Parameter optimization method and device of battery cooling system, electronic equipment and medium

Abstract

The invention relates to a parameter optimization method and device of a battery cooling system, electronic equipment and a medium. The method comprises the following steps: determining to-be-optimized power battery cooling system parameters; based on the to-be-optimized power battery cooling system parameters, generating an initial population and a plurality of individuals of the initial population by using a preset genetic algorithm, performing clustering analysis on the plurality of initial populations, and calculating the fitness of each individual according to a clustering analysis result; and after the fitness calculation of each individual in the initial population is completed, generating a new population and a plurality of individuals of the new population based on the initial population, and re-executing the step of performing clustering analysis on the new population until a preset iteration condition is met, thereby obtaining the optimized power battery cooling system parameters. Therefore, by adding an efficient fitness estimation mechanism in the simulation process, the evaluation period of a single design scheme in the simulation process is remarkably shortened, the pressure of computing resources is relieved, and the simulation evaluation efficiency is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal management, and particularly to a method, device, electronic device and medium for optimizing parameters of a battery cooling system. Background Art

[0002] The battery thermal management system (BTMS) of power batteries is a crucial component in electric vehicles and energy storage systems. It ensures the performance, safety, and lifespan of the batteries by controlling their temperature. Currently, the widely adopted heat dissipation technologies in the industry include air cooling, liquid cooling, phase change material cooling, heat pipe technology, and hybrid applications of these technologies. To confirm whether the design scheme of the battery thermal management system is reasonable, it is necessary to first perform simulation on the battery thermal management system before putting it into use.

[0003] In the related art, a power battery model is usually established by a computer, various parameters of the power battery system are collected, the battery thermal management process is simulated, and the design scheme is optimized according to the simulation results.

[0004] However, due to the intertwined influence of multiple factors on the internal temperature of the battery, the above-mentioned technical means can only perform calculations according to the preset model when simulating the battery thermal management system, resulting in time-consuming and laborious calculation processes and prone to redundant data, which urgently needs to be solved. Summary of the Invention

[0005] The present invention provides a method, device, electronic device and medium for optimizing parameters of a battery cooling system, so as to solve the problem that the calculation process in the related art is time-consuming and laborious and prone to redundant data due to only being able to perform calculations according to the preset model, significantly shortening the evaluation cycle of a single design scheme during the simulation process, alleviating the pressure on computing resources, and greatly improving the simulation evaluation efficiency.

[0006] To achieve the above object, the first aspect embodiment of the present invention proposes a method for optimizing parameters of a battery cooling system, including the following steps:

[0007] Determine the parameters of the power battery cooling system to be optimized;

[0008] Based on the parameters of the power battery cooling system to be optimized, use the preset genetic algorithm to generate an initial population and multiple individuals of the initial population, perform clustering analysis on the multiple initial populations, and calculate the fitness of each individual according to the clustering analysis results;

[0009] After the fitness of each individual in the initial population is calculated, a new population and multiple individuals of the new population are generated based on the initial population, and the step of performing cluster analysis on the new population is re-executed until a preset iteration condition is reached, and the optimized parameters of the power battery cooling system are obtained.

[0010] According to an embodiment of the present invention, the performing cluster analysis on the initial population and calculating the fitness value of each individual according to the cluster analysis result includes:

[0011] Taking the first individual in the initial population as the current individual, and determining whether the current individual meets a preset cluster center condition;

[0012] If the current individual meets the preset cluster center condition, a data file for calculating the fitness value of the current individual is generated, and the fitness value of the current individual is calculated according to the data file; otherwise, the fitness value of the current individual is calculated based on a preset fitness calculation strategy;

[0013] Taking the second individual in the initial population as the current individual, and re-executing the step of determining whether the current individual meets the preset cluster center condition until the fitness values of each individual in the initial population are obtained.

[0014] According to an embodiment of the present invention, the generating a data file for calculating the fitness value of the current individual includes:

[0015] Generating a Gambit log file and a Fluent log file of the current individual;

[0016] Obtaining a grid according to the Gambit log file, and generating a data file for calculating the fitness value of the current individual according to the grid and the Fluent log file.

[0017] According to an embodiment of the present invention, the preset evaluation strategy includes:

[0018] Calculating the Euclidean distance from the current individual to the cluster center corresponding to the current individual;

[0019] Based on the Euclidean distance, calculating the similarity of the current individual to those meeting the preset cluster center condition;

[0020] Determining the fitness adjustment factor of the current individual, and calculating the fitness value of the current individual based on the fitness adjustment factor and the similarity.

[0021] According to an embodiment of the present invention, the fitness adjustment factor of the current individual is:

[0022]

[0023] Among them, j represents the dimension, g is the number of iteration generations, and i is the number of sub-populations. is the fitness value of the representative individual in the previous generation of sub-populations, and is the attribute value of the j-th dimension corresponding to the representative individual in the previous generation of sub-populations.

[0024] According to the parameter optimization method of the battery cooling system proposed by the embodiments of the present invention, an initial population containing diverse design parameter combinations is generated through a preset genetic algorithm, and clustering analysis is performed on each individual in the initial population to identify the representative cluster centers among them; for the cluster centers, simulation calculations are performed through advanced simulation software to obtain the fitness of the cluster centers; for the individuals that are not cluster centers, a rapid evaluation of the fitness is performed through a preset fitness evaluation strategy, and the iterative process is repeated until a preset number of iterations is reached. Thus, by adding an efficient fitness estimation mechanism during the simulation process, the evaluation cycle of a single design scheme in the simulation process is significantly shortened, the pressure on computing resources is alleviated, and the simulation evaluation efficiency is greatly improved.

[0025] To achieve the above object, an embodiment of the second aspect of the present invention proposes a parameter optimization device for a battery cooling system, including:

[0026] A determination module, configured to determine the parameters of the power battery cooling system to be optimized;

[0027] A fitness calculation module, configured to generate an initial population and multiple individuals of the initial population by using a preset genetic algorithm based on the parameters of the power battery cooling system to be optimized, perform clustering analysis on the multiple initial populations, and calculate the fitness of each individual according to the clustering analysis result;

[0028] An output module, configured to, after the fitness of each individual in the initial population is calculated, generate a new population and multiple individuals of the new population based on the initial population, and re-execute the step of performing clustering analysis on the new population until a preset iteration condition is reached, to obtain the optimized parameters of the power battery cooling system.

[0029] According to an embodiment of the present invention, the fitness calculation module includes:

[0030] A judgment unit, configured to use the first individual in the initial population as the current individual, and judge whether the current individual meets a preset cluster center condition;

[0031] A calculation unit, when the current individual meets the preset cluster center condition, generates a data file for calculating the fitness value of the current individual, and calculates the fitness value of the current individual according to the data file, otherwise, calculates the fitness value of the current individual based on a preset fitness calculation strategy.

[0032] An iteration unit, configured to use the second individual in the initial population as the current individual, and re - execute the step of determining whether the current individual meets the preset clustering center condition until the fitness values of each individual in the initial population are obtained.

[0033] According to an embodiment of the present invention, the calculation unit is specifically configured to:

[0034] Generate a Gambit log file and a Fluent log file for the current individual;

[0035] Obtain a grid according to the Gambit log file, and generate a data file for calculating the fitness value of the current individual according to the grid and the Fluent log file.

[0036] According to an embodiment of the present invention, the preset evaluation strategy includes:

[0037] Calculate the Euclidean distance from the current individual to the clustering center corresponding to the current individual;

[0038] Based on the Euclidean distance, calculate the similarity of the current individual to those meeting the preset clustering center condition;

[0039] Determine the fitness adjustment factor of the current individual, and calculate the fitness value of the current individual based on the fitness adjustment factor and the similarity.

[0040] According to an embodiment of the present invention, the fitness adjustment factor of the current individual is:

[0041]

[0042] Where j represents the dimension, g is the iteration generation number, i is the number of sub - populations, is the fitness value of the representative individual in the previous generation of sub - populations, and is the attribute value of the j - th dimension corresponding to the representative individual in the previous generation of sub - populations.

[0043] The parameter optimization device for a battery cooling system according to an embodiment of the present invention generates an initial population containing diverse combinations of design parameters through a preset genetic algorithm, and performs clustering analysis on each individual in the initial population to identify representative cluster centers therein; for the cluster centers, simulation calculations are performed through advanced simulation software to obtain the fitness of the cluster centers; for individuals that are not cluster centers, a rapid fitness evaluation is performed through a preset fitness evaluation strategy, and the iterative process is repeated until a preset number of iterations is reached. Thus, by adding an efficient fitness estimation mechanism during the simulation process, the evaluation cycle of a single design scheme in the simulation process is significantly shortened, the pressure on computing resources is alleviated, and the simulation evaluation efficiency is greatly improved.

[0044] To achieve the above object, an embodiment of the third aspect of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the parameter optimization method for the battery cooling system as described in the above embodiment.

[0045] To achieve the above object, an embodiment of the fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to be used to implement the parameter optimization method for the battery cooling system as described in the above embodiment.

[0046] To achieve the above object, an embodiment of the fifth aspect of the present invention provides a computer program product, including a computer program, and when the computer program is executed by a processor, it is used to implement the parameter optimization method for the battery cooling system as described in the above embodiment.

[0047] The additional aspects and advantages of the present invention will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present invention. Description of the Drawings

[0048] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0049] Figure 1 It is a flowchart of a parameter optimization method for a battery cooling system according to an embodiment of the present invention;

[0050] Figure 2 It is a schematic flowchart of a parameter optimization method for a battery cooling system according to a specific embodiment of the present invention;

[0051] Figure 3 It is a schematic diagram of the influence of population size on calculation results in the parameter optimization method for a battery cooling system according to an embodiment of the present invention;

[0052] Figure 4 Schematic block diagram of a parameter optimization device for a battery cooling system provided according to an embodiment of the present invention;

[0053] Figure 5 Schematic structural diagram of an electronic device provided according to an embodiment of the present invention.

[0054] Reference numerals:

[0055] 10 - Parameter optimization device for battery cooling system, 100 - Determination module, 200 - Fitness calculation module, 300 - Output module, 501 - Memory, 502 - Processor, 503 - Communication interface. Detailed implementation manners

[0056] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0057] A parameter optimization method, device, electronic device and medium for a battery cooling system according to an embodiment of the present invention will be described below with reference to the accompanying drawings. First, a parameter optimization method for a battery cooling system according to an embodiment of the present invention will be described with reference to the accompanying drawings. In view of the problem in the background art that only calculations can be performed according to a set model, resulting in time-consuming and laborious calculation processes and prone to redundant data, the present invention provides a parameter optimization method for a battery cooling system. An initial population containing diverse combinations of design parameters is generated through a preset genetic algorithm, and clustering analysis is performed on each individual in the initial population to identify representative clustering centers among them; for the clustering centers, simulation calculations are performed through high - level simulation software to obtain the fitness of the clustering centers; for individuals that are not clustering centers, a rapid evaluation of fitness is performed through a preset fitness evaluation strategy, and the iterative process is repeated until a preset number of iterations is reached. Thus, by adding an efficient fitness estimation mechanism in the simulation process, the evaluation cycle of a single design scheme in the simulation process is significantly shortened, the pressure on computing resources is alleviated, and the simulation evaluation efficiency is greatly improved.

[0058] Figure 1 It is a flowchart of a parameter optimization method for a battery cooling system provided according to an embodiment of the present invention.

[0059] As Figure 1 shown, the parameter optimization method for the battery cooling system includes the following steps:

[0060] In step S101, determine the parameters of the power battery cooling system to be optimized.

[0061] Specifically, the battery cooling system includes types such as air cooling, liquid cooling, and heat pipe cooling. Each type of cooling system has its specific parameter requirements and design criteria. For example, the air cooling system includes components such as a cooling fan and an exhaust port, so air flow and pressure loss need to be considered; the liquid cooling system includes components such as water cooling pipes, a cooling pump, and a cooling valve, so parameters such as the flow rate of the coolant, the inlet and outlet temperatures, and the pressure need to be considered. According to the relevant parameters of different components required for different types of cooling systems, the present invention can determine the parameters of the power battery cooling system to be optimized.

[0062] Exemplarily, the type of the power battery cooling system in an embodiment of the present invention is an air cooling system. Therefore, the parameters of the power battery cooling system can be set as parameters such as the battery discharge rate, the ambient temperature, and the cooling air wind speed. The battery discharge rate is obtained through the Battery Management System (BMS), the ambient temperature is obtained through a temperature sensor, and the cooling air wind speed is obtained through the rotation speed of the cooling fan.

[0063] It should be noted that the parameters of the power battery cooling system to be optimized determined by the above air cooling system are only exemplary. According to the different types of the power battery cooling system to be optimized, the types of parameters that can be obtained in the embodiments of the present invention are also different.

[0064] In step S102, based on the parameters of the power battery cooling system to be optimized, an initial population and multiple individuals of the initial population are generated by using a preset genetic algorithm, cluster analysis is performed on the multiple initial populations, and the fitness of each individual is calculated according to the cluster analysis result.

[0065] Specifically, after determining the parameters of the power battery cooling system to be optimized, the embodiments of the present invention can set the scale of the initial population generated in the genetic algorithm (i.e., the number of individuals included in the initial population). Each individual in the initial population represents a design scheme of a power battery cooling system. The initial population is randomly generated based on the parameters of the power battery cooling system to be optimized, cluster analysis is performed on the population individuals and the AP clustering parameters are set to obtain the cluster analysis result, and the fitness of each individual is calculated according to the cluster analysis result, so as to judge the optimal solution of the design scheme of the power battery cooling system.

[0066] As a possible implementation manner, in some embodiments, clustering analysis is performed on the initial population, and the fitness value of each individual is calculated according to the clustering analysis result, including: taking the first individual in the initial population as the current individual, and determining whether the current individual meets the preset clustering center condition; if the current individual meets the preset clustering center condition, generating a data file for calculating the fitness value of the current individual, and calculating the fitness value of the current individual according to the data file, otherwise, calculating the fitness value of the current individual based on a preset fitness calculation strategy; taking the second individual in the initial population as the current individual, and re-executing the step of determining whether the current individual meets the preset clustering center condition until the fitness values of each individual in the initial population are obtained.

[0067] Wherein, the clustering center refers to the center point or average position of all individuals in a certain cluster.

[0068] Specifically, after performing clustering analysis on the population individuals, the embodiments of the present invention judge the clustering center of each individual according to the preset clustering center judgment condition to identify representative clustering centers. For the individuals at the clustering center, the embodiments of the present invention generate a data file for calculating the fitness value of the individual through simulation software, and calculate the fitness value of the current individual according to the data file; for the individuals not at the clustering center, the embodiments of the present invention calculate the fitness value of the current individual through a preset fitness calculation strategy.

[0069] Wherein, in some embodiments, the preset evaluation strategy includes: calculating the Euclidean distance from the current individual to the clustering center corresponding to the current individual; calculating the similarity of the current individual with those meeting the preset clustering center condition based on the Euclidean distance; determining the fitness adjustment factor of the current individual, and calculating the fitness value of the current individual based on the fitness adjustment factor and the similarity.

[0070] Specifically, in the embodiments of the present invention, the fitness of a non-cluster center individual is estimated by the distance from the non-cluster center individual to the cluster center. First, the Euclidean distance from the current individual to the corresponding cluster center is calculated. Due to the characteristics of the clustering algorithm, the cluster center is not a real data point. Therefore, in the embodiments of the present invention, the distance from the current individual to the cluster center is calculated by estimating the similarity between the current individual and the preset cluster center condition, and the similarity between the current individual and the preset cluster center condition can be calculated by a preset similarity formula and the Euclidean distance from the current individual to the corresponding cluster center. The embodiments of the present invention consider that the influence weights of input parameters on the optimization result are different, that is, the weights of each parameter set by the traditional algorithm are the same. However, in actual situations, it may occur that one parameter has a greater influence on the result, while another parameter has a smaller influence on the result. Therefore, before calculating the fitness of the current individual, the embodiments of the present invention set the adjustment factor of the current individual, and flexibly control the change degree of the estimated fitness by changing the value of the adjustment factor.

[0071] For example, taking as a non-representative individual, as the cluster center, then the Euclidean distance calculation formula between the non-representative individual and the cluster center is as follows:

[0072]

[0073] where D is the dimension of the individuals in the population, i is the number of sub-populations, g is the number of iteration generations, represents the j-th attribute of the cluster center, represents the j-th attribute of the non-representative individual, and 1 ≤ j ≤ D.

[0074] The similarity between the non-representative individual and the representative individual after AP clustering is as follows:

[0075]

[0076] where, represents the Euclidean distance between the non-representative individual and the cluster center .

[0077] The fitness estimation formula between the non-representative individual and the representative individual after AP clustering is as follows:

[0078] f(p o i,g )=((1 - λ)×S(p o i,g ) + λ)×(f(p * i,g )×λ, λ ∈ [0, 1]

[0079] Among them, is the similarity between the non-representative individual and the representative individual, is the fitness value of the clustering center point, and λ is the adjustment factor.

[0080] Furthermore, in some embodiments, the fitness adjustment factor of the current individual is:

[0081]

[0082] Among them, j represents the dimension, g is the iteration generation number, i is the number of sub-populations, is the fitness value of the representative individual in the previous generation of sub-populations, and is the attribute value of the j-th dimension corresponding to the representative individual in the previous generation of sub-populations.

[0083] Optionally, in some embodiments, generating a data file for calculating the fitness value of the current individual includes: generating the Gambit log file and the Fluent log file of the current individual; obtaining the grid according to the Gambit log file, and generating a data file for calculating the fitness value of the current individual according to the grid and the Fluent log file.

[0084] It should be noted that the data file generated in the embodiments of the present invention for calculating the fitness value of the current individual specifically uses ANSYS Fluent, an advanced tool based on Computational Fluid Dynamics (CFD), to conduct a detailed simulation analysis on the lithium-ion battery. This process involves using discrete mathematics methods to accurately solve the complex fluid-structure coupling problems involved in the heat transfer process of the battery module, specifically manifested as the numerical solution of a series of partial differential equations.

[0085] Specifically, create a geometric model in the Gambit simulation software and set the grid parameters, for example, the element size, shape, and boundary strip, and generate the grid of the current individual according to the parameters of the current individual and the grid parameters; import the corresponding grid of the current individual in the Fluent simulation software and set the physical model of the power battery for simulation, and generate a data file for calculating the fitness value of the current individual.

[0086] Particularly, in a certain embodiment of the present invention, air is selected as the cooling medium, and its flow and heat transfer characteristics are accurately described by the simulation control equation system, which covers the basic laws of mass conservation, momentum conservation, energy conservation, and turbulent motion, ensuring the scientificity and accuracy of the simulation results.

[0087] In step S103, after the fitness of each individual in the initial population is calculated, a new population and multiple individuals of the new population are generated based on the initial population, and the step of performing cluster analysis on the new population is re-executed until a preset iteration condition is reached, and the optimized parameters of the power battery cooling system are obtained.

[0088] Specifically, after calculating the fitness of each individual in the initial population, the embodiment of the present invention can generate a new population based on the initial population by combining genetic operations such as selection, crossover, or mutation, and obtain multiple individuals in the new population. Then, cluster analysis is performed on these individuals again and step S102 is executed until the fitness of each individual in the new population is calculated. Based on the new population, genetic operations such as selection, crossover, or mutation are performed again, continuously generating and optimizing a new generation of populations until the preset iteration condition of the embodiment of the present invention is reached, and finally the optimal solution among them is obtained, and the optimized parameters of the power battery cooling system are output.

[0089] To enable those skilled in the art to further understand the parameter optimization method of the battery cooling system of the embodiment of the present invention, the following will be elaborated in detail with specific embodiments.

[0090] Specifically, as Figure 2 shown, Figure 2 is a schematic flowchart of the parameter optimization method of the battery cooling system provided according to a specific embodiment of the present invention. The parameter optimization method of the battery cooling system includes:

[0091] S201, Start.

[0092] S202, Initialize the population Pg = p1,g, p2,g,..., pI,g (g = 0).

[0093] S203, Initialize the parameters of Gambit and Fluent software.

[0094] S204, Perform AP clustering on the population.

[0095] S205, Initialize a single counter i: i = 1.

[0096] S206, Determine whether pi,g is a cluster center. If so, execute step S207; if not, execute step S208.

[0097] S207, Perform fitness simulation on pi,g and execute step S209.

[0098] S208, Perform fitness estimation on pi,g and execute step S209.

[0099] S209, Determine whether i is less than or equal to I. If so, execute S210; if not, execute step S211.

[0100] Wherein, I is the total number of individuals in the population.

[0101] S210, i = i + 1, and execute S206.

[0102] S211, perform selection, crossover, or mutation operations on the population.

[0103] S212, determine whether the preset stop condition is satisfied. If so, execute step S214; if not, execute step S213.

[0104] S213, generate the iteration counter g = g + 1, and return to execute step S204.

[0105] S214, end.

[0106] Exemplarily, under the condition that the maximum number of iterations of the genetic algorithm is set to 20, multi-dimensional experiments were carried out on the population size, which were set to 10, 16, 20, 25, and 40 individuals respectively. Figure 3 The left part intuitively shows the normal distribution form of the algorithm results, where the peak of the probability density reflects the highest point of data concentration. The experimental results show that when the population size is set to 20, the probability density reaches the peak, and at the same time the corresponding lowest temperature drops to 32.22 °C, indicating that the algorithm can converge to the optimal solution, that is, the lowest temperature point, effectively and stably at this population size. In contrast, whether the population size is too small (such as 10) or too large (such as 25), a significant expansion of the optimal solution distribution range is observed, and the optimization result deviates from the lowest temperature of 32.22 °C, revealing that an inappropriate population size may lead to instability and result deviation in the optimization process. In addition, to deeply explore the influence of the population size on the optimization process, this study also recorded the evolution trend of the average temperature of the power battery air-cooling system under different population sizes during 500 fitness simulations. As Figure 3 As shown in the right figure, when the population size is 20, the algorithm shows the most significant optimization effect, further verifying the key role of a moderate population size in ensuring the stability and efficiency of the optimization process.

[0107] In addition, "evolutionary generation = 200" was set as the termination condition, and minimizing the average temperature inside the battery module was taken as the optimization objective. The AP-GA (Adaptive Genetic Algorithm) was used for 10 independent optimization runs. During this period, the Preference parameter was set to "median, 0.5median, 2median, mean, min" respectively, and the results of each optimization were recorded in detail. To further explore the potential impact of different Preference settings on the algorithm performance when the time cost is the same, in another set of experiments, "the average number of clustering centers multiplied by the total number of generations = 1000" was set as the operation criterion, and the corresponding simulation was performed and data was collected. Analyzing the results of the two sets of experiments, we found that although the different termination conditions led to differences in the order of the optimal Preference settings, a significant common point was that when Preference was set to "median", the best optimization performance could be obtained under both termination conditions. This finding not only emphasizes the wide applicability of the "median" preference in balancing the optimization process but also reveals the relative efficiency differences of different preference settings under specific conditions.

[0108] Finally, the corresponding program code was written using MatLab software to control Gambit software to generate the required battery module grid model, and numerical simulation was carried out using FLUENT software. The experimental parameter settings are as follows: the battery discharge rate is constantly 2C, the ambient temperature is 298.15K, the cooling air velocity is 5m / S, the population size is 20, the maximum number of iterative generations is 20, the crossover rate is 0.7, and the mutation rate is 0.1. The optimization objectives are the highest temperature, average temperature, and maximum temperature difference inside the air-cooling system. The algorithm operation results are shown in Table 1.

[0109] Table 1

[0110]

[0111]

[0112] According to the parameter optimization method of the battery cooling system proposed in the embodiment of the present invention, an initial population containing diverse design parameter combinations is generated through a preset genetic algorithm, and clustering analysis is performed on each individual in the initial population to identify the representative clustering centers therein; for the clustering centers, simulation calculations are carried out through an advanced simulation software to obtain the fitness of the clustering centers; for the individuals that are not clustering centers, a fast evaluation of the fitness is performed through a preset fitness evaluation strategy, and the iterative process is repeated until the preset number of iterations is reached. Thus, by adding an efficient fitness estimation mechanism in the simulation process, the evaluation period of a single design scheme in the simulation process is significantly shortened, the pressure on computing resources is alleviated, and the simulation evaluation efficiency is greatly improved.

[0113] Next, a parameter optimization device for a battery cooling system according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0114] Figure 4 FIG. 1 is a block diagram of a parameter optimization device for a battery cooling system according to an embodiment of the present invention.

[0115] As Figure 4 shown in FIG. 1, the parameter optimization device 10 for the battery cooling system includes: a determination module 100, a fitness calculation module 200, and an output module 300.

[0116] Among them, the determination module 100 is configured to determine the parameters of the power battery cooling system to be optimized;

[0117] The fitness calculation module 200 is configured to generate an initial population and multiple individuals of the initial population based on the parameters of the power battery cooling system to be optimized, perform cluster analysis on the multiple initial populations, and calculate the fitness of each individual according to the cluster analysis result;

[0118] The output module 300 is configured to, after the fitness of each individual in the initial population is calculated, generate a new population and multiple individuals of the new population based on the initial population, and re-execute the step of performing cluster analysis on the new population until a preset iteration condition is reached, and obtain the optimized parameters of the power battery cooling system.

[0119] According to an embodiment of the present invention, the fitness calculation module 200 includes:

[0120] A judgment unit, configured to use the first individual in the initial population as the current individual and judge whether the current individual meets a preset cluster center condition;

[0121] A calculation unit, when the current individual meets the preset cluster center condition, generates a data file for calculating the fitness value of the current individual, and calculates the fitness value of the current individual according to the data file, otherwise, calculates the fitness value of the current individual based on a preset fitness calculation strategy;

[0122] An iteration unit, configured to use the second individual in the initial population as the current individual and re-execute the step of judging whether the current individual meets the preset cluster center condition until the fitness value of each individual in the initial population is obtained.

[0123] According to an embodiment of the present invention, the calculation unit is specifically configured to: generate a Gambit log file and a Fluent log file of the current individual; obtain a grid according to the Gambit log file, and generate a data file for calculating the fitness value of the current individual according to the grid and the Fluent log file.

[0124] According to an embodiment of the present invention, the preset evaluation strategy includes: calculating the Euclidean distance from the current individual to the cluster center corresponding to the current individual; calculating the similarity of the current individual to the preset cluster center condition based on the Euclidean distance; determining the fitness adjustment factor of the current individual, and calculating the fitness value of the current individual based on the fitness adjustment factor and the similarity.

[0125] According to an embodiment of the present invention, the fitness adjustment factor of the current individual is:

[0126]

[0127] where j represents the dimension, g is the iteration generation number, i is the number of subpopulations, is the fitness value of the representative individual in the previous generation of subpopulations, and is the attribute value of the j-th dimension corresponding to the representative individual in the previous generation of subpopulations.

[0128] The parameter optimization device for the battery cooling system proposed according to the embodiment of the present invention generates an initial population containing diverse design parameter combinations through a preset genetic algorithm, performs clustering analysis on each individual in the initial population, and identifies the representative cluster centers therein; performs simulation calculations on the cluster centers through high-level simulation software to obtain the fitness of the cluster centers; for the individuals that are not cluster centers, quickly evaluate the fitness through a preset fitness evaluation strategy, and repeat the iterative process until the preset number of iterations is reached. Thus, by adding an efficient fitness estimation mechanism during the simulation process, the evaluation cycle of a single design scheme in the simulation process is significantly shortened, the pressure on computing resources is alleviated, and the simulation evaluation efficiency is greatly improved.

[0129] Figure 5 The structural schematic diagram of the electronic device provided by the embodiment of the present invention. The electronic device may include:

[0130] A memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.

[0131] When the processor 502 executes the program, it implements the parameter optimization method for the battery cooling system provided in the above embodiment.

[0132] Further, the electronic device further includes:

[0133] A communication interface 503 for communication between the memory 501 and the processor 502.

[0134] The memory 501 is used to store a computer program executable on the processor 502.

[0135] The memory 501 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0136] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be interconnected through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0137] Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 can communicate with each other through an internal interface.

[0138] The processor 502 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0139] The embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the parameter optimization method of the battery cooling system as described above is implemented.

[0140] The embodiments of the present invention also provide a computer program product, including a computer program, and when the program is executed by a processor, the parameter optimization method of the battery cooling system as described above is implemented.

[0141] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0142] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0143] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A parameter optimization method for a battery cooling system, characterized in that: The following steps are involved: Determine the power battery cooling system parameters to be optimized; Based on the power battery cooling system parameters to be optimized, an initial population and a plurality of individuals of the initial population are generated by using a preset genetic algorithm, cluster analysis is performed on the plurality of initial populations, and the fitness of each individual is calculated according to the cluster analysis results; After the fitness calculation of each individual in the initial population is completed, a new population and multiple individuals of the new population are generated based on the initial population, and the step of performing cluster analysis on the new population is re-executed until a preset iteration condition is reached to obtain optimized power battery cooling system parameters.

2. The method according to claim 1, characterized in that The cluster analysis is performed on the initial population, and the fitness value of each individual is calculated according to the cluster analysis result, including: Taking the first individual in the initial population as the current individual, and determining whether the current individual satisfies a preset cluster center condition; If the current individual meets the preset cluster center condition, a data file for calculating the fitness value of the current individual is generated, and the fitness value of the current individual is calculated according to the data file; otherwise, the fitness value of the current individual is calculated based on a preset fitness calculation strategy; The second individual in the initial population is used as the current individual, and the step of determining whether the current individual satisfies the preset cluster center condition is re-executed until the fitness value of each individual in the initial population is obtained.

3. The method according to claim 2, characterized in that The generating of a data file for calculating the fitness value of the current individual comprises: Generate a Gambit log file and a Fluent log file of the current individual; A grid is obtained according to the Gambit log file, and a data file for calculating the fitness value of the current individual is generated according to the grid and the Fluent log file.

4. The method according to claim 1, characterized in that The preset evaluation strategy includes: Calculate the Euclidean distance from the current individual to the cluster center corresponding to the current individual; Based on the Euclidean distance, calculating the similarity between the current individual and the cluster center that meets the preset cluster center condition; A fitness adjustment factor of the current individual is determined, and a fitness value of the current individual is calculated based on the fitness adjustment factor and the similarity.

5. The method according to claim 4, characterized in that The fitness adjustment factor of the current individual is: Among them, j represents the dimension, g is the iteration number, i is the number of subpopulations, is the fitness value of the representative individual in the previous generation subpopulation, is the attribute value of the jth dimension corresponding to the representative individual in the previous subpopulation.

6. A parameter optimization device for a battery cooling system, characterized in that: include: A determination module, used to determine the power battery cooling system parameters to be optimized; A fitness calculation module, used to generate an initial population and a plurality of individuals of the initial population using a preset genetic algorithm based on the power battery cooling system parameters to be optimized, perform cluster analysis on the plurality of initial populations, and calculate the fitness of each individual according to the cluster analysis results; The output module is used to generate a new population and multiple individuals of the new population based on the initial population after the fitness calculation of each individual in the initial population is completed, and re-execute the step of clustering analysis on the new population until the preset iteration condition is reached to obtain the optimized power battery cooling system parameters.

7. The device according to claim 6, according to an embodiment of the present invention, the fitness calculation module comprises: A judging unit, configured to take the first individual in the initial population as a current individual and judge whether the current individual satisfies a preset cluster center condition; A calculation unit, when the current individual meets the preset cluster center condition, generates a data file for calculating the fitness value of the current individual, and calculates the fitness value of the current individual according to the data file; otherwise, calculates the fitness value of the current individual based on a preset fitness calculation strategy; The iteration unit is used to take the second individual in the initial population as the current individual and re-execute the step of determining whether the current individual meets the preset cluster center condition until the fitness value of each individual in the initial population is obtained.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the parameter optimization method for a battery cooling system according to any one of claims 1 to 5.

9. A computer storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the parameter optimization method of the battery cooling system according to any one of claims 1 to 5.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, is used to implement the parameter optimization method of the battery cooling system according to any one of claims 1 to 5.

Images