Automobile power battery thermal management control method and system based on charging and discharging parameters

Abstract

The invention provides an automobile power battery thermal management control method and system based on charging and discharging parameters, and relates to the technical field of power battery thermal management. Comprising the following steps: predicting the predicted temperature of the power battery in future; a deep reinforcement learning control strategy is adopted, a state is defined as a current state and a predicted temperature of the power battery, an action is a charge and discharge control parameter of the power battery, a reward function is defined as a comprehensive index of performance and service life of the power battery, and an optimal control strategy of the power battery is learned by taking a maximum value of the reward function as a target. Optimal power battery charging and discharging control parameters are obtained; and controlling the power battery according to the optimal power battery charging and discharging control parameters to realize thermal management of the power battery. According to the method, the optimal power battery charging and discharging control parameters which follow the predicted temperature of the power battery at the future moment are obtained, charging and discharging control over the power battery is achieved based on the optimal power battery charging and discharging control parameters, and then dynamic control over the temperature of the power battery is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of thermal management of power batteries, and in particular to a thermal management control method and system for automotive power batteries based on charge and discharge parameters. Background Art

[0002] Existing power battery thermal management systems have limitations in quickly responding to temperature changes and adapting to different operating conditions, making it difficult to optimally ensure battery performance and safety. For example, traditional thermal management systems usually rely on preset control strategies and cannot be dynamically adjusted based on real-time data, which may lead to overheating or inefficient cooling.

[0003] In addition, in flying cars, the existing systems are even more inadequate due to their unique operating environment and frequent changes in operating conditions.

[0004] In the Chinese invention patent application with publication number CN 115295927 A and titled Temperature Control Method, Device, Equipment and Storage Medium for Energy Storage System, a preset temperature control strategy is disclosed, in which a first preset safety temperature threshold and a second preset safety temperature threshold are set:

[0005] Under the condition that the battery operating temperature is lower than the first preset safety temperature threshold, the battery operates at the maximum safe charging and discharging power, which can maximize the charging and discharging performance of the battery;

[0006] The second preset safety temperature threshold is a temperature value for judging the working state of the battery. When the current battery temperature is greater than the second preset safety temperature threshold, the battery temperature may be too high to cause fire, explosion and other safety accidents. At this time, when the battery temperature reaches the second preset safety temperature threshold, the energy storage system will stop working to avoid safety accidents. Of course, when the current battery temperature is less than the second preset safety temperature threshold, although the battery is in a high temperature working state, the battery will not have the above dangerous emergency situations.

[0007] Therefore, in the above-mentioned existing patents, in order to cool down the battery, the ambient temperature is first adjusted to affect the battery temperature. During this process, the battery always works at the maximum safe charging and discharging power; and when the battery temperature reaches the limit temperature, it will stop working directly. Although this cliff-like battery charging and discharging control claims that it will not cause the battery temperature to be too high and cause a dangerous emergency, the above-mentioned control strategy will have a certain impact on the battery's service life and performance, which is not conducive to extending the battery's service life. Summary of the invention

[0008] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a thermal management control method and system for an automobile power battery based on charging and discharging parameters. According to the predicted temperature of the power battery at the future moment, a deep reinforcement learning control strategy is adopted to obtain the optimal power battery charging and discharging control parameters that follow the predicted temperature of the power battery at the future moment. Based on the optimal power battery charging and discharging control parameters, the charging and discharging control of the power battery is realized, thereby realizing dynamic control of the power battery temperature.

[0009] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0010] A first aspect of the present invention provides a thermal management control method for an automotive power battery based on charge and discharge parameters.

[0011] The thermal management control method of an automobile power battery based on charge and discharge parameters comprises the following steps:

[0012] Obtain power battery status parameters and perform preprocessing;

[0013] The preprocessed power battery state parameters are input into the pre-trained deep learning prediction model to predict the power battery's predicted temperature at a future time.

[0014] A deep reinforcement learning control strategy is adopted. The state is defined as the current state and predicted temperature of the power battery, the action is defined as the power battery charge and discharge control parameters, and the reward function is defined as a comprehensive indicator of the power battery performance and life. The optimal control strategy of the power battery is learned with the maximum value of the reward function as the goal, and the optimal power battery charge and discharge control parameters are obtained.

[0015] The power battery is controlled with the optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

[0016] As a further technical solution, the power battery status parameters are obtained and preprocessed, including:

[0017] Obtaining power battery status parameters including power battery temperature, voltage and current data;

[0018] De-noising and normalizing the power battery state parameters;

[0019] Based on the power battery temperature data, the power battery temperature change rate is calculated to realize battery status feature extraction.

[0020] As a further technical solution, it also includes pre-training the deep learning prediction model, specifically:

[0021] The LSTM network model is selected as the deep learning prediction model to obtain the historical values ​​of the power battery status parameters;

[0022] Based on the historical values ​​of the power battery status parameters, the LSTM network model is trained to obtain a trained LSTM network model;

[0023] The historical values ​​of the power battery state parameters include historical values ​​of the power battery temperature, voltage and current data, and historical values ​​of the power battery temperature change rate.

[0024] As a further technical solution, the training loss function of the LSTM network model is defined as the mean square error between the predicted temperature and the actual temperature:

[0025]

[0026] Where N is the number of samples, is the predicted temperature of the ith sample, is the actual temperature.

[0027] As a further technical solution, the deep reinforcement learning control strategy is a deep deterministic policy gradient algorithm, and the reward function is:

[0028] R=w1·P bat +w2·L bat ;

[0029] Where P bat Is the battery performance index; L bat is the battery life indicator; w1 and w2 are weight coefficients.

[0030] As a further technical solution, the power battery is controlled with the optimal power battery charge and discharge control parameters to achieve thermal management of the power battery, including:

[0031] An adaptive PID controller is used to dynamically adjust the charging and discharging control parameters of the power battery according to the optimal charging and discharging control parameters of the power battery output by the deep reinforcement learning algorithm.

[0032] As a further technical solution, an adaptive PID controller is used to dynamically adjust the charging and discharging control parameters of the power battery. The calculation formula is:

[0033]

[0034] Among them, Kp, Ki and Kd are proportional, integral and differential control coefficients respectively; e(t) is the deviation signal.

[0035] A second aspect of the present invention provides an automotive power battery thermal management control system based on charge and discharge parameters.

[0036] The automotive power battery thermal management control system based on charge and discharge parameters includes:

[0037] The data acquisition module is configured to: acquire power battery status parameters and perform preprocessing;

[0038] The temperature prediction module is configured to: input the preprocessed power battery state parameters into the pre-trained deep learning prediction model to predict the predicted temperature of the power battery at a future time;

[0039] The reinforcement learning module is configured to: adopt a deep reinforcement learning control strategy, define the state as the current state and predicted temperature of the power battery, define the action as the power battery charge and discharge control parameters, define the reward function as a comprehensive indicator of the power battery performance and life, and learn the optimal control strategy of the power battery with the maximum value of the reward function as the goal to obtain the optimal power battery charge and discharge control parameters;

[0040] The control module is configured to control the power battery with optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

[0041] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the automotive power battery thermal management control method based on charge and discharge parameters as described in the first aspect of the present invention.

[0042] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the automotive power battery thermal management control method based on charging and discharging parameters as described in the first aspect of the present invention are implemented.

[0043] One or more of the above technical solutions have the following beneficial effects:

[0044] The present invention provides a thermal management control method and system for an automobile power battery based on charge and discharge parameters. The method and system do not rely on a preset control strategy, but adopt a deep reinforcement learning control strategy based on the predicted temperature of the power battery at a future time, to obtain optimal power battery charge and discharge control parameters that follow the predicted temperature of the power battery at a future time, and implement charge and discharge control of the power battery based on the optimal power battery charge and discharge control parameters, thereby achieving accurate and dynamic control of the power battery temperature.

[0045] In the deep reinforcement learning control strategy of the present invention, the reward function is defined as a comprehensive indicator of the performance and life of the power battery. The optimal control strategy of the power battery is learned with the maximum value of the reward function as the goal. The implicit relationship between the predicted temperature and the charge and discharge control parameters is deeply explored, thereby realizing the control of the charge and discharge control parameters, and then effectively controlling the battery temperature.

[0046] The present invention will not cause a cliff-like change in the charge and discharge control parameters, and can improve the safety of the power battery, as well as the service life and performance of the power battery. It can also be well applied to vehicle-mounted power batteries with unique operating environments and frequent operating condition changes, such as flying cars.

[0047] When the LSTM network model is used to predict the temperature of the power battery at a future time, the present invention takes into account the power battery temperature, voltage and current data, and the power battery temperature change rate, so that more accurate temperature prediction can be achieved and a more accurate temperature prediction result can be obtained.

[0048] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0050] Figure 1 This is a flow chart of the method of the first embodiment.

[0051] Figure 2 This is a diagram of information interaction between modules of the vehicle control system of the first embodiment. DETAILED DESCRIPTION

[0052] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0053] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0054] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0055] Embodiment 1

[0056] Before explaining in detail the automotive power battery thermal management control method based on charging and discharging parameters provided in the embodiment of the present application, the application scenario provided in the embodiment of the present application is first introduced.

[0057] The inventors found that in the prior art, when thermal management control is performed on power batteries, a cooling strategy that uses an external cooling device to start and stop is often used. The start and stop of the external cooling device will affect the ambient temperature, thereby changing the temperature of the power battery itself through the change in ambient temperature. In this process, the charge and discharge control parameters of the power battery often remain unchanged. The charge and discharge parameter control and temperature control of the power battery are separate.

[0058] The above-mentioned power battery thermal management system has limitations in terms of rapid response to temperature changes and adaptation to different operating conditions, which makes it difficult to optimally ensure battery performance and safety, and easily affects the battery's service life.

[0059] In addition, the above-mentioned traditional thermal management systems usually rely on preset control strategies and cannot be dynamically adjusted according to real-time data, which may cause problems such as overheating or inefficient cooling.

[0060] Based on such an application scenario, the embodiment of the present application provides a thermal management control method for an automotive power battery based on charging and discharging parameters, which integrates cloud computing, machine learning prediction models and advanced control strategies. It can be used for the temperature control and management of power batteries of flying cars and has broad application prospects.

[0061] Next, the automotive power battery thermal management control method based on charge and discharge parameters provided by the embodiment of the present application will be explained in detail with reference to the accompanying drawings. Figure 1 As shown, the thermal management control method of the automotive power battery based on the charge and discharge parameters includes the following steps:

[0062] Obtain power battery status parameters and perform preprocessing;

[0063] The preprocessed power battery state parameters are input into the pre-trained deep learning prediction model to predict the power battery's predicted temperature at a future time.

[0064] A deep reinforcement learning control strategy is adopted. The state is defined as the current state and predicted temperature of the power battery, the action is defined as the power battery charge and discharge control parameters, and the reward function is defined as a comprehensive indicator of the power battery performance and life. The optimal control strategy of the power battery is learned with the maximum value of the reward function as the goal, and the optimal power battery charge and discharge control parameters are obtained.

[0065] The power battery is controlled with the optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

[0066] This embodiment does not rely on a preset control strategy, but adopts a deep reinforcement learning control strategy based on the predicted temperature of the power battery at the future moment, obtains the optimal power battery charge and discharge control parameters that follow the predicted temperature of the power battery at the future moment, and realizes the charge and discharge control of the power battery based on the optimal power battery charge and discharge control parameters, thereby realizing accurate and dynamic control of the temperature of the power battery. In this way, the cliff-like changes in the charge and discharge control parameters of the power battery can be avoided, and in the process of dynamic control of the power battery temperature based on the charge and discharge control parameters, the safety of the power battery can be ensured, further improving the safety performance of the system.

[0067] In the deep reinforcement learning control strategy of this embodiment, the reward function is defined as a comprehensive indicator of the performance and life of the power battery. The optimal control strategy of the power battery is learned with the maximum value of the reward function as the goal, and the implicit relationship between the predicted temperature and the charge and discharge control parameters is deeply mined, so as to realize the control of the charge and discharge control parameters and further effectively control the battery temperature.

[0068] In some embodiments, obtaining power battery status parameters and performing preprocessing includes:

[0069] Obtaining power battery status parameters including power battery temperature, voltage and current data;

[0070] De-noising and normalizing the power battery state parameters;

[0071] Based on the power battery temperature data, the power battery temperature change rate is calculated to realize battery status feature extraction.

[0072] Further:

[0073] The calculation formula of battery temperature change rate ΔT is:

[0074]

[0075] Where T(t) is the battery temperature at the current moment, T(t-Δt) is the battery temperature at the previous moment, and Δt is the time interval.

[0076] In some embodiments, the deep learning prediction model is also pre-trained, specifically:

[0077] The LSTM network model is selected as the deep learning prediction model to obtain the historical values ​​of the power battery status parameters;

[0078] Based on the historical values ​​of the power battery status parameters, the LSTM network model is trained to obtain a trained LSTM network model;

[0079] The historical values ​​of the power battery state parameters include historical values ​​of the power battery temperature, voltage and current data, and historical values ​​of the power battery temperature change rate.

[0080] In some embodiments, the training loss function of the LSTM network model is defined as the mean square error between the predicted temperature and the actual temperature:

[0081]

[0082] Where N is the number of samples, is the predicted temperature of the ith sample, is the actual temperature.

[0083] It can be understood that during the model training process, the historical values ​​of the power battery status parameters are input into the LSTM network model, and after the transmission of information, the predicted temperature value is finally obtained; the loss function is calculated based on the predicted temperature value and the actual temperature value until the loss function is minimized or the set number of iterations is reached, and the training of the LSTM network model is completed.

[0084] This embodiment uses the LSTM network model to predict the temperature of the power battery at a future time, taking into account the power battery temperature, voltage and current data, and the power battery temperature change rate, so that a more accurate temperature prediction can be achieved and a more accurate temperature prediction result can be obtained. The structure of the LSTM can adopt the existing technology, and this embodiment will not be elaborated on.

[0085] In some embodiments, the deep reinforcement learning control strategy is a deep deterministic policy gradient algorithm, and the reward function R is defined as a comprehensive indicator of battery performance and life:

[0086] R=w1·P bat +w2·L bat ;

[0087] Where P bat Is the battery performance index; L bat is the battery life indicator; w1 and w2 are weight coefficients.

[0088] In some embodiments, the power battery is controlled with optimal power battery charge and discharge control parameters to achieve thermal management of the power battery, including:

[0089] An adaptive PID controller is used to dynamically adjust the charging and discharging control parameters of the power battery according to the optimal charging and discharging control parameters of the power battery output by the deep reinforcement learning algorithm.

[0090] In some embodiments, an adaptive PID controller is used to dynamically adjust the charge and discharge control parameters of the power battery, and the calculation formula is:

[0091]

[0092] Among them, Kp, Ki and Kd are proportional, integral and differential control coefficients respectively; e(t) is the deviation signal.

[0093] This embodiment will not cause a cliff-like change in the charge and discharge control parameters, and can improve the safety of the power battery, as well as the service life and performance of the power battery. It can also be well applied in vehicle-mounted power batteries with unique operating environments and frequent operating condition changes, such as flying cars.

[0094] The following will be combined with the specific use environment and attached Figure 2 , further description of the technical solution is provided.

[0095] like Figure 2 As shown, in a vehicle control system including an on-board battery management system (BMS), an on-board communication module, a cloud server, and a real-time control instruction generator:

[0096] BMS collects battery status data in real time and performs pre-processing such as denoising and normalization;

[0097] The on-board communication module encrypts and compresses the pre-processed data and transmits it to the cloud server;

[0098] The data processing unit of the cloud server cleans and extracts features from the received data, uses the LSTM network to train the model, and predicts the temperature changes of the battery under different working conditions. The DDPG algorithm is used to define the state as the current state of the battery and the predicted temperature, the action as the charge and discharge control parameters, and the reward as the battery performance and life indicators, and the training model learns the optimal control strategy. According to the output of the DDPG algorithm, the adaptive PID controller dynamically adjusts the charge and discharge control parameters.

[0099] BMS performs charging and discharging operations according to the control instructions sent by the cloud server.

[0100] Finally, the system collects the charging and discharging execution results and feeds them back to the cloud server for further optimization of the model and strategy.

[0101] Further:

[0102] 1. On-board battery management system (BMS): real-time monitoring of battery status, including temperature, voltage, current and other parameters; data preprocessing, such as denoising, normalization and feature extraction.

[0103] 2. On-board communication module: encrypts and transmits data to the cloud server safely and efficiently; uses data compression technology to reduce transmission delays and data loss.

[0104] 3. Cloud server: deploy deep learning models for temperature prediction, reinforcement learning algorithms for control strategy optimization, and adaptive algorithms for charging and discharging strategy adjustment.

[0105] 4. Data processing unit: Receive and process data from BMS, clean and extract features, and input into the deep learning model.

[0106] 5. Deep learning prediction model (such as LSTM network): Use a long short-term memory (LSTM) network to predict battery temperature changes based on historical and real-time data; the training loss function is defined as the mean square error between the predicted temperature and the actual temperature.

[0107] 6. Deep reinforcement learning control strategy (such as DDPG algorithm): Use the deep deterministic policy gradient (DDPG) algorithm, define the state as the current state of the battery and the predicted temperature, and the action as the charge and discharge control parameters; the reward function R is defined as a comprehensive indicator of battery performance and life.

[0108] 7. Adaptive control algorithm (such as adaptive PID controller): Use an adaptive PID controller to dynamically adjust the charge and discharge control parameters based on the output of the deep reinforcement learning algorithm.

[0109] 8. Real-time control instruction generator: converts the control strategy into specific execution instructions and sends them back to the BMS through the on-board communication module; the BMS performs charging and discharging operations and feeds back the execution results to the cloud server for further optimization of the model and strategy.

[0110] In a vehicle control system including an on-board battery management system (BMS), an on-board communication module, a cloud server, and a real-time control instruction generator, this embodiment can achieve:

[0111] (1) Efficient data processing: The data compression technology of the vehicle communication module reduces the delay and loss of data transmission;

[0112] (2) Accurate temperature prediction: The machine learning model can accurately predict the temperature changes of the battery under different operating conditions;

[0113] (3) Optimal control strategy: Advanced control algorithms can generate optimal thermal management control instructions based on prediction results and real-time data;

[0114] (4) Improve system adaptability: The system can adapt to different operating conditions and environmental changes, improving battery performance and safety.

[0115] Embodiment 2

[0116] This embodiment discloses a thermal management control system for an automotive power battery based on charging and discharging parameters.

[0117] The automotive power battery thermal management control system based on charge and discharge parameters includes:

[0118] The data acquisition module is configured to: acquire power battery status parameters and perform preprocessing;

[0119] The temperature prediction module is configured to: input the preprocessed power battery state parameters into the pre-trained deep learning prediction model to predict the predicted temperature of the power battery at a future time;

[0120] The reinforcement learning module is configured to: adopt a deep reinforcement learning control strategy, define the state as the current state and predicted temperature of the power battery, define the action as the power battery charge and discharge control parameters, define the reward function as a comprehensive indicator of the power battery performance and life, and learn the optimal control strategy of the power battery with the maximum value of the reward function as the goal to obtain the optimal power battery charge and discharge control parameters;

[0121] The control module is configured to control the power battery with optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

[0122] Embodiment 3

[0123] The purpose of this embodiment is to provide a computer-readable storage medium.

[0124] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the automotive power battery thermal management control method based on charge and discharge parameters as described in Example 1 of the present disclosure.

[0125] Embodiment 4

[0126] The purpose of this embodiment is to provide an electronic device.

[0127] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the automotive power battery thermal management control method based on charging and discharging parameters as described in Example 1 of the present disclosure are implemented.

[0128] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0129] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0130] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A thermal management control method for automotive power batteries based on charge and discharge parameters, characterized in that: The following steps are involved: Obtain power battery status parameters and perform preprocessing; The preprocessed power battery state parameters are input into the pre-trained deep learning prediction model to predict the power battery temperature at a future time. A deep reinforcement learning control strategy is adopted. The state is defined as the current state and predicted temperature of the power battery, the action is defined as the power battery charge and discharge control parameters, and the reward function is defined as a comprehensive indicator of the power battery performance and life. The optimal control strategy of the power battery is learned with the maximum value of the reward function as the goal, and the optimal power battery charge and discharge control parameters are obtained. The power battery is controlled with the optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

2. The automotive power battery thermal management control method based on charge and discharge parameters according to claim 1, characterized in that: Obtain power battery status parameters and perform preprocessing, including: Obtaining power battery status parameters including power battery temperature, voltage and current data; De-noising and normalizing the power battery state parameters; Based on the power battery temperature data, the power battery temperature change rate is calculated to realize battery status feature extraction.

3. The automotive power battery thermal management control method based on charge and discharge parameters as claimed in claim 2, characterized in that: It also includes pre-training of deep learning prediction models, specifically: The LSTM network model is selected as the deep learning prediction model to obtain the historical values ​​of the power battery status parameters; Based on the historical values ​​of the power battery status parameters, the LSTM network model is trained to obtain a trained LSTM network model; The historical values ​​of the power battery state parameters include historical values ​​of the power battery temperature, voltage and current data, and historical values ​​of the power battery temperature change rate.

4. The automotive power battery thermal management control method based on charge and discharge parameters as claimed in claim 3, characterized in that: The training loss function of the LSTM network model is defined as the mean square error between the predicted temperature and the actual temperature: Where N is the number of samples, is the predicted temperature of the ith sample, is the actual temperature.

5. The automotive power battery thermal management control method based on charge and discharge parameters as claimed in claim 1, characterized in that: The deep reinforcement learning control strategy is a deep deterministic policy gradient algorithm, and the reward function is: R=w1·P bat +w2·L bat ; Where P bat Is the battery performance index; L bat is the battery life indicator; w1 and w2 are weight coefficients.

6. The automotive power battery thermal management control method based on charge and discharge parameters as claimed in claim 1, characterized in that: Control the power battery with the optimal power battery charge and discharge control parameters to achieve thermal management of the power battery, including: An adaptive PID controller is used to dynamically adjust the charging and discharging control parameters of the power battery according to the optimal charging and discharging control parameters of the power battery output by the deep reinforcement learning algorithm.

7. The automotive power battery thermal management control method based on charge and discharge parameters as claimed in claim 6, characterized in that: Use the adaptive PID controller to dynamically adjust the charging and discharging control parameters of the power battery. The calculation formula is: Among them, Kp, Ki and Kd are proportional, integral and differential control coefficients respectively; e(t) is the deviation signal.

8. An automotive power battery thermal management control system based on charge and discharge parameters, characterized in that: include: The data acquisition module is configured to: acquire power battery status parameters and perform preprocessing; The temperature prediction module is configured to: input the preprocessed power battery state parameters into the pre-trained deep learning prediction model to predict the predicted temperature of the power battery at a future time; The reinforcement learning module is configured to: adopt a deep reinforcement learning control strategy, define the state as the current state and predicted temperature of the power battery, define the action as the power battery charge and discharge control parameters, define the reward function as a comprehensive indicator of the power battery performance and life, and learn the optimal control strategy of the power battery with the maximum value of the reward function as the goal to obtain the optimal power battery charge and discharge control parameters; The control module is configured to control the power battery with optimal power battery charge and discharge control parameters to achieve thermal management of the power battery.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the automotive power battery thermal management control method based on charge and discharge parameters as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the automotive power battery thermal management control method based on charging and discharging parameters as described in any one of claims 1 to 7 are implemented.

Images