Battery thermal management control method and system

Abstract

The invention relates to the technical field of battery thermal management, in particular to a battery thermal management control method and system, and the method comprises the steps: obtaining the basic operation parameter data of an automobile battery in real time, and carrying out the multi-dimensional data fusion, and obtaining a multi-dimensional data set; based on the thermodynamic model and the multi-dimensional data set, the temperature distribution condition in the battery is calculated in real time, and real-time temperature distribution information is obtained; based on the historical data and the operation state, the future temperature change trend of the battery is predicted through a recurrent neural network model; dynamically adjusting a control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction result; and analyzing the temperature difference condition of the battery monomers, detecting abnormal temperature rise, and performing temperature difference balance adjustment and triggering a multi-stage protection mechanism when the abnormal temperature rise exceeds a threshold value. According to the invention, the problems of inaccurate temperature prediction and response lag in the prior art are effectively solved, the control strategy is dynamically adjusted through real-time data fusion and recurrent neural network prediction, temperature difference balance and abnormal temperature rise detection are realized, the safety of the battery is improved, and the service life of the battery is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of battery thermal management, and in particular to a battery thermal management control method and system. Background Art

[0002] With the rapid development of new energy vehicles, power batteries, as core components, have received widespread attention for their operating safety, efficiency and life. During operation, battery packs are affected by multiple factors such as ambient temperature, charge and discharge rates, and operating conditions, and are prone to problems such as uneven temperature, local overheating, or decreased low-temperature performance.

[0003] Existing battery thermal management methods are mainly based on fixed rules or simple temperature monitoring, which makes it difficult to cope with the complex dynamic characteristics of temperature changes. For example, during operation, it is impossible to calculate the internal temperature distribution of the battery in real time, and there is a lack of accurate prediction of future temperature trends, which leads to lagging control strategies and makes it difficult to effectively solve problems such as uneven temperature distribution and abnormal temperature rise. In addition, in the event of abnormal temperature rise or excessive temperature difference, existing systems often rely on a single protection mechanism, such as forced power off or a single cooling method, which can easily affect the reliability and stability of the system. Summary of the invention

[0004] The present invention provides a battery thermal management control method and system, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A battery thermal management control method, comprising: Obtain the basic operating parameter data of the car battery in real time, and perform multi-dimensional data fusion to obtain a multi-dimensional data set; Based on the thermodynamic model and the multidimensional data set, the temperature distribution inside the battery is calculated in real time to obtain real-time temperature distribution information; Based on historical data and operating status, the future temperature change trend of the battery is predicted through a recurrent neural network model; Dynamically adjust the control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction results; Analyze the temperature difference of battery cells and detect abnormal temperature rise. When the threshold is exceeded, adjust the temperature difference and trigger the multi-level protection mechanism.

[0006] Furthermore, based on the thermodynamic model and the multidimensional data set, the temperature distribution inside the battery is calculated in real time to obtain real-time temperature distribution information, including: According to the physical structure and thermal characteristics of the battery pack, a preset thermodynamic model is loaded, wherein the thermodynamic model includes heat conduction, convection and heat dissipation models; Based on the thermodynamic model and multi-dimensional data set, the internal temperature distribution of the battery is solved in real time to obtain the overall temperature distribution information, and the local hot spot area is identified and the possible overheating risk is judged; Combined with the continuous temperature distribution calculation results, the time dynamic change characteristics of the battery temperature field are analyzed, the temperature change trend is formed, and the real-time temperature distribution information is output.

[0007] Furthermore, based on historical data and operating status, the future temperature change trend of the battery is predicted through a recurrent neural network model, including: Acquire historical operation data from the historical data, extract time series features, and train the recursive neural network model; Using the trained recursive neural network model to predict the future temperature change trend of the battery to obtain a prediction result; Based on the prediction result, the risk of overheating or overcooling of the battery is assessed to obtain a risk assessment result.

[0008] Furthermore, the recursive neural network model includes: The input layer receives the real-time collected battery operating parameters and combines them with the historical operating data to form time series input features; The hidden layer uses multiple recursive neural network units to learn the timing characteristics and nonlinear relationships of battery temperature changes through time series modeling, capturing the relationship between historical states and future trends; The output layer converts the hidden layer processing results into the predicted value of the battery temperature change trend in the future time period; Model optimization mechanism, including offline training and online update.

[0009] Furthermore, the offline training and online updating include: Offline training, using the historical operation data to optimize model parameters, optimize the deep learning algorithm, and test it through a validation set; Online update: During actual operation, the model weights are adjusted according to real-time input data, the model parameters are dynamically adjusted, and the model is optimized by comparing the predicted results with the actual data.

[0010] Furthermore, according to the real-time temperature distribution information and the prediction result, the control strategy of the battery thermal management system is dynamically adjusted, including: Based on the real-time temperature distribution information and the recursive neural network prediction result, the overall temperature state of the battery pack is evaluated to form a temperature control evaluation result; Based on the temperature control evaluation result, a control strategy adapted to the current temperature control demand is generated and converted into executable control instructions.

[0011] Furthermore, the control strategy includes: Heating strategy: when the overall or local temperature is below the preset range, heating power is allocated to the low temperature area first; Cooling strategy, when a high temperature area or abnormal temperature rise trend is detected, the cooling equipment operating parameters are adjusted to quickly reduce the local temperature; The power regulation strategy dynamically adjusts the charge and discharge power to reduce the heat load or reduce low-temperature damage when abnormal heating or overcooling is predicted in the future.

[0012] Furthermore, the temperature difference of the battery cells is analyzed and abnormal temperature rise is detected. When the threshold is exceeded, the temperature difference is balanced and a multi-level protection mechanism is triggered, including: Based on the real-time temperature distribution information, calculate the temperature difference between the battery cells, analyze the temperature difference distribution, and identify the area where the temperature difference exceeds the set threshold; Determine whether there is an abnormal temperature rise phenomenon according to the real-time temperature change rate and the prediction result; When it is detected that the temperature difference exceeds the set threshold, the operating state of the thermal management system is dynamically adjusted, including heating the low-temperature area or cooling the high-temperature area to restore the temperature difference to a safe range; When abnormal temperature rise is detected or temperature difference equalization adjustment cannot effectively reduce the risk, protective measures are triggered.

[0013] A battery thermal management control system, the system comprising: The multi-dimensional data fusion module obtains the basic operating parameter data of the automobile battery in real time and performs multi-dimensional data fusion to obtain a multi-dimensional data set; A temperature distribution acquisition module calculates the temperature distribution inside the battery in real time based on the thermodynamic model and the multidimensional data set to obtain real-time temperature distribution information; The change trend prediction module predicts the future temperature change trend of the battery through a recursive neural network model based on historical data and operating status; A control strategy adjustment module dynamically adjusts the control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction result; The single-cell adjustment protection module analyzes the temperature difference of battery cells and detects abnormal temperature rise. When the threshold is exceeded, the temperature difference is balanced and a multi-level protection mechanism is triggered.

[0014] Furthermore, the change trend prediction module includes: A recursive model training unit, which obtains historical operation data from the historical data, extracts time series features, and trains the recursive neural network model; A prediction result acquisition unit, using the trained recursive neural network model to predict the future temperature change trend of the battery to obtain a prediction result; The reputation result acquisition unit evaluates the risk of overheating or overcooling of the battery according to the prediction result to obtain a risk assessment result.

[0015] The technical solution of the present invention can achieve the following technical effects: It effectively solves the problems of inaccurate temperature prediction and delayed response in existing technologies. Through real-time data fusion and recursive neural network prediction, it dynamically adjusts the control strategy to achieve temperature difference balance and abnormal temperature rise detection, thereby improving battery safety and service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of a battery thermal management control method; Figure 2 A schematic diagram of the process for obtaining real-time temperature distribution information; Figure 3 A schematic diagram of a process for predicting the future temperature change trend of a battery; Figure 4 A flow chart showing a control strategy for dynamically adjusting a battery thermal management system; Figure 5 A flow chart for adjusting the temperature difference balance and triggering the multi-level protection mechanism. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0020] Embodiment 1 like Figure 1 As shown, the present invention provides a battery thermal management control method, the method comprising: S1: Obtain the basic operating parameter data of the automobile battery in real time, and perform multi-dimensional data fusion to obtain a multi-dimensional data set; Specifically, the basic operating parameter data of the automotive battery is obtained in real time, including information such as battery cell voltage, current, temperature, state of charge (SOC), discharge power and ambient temperature, and these parameter data are fused in multiple dimensions. Through data fusion technology, the data collected by various sensors are uniformly processed and analyzed to obtain a complete multi-dimensional data set. This set not only includes the real-time battery status, but also combines external environmental factors to ensure that it can accurately reflect the current working status and thermal management requirements of the battery, and provide the necessary basic data support for subsequent temperature distribution calculation and prediction.

[0021] S2: Based on the thermodynamic model and multi-dimensional data set, the temperature distribution inside the battery is calculated in real time to obtain real-time temperature distribution information; Specifically, by calculating the temperature distribution inside the battery in real time based on thermodynamic models and multidimensional data sets, and accurately monitoring the temperature conditions of each single cell of the battery, and by obtaining real-time temperature distribution information, possible hot spots and temperature abnormalities in the battery pack can be identified, and overheating risks can be discovered in advance, thereby providing data support for subsequent thermal management strategies, ensuring that the battery system operates within a safe and stable temperature range, and preventing excessively high or low temperatures from adversely affecting battery performance and life.

[0022] S3: Based on historical data and operating status, the future temperature change trend of the battery is predicted through a recurrent neural network model; Specifically, through the recursive neural network model, based on historical data and the operating status of the battery, the future temperature change trend of the battery is predicted. By learning the historical temperature data, battery load status and environmental conditions, the model can identify the timing patterns of temperature changes and predict future temperature increases or decreases. The prediction results help to identify potential temperature anomalies in advance, such as overheating or overcooling risks, provide early warning for subsequent thermal management strategies, and optimize the temperature control adjustment of the battery.

[0023] S4: Dynamically adjust the control strategy of the battery thermal management system based on real-time temperature distribution information and prediction results; Specifically, based on the real-time temperature distribution information and predicted future temperature change trends, the control strategy of the battery thermal management system is dynamically adjusted to ensure that the battery always operates within the optimal temperature range. By real-time monitoring of temperature changes and predicting future temperature change trends, it is possible to promptly identify and respond to abnormal battery temperatures, such as overheating or overcooling. Dynamic adjustment of control strategies includes optimizing heating, cooling, and power regulation measures.

[0024] S5: Analyze the temperature difference of the battery cells and detect abnormal temperature rise. When the temperature exceeds the threshold, adjust the temperature difference and trigger the multi-level protection mechanism.

[0025] Specifically, through real-time temperature distribution information and predicted temperature change trends, the control strategy of the battery thermal management system can be adjusted in time to ensure that the battery is within the optimal operating temperature range. By dynamically optimizing heating, cooling and power regulation measures, overheating or overcooling can be effectively prevented, improving battery safety, stability and performance, extending battery life, and ultimately improving the overall efficiency of the battery system.

[0026] The present invention effectively solves the problems of inaccurate temperature prediction and delayed response in the prior art. Through real-time data fusion and recursive neural network prediction, the control strategy is dynamically adjusted to achieve temperature difference balance and abnormal temperature rise detection, thereby improving battery safety and service life.

[0027] As a preferred embodiment of the above, Figure 2 As shown, step S2, based on the thermodynamic model and the multidimensional data set, calculates the temperature distribution inside the battery in real time to obtain real-time temperature distribution information, including: S21: Loading a preset thermodynamic model according to the physical structure and thermal characteristics of the battery pack, the thermodynamic model including heat conduction, convection and heat dissipation models; S22: Based on thermodynamic models and multi-dimensional data sets, the internal temperature distribution of the battery is solved in real time to obtain the overall temperature distribution information, while identifying local hot spots and judging possible overheating risks; S23: Combined with the continuous temperature distribution calculation results, the time dynamic change characteristics of the battery temperature field are analyzed to form a temperature change trend and output real-time temperature distribution information.

[0028] Specifically, according to the physical structure, thermal characteristics and actual operating environment of the battery pack, a preset thermodynamic model is loaded. The model covers physical phenomena such as heat conduction, convection and heat dissipation, and simulates the heat conduction process inside the battery. Through these models, the heat transfer and heat exchange process between the cells inside the battery can be fully reflected; based on the thermodynamic model and the multidimensional data set collected by the sensor, the temperature distribution inside the battery is calculated in real time. This process takes into account factors such as the internal structure of the battery, the heat exchange between different cells, the ambient temperature and the battery load, and calculates the temperature distribution information of the entire battery pack. At the same time, through the calculation of the temperature distribution, the local hot spot area is identified, and it is determined whether there is a possible overheating risk, which provides a basis for subsequent thermal management and temperature control strategies; after obtaining the continuous temperature distribution calculation results, the dynamic change characteristics of the battery temperature field are analyzed in combination with the time series data. Through the analysis of the temperature change trend, the change law and characteristics of the battery pack temperature field are extracted, the future temperature change trend is predicted, and the real-time temperature distribution information is output.

[0029] As a preferred embodiment of the above, Figure 3 As shown, step S3 predicts the future temperature change trend of the battery through a recursive neural network model based on historical data and operating status, including: S31: Obtain historical operation data from historical data, extract time series features, and train a recursive neural network model; S32: using the trained recursive neural network model to predict the future temperature change trend of the battery to obtain a prediction result; S33: Based on the prediction result, assess whether the battery has a risk of overheating or overcooling, and obtain a risk assessment result.

[0030] Specifically, historical operating data is obtained from the battery management system, and time series features are extracted from these data to form a historical data set. These features include the short-term and long-term temperature change trends of the battery, load changes, environmental conditions, etc. Time series analysis technology is used to process these data, and important features related to temperature changes are extracted to provide input for the subsequent training of the recursive neural network model; the extracted time series features are used to train the recursive neural network (RNN). During the training process, the model analyzes the historical temperature change data of the battery, learns the timing laws and influencing factors of the battery temperature change, captures the nonlinear characteristics of the battery system, and uses an appropriate recursive neural network architecture (such as LSTM or GRU) to process the data, and continuously optimizes the model's weights and parameters to improve the model's prediction accuracy for future battery temperature changes; after training is completed, the trained recursive neural network model is used to predict the future temperature change trend of the battery. The model will predict the temperature changes of the battery in the future based on the real-time input operating status data (such as the battery's current voltage, temperature, load, etc.), and evaluate the possible overheating or overcooling risks of the battery based on the prediction results. If the prediction results show that the battery temperature will exceed the safe temperature range or be lower than the minimum operating temperature in the future, the corresponding risk assessment results will be generated as input for subsequent thermal management control strategies.

[0031] As a preferred embodiment of the above embodiment, the recursive neural network model includes: The input layer receives the real-time collected battery operating parameters and combines them with the historical operating data to form time series input features; The hidden layer uses multiple recursive neural network units to learn the timing characteristics and nonlinear relationships of battery temperature changes through time series modeling, capturing the relationship between historical states and future trends; The output layer converts the hidden layer processing results into the predicted value of the battery temperature change trend in the future time period; Model optimization mechanism, including offline training and online update.

[0032] As a preferred embodiment of the above, offline training and online updating include: Offline training uses historical operation data to optimize model parameters, optimize deep learning algorithms, and test them through validation sets; Online update: During actual operation, the model weights are adjusted according to real-time input data, the model parameters are dynamically adjusted, and the model is optimized by comparing the predicted results with the actual data.

[0033] Specifically, first, the input layer receives real-time operating data and historical data from the battery. After preprocessing, these data are combined with historical operating data to form time series input features, which comprehensively reflect the operating status of the battery under different working conditions as the input of the model; secondly, the hidden layer is composed of multiple recursive neural network units (such as LSTM or GRU), which are used to learn the timing characteristics and nonlinear relationships of battery temperature changes. Through these recursive units, the network can capture the complex relationship between historical states and future trends. Especially in battery systems, temperature changes are usually affected by multiple factors, and the hidden layer can handle long-term and short-term dependencies in battery temperature changes; then, the output layer converts the processing results of the hidden layer into battery temperature in the future. The predicted value of temperature change outputs the overall temperature change trend of the battery pack, the possibility of local hot spots, and the dynamic characteristics of temperature rise or temperature drop. These predicted values ​​will serve as an important basis for the battery thermal management system adjustment strategy, helping the system to respond to possible overheating or overcooling risks in a timely manner; finally, the model optimization mechanism includes two parts: offline training and online update. In the offline training stage, the model is optimized using historical operating data, the model parameters are adjusted through deep learning algorithms, and its accuracy is tested through validation sets. In actual operation, the model is updated online using real-time input data. Based on the comparison between real-time monitoring data and prediction results, the model weights are continuously adjusted to improve the model's adaptability to changes in the environment and operating status, thereby ensuring prediction accuracy and response speed.

[0034] As a preferred embodiment of the above, Figure 4 As shown, step S4 dynamically adjusts the control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction result, including: S41: Based on the real-time temperature distribution information and the recursive neural network prediction result, the overall temperature state of the battery pack is evaluated to form a temperature control evaluation result; S42: Generate a control strategy that meets the current temperature control requirements based on the temperature control evaluation results, and convert it into executable control instructions.

[0035] Specifically, based on the real-time temperature distribution information and the future temperature change trend predicted by the recursive neural network, the temperature status of the battery pack is comprehensively evaluated. By analyzing the overall temperature of the battery pack and the temperature difference between the individual cells, potential overheating or overcooling risks can be identified. The evaluation results will provide a basis for whether heating, cooling or temperature difference balance adjustment is needed to ensure that the battery always works within a safe temperature range; based on the temperature control evaluation results, control strategies that adapt to the current battery temperature control needs are generated. These strategies will be adjusted according to the actual temperature status and predicted trends of the battery. For example, when the temperature in a certain area is too low, heating power is allocated first. When the temperature in a certain area is too high, cooling measures are adjusted to lower the temperature. Finally, the control strategy will be converted into executable control instructions to directly adjust the battery's temperature control measures to ensure that the battery remains within the ideal operating temperature range.

[0036] As a preferred embodiment of the above, the control strategy includes: Heating strategy: when the overall or local temperature is below the preset range, heating power is allocated to the low temperature area first; Cooling strategy, when a high temperature area or abnormal temperature rise trend is detected, the cooling equipment operating parameters are adjusted to quickly reduce the local temperature; The power regulation strategy dynamically adjusts the charge and discharge power to reduce the heat load or reduce low-temperature damage when abnormal heating or overcooling is predicted in the future.

[0037] Specifically, when the overall or local temperature is lower than the preset range, the heating strategy preferentially allocates heating power to the low-temperature area. This measure can effectively increase the local temperature of the battery and ensure that the battery can still work normally in a cold environment. By dynamically adjusting the distribution of heating power, overheating can be avoided and energy efficiency can be optimized to keep the battery within the ideal temperature range. When the cooling strategy detects a high-temperature area or an abnormal heating trend, it quickly reduces the local temperature by adjusting the operating parameters of the cooling equipment (such as coolant flow rate, fan speed, etc.). This strategy can effectively deal with the heating problem of the battery under high load or high ambient temperature, ensure that the hot spot area is cooled in time, and avoid overheating from damaging the battery performance and life. When the power regulation strategy predicts abnormal heating or overcooling in the future, it dynamically adjusts the charging and discharging power to reduce the heat load or reduce low-temperature damage. For example, under high temperature conditions, the control strategy slows down the temperature rise by limiting the discharge power. At low temperatures, reducing the charging power can avoid damage to the battery by low temperature. This strategy can adjust the power output in time under different working conditions of the battery to optimize the operating safety and efficiency of the battery. Through the synergistic effect of the three strategies of heating, cooling and power regulation, the battery temperature control measures can be accurately adjusted under different working conditions to ensure that the battery is always in a stable and safe working state, thereby improving the battery performance, extending its service life, and ensuring its efficient operation.

[0038] As a preferred embodiment of the above, Figure 5 As shown, step S5 analyzes the temperature difference of the battery cells and detects abnormal temperature rise. When the temperature exceeds the threshold, the temperature difference is balanced and a multi-level protection mechanism is triggered, including: S51: Calculating the temperature difference between battery cells based on the real-time temperature distribution information, analyzing the temperature difference distribution, and identifying areas where the temperature difference exceeds a set threshold; S52: judging whether there is an abnormal temperature rise phenomenon according to the real-time temperature change rate and the prediction result; S53: When it is detected that the temperature difference exceeds the set threshold, dynamically adjust the operation state of the thermal management system, including heating the low temperature area or cooling the high temperature area, to restore the temperature difference to a safe range; S54: When abnormal temperature rise is detected or temperature difference equalization adjustment cannot effectively reduce the risk, protective measures are triggered.

[0039] Specifically, we first use real-time temperature data to calculate the temperature difference between each single cell in the battery pack, and analyze the distribution of the temperature difference. By identifying those areas that exceed the preset safety threshold, we can effectively locate the battery cells that may have the risk of abnormal temperature rise. According to the real-time temperature change rate of each single cell of the battery and the predicted future temperature change trend, we can judge whether abnormal temperature rise occurs. By comparing with historical data, we can predict the temperature change in the future to help judge whether the temperature rise is a short-term fluctuation or a continuous abnormal temperature rise trend. If the temperature difference is found to exceed the safety threshold, we will dynamically adjust the thermal management operation. This includes heating the low-temperature area or cooling the high-temperature area to restore the temperature difference of the battery pack to a safe range, which can ensure the balance of battery temperature and avoid local overheating or overcooling that has a negative impact on battery performance and safety; when adjusting the thermal management operation fails to effectively reduce the battery temperature difference or temperature rise, and the temperature difference is still in a high-risk state, multi-level protection measures will be triggered. These measures may include reducing the battery's charge and discharge power, limiting the use of high-temperature batteries, or even disconnecting the battery module to prevent further temperature increases or other safety hazards. Through the multi-level protection mechanism, battery damage can be minimized to ensure battery safety.

[0040] Embodiment 2 Based on the same inventive concept as the battery thermal management control method in the aforementioned embodiment, the present invention further provides a battery thermal management control system, the system comprising: The multi-dimensional data fusion module obtains the basic operating parameter data of the automobile battery in real time and performs multi-dimensional data fusion to obtain a multi-dimensional data set; The temperature distribution acquisition module calculates the temperature distribution inside the battery in real time based on the thermodynamic model and multi-dimensional data set to obtain real-time temperature distribution information; The change trend prediction module predicts the future temperature change trend of the battery through a recursive neural network model based on historical data and operating status; The control strategy adjustment module dynamically adjusts the control strategy of the battery thermal management system based on real-time temperature distribution information and prediction results; The single-cell adjustment protection module analyzes the temperature difference of battery cells and detects abnormal temperature rise. When the threshold is exceeded, the temperature difference is balanced and a multi-level protection mechanism is triggered.

[0041] The above evaluation system in the present invention can effectively implement the battery thermal management control method, which can be described.

[0042] As a preferred embodiment of the above, the change trend prediction module includes: A recursive model training unit obtains historical operation data from historical data, extracts time series features, and trains a recursive neural network model; A prediction result acquisition unit uses the trained recursive neural network model to predict the future temperature change trend of the battery and obtain a prediction result; The risk evaluation result acquisition unit evaluates the risk of overheating or overcooling of the battery based on the prediction results and obtains a risk evaluation result.

[0043] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0044] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application.

[0045] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. A battery thermal management control method, characterized in that: include: Obtain the basic operating parameter data of the car battery in real time, and perform multi-dimensional data fusion to obtain a multi-dimensional data set; Based on the thermodynamic model and the multidimensional data set, the temperature distribution inside the battery is calculated in real time to obtain real-time temperature distribution information; Based on historical data and operating status, the future temperature change trend of the battery is predicted through a recurrent neural network model; Dynamically adjust the control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction results; Analyze the temperature difference of battery cells and detect abnormal temperature rise. When the threshold is exceeded, adjust the temperature difference and trigger the multi-level protection mechanism.

2. The battery thermal management control method according to claim 1, characterized in that: Based on the thermodynamic model and the multi-dimensional data set, the temperature distribution inside the battery is calculated in real time to obtain real-time temperature distribution information, including: According to the physical structure and thermal characteristics of the battery pack, a preset thermodynamic model is loaded, wherein the thermodynamic model includes heat conduction, convection and heat dissipation models; Based on the thermodynamic model and multi-dimensional data set, the internal temperature distribution of the battery is solved in real time to obtain the overall temperature distribution information, and the local hot spot area is identified and the possible overheating risk is judged; Combined with the continuous temperature distribution calculation results, the time dynamic change characteristics of the battery temperature field are analyzed, the temperature change trend is formed, and the real-time temperature distribution information is output.

3. The battery thermal management control method according to claim 1, characterized in that: Based on historical data and operating status, the recurrent neural network model is used to predict the future temperature change trend of the battery, including: Acquire historical operation data from the historical data, extract time series features, and train the recursive neural network model; Using the trained recursive neural network model to predict the future temperature change trend of the battery to obtain a prediction result; Based on the prediction result, the risk of overheating or overcooling of the battery is assessed to obtain a risk assessment result.

4. The battery thermal management control method according to claim 1, characterized in that: The recursive neural network model includes: The input layer receives the real-time collected battery operating parameters and combines them with the historical operating data to form time series input features; The hidden layer uses multiple recursive neural network units to learn the timing characteristics and nonlinear relationships of battery temperature changes through time series modeling, capturing the relationship between historical states and future trends; The output layer converts the hidden layer processing results into the predicted value of the battery temperature change trend in the future time period; Model optimization mechanism, including offline training and online update.

5. The battery thermal management control method according to claim 4, characterized in that: The offline training and online updating include: Offline training, using the historical operation data to optimize model parameters, optimize the deep learning algorithm, and test it through a validation set; Online update: During actual operation, the model weights are adjusted according to real-time input data, the model parameters are dynamically adjusted, and the model is optimized by comparing the predicted results with the actual data.

6. The battery thermal management control method according to claim 1, characterized in that: According to the real-time temperature distribution information and the prediction result, the control strategy of the battery thermal management system is dynamically adjusted, including: Based on the real-time temperature distribution information and the recursive neural network prediction result, the overall temperature state of the battery pack is evaluated to form a temperature control evaluation result; Based on the temperature control evaluation result, a control strategy adapted to the current temperature control demand is generated and converted into executable control instructions.

7. The battery thermal management control method according to claim 6, characterized in that: The control strategy includes: Heating strategy: when the overall or local temperature is below the preset range, heating power is allocated to the low temperature area first; Cooling strategy, when a high temperature area or abnormal temperature rise trend is detected, the cooling equipment operating parameters are adjusted to quickly reduce the local temperature; The power regulation strategy dynamically adjusts the charge and discharge power to reduce the heat load or reduce low-temperature damage when abnormal heating or overcooling is predicted in the future.

8. The battery thermal management control method according to claim 1, characterized in that: Analyze the temperature difference of battery cells and detect abnormal temperature rise. When the threshold is exceeded, adjust the temperature difference and trigger a multi-level protection mechanism, including: Based on the real-time temperature distribution information, calculate the temperature difference between the battery cells, analyze the temperature difference distribution, and identify the area where the temperature difference exceeds the set threshold; Determine whether there is an abnormal temperature rise phenomenon according to the real-time temperature change rate and the prediction result; When it is detected that the temperature difference exceeds the set threshold, the operating state of the thermal management system is dynamically adjusted, including heating the low-temperature area or cooling the high-temperature area to restore the temperature difference to a safe range; When abnormal temperature rise is detected or temperature difference equalization adjustment cannot effectively reduce the risk, protective measures are triggered.

9. A battery thermal management control system, characterized in that: The system comprises: The multi-dimensional data fusion module obtains the basic operating parameter data of the automobile battery in real time and performs multi-dimensional data fusion to obtain a multi-dimensional data set; A temperature distribution acquisition module calculates the temperature distribution inside the battery in real time based on the thermodynamic model and the multidimensional data set to obtain real-time temperature distribution information; The change trend prediction module predicts the future temperature change trend of the battery through a recursive neural network model based on historical data and operating status; A control strategy adjustment module dynamically adjusts the control strategy of the battery thermal management system according to the real-time temperature distribution information and the prediction result; The single-cell adjustment protection module analyzes the temperature difference of battery cells and detects abnormal temperature rise. When the threshold is exceeded, the temperature difference is balanced and a multi-level protection mechanism is triggered.

10. The battery thermal management control system according to claim 9, characterized in that: The change trend prediction module includes: A recursive model training unit, which obtains historical operation data from the historical data, extracts time series features, and trains the recursive neural network model; A prediction result acquisition unit, using the trained recursive neural network model to predict the future temperature change trend of the battery to obtain a prediction result; The reputation result acquisition unit evaluates the risk of overheating or overcooling of the battery according to the prediction result to obtain a risk assessment result.

Images