and combining various working conditions, each target area can be combined into 6 environmental working conditions. After calculation, the weight of each environmental working condition in the six target areas can be obtained. For example, the weight of low temperature and standard altitude working conditions in Northeast China is The calculation method is:

[0039]

[0040] Table 1 Probability survey and statistical results of each environmental condition in the six target areas

[0041]

[0042] Table 2 Weight calculation results of each target area under six environmental conditions

[0043]

[0044] S130, generating multiple solution sets according to the initial design parameters, inputting the multiple solution sets into the genetic algorithm, and updating and screening the multiple solution sets by maximizing the fitness function.

[0045] The initial design parameters are a set of design parameters, such as motor parameters, battery parameters, vehicle shape and size, and curb weight. Each parameter in this set of parameters is expanded to form a parameter space. Each parameter space is sampled, and the parameters sampled once from each parameter space are summarized to obtain a set of design parameters, that is, a set of solution sets. After sampling each parameter space m times, m sets of solution sets are generated as the initial input of the genetic algorithm.

[0046] Figure 2 It is a schematic diagram of the genetic algorithm provided by the embodiment of the present invention. Drawing on the theory of biological evolution, the genetic algorithm simulates the problem to be solved into a biological evolution process, generates the next generation of solutions through operations such as replication, crossover, and mutation, and gradually eliminates solutions with low fitness function values, and increases solutions with high fitness function values. After multiple generations of evolution, it is very likely that individuals with very high fitness function values ​​will evolve. This embodiment applies the genetic algorithm to multi-objective optimization problems, that is, to maximize multiple performance indicators, including the inverse of energy consumption, endurance, and power, that is, to minimize energy consumption (electricity consumption or fuel consumption), maximize endurance, and maximize power (high vehicle speed or maximum climbing grade).

[0047] See also Figure 2 , first take m groups of solutions as the initial population, and each group of solutions as an individual. Calculate the fitness function value of each group of solutions (i.e., each individual) based on multiple performance indicators. Fitness function as follows:

[0048]

[0049] Each parameter in the fitness function is explained below. Represents the weight of the ith performance indicator under the jth environmental condition, such as the weight of the reciprocal of energy consumption under the standard temperature and standard altitude environmental condition, which reflects the importance of the performance indicator in different environmental conditions. Optionally, the weight of the ith performance indicator under the jth environmental condition is determined according to the degree of influence of each environmental condition on each performance indicator. For example, low temperature conditions have a greater impact on driving range and energy consumption, and a general impact on power; high altitude conditions have a greater impact on power, and a general impact on energy consumption and driving range. Therefore, the performance indicators with a greater impact should be focused on. Specifically, the whole vehicle driving test can be carried out under various environmental conditions, and the performance indicators of the whole vehicle can be tested during the test, so as to obtain the difference between the tested performance indicators and the nominal performance indicators, that is, the degree of influence. The degree of influence is normalized to obtain the weight of the ith performance indicator under the jth environmental condition.

[0050] Represents the i-th performance index of each solution set x applied to the target vehicle model under the j-th environmental condition. For example, the inverse of energy consumption, endurance and power when the target vehicle model applies the first solution set x (including motor parameters, battery parameters, vehicle shape and size, and curb weight) at standard temperature and standard altitude. These performance indicators can be obtained in a variety of ways, such as simulation tests, bench tests, etc. However, since there are many groups of solution sets and multiple environmental conditions, obtaining performance indicators one by one through simulation and bench tests will bring a lot of workload and cost loss. Based on this, this embodiment proposes a prediction scheme based on deep learning, which trains a prediction model based on deep learning through big data, so that the model can accurately convert the input design parameters and environmental conditions into corresponding performance indicators.

[0051] The prediction model based on deep learning can be a BP neural network model, which is designed as a multi-input and three-output model. The design parameters of each in-service vehicle model and the performance indicators under various environmental conditions are collected in advance. For each in-service vehicle model, its design parameters, environmental conditions and corresponding performance indicators form a data set. The data set is divided into a training set and a validation set. The design parameters and environmental conditions in the training set are used as samples, and the performance indicators are used as labels. The prediction model is pre-trained through samples and labels. The trained prediction model is then verified through the validation set. The prediction model obtained in this way can obtain three performance indicators based on a set of design parameters and an environmental condition. In the genetic algorithm process, each solution set and any environmental condition are input into the prediction model based on deep learning to obtain multiple performance indicators of the target vehicle model applying each solution set under any environmental condition.

[0052] Represents the distribution probability of the jth environmental condition in the target region. The distribution probabilities of different environmental conditions in the target region are different. For example, the distribution probability of low temperature and standard altitude in Northeast China is 50%, but the distribution probability of high temperature and standard altitude is only 20%. It should only be possible to improve the performance of the target model in environmental conditions with higher distribution probabilities, so that the vehicle can meet the needs of users in most cases. Therefore, the higher the distribution probability, the larger the fitness function, and the more suitable solution set can be screened out.

[0053] It should be noted that if there are more than two target regions obtained in S110, a fitness function is calculated for each target region obtained in S110, and finally the fitness functions of the target regions are added together.

[0054] After obtaining the fitness function value of each solution set, select the target solution set whose fitness function value is greater than the set threshold. The set threshold can be determined according to business needs to select a solution set with excellent performance from multiple solution sets. This embodiment evaluates the quality of each solution set based on the fitness function value and the set threshold. Figure 2 If the number of target solution sets is less than 50% of all solution sets or the number of crossovers and mutations is less than the set number (for example, 10 times), the termination condition is considered to be not met, and the target solution set is crossover and mutation. Crossover and mutation are used to generate new solution sets to explore different areas of the solution space. The new solution set will continue to return to the evaluation step of the fitness function. If the number of target solution sets is greater than or equal to 50% of all solution sets or the number of crossovers and mutations is less than the set number (for example, 10 times), the termination condition is considered to be met, and the solution set obtained at this time can be called the current solution set. The number of current solution sets can be at least one, and each current solution set includes a complete set of design parameters.

[0055] Preferably, considering that the fitness function is a weighted sum of multiple performance indicators, it is found in practice that although a solution set with a higher fitness function value is screened out, a certain performance indicator of the solution set may be very low under a certain environmental condition. For example, the driving range under low temperature conditions is less than 1 / 3 of the nominal driving range. In this case, such a solution set should not be selected. Therefore, after selecting a target solution set with a fitness function value greater than a set threshold, the performance indicators of the target solution set applied to the target vehicle model under each environmental condition are determined; and the target solution set with each performance indicator lower than the indicator threshold is eliminated. The indicator threshold can be determined according to business needs. In this way, this embodiment screens the solution set by the fitness function value and eliminates the solution set by the indicator threshold, thereby obtaining a suitable target solution set.

[0056] S140. When the termination condition of the genetic algorithm is met, determine the current solution set and the performance indicators of the target vehicle model applying the current solution set under the jth environmental condition; wherein the current solution set includes a plurality of design parameters.

[0057] When the termination condition of the genetic algorithm is met, the performance indicators of the current solution set can be calculated according to the fitness function. It is obtained that the target vehicle model adopts various performance indicators under the jth environmental condition using the current solution set, which is applicable to each target region obtained by S110.

[0058] The embodiments of the present invention have the following technical effects:

[0059] (1) The present invention takes into account the regional characteristics of the target vehicle model and the distribution probability of environmental conditions, and applies the distribution probability of environmental conditions to the construction of the fitness function, thereby obtaining the optimal performance index and corresponding solution set of various environmental conditions, and finally achieving multi-objective optimization.

[0060] (2) The present invention combines the weight of the i-th performance indicator under the j-th environmental condition, the distribution probability of the performance indicator and the environmental condition to obtain the fitness function, thereby obtaining the current optimal solution set of the comprehensive performance indicator weight and the environmental condition distribution, making the solution set more scientific and reasonable, and having better performance for important performance indicators under most environmental conditions.

[0061] (3) The present invention optimizes multiple design parameters through genetic algorithms, eliminating the need for experimental testing or vehicle modeling and simulation, saving time and cost investment in experimental equipment operation and vehicle modeling and simulation, and ensuring high efficiency and low cost of the algorithm.

[0062] (4) In the present invention, the prediction model provides the genetic algorithm model with the calculation of performance indicators, and the genetic algorithm provides the solution optimization function for the prediction of the prediction model, thereby achieving the purpose of combining the prediction model and the genetic algorithm to optimize the design parameters and performance indicators of the target vehicle model.

[0063] Example 2

[0064] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0065] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0066] The memory 402 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the vehicle performance index optimization method based on big data and / or other desired functions of any embodiment of the present invention described above. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0067] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0068] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0069] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the vehicle performance index optimization method based on big data provided by any embodiment of the present invention.

[0070] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0071] In addition, an embodiment of the present invention may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the vehicle performance index optimization method based on big data provided in any embodiment of the present invention.

[0072] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0073] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0074] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle performance index optimization method based on big data, characterized in that: include: S110, obtaining a plurality of initial design parameters of a target vehicle model and a target region; S120, determining the distribution probability of each environmental condition according to the target area; S130, generating multiple sets of solutions according to the initial design parameters, inputting the multiple sets of solutions into a genetic algorithm, and updating and screening the multiple sets of solutions by maximizing a fitness function; wherein the fitness function of the genetic algorithm is as follows: in, Represents the weight of the i-th performance indicator under the j-th environmental condition; represents the i-th performance index of each solution set x applied to the target vehicle model under the j-th environmental condition; represents the distribution probability of the jth environmental condition in the target area; Methods for determining include: Input each solution set and any environmental condition into a prediction model based on deep learning to obtain a plurality of performance indicators of the target vehicle model applying each solution set under the any environmental condition; The prediction model based on deep learning is obtained by pre-training samples and labels, wherein the samples include design parameters and environmental condition samples, and the labels include multiple performance indicators of the vehicle model under the samples; The determination method is as follows: according to the influence of each environmental condition on each performance indicator, the weight of the i-th performance indicator under the j-th environmental condition is determined; The multiple performance indicators include the inverse of energy consumption, endurance and power; the various environmental conditions include conditions combining different temperatures and different altitudes; S140. When the termination condition of the genetic algorithm is met, determine the current solution set and the performance indicators of the target vehicle model applying the current solution set; wherein the current solution set includes a plurality of design parameters.

2. The method according to claim 1, characterized in that: The updating and screening of multiple solution sets by maximizing the fitness function includes: Calculate the fitness function value of each solution set according to the multiple performance indicators; A target solution set whose fitness function value is greater than a set threshold is selected, and crossover and mutation are performed on the target solution set.

3. The method according to claim 2, characterized in that After selecting the target solution set whose fitness function value is greater than the set threshold, it also includes: Determining the performance indicators of the target vehicle model applying the target solution set under various environmental conditions; Eliminate the target solution set whose performance indicators are lower than the indicator threshold.

4. The method according to claim 1, characterized in that: The S120 includes: Determining the distribution probability of each temperature condition and the distribution probability of each altitude condition according to the target region; The distribution probability of each temperature condition and the distribution probability of each altitude condition are combined in pairs to obtain the distribution probability of each environmental condition in the target area.

5. The method according to claim 1, characterized in that: The S110 includes: Collecting the positioning position of each vehicle corresponding to the target vehicle type; The positioning positions are clustered to obtain a target area where the target vehicle type is located.

6. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the steps of the vehicle performance index optimization method based on big data as described in any one of claims 1 to 5 by calling the program or instructions stored in the memory.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and the programs or instructions enable a computer to execute the steps of the vehicle performance index optimization method based on big data as described in any one of claims 1 to 5.