Battery pack thermal management system control method based on improved adaptive genetic algorithm

Abstract

The application provides a battery pack thermal management system control method based on an improved adaptive genetic algorithm, and comprises the following steps: establishing a battery pack thermal model considering the thermal coupling effect between battery modules, constructing a dynamic change model of the battery module temperature, and then obtaining the temperature model of the first and last battery modules in the battery pack according to the dynamic change model of the battery module temperature; a multi-objective optimization function is constructed by comprehensively considering the cooling system energy consumption, the battery pack temperature control accuracy and the battery module temperature uniformity; an improved adaptive genetic algorithm is obtained by introducing an adaptive crossover and mutation mechanism, an elite reservation strategy and a dynamic penalty function; the multi-objective optimization function is solved based on the improved adaptive genetic algorithm to obtain an optimal cooling liquid flow rate; and the optimal cooling liquid flow rate is converted into a control instruction of the electronic water pump rotating speed through a water pump characteristic curve, so that the electronic water pump rotating speed is adjusted in real time. The application can realize accurate control of the battery pack thermal management system.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, and more specifically to a control method for a battery pack thermal management system based on an improved adaptive genetic algorithm. Background Technology

[0002] Among the core technologies of new energy vehicles, the performance of the power battery system is crucial. Lithium-ion power batteries, with their advantages of high energy density, high specific power, lightweight design, and long cycle life, have become the mainstream choice for power batteries in new energy vehicles. However, the performance of lithium-ion power batteries is closely related to their operating temperature. Studies have shown that exceeding the optimal operating temperature range will lead to a significant reduction in charge and discharge efficiency, accelerated cycle life decay, and even serious safety issues such as thermal runaway. Especially under extreme operating conditions in extremely hot regions (maximum vehicle speed, high-speed uphill driving, etc.), the large amount of heat generated by the battery can exacerbate localized temperature hotspots, posing a significant safety hazard to the battery module. The suitable operating temperature for lithium-ion batteries should be controlled within the range of 25-40°C, and the temperature difference between battery modules should ideally be controlled within 5°C. Therefore, an efficient and stable power battery thermal management system is crucial for ensuring battery performance and overall vehicle safety.

[0003] Currently, the control methods for power battery thermal management systems mainly fall into four categories: traditional PID control, model predictive control, deep learning-based intelligent control, and intelligent optimization algorithm control. Traditional PID control is widely used due to its simple structure and ease of implementation, but its fixed control parameters make it difficult to adapt to the dynamic characteristics of the battery under different operating conditions. While model predictive control possesses predictive and constraint handling capabilities, its performance heavily relies on the accuracy of the system model, and it suffers from high computational complexity and difficulty in guaranteeing real-time performance. Although deep learning-based intelligent control methods can handle nonlinear relationships, existing solutions still suffer from problems such as a single model structure and insufficient feature extraction capabilities.

[0004] In the field of intelligent optimization algorithms, genetic algorithms have attracted widespread attention due to their global search capabilities and ability to handle complex nonlinear problems. Traditional genetic algorithms can search for optimal solutions without requiring specialized knowledge of the problem domain by simulating natural selection and genetic processes. However, in complex real-time control problems such as battery thermal management systems, traditional genetic algorithms still suffer from slow convergence speed, poor global search capabilities, and difficulty in effectively handling multi-objective optimization problems. In particular, the trade-offs between temperature uniformity, temperature control accuracy, and energy efficiency affect the control accuracy of battery pack thermal management systems. Summary of the Invention

[0005] In view of this, the present invention provides a control method for a battery pack thermal management system based on an improved adaptive genetic algorithm, in order to solve the problems of slow convergence speed, poor global search capability, and difficulty in effectively handling multi-objective optimization problems in the prior art, which affect the control accuracy of the battery pack thermal management system.

[0006] A control method for a battery pack thermal management system based on an improved adaptive genetic algorithm, comprising:

[0007] Step S1: Establish a battery pack thermal model that considers the thermal coupling effect between battery modules. Based on the battery pack thermal model, obtain the heat generation of the battery modules, the convective heat transfer between the battery modules and the coolant, and the heat conduction between the battery modules. Then, construct a dynamic change model of the battery module temperature. Based on the dynamic change model of the battery module temperature, obtain the temperature model of the first and last battery modules in the battery pack.

[0008] Step S2: Based on the temperature models of the first and last battery modules and the heat generation of the battery modules, and combined with the battery pack temperature control accuracy model, construct a multi-objective optimization function that comprehensively considers the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery modules.

[0009] Step S3: By introducing an adaptive crossover and mutation mechanism, an elite retention strategy, and a dynamic penalty function, an improved adaptive genetic algorithm is obtained.

[0010] Step S4: Based on the improved adaptive genetic algorithm, the multi-objective optimization function is solved to obtain the optimal coolant flow rate;

[0011] Step S5: The optimal coolant flow rate is converted into a control command for the electric water pump speed by the water pump characteristic curve, and the control command is sent to the actuator of the battery pack thermal management system via the CAN bus to realize real-time adjustment of the electric water pump speed.

[0012] The battery pack thermal management system control method based on an improved adaptive genetic algorithm provided by the present invention has the following beneficial effects:

[0013] 1. This invention establishes a battery pack thermal model that considers the thermal coupling effect between battery modules, and obtains the amount of heat generated by the battery module, the convective heat transfer between the battery module and the coolant, and the amount of heat conduction between the battery modules. It can integrate the coupling mechanisms of multiple physical fields such as reversible and irreversible heat generation, convective heat transfer and heat conduction, and provide a reliable calculation basis for the optimization of the thermal management system.

[0014] 2. This invention designs a multi-objective optimization function that comprehensively considers the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery module. Based on an improved adaptive genetic algorithm, it optimizes the cooling water flow rate of the battery pack to achieve the multi-objective goal of simultaneously optimizing the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery module.

[0015] 3. By improving the traditional genetic algorithm, an adaptive crossover and mutation mechanism, an elite retention strategy, and a dynamic penalty function are introduced, significantly improving the algorithm's convergence speed and global search capability. Experimental results show that under extreme operating conditions, the method of this invention controls the battery module temperature difference within a smaller range, and the system energy efficiency is significantly improved compared to traditional methods. By solving the multi-objective optimization function, the optimized coolant flow rate is converted into a control command for the electric water pump speed, and transmitted in real time via the CAN bus, ultimately achieving precise control of the battery pack thermal management system. Attached Figure Description

[0016] Figure 1 A flowchart of a battery pack thermal management system control method based on an improved adaptive genetic algorithm provided in an embodiment of the present invention;

[0017] Figure 2 A comparison chart of the total energy consumption of cooling systems using different methods;

[0018] Figure 3 A comparison chart of the temperature control accuracy of battery packs using different methods;

[0019] Figure 4 This is a graph showing the maximum temperature difference ratio of battery modules using different methods. Detailed Implementation

[0020] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein 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 intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0021] Please see Figure 1 The present invention provides a battery pack thermal management system control method based on an improved adaptive genetic algorithm, comprising steps S1 to S5:

[0022] Step S1: Establish a battery pack thermal model that considers the thermal coupling effect between battery modules. Based on the battery pack thermal model, obtain the heat generation of the battery modules, the convective heat transfer between the battery modules and the coolant, and the heat conduction between the battery modules. Then, construct a dynamic change model of the battery module temperature. Finally, obtain the temperature model of the first and last battery modules in the battery pack based on the dynamic change model of the battery module temperature.

[0023] The battery module heat generation model considers both reversible and irreversible heat generation, and its expression is as follows:

[0024] ;

[0025] in, For the first The amount of heat generated by each battery module Indicates the battery module current; This is the internal resistance of the battery module, and its value is related to the module temperature and the amount of power. In this embodiment, it is taken as 0.8mΩ. Indicates the first The temperature of each battery module is the entropy thermal coefficient, which is related to the SOC state of the battery module, and its value is shown in Table 1; The part that generates heat reversibly. This is the part that generates heat irreversibly.

[0026] Table 1 Entropy-Heat Coefficient Lookup Table

[0027]

[0028] In this embodiment, the coolant is a 50% (by volume) ethylene glycol aqueous solution. In the liquid cooling system, heat transfer within the battery pack mainly includes convective heat transfer and thermal conduction. For convective heat transfer between the battery module and the coolant, the following equation holds:

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] in, For the first The convective heat transfer between the battery module and the coolant The convective heat transfer coefficient is calculated using the Dittus-Boelter correlation in this embodiment; In this embodiment, the effective heat exchange area is 0.012283 m². 2 ; For the first The temperature of the coolant at each battery module The Reynolds coefficient of the coolant within the system. For Prandtl coefficient, The dynamic viscosity of the coolant at the average temperature inside the pipe. In this embodiment, the dynamic viscosity of the coolant is at the pipe wall temperature. Take 1.02; The thermal conductivity of the coolant is taken as 0.4 W / (m•K) in this embodiment; The diameter of the coolant pipe is 22 mm in this embodiment; The specific heat capacity of the coolant is 3320 J / (kg•℃); The dynamic viscosity of the coolant is 3.5 mPa•s at 25°C. The density of the coolant is 1082 kg / m³. 3 ; This refers to the coolant flow rate.

[0034] For heat transfer through conduction between battery modules, the following equation applies:

[0035] ;

[0036] in, For the first Thermal conductivity of each battery module The thermal conductivity coefficient between adjacent battery cells is taken as 1000 W / (m•℃) in this embodiment; For the first The temperature of each battery module For the first The temperature of each battery module For the first The battery module and the first Contact area between battery modules For the first The battery module and the first The thermal conductivity characteristic length between battery modules For the first The battery module and the first Contact area between battery modules For the first The battery module and the first The thermal conductivity characteristic length between individual battery modules. In this embodiment, the thermal conductivity coefficient, contact area, and thermal conductivity characteristic length are all the same between adjacent battery cells. and The value is 0.035811 mm. 2 ; and The value is 0.01m.

[0037] Based on the principle of energy conservation, the dynamic change model of battery module temperature can be obtained by satisfying the following equation:

[0038] ;

[0039] in, This represents the specific heat capacity of a single battery cell, taken as 1128.45 J / (kg•℃); The mass of a single battery pack unit is 3.2 kg in this embodiment; Indicates the first Rate of temperature change of each battery module over time.

[0040] In the module structure design of a battery pack, the first battery module (module 1) is typically located at the inlet of the cooling water pipe, while the last battery module is located at the outlet of the cooling pipe. The coolant continuously absorbs heat from each module along the flow direction, causing its temperature to gradually increase. Therefore, the temperature of module 1, which is closer to the inlet, is usually lower than that of the last module at the outlet. Based on this temperature gradient characteristic, the temperature distribution pattern of the entire battery pack can be derived by establishing a thermodynamic model for only the first and last battery modules.

[0041] In this embodiment, the total number of battery modules It is 44.

[0042] ;

[0043] ;

[0044] in, This represents the rate of temperature change of the first battery module over time. Indicates the first Rate of temperature change of each battery module over time In this embodiment, the total number of battery modules is [number]. It is 44. This indicates the temperature of the first battery module. This indicates the temperature of the second battery module. Indicates the first The temperature of each battery module Indicates the first The temperature of each battery module The temperature of the coolant at the first battery module is set to 20°C. For the first The temperature of the coolant at each battery module , , It is an intermediate variable.

[0045] According to the laws of heat transfer, the total heat absorbed by the cooling fluid in the battery pack cooling pipe from the inlet to the outlet per unit time is... for:

[0046] ;

[0047] The total heat dissipation of the modules within the battery pack is equal to the total heat absorbed by the internal coolant from the inlet to the outlet. According to the law of conservation of energy:

[0048] .

[0049] Within the cooling pipes of the battery module, along the flow direction of the coolant, if heat transfer between battery modules is neglected, the coolant temperature around each battery can be considered to increase at a constant amplitude. Since the test conditions in this embodiment are high-temperature extreme steady-state conditions, and the temperature difference between battery modules is relatively small, research shows that under steady-state conditions, the convective heat transfer conditions formed by the coolant flow are relatively stable, and the heat exchange rate remains relatively constant in the flow channel. This stable heat exchange mechanism makes the temperature change along the flow direction exhibit approximately linear characteristics. Therefore, when processing the battery module and coolant temperature distribution model, it is approximately considered to increase at a constant amplitude. Its expression is:

[0050] ;

[0051] ;

[0052] in, This indicates the temperature of the third battery module. This refers to the temperature of the coolant at the second battery module. This refers to the temperature of the coolant at the third battery module. For the first The temperature of the coolant at each battery module.

[0053] Therefore, the temperature model of the first and last battery modules can be derived to satisfy the following formula:

[0054] ;

[0055] ;

[0056] ;

[0057] ;

[0058] ;

[0059] ;

[0060] ;

[0061] ;

[0062] ;

[0063] ;

[0064] in, The rate of temperature change of the first battery module over time. For the first Rate of temperature change of each battery module over time The temperature of the first battery module. For the first The temperature of each battery module , , , , , For custom intermediate values, , , and As an intermediate variable, , These are the first intermediate function and the second intermediate function, respectively. , This refers to the contact area between battery modules. The characteristic length of thermal conduction between battery modules; ; ; ; This refers to the temperature of the coolant at the first battery module.

[0065] Step S2: Based on the temperature models of the first and last battery modules and the heat generation of the battery modules, and combined with the battery pack temperature control accuracy model, construct a multi-objective optimization function that comprehensively considers the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery modules.

[0066] The expression for the multi-objective optimization function is as follows:

[0067] ;

[0068] in, Represents a multi-objective optimization function. For cooling system energy consumption, To ensure accurate temperature control of the battery pack, This represents the maximum temperature difference of the battery module. For the reference value of cooling system energy consumption, 500J is used in this embodiment; For the reference value of battery pack temperature control accuracy, 5℃ is used in this embodiment; The maximum temperature difference reference value for the battery module is 3℃ in this embodiment. , , These are the weighting coefficients, and ;

[0069] ;

[0070] in, It is the acceleration due to gravity. The pump head is set to 2.5m in this embodiment; For traffic, , For time The differential;

[0071] ;

[0072] in, This represents the average temperature of the battery module. The target temperature for the battery module is 25°C in this embodiment;

[0073] .

[0074] Step S3: By introducing an adaptive crossover and mutation mechanism, an elite retention strategy, and a dynamic penalty function, an improved adaptive genetic algorithm is obtained.

[0075] Among them, the adaptive crossover and mutation mechanism dynamically adjusts the crossover rate and mutation rate, enabling the algorithm to adaptively balance global exploration and local exploitation capabilities during the search process. The adaptive crossover and mutation mechanism satisfies the following formula:

[0076] ;

[0077] ;

[0078] in, Indicates adaptive crossover rate. Indicates the adaptive mutation rate. , , , These are preset parameters. This represents the larger fitness value among the two individuals participating in the crossover operation. This represents the fitness value of an individual. The average fitness of the current population. This represents the maximum fitness of the current population. In this embodiment, , , , .

[0079] The elite retention strategy satisfies the following formula:

[0080] ;

[0081] ;

[0082] in, Indicates the first A collection of the elite of the era The first in the population individual, for fitness value, Selecting a threshold for elites and These are the maximum and minimum fitness of the current population, respectively; The ratio of elites is 5% in this embodiment.

[0083] The dynamic penalty function satisfies the following equation:

[0084] ;

[0085] ;

[0086] ;

[0087] in, This represents the fitness function after considering constraints; The original fitness function; This is a dynamic penalty item; This represents the number of iterations. Let be the penalty coefficient, representing the basic strength controlling the penalty. Considering the early iteration space search speed and accelerating convergence speed, we take . =2; Let be the time factor, representing the rate at which the penalty intensity increases with the number of iterations. To provide a good balance, take . =2.5; For the first One constraint condition; This represents the total number of constraints. For indicator functions; The violation factor represents the sensitivity of the control to the degree of constraint violation. To provide an optimal balance between temperature uniformity, temperature control accuracy, and energy efficiency, we take... =2.

[0088] In addition, this embodiment introduces a knowledge-guided initial population generation mechanism, in which 50% of the initial population individuals are set near the historical optimal solution, 30% are set in the estimated optimal solution region, and the remaining 20% ​​are randomly generated to maintain population diversity.

[0089] Step S4: Based on the improved adaptive genetic algorithm, the multi-objective optimization function is solved to obtain the optimal coolant flow rate.

[0090] Solving the multi-objective optimization function involves optimizing the coolant flow rate. To obtain the optimal coolant flow rate To minimize the multi-objective optimization function And while ensuring battery safety, balance system energy consumption and temperature uniformity.

[0091] Specifically, when solving a multi-objective optimization function, the boundary conditions are as follows:

[0092] ;

[0093] ;

[0094] .

[0095] In practice, the vehicle's built-in sensors collect real-time data on the battery pack's State of Charge (SOC), current, and voltage. The real-time heat load is calculated using a built-in model and parameters. Coolant flow rate is used as a decision variable, encoded as a real number. For dynamic operating conditions, the control cycle is discretized into several time intervals, each corresponding to a flow rate value, forming a decision vector.

[0096] Step S5: The optimal coolant flow rate is converted into a control command for the electric water pump speed by the water pump characteristic curve, and the control command is sent to the actuator of the battery pack thermal management system via the CAN bus to realize real-time adjustment of the electric water pump speed.

[0097] Wherein, step S5 satisfies the following formula:

[0098] ;

[0099] in, Indicates the speed of the electronic water pump. and These are the characteristic parameters of the water pump; The optimal coolant flow rate is determined.

[0100] Finally, the control commands are sent to the actuator of the battery pack thermal management system via the CAN bus to achieve real-time adjustment of the speed of the battery pack electronic water pump.

[0101] In this embodiment, a real vehicle was tested at its maximum speed (120 km / h) in an environmental chamber at 40°C. The energy consumption, temperature control accuracy, and maximum temperature difference of the battery module under the PID control strategy, the genetic algorithm (GA) control strategy, and the method of this invention were compared and analyzed. Figure 2 As can be seen, under the same operating conditions, the cooling system of this invention has the lowest energy consumption. From... Figure 3 As can be seen, the genetic algorithm (GA) control strategy of this invention can reach the target temperature faster and with higher control accuracy than the PID control strategy, but this invention offers a slight improvement in control accuracy compared to the genetic algorithm (GA) control strategy. Figure 4 As can be seen, the battery module of the present invention has the smallest temperature difference, only about 0.5℃.

[0102] In summary, the battery pack thermal management system control method based on the improved adaptive genetic algorithm according to the above embodiments has the following beneficial effects:

[0103] 1. This invention establishes a battery pack thermal model that considers the thermal coupling effect between battery modules, and obtains the amount of heat generated by the battery module, the convective heat transfer between the battery module and the coolant, and the amount of heat conduction between the battery modules. It can integrate the coupling mechanisms of multiple physical fields such as reversible and irreversible heat generation, convective heat transfer and heat conduction, and provide a reliable calculation basis for the optimization of the thermal management system.

[0104] 2. This invention designs a multi-objective optimization function that comprehensively considers the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery module. Based on an improved adaptive genetic algorithm, it optimizes the cooling water flow rate of the battery pack to achieve the multi-objective goal of simultaneously optimizing the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery module.

[0105] 3. By improving the traditional genetic algorithm, an adaptive crossover and mutation mechanism, an elite retention strategy, and a dynamic penalty function are introduced, significantly improving the algorithm's convergence speed and global search capability. Experimental results show that under extreme operating conditions, the method of this invention controls the battery module temperature difference within a smaller range, and the system energy efficiency is significantly improved compared to traditional methods. By solving the multi-objective optimization function, the optimized coolant flow rate is converted into a control command for the electric water pump speed, and transmitted in real time via the CAN bus, ultimately achieving precise control of the battery pack thermal management system.

[0106] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A control method for a battery pack thermal management system based on an improved adaptive genetic algorithm, characterized in that, include: Step S1: Establish a battery pack thermal model that considers the thermal coupling effect between battery modules. Based on the battery pack thermal model, obtain the heat generation of the battery modules, the convective heat transfer between the battery modules and the coolant, and the heat conduction between the battery modules. Then, construct a dynamic change model of the battery module temperature. Based on the dynamic change model of the battery module temperature, obtain the temperature model of the first and last battery modules in the battery pack. Step S2: Based on the temperature models of the first and last battery modules and the heat generation of the battery modules, and combined with the battery pack temperature control accuracy model, construct a multi-objective optimization function that comprehensively considers the energy consumption of the cooling system, the temperature control accuracy of the battery pack, and the temperature uniformity of the battery modules. Step S3: By introducing an adaptive crossover and mutation mechanism, an elite retention strategy, and a dynamic penalty function, an improved adaptive genetic algorithm is obtained. Step S4: Based on the improved adaptive genetic algorithm, the multi-objective optimization function is solved to obtain the optimal coolant flow rate; Step S5: The optimal coolant flow rate is converted into a control command for the electric water pump speed through the water pump characteristic curve, and the control command is sent to the actuator of the battery pack thermal management system through the CAN bus to realize the real-time adjustment of the electric water pump speed. In step S1, the dynamic change model of the battery module temperature satisfies the following equation: ； in, This indicates the specific heat capacity of a single cell in the battery pack. For the mass of a single battery pack cell, Indicates the first Rate of temperature change of each battery module over time For the first The amount of heat generated by each battery module For the first The convective heat transfer between the battery module and the coolant For the first Thermal conductivity of each battery module; ； in, Indicates the battery module current. This refers to the internal resistance of the battery module. Indicates the first The temperature of each battery module It is the entropy heat coefficient; ； ； ； ； in, The convective heat transfer coefficient is... For effective heat exchange area, For the first The temperature of the coolant at each battery module The Reynolds coefficient of the coolant within the system. For Prandtl coefficient, The dynamic viscosity of the coolant at the average temperature inside the pipe. The dynamic viscosity of the coolant at the pipe wall temperature. The thermal conductivity of the coolant. The diameter of the coolant pipe. The specific heat capacity of the coolant. The dynamic viscosity of the coolant. For coolant density, This refers to the coolant flow rate; ； in, The thermal conductivity coefficient between adjacent battery cells. For the first The temperature of each battery module For the first The temperature of each battery module For the first The battery module and the first Contact area between battery modules For the first The battery module and the first The thermal conductivity characteristic length between battery modules For the first The battery module and the first Contact area between battery modules For the first The battery module and the first The thermal conductivity characteristic length between battery modules.

2. The battery pack thermal management system control method based on an improved adaptive genetic algorithm according to claim 1, characterized in that, In step S1, the temperature models of the first and last battery modules satisfy the following formula: ； ； ； ； ； ； ； ； ； ； in, The rate of temperature change of the first battery module over time. For the first Rate of temperature change of each battery module over time This represents the total number of battery modules. The temperature of the first battery module. For the first The temperature of each battery module , , , , , For custom intermediate values, , , and As an intermediate variable, , These are the first intermediate function and the second intermediate function, respectively. , This refers to the contact area between battery modules. The characteristic length of thermal conduction between battery modules; ; ; ; This refers to the temperature of the coolant at the first battery module.

3. The battery pack thermal management system control method based on an improved adaptive genetic algorithm according to claim 2, characterized in that, In step S2, the expression for the multi-objective optimization function is: ； in, Represents a multi-objective optimization function. For cooling system energy consumption, To ensure accurate temperature control of the battery pack, This represents the maximum temperature difference of the battery module. This is a reference value for the energy consumption of the cooling system. This serves as a reference value for the accuracy of battery pack temperature control. This is a reference value for the maximum temperature difference of the battery module. , , These are the weighting coefficients, and ; ； in, It is the acceleration due to gravity. For the head of the water pump, For traffic, , For time The differential; ； in, This represents the average temperature of the battery module. The target temperature for the battery module; 。 4. The battery pack thermal management system control method based on an improved adaptive genetic algorithm according to claim 1, characterized in that, In step S3, the adaptive crossover mutation mechanism satisfies the following equation: ； ； in, Indicates adaptive crossover rate. Indicates the adaptive mutation rate. , , , These are preset parameters. This represents the larger fitness value among the two individuals participating in the crossover operation. This represents the fitness value of an individual. The average fitness of the current population. This represents the maximum fitness of the current population. The elite retention strategy satisfies the following formula: ； ； in, Indicates the first A collection of the elite of the era The first in the population individual, for fitness value, Selecting a threshold for elites and These are the maximum and minimum fitness of the current population, respectively. This represents the proportion of elites. The dynamic penalty function satisfies the following equation: ； ； ； in, This represents the fitness function after considering constraints; The original fitness function; This is a dynamic penalty item; This represents the number of iterations. This is the penalty coefficient; The time factor; For the first One constraint condition; This represents the total number of constraints. For indicator functions; This is the violation factor.

5. The battery pack thermal management system control method based on an improved adaptive genetic algorithm according to claim 3, characterized in that, In step S4, when solving the multi-objective optimization function, the boundary conditions are as follows: ； ； 。 6. The battery pack thermal management system control method based on an improved adaptive genetic algorithm according to claim 5, characterized in that, Step S5 satisfies the following formula: ； in, Indicates the speed of the electronic water pump. and These are the characteristic parameters of the water pump. The optimal coolant flow rate.

Images