Energy storage battery temperature management system and method based on liquid cooling technology

Abstract

The present application relates to the technical field of battery temperature management, and discloses an energy storage battery temperature management system and method based on liquid cooling technology. The method includes: initializing a population of design parameters of the battery liquid cooling system to generate multiple first combinations of liquid cooling system design parameters; respectively performing heat dissipation simulation during the discharging process of the target energy storage battery and constructing a three-dimensional temperature distribution based on the multiple first combinations of liquid cooling system design parameters to obtain three-dimensional temperature distribution data; constructing a first relationship vector between the number of channels and the temperature and constructing a second relationship vector between the coolant flow rate and the temperature; inputting the first relationship vector and the second relationship vector into a multi-task deep learning model to predict the optimized combination parameters, so as to obtain a second combination of liquid cooling system design parameters, thereby improving the liquid cooling heat dissipation efficiency of the energy storage battery and the thermal management accuracy during the battery discharging process.

Description

Technical Field

[0001] This application relates to the technical field of battery temperature management, and particularly to an energy storage battery temperature management system and method based on liquid cooling technology. Background Art

[0002] The rapid development of energy storage battery technology has become an indispensable part of modern energy systems. However, with the increase in battery energy density and the complexity of application scenarios, the thermal management problem of batteries has become increasingly prominent. Poor thermal management not only leads to a decline in battery performance but may also pose safety risks, such as thermal runaway and even fire of the battery caused by overheating.

[0003] Traditional air cooling technology is difficult to meet the requirements of current high-performance battery systems due to its insufficient cooling efficiency under high load conditions. Liquid cooling technology has become a powerful alternative due to its excellent heat conduction ability and better temperature uniformity. Although liquid cooling systems can effectively manage the temperature of batteries, the system design is complex and requires precise control of the coolant flow rate and channel layout to adapt to the thermal load characteristics of different battery packs. This requires the system to not only have high adaptability but also be able to dynamically adjust according to the real-time thermal state of the battery during actual operation, which poses higher requirements for the control strategy and design of the system. Summary of the Invention

[0004] This application provides an energy storage battery temperature management system and method based on liquid cooling technology, thereby improving the liquid cooling heat dissipation efficiency of energy storage batteries and the thermal management accuracy during the battery discharge process.

[0005] In the first aspect of this application, an energy storage battery temperature management method based on liquid cooling technology is provided. The energy storage battery temperature management method based on liquid cooling technology includes:

[0006] Initializing the design parameter population of the battery liquid cooling system to generate multiple first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: the initial number of channels and the initial coolant flow rate;

[0007] Based on the multiple first liquid cooling system design parameter combinations, respectively performing heat dissipation simulation during the discharge process of the target energy storage battery and constructing a three-dimensional temperature distribution to obtain the three-dimensional temperature distribution data of each first liquid cooling system design parameter combination;

[0008] Constructing a first relationship vector between the number of channels and temperature according to the initial number of channels and the three-dimensional temperature distribution data, and constructing a second relationship vector between the coolant flow rate and temperature according to the initial coolant flow rate and the three-dimensional temperature distribution data;

[0009] Input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction to obtain a second liquid cooling system design parameter combination.

[0010] In a second aspect of the present application, there is provided an energy storage battery temperature management system based on liquid cooling technology. The energy storage battery temperature management system based on liquid cooling technology includes:

[0011] An initialization module, configured to initialize the design parameter population of the battery liquid cooling system to generate a plurality of first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: an initial channel number and an initial coolant flow rate;

[0012] A simulation module, configured to perform heat dissipation simulation during the discharging process of the target energy storage battery and construct a three-dimensional temperature distribution based on the plurality of first liquid cooling system design parameter combinations to obtain three-dimensional temperature distribution data of each first liquid cooling system design parameter combination;

[0013] A construction module, configured to construct a first relationship vector between the channel number and the temperature according to the initial channel number and the three-dimensional temperature distribution data, and construct a second relationship vector between the coolant flow rate and the temperature according to the initial coolant flow rate and the three-dimensional temperature distribution data;

[0014] A prediction module, configured to input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction to obtain a second liquid cooling system design parameter combination.

[0015] In a third aspect of the present application, there is provided a computer device, including: a memory and at least one processor, where instructions are stored in the memory; the at least one processor invokes the instructions in the memory to enable the computer device to execute the above-mentioned energy storage battery temperature management method based on liquid cooling technology.

[0016] In a fourth aspect of the present application, there is provided a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a computer, the computer is enabled to execute the above-mentioned energy storage battery temperature management method based on liquid cooling technology.

[0017] In the technical solution provided by this application, by using liquid as the cooling medium, compared with the traditional air-cooling system, the liquid-cooling system can transfer and disperse heat more effectively. The battery can be cooled down more quickly during high-load operation, thereby improving the performance and lifespan of the battery. Through the design of optimized flow channels and flow control, the temperature uniformity among battery cells and within a single battery is achieved. The uniform distribution of temperature is crucial for the long-term stability and safety of the battery, and it can avoid structural damage or performance degradation caused by local overheating and large temperature gradients. A multi-task deep learning model is adopted to predict and optimize the design parameters of the liquid-cooling system, the coolant flow rate, and the number of channels. Through intelligent adaptive adjustment, the cooling strategy can be dynamically adjusted according to the actual working conditions of the battery and environmental changes, ensuring that the battery system can maintain the best working state under various environments. By precisely controlling the parameters of the liquid-cooling system, unnecessary energy consumption can be effectively reduced because the system can avoid overcooling and non-uniform cooling. The effectiveness of temperature management directly affects the safe operation of the battery. The liquid-cooling system can quickly respond to battery temperature changes and conduct effective control, thereby reducing the safety risks caused by battery overheating, and further improving the liquid-cooling heat dissipation efficiency of the energy storage battery and the thermal management accuracy during the battery discharge process. Description of the Drawings

[0018] Figure 1 It is a schematic diagram of an embodiment of the energy storage battery temperature management method based on liquid-cooling technology in the embodiment of this application;

[0019] Figure 2 It is a schematic diagram of an embodiment of the energy storage battery temperature management system based on liquid-cooling technology in the embodiment of this application. Detailed Embodiments

[0020] The embodiment of this application provides an energy storage battery temperature management system and method based on liquid-cooling technology, thereby improving the liquid-cooling heat dissipation efficiency of the energy storage battery and the thermal management accuracy during the battery discharge process.

[0021] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0022] For ease of understanding, the specific process of the embodiment of the present application will be described below. Please refer to Figure 1 An embodiment of the energy storage battery temperature management method based on liquid cooling technology in the embodiment of the present application includes:

[0023] Step 101: Initialize the design parameter population of the battery liquid cooling system to generate multiple first liquid cooling system design parameter combinations. Among them, the first liquid cooling system design parameter combination includes: the initial number of channels and the initial coolant flow rate;

[0024] It can be understood that the execution subject of the present application can be an energy storage battery temperature management system based on liquid cooling technology, or a terminal or a server. Specifically, it is not limited here. The embodiment of the present application takes the server as the execution subject as an example for illustration.

[0025] Specifically, define the threshold of the number of channels and the threshold of the flow rate parameter of the battery liquid cooling system. These thresholds are the upper or lower limits in the design process to ensure the feasibility and efficiency of the design parameters in actual applications. To generate multiple initial liquid cooling system design parameter combinations, the particle swarm optimization algorithm (PSO) is used. This is a population-based optimization tool that updates the particle positions by simulating the hunting behavior of bird flocks to effectively search for the optimal solution. In the particle swarm optimization algorithm, a group of particles is randomly initialized, and each particle represents a possible design parameter combination, that is, the first random value of the number of channels and the second random value of the coolant flow rate. Random numbers are generated within the defined thresholds of the number of channels and the flow rate parameter to form an initial candidate set of design parameters. The randomly generated parameter values are combined to form multiple candidate liquid cooling system design parameter combinations. Calculate the target fitness data of each candidate design parameter combination. The target fitness data is calculated according to criteria such as the expected cooling effect, energy efficiency, and cost-effectiveness of the design parameter combination. These data can be obtained through simulation or analysis based on previous experimental data. Compare the target fitness data with the preset standard fitness data, and evaluate the performance of each design parameter combination by calculating the difference data between the two. After obtaining the target difference data of each candidate design parameter combination, calculate the average value of these difference data. The average difference data provides a quantitative index reflecting the deviation degree of each design parameter combination from the standard fitness. Select parameter combinations according to the average difference data, and screen out those design parameter combinations with the smallest differences. These combinations are closer to or better than the preset performance standards. Through the screening and optimization process, multiple first liquid cooling system design parameter combinations are obtained, including the optimal solutions of the initial number of channels and the initial coolant flow rate.

[0026] Step 102: Based on multiple first liquid cooling system design parameter combinations, perform heat dissipation simulation during the discharge process of the target energy storage battery and construct a three-dimensional temperature distribution to obtain the three-dimensional temperature distribution data of each first liquid cooling system design parameter combination;

[0027] Specifically, a heat dissipation simulation model is constructed for each combination of liquid cooling system design parameters. The model is established based on the principle of computational fluid dynamics (CFD) and is used to simulate and analyze the flow path, velocity of the coolant inside the battery, and its impact on the temperature of the battery pack. The models for each combination of design parameters have different numbers of channels and coolant flow rates. The simulation helps predict and optimize the performance of the liquid cooling system to ensure that it can effectively control the temperature rise of the battery during discharge. Based on preset discharge parameters, such as discharge rate and ambient temperature, etc., actual heat dissipation tests of the discharge process are carried out on each liquid cooling heat dissipation simulation model. Battery temperature data is collected through specialized software and hardware tools, and the temperature changes inside the battery pack at different discharge stages are recorded. These data provide a direct basis for evaluating the performance of the liquid cooling system and show the influence of the cooling system design parameters on the heat dissipation efficiency. The collected battery temperature data is subjected to three-dimensional temperature distribution analysis. Each temperature data point inside the battery is converted into three-dimensional space coordinates to understand the temperature distribution inside the battery pack. Through three-dimensional mapping, the temperature distribution throughout the battery pack is visualized. Based on the three-dimensional space coordinates of each obtained temperature data point, a three-dimensional temperature distribution field mapping of the liquid cooling heat dissipation simulation model is carried out to obtain the heat dissipation performance of the liquid cooling system in space, and it can also be used to adjust and optimize the design parameters to ensure that the battery can be maintained within the optimal operating temperature range during actual use.

[0028] Step 103: Construct a first relationship vector between the number of channels and temperature based on the initial number of channels and three-dimensional temperature distribution data, and construct a second relationship vector between the coolant flow rate and temperature based on the initial coolant flow rate and three-dimensional temperature distribution data;

[0029] It should be noted that for the three-dimensional temperature distribution data, feature analysis is carried out to extract multiple temperature distribution characteristics of the battery under each combination of the first liquid cooling system design parameters. These characteristics may include the maximum value, minimum value, average value of the temperature, as well as the temperature gradient, etc., which jointly describe the thermal behavior pattern of the battery under a specific cooling system configuration. The mean value of multiple temperature distribution characteristics is calculated, and based on the mean value, the volatility of the temperature data is analyzed, and the temperature coefficient of variation is calculated. The temperature coefficient of variation is an important index to measure the stability of temperature distribution characteristics, and can reflect the consistency and fluctuation range of the battery temperature distribution under different design parameters. At the same time, for each design parameter - such as the initial number of channels and the initial coolant flow rate - the corresponding coefficient of variation is calculated, and the calculation results show the degree of change of each design parameter under different experimental or simulation conditions. The obtained quantity coefficient of variation is combined with the temperature coefficient of variation to calculate the quantity weight of the initial number of channels. At the same time, in combination with the flow coefficient of variation and the temperature coefficient of variation, the flow weight of the initial coolant flow rate is calculated. These weights reflect the relative importance of each design parameter in battery temperature management and provide a weighted benchmark for subsequent data processing. Using the calculated quantity weight and the first weight, vector transformation and vector weighted analysis are carried out on the initial number of channels and multiple temperature distribution characteristics. Through mathematical modeling and data processing techniques, a first relationship vector reflecting the relationship between the number of channels and the battery temperature distribution is constructed. Similarly, by using the flow weight and the second weight to process the initial coolant flow rate and the temperature distribution characteristics, a second relationship vector reflecting the relationship between the coolant flow rate and the battery temperature is generated. These two relationship vectors not only provide the relationship between the quantified design parameters and the battery performance, but also can guide future system design and optimization work to ensure that the battery is maintained within the optimal temperature range during operation, thereby improving the use efficiency and life of the battery.

[0030] Search for characteristic points in the three-dimensional temperature distribution data to identify multiple initial three-dimensional temperature characteristic points from complex datasets. These characteristic points are usually key positions in the temperature distribution, such as local maximum temperature points, minimum temperature points, or other significant change points, which are crucial for understanding the overall temperature distribution pattern. Subsequently, analyze the initial three-dimensional temperature characteristic points, including the identification of neighboring points. By searching the surrounding area of each characteristic point, determine the set of neighboring temperature characteristic points, which contain other temperature points similar or related to the initial characteristic point, thus capturing and reflecting the spatial continuity and local changes of the battery temperature. Use the set of neighboring temperature characteristic points to construct the temperature characteristic point distribution map corresponding to each initial three-dimensional temperature characteristic point. The distribution map is a visual representation of the spatial pattern of the internal temperature distribution of the battery, providing an intuitive way to analyze how the temperature spreads and concentrates inside the battery. Each distribution map not only shows the spatial distribution of the temperature but also reveals how the cooling effect is affected by the design parameters of the liquid cooling system. Calculate the clustering center for each temperature characteristic point distribution map, and determine the temperature distribution center or key area through mathematical methods. Through clustering analysis, identify the core areas where the temperature is concentrated in each distribution map, which are usually the key to controlling or optimizing the temperature management strategy. Determine multiple target three-dimensional temperature characteristic points based on the clustering center, and these characteristic points represent the key temperature control points under each combination of design parameters. From these target three-dimensional temperature characteristic points, generate multiple temperature distribution characteristics for each combination of the first liquid cooling system design parameters, which are used to evaluate and optimize the performance of the liquid cooling system.

[0031] Step 104: Input the first relationship vector and the second relationship vector into a preset multi-task deep learning model to predict the optimized combination parameters, and obtain the combination of the second liquid cooling system design parameters.

[0032] Specifically, a multi-task deep learning model is constructed, which can simultaneously process and optimize multiple outputs, such as the number of channels and the coolant flow rate. The model includes a convolutional neural network (CNN) with two branches, namely the first convolutional neural network and the second convolutional neural network, which are respectively responsible for extracting spatial features from the input relationship vectors. These convolutional neural networks are followed by a shared hidden layer, which serves as a hub for information integration, merging the features of the two networks and providing a more rich and comprehensive feature representation for subsequent processing. Subsequently, two Transformer networks are introduced, namely the first Transformer network and the second Transformer network, which are specifically trained for the prediction of the number of channels and the coolant flow rate respectively. The Transformer network has significant advantages in dealing with such problems because it can process sequential data and is excellent at capturing long-range dependencies. By inputting the first relationship vector and the second relationship vector into this multi-task deep learning model, the model can comprehensively consider the complex relationship between the two parameters and the battery temperature management performance, and predict the optimal number of channels and the optimal coolant flow rate. The prediction process is carried out through multiple layers of processing and feature extraction inside the model, ensuring that the output parameter combination can maximize the cooling efficiency and overall performance of the battery. After obtaining the optimal number of channels and the optimal coolant flow rate predicted by the model, the second set of design parameters for the battery liquid cooling system is generated based on these data. This new set of design parameters is verified and adjusted in practical applications to ensure its effectiveness and practicality in the real environment. By using a multi-task deep learning model that comprehensively utilizes convolutional neural networks and Transformer networks, the accuracy and operating efficiency of the liquid cooling system design can be significantly improved, thus providing a more stable and efficient temperature management solution for energy storage batteries.

[0033] Input the first relational vector into the first convolutional neural network for convolutional feature operation to obtain the first convolutional vector and extract features related to the number of channels. Input the second relational vector into the second convolutional neural network for convolutional feature operation to obtain the second convolutional vector and extract features related to the coolant flow rate. The first and second convolutional vectors represent the deep and non-linear features of the input data. Subsequently, concatenate the first relational vector and the second relational vector to obtain the concatenated relational vector, enabling the model to consider the correlation and interaction between the two vectors in subsequent processing, thus understanding and predicting the design parameters more comprehensively. Input the concatenated relational vector into the shared hidden layer for feature extraction, converting the concatenated vector into a target feature vector that contains all the necessary information for accurate prediction in subsequent steps. Input the first convolutional vector and the target feature vector into the first Transformer network, which is specifically configured to predict the optimal number of channels. The Transformer network optimizes the handling of long-range dependencies through its attention mechanism, facilitating the understanding and prediction of the channel configuration of the liquid cooling system. Similarly, input the second convolutional vector and the target feature vector into the second Transformer network to predict the optimal coolant flow rate. These two networks respectively output the predicted optimal number of channels and coolant flow rate, which are based on the complex patterns and relationships learned from the data. Integrate and output the optimal number of channels and the optimal coolant flow rate obtained from the two Transformer networks through the output layer. The output layer adjusts and optimizes the final output according to the weights and biases determined during model training, ensuring that the output result can maximize the performance of the battery liquid cooling system.

[0034] In the embodiments of the present application, by using a liquid as a cooling medium, compared with the traditional air-cooling system, the liquid-cooling system can transfer and disperse heat more effectively. The battery can be cooled down more quickly during high-load operation, thereby improving the performance and lifespan of the battery. Through the design of optimized flow channels and flow control, the temperature uniformity between battery cells and within a single battery is achieved. The uniform distribution of temperature is crucial for the long-term stability and safety of the battery, and can avoid structural damage or performance degradation caused by local overheating and large temperature gradients. A multi-task deep learning model is adopted to predict and optimize the design parameters of the liquid-cooling system, the coolant flow rate and the number of channels. Through intelligent adaptive adjustment, the cooling strategy can be dynamically adjusted according to the actual working conditions and environmental changes of the battery, ensuring that the battery system can maintain the best working state in various environments. By precisely controlling the parameters of the liquid-cooling system, unnecessary energy consumption can be effectively reduced, because the system can avoid over-cooling and uneven cooling. The effectiveness of temperature management directly affects the safe operation of the battery. The liquid-cooling system can quickly respond to battery temperature changes and carry out effective control, thereby reducing the safety risks caused by battery overheating, and further improving the liquid-cooling heat dissipation efficiency of the energy storage battery and the thermal management accuracy during the battery discharge process.

[0035] In a specific embodiment, the process of executing step 101 may specifically include the following steps:

[0036] (1) Define the threshold of the number of channels and the threshold of the flow rate parameter of the battery liquid-cooling system;

[0037] (2) Through the particle swarm optimization algorithm, perform random initialization according to the threshold of the number of channels and the threshold of the flow rate parameter, and obtain multiple first random values of the number of channels and multiple second random values of the coolant flow rate;

[0038] (3) Combine the multiple first random values and the multiple second random values to generate multiple candidate liquid-cooling system design parameter combinations;

[0039] (4) Calculate the target fitness data of each candidate liquid-cooling system design parameter combination respectively, and obtain the preset standard fitness data;

[0040] (5) Calculate the difference data between the target fitness data and the standard fitness data to obtain the target difference data of each candidate liquid-cooling system design parameter combination;

[0041] (6) Calculate the average difference data corresponding to the target difference data of each candidate liquid-cooling system design parameter combination, and perform parameter combination selection on the multiple candidate liquid-cooling system design parameter combinations according to the average difference data to obtain multiple first liquid-cooling system design parameter combinations, where the first liquid-cooling system design parameter combination includes: the initial number of channels and the initial coolant flow rate.

[0042] Specifically, define the key design parameters of the battery liquid cooling system, namely the threshold values of the number of channels and the coolant flow rate. These threshold values are the key constraints in the entire design process, determining the upper and lower limits of the system design, ensuring that the liquid cooling system can meet the cooling requirements without causing unnecessary resource waste due to over-design. After setting the threshold values, use the Particle Swarm Optimization (PSO) algorithm to randomly initialize the parameters. The Particle Swarm Optimization algorithm is a swarm intelligence algorithm that simulates the hunting behavior of bird flocks to find the optimal solution and achieves global optimality through information sharing among individuals. Randomly generate preliminary design parameters according to the threshold value of the number of channels and the threshold value of the coolant flow rate to obtain the first random value and the second random value. For example, if the threshold value of the number of channels is set between 10 and 50, and the threshold value of the coolant flow rate is set between 100 and 500 liters per hour, the particle swarm algorithm will generate a series of random combination values within these ranges, and these values reflect different possible design schemes. Subsequently, these randomly generated numbers of channels and coolant flow rates are combined into multiple candidate liquid cooling system design parameter combinations. For example, a specific combination may be 30 channels and a flow rate of 250 liters / hour, while another combination may be 45 channels and a flow rate of 300 liters / hour, and each combination represents a potential liquid cooling system configuration. Evaluate the candidate liquid cooling system design parameter combinations and calculate their objective fitness data. The objective fitness data is calculated based on a series of predefined performance criteria, which may include the cooling efficiency, energy consumption, cost, and implementability of the system. Compare the performance of each design parameter combination with the preset standard fitness data to obtain how effective each combination is. The standard fitness data usually comes from previous design experiences or the expected performance of an ideal model. By comparing the difference between the objective fitness data and the standard fitness data, obtain the objective difference data of each candidate liquid cooling system design parameter combination. This data reflects the degree of deviation of each combination from the ideal state, and the smaller the difference, the closer the design scheme is to the ideal model. For example, if the difference between the fitness value of a design parameter combination and the standard value is only 5%, while the difference of another combination is 10%, then the former is better. Rank and screen them by calculating the average value of the objective difference data of all candidate design parameter combinations. The average difference data provides a quantitative indicator to evaluate the overall performance of each design parameter combination, and a lower average difference value indicates a more excellent liquid cooling system design. Based on this data, select multiple design parameter combinations, and these combinations constitute the final first liquid cooling system design parameter combination, including the optimal number of channels and coolant flow rate.

[0043] In a specific embodiment, the process of performing step 102 may specifically include the following steps:

[0044] (1) Based on multiple combinations of the first liquid cooling system design parameters, a heat dissipation simulation model is constructed for the target energy storage battery respectively, and a liquid cooling heat dissipation simulation model for each combination of the first liquid cooling system design parameters is obtained;

[0045] (2) Based on the preset discharge parameter data, the heat dissipation test during the discharge process and the battery temperature data collection are carried out on the liquid cooling heat dissipation simulation model, and the battery temperature data of each liquid cooling heat dissipation simulation model are obtained;

[0046] (3) Three-dimensional temperature distribution analysis is carried out on multiple temperature data points in the battery temperature data, and the three-dimensional space coordinates of each temperature data point are obtained;

[0047] (4) According to the three-dimensional space coordinates of each temperature data point, three-dimensional temperature distribution field mapping is carried out on the liquid cooling heat dissipation simulation model, and three-dimensional temperature distribution data of each combination of the first liquid cooling system design parameters are obtained.

[0048] Specifically, a heat dissipation simulation model for the target energy storage battery is constructed based on multiple combinations of the first liquid cooling system design parameters. The design parameter combinations generally include factors such as the layout, quantity of the cooling channels, the type of the coolant and its flow rate, etc. Each parameter combination is optimized based on different cooling requirements and expected heat loads to simulate various thermal management scenarios that the battery may encounter during actual use. For example, if the battery pack is designed to operate under high load conditions, a liquid cooling system with more cooling channels and a higher coolant flow rate may be required. In this case, a combination of the liquid cooling system design parameters may include 50 cooling channels and a coolant flow rate of 500 liters per hour. For this design parameter combination, a corresponding liquid cooling heat dissipation simulation model is constructed using computational fluid dynamics (CFD) software to simulate the flow of the coolant within the battery module and its impact on the battery temperature. Based on the preset discharge parameter data, a heat dissipation test during the discharge process and battery temperature data collection are performed for each liquid cooling heat dissipation simulation model. The discharge parameters include the battery discharge rate, discharge depth, and ambient temperature, etc., and these parameters directly affect the heat generation and heat dissipation requirements of the battery. By simulating the actual working conditions of the battery, temperature data of the battery under various operating conditions are collected. For example, when simulating a scenario with a high discharge rate, it may be observed that the temperature of certain areas of the battery rises sharply, and this data is crucial for evaluating the effectiveness of the liquid cooling system. Subsequently, a three-dimensional temperature distribution analysis is performed on multiple temperature data points in the collected battery temperature data, and this analysis can reveal the detailed distribution of the internal temperature of the battery. By converting the temperature data into three-dimensional space coordinates, the high and low temperatures are obtained, and the specific positions of these high and low temperature points inside the battery are obtained. Through data analysis software and algorithms, the simple temperature readings are converted into a temperature map in three-dimensional space. According to the three-dimensional space coordinates of each temperature data point, a three-dimensional temperature distribution field mapping is performed for each liquid cooling heat dissipation simulation model. By combining the three-dimensional temperature data with the liquid cooling heat dissipation simulation model, a comprehensive three-dimensional temperature distribution map is obtained, which shows how the temperature of the battery is distributed throughout the entire battery module under a specific combination of the liquid cooling system design parameters. For example, if it is found that a certain design parameter combination results in excessive temperature in a certain area of the battery, then the layout of the cooling channels can be further adjusted or the flow rate of the coolant can be changed to achieve a better heat dissipation effect.

[0049] In a specific embodiment, the process of executing step 103 may specifically include the following steps:

[0050] (1) Perform feature analysis on the three-dimensional temperature distribution data to obtain multiple temperature distribution features for each combination of the first liquid cooling system design parameters;

[0051] (2) Calculate the mean value of the multiple temperature distribution features to obtain the feature mean value, and calculate the temperature coefficient of variation of the multiple temperature distribution features based on the feature mean value;

[0052] (3) Calculate the coefficient of variation for the initial number of channels to obtain the quantity coefficient of variation, and calculate the coefficient of variation for the initial coolant flow rate to obtain the flow rate coefficient of variation;

[0053] (4) Calculate the quantity weight of the initial number of channels and the first weight of the temperature coefficient of variation based on the quantity coefficient of variation and the temperature coefficient of variation, and calculate the flow rate weight of the initial coolant flow rate and the second weight of the temperature coefficient of variation based on the flow rate coefficient of variation and the temperature coefficient of variation;

[0054] (5) Perform vector transformation and vector weighted analysis on the initial number of channels and multiple temperature distribution characteristics according to the quantity weight and the first weight to obtain the first relationship vector between the number of channels and the temperature;

[0055] (6) Perform vector transformation and vector weighted analysis on the initial coolant flow rate and multiple temperature distribution characteristics according to the flow rate weight and the second weight to obtain the second relationship vector between the coolant flow rate and the temperature.

[0056] Specifically, by performing feature analysis on the three-dimensional temperature distribution data, multiple temperature distribution features of each combination of liquid cooling system design parameters are identified. These features include the highest point, the lowest point, the average temperature, and the temperature gradient of the temperature. By using data analysis tools and techniques, such as using computational fluid dynamics (CFD) simulation and subsequent data processing software to extract key data from the simulation results. Calculate the mean value of the temperature distribution features to obtain the average thermal behavior of the battery under different liquid cooling system designs. For example, if a combination of liquid cooling system design parameters produces multiple highest temperature points, calculating the average value of these highest points helps the system evaluate the cooling efficiency of this combination of design parameters. Based on the feature mean, calculate the coefficient of variation of multiple temperature distribution features. This coefficient is an important indicator to measure the consistency of the temperature distribution and can reflect the influence of design parameters on the stability of temperature control. Subsequently, calculate the coefficient of variation of the initial number of channels and the coolant flow rate. The coefficient of variation refers to the degree of change of a parameter under different operating conditions and can help the system understand the sensitivity of the number of channels and the coolant flow rate to battery temperature control within a predetermined operating range. For example, if a certain combination of design parameters shows a high coefficient of variation under high-load operating conditions, this may mean that its performance is more sensitive to operating conditions and may require further optimization to improve the robustness of the system. Calculate the weights of the coefficient of variation of the number of channels and the coolant flow rate. The weights are calculated based on the degree of association between the coefficient of variation and the coefficient of variation of temperature, quantifying the influence of each design parameter in the overall temperature management. For example, if the coefficient of variation of the number of channels is high, its quantity weight will also be correspondingly high, indicating that special attention needs to be paid to the adjustment of the number of channels during the design optimization process. By combining the quantity weight and the first weight (calculated based on the coefficient of variation of temperature), perform vector transformation and vector weighted analysis on the initial number of channels and multiple temperature distribution features, and finally generate a first relationship vector describing the relationship between the number of channels and temperature. Similarly, use the flow rate weight and the second weight (also calculated based on the coefficient of variation of temperature) to process the initial coolant flow rate and temperature distribution features, and generate a second relationship vector describing the relationship between the coolant flow rate and temperature.

[0057] In a specific embodiment, the process of performing feature analysis on the three-dimensional temperature distribution data to obtain multiple temperature distribution features of each combination of the first liquid cooling system design parameters may specifically include the following steps:

[0058] (1) Search for feature points in the three-dimensional temperature distribution data to obtain multiple initial three-dimensional temperature feature points;

[0059] (2) Identify adjacent points for each of the multiple initial three-dimensional temperature feature points to obtain a set of adjacent temperature feature points corresponding to each initial three-dimensional temperature feature point;

[0060] (3) Construct a temperature feature point distribution map corresponding to each initial three-dimensional temperature feature point based on the adjacent temperature feature point set;

[0061] (4) Calculate the clustering centers of the temperature feature point distribution maps respectively to obtain the target clustering centers of each temperature feature point distribution map;

[0062] (5) Determine the corresponding multiple target three-dimensional temperature feature points according to the target clustering centers, and generate multiple temperature distribution features of each first liquid cooling system design parameter combination according to the multiple target three-dimensional temperature feature points.

[0063] Specifically, search for feature points in the three-dimensional temperature distribution data to identify meaningful temperature feature points in the three-dimensional temperature distribution data. These feature points usually include extreme points of temperature, such as the highest temperature point and the lowest temperature point, as well as other thermodynamically significant change points, which may represent key regions of heat accumulation or dissipation. For example, if there is a region inside a battery cell that continuously shows a higher temperature than the surrounding environment, the highest temperature point in this region will be marked as an initial three-dimensional temperature feature point. This identification usually relies on advanced image processing or data analysis software, which can process data from temperature sensors or simulation software and automatically identify key hot spots. After determining the initial three-dimensional temperature feature points, identify adjacent points. Search the surrounding area of each feature point to identify a set of points with temperatures similar to the main feature point, forming an adjacent temperature feature point set. The adjacent point set helps to understand the thermal behavior of the feature point and its impact on the surrounding environment. For example, the adjacent point set around a high-temperature feature point may show a temperature gradient that gradually decreases from the center outwards, which helps to reveal how heat spreads in this area. Based on each adjacent temperature feature point set, construct the corresponding temperature feature point distribution map. The distribution map graphically shows the temperature distribution of each feature point and its adjacent points, enabling the system to intuitively see the temperature distribution pattern in three-dimensional space. Calculate the clustering centers of the temperature feature point distribution maps to identify the temperature aggregation centers in each distribution map. Clustering analysis techniques such as K-means or DBSCAN determine the center points in a set of points through algorithms, and these center points represent the main temperature aggregation regions. Each clustering center reflects a key thermal management region that requires special attention in the design of the liquid cooling system. Determine the corresponding target three-dimensional temperature feature points based on the clustering centers. Generate or optimize the temperature distribution features of each first liquid cooling system design parameter combination according to the feature points. For example, if the analysis shows that a specific clustering center is located in a certain corner of the battery module and this region continuously shows a higher temperature in all simulation scenarios, the system may decide to increase more cooling channels or increase the flow rate of the coolant in this region to solve the overheating problem.

[0064] In a specific embodiment, the process of executing step 104 may specifically include the following steps:

[0065] (1) Construct a multi-task deep learning model, which includes a first convolutional neural network, a second convolutional neural network, a shared hidden layer, a first Transformer network, a second Transformer network, and an output layer;

[0066] (2) Input the first relationship vector and the second relationship vector into the multi-task deep learning model for optimal channel number prediction and optimal coolant flow prediction, and output the optimal channel number and the optimal coolant flow;

[0067] (3) Generate a second set of design parameters for the battery liquid cooling system according to the optimal channel number and the optimal coolant flow.

[0068] Specifically, a multi-task deep learning model is constructed. The core architecture of the model includes two Convolutional Neural Networks (CNNs) and two Transformer networks, which are interconnected through a shared hidden layer. This structural design utilizes the capabilities of CNNs in processing image and spatial data, as well as the advantages of Transformers in processing sequence data and capturing long-range dependencies. The first Convolutional Neural Network mainly processes features related to the number of channels, while the second Convolutional Neural Network processes features related to the coolant flow rate. These two types of features are extracted from their respective relationship vectors, which may include temperature distribution data, system efficiency, and historical operation data, etc. After being processed by the convolutional layers, the feature vectors are passed to the shared hidden layer to merge the information of the two streams for comprehensive analysis. The shared layer helps reduce the complexity of the model and enables the model to learn general features across tasks during training, thereby improving the accuracy of predictions for different tasks. The features processed by the shared hidden layer are input into two different Transformer networks. The first Transformer network is responsible for predicting the optimal number of channels, while the second Transformer network is responsible for predicting the optimal coolant flow rate. The Transformer network is used because its self-attention mechanism can effectively capture the complex relationships between input features and provide accurate prediction outputs. After obtaining the predicted values of the optimal number of channels and the optimal coolant flow rate from the Transformer networks, this data is passed to the output layer of the model. The output layer integrates the prediction results and outputs the final combination of design parameters. For example, if the prediction results show that under the current test conditions and target performance metrics, the optimal number of channels is 40 and the optimal coolant flow rate is 200 liters per hour, this data will be directly used to guide the actual design and manufacturing of the liquid cooling system. Using the multi-task deep learning model to predict design parameters can significantly improve the design efficiency and optimize the system performance through precise data-driven decision-making. For example, in the energy management systems of electric vehicles or large-scale data centers, it can quickly adjust the design of the liquid cooling system according to different usage scenarios and environmental conditions to achieve the best heat dissipation effect and energy efficiency.

[0069] In a specific embodiment, the process of inputting the first relationship vector and the second relationship vector into the multi-task deep learning model for predicting the optimal number of channels and the optimal coolant flow rate and outputting the optimal number of channels and the optimal coolant flow rate may specifically include the following steps:

[0070] (1) Input the first relationship vector into the first Convolutional Neural Network for convolutional feature operation to obtain the first convolutional vector;

[0071] (2) Input the second relationship vector into the second Convolutional Neural Network for convolutional feature operation to obtain the second convolutional vector;

[0072] (3) Concatenate the first relationship vector and the second relationship vector to obtain a concatenated relationship vector, and input the concatenated relationship vector into a shared hidden layer for feature extraction to obtain a target feature vector;

[0073] (4) Input the first convolutional vector and the target feature vector into a first Transformer network for channel number prediction to obtain an optimal channel number, and input the second convolutional vector and the target feature vector into a second Transformer network for coolant flow rate prediction to obtain an optimal coolant flow rate;

[0074] (5) Integrate and output the optimal channel number and the optimal coolant flow rate through an output layer.

[0075] Specifically, the first relationship vector and the second relationship vector respectively represent data of different parameters and operating states related to the channel number and coolant flow rate of the battery liquid cooling system. For example, the first relationship vector may contain information such as temperature gradient, heat flux density, and the layout of liquid cooling channels extracted from historical operation data, while the second relationship vector may include data such as the physical properties, flow rate, and temperature of the coolant. These vectors are respectively input into two convolutional neural networks, namely the first convolutional neural network and the second convolutional neural network, which are designed to extract spatial features related to their respective tasks. The convolutional neural network detects local features in the input data by applying multiple filters, and each filter can identify specific patterns in the data, which is the key to achieving effective feature extraction. During this process, the first convolutional neural network may identify patterns related to channel layout and heat distribution, while the second network focuses on capturing patterns of coolant flow and temperature changes. Subsequently, the first and second convolutional vectors obtained from the two convolutional networks are concatenated together to form a comprehensive concatenated relationship vector. Combining all the key information related to channel design and coolant characteristics. The concatenated vector is input into a shared hidden layer, and the features are synthesized and refined through non-linear transformation to generate a target feature vector. The target feature vector is input into two different Transformer networks. The first Transformer network uses the target feature vector and the first convolutional vector for channel number prediction, while the second Transformer network uses the target feature vector and the second convolutional vector to predict the coolant flow rate. Each network deeply learns the dependencies in the input data through the self-attention mechanism and generates prediction results for their respective tasks. The prediction results (optimal channel number and optimal coolant flow rate) are input into the output layer of the model. In the output layer, these data are further integrated and output as a final combination of design parameters, which directly guides the actual design and manufacturing of the liquid cooling system.

[0076] The above describes the energy storage battery temperature management method based on liquid cooling technology in the embodiments of the present application. Next, the energy storage battery temperature management system based on liquid cooling technology in the embodiments of the present application will be described. Please refer to Figure 2 , an embodiment of the energy storage battery temperature management system based on liquid cooling technology in the embodiments of the present application includes:

[0077] An initialization module 201, configured to initialize the design parameter population of the battery liquid cooling system, and generate a plurality of first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: an initial number of channels and an initial coolant flow rate;

[0078] A simulation module 202, configured to perform heat dissipation simulation during the discharge process of the target energy storage battery and construct a three-dimensional temperature distribution based on a plurality of first liquid cooling system design parameter combinations, and obtain three-dimensional temperature distribution data for each first liquid cooling system design parameter combination;

[0079] A construction module 203, configured to construct a first relationship vector between the number of channels and the temperature according to the initial number of channels and the three-dimensional temperature distribution data, and construct a second relationship vector between the coolant flow rate and the temperature according to the initial coolant flow rate and the three-dimensional temperature distribution data;

[0080] A prediction module 204, configured to input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction, and obtain a second liquid cooling system design parameter combination.

[0081] Through the collaborative cooperation of the above-mentioned various components, by using liquid as the cooling medium, compared with the traditional air-cooled system, the liquid cooling system can transfer and disperse heat more effectively. The battery can be cooled down more quickly during high-load operation, thereby improving the performance and lifespan of the battery. Through the design of optimized flow channels and flow control, the temperature uniformity between battery cells and inside a single battery is achieved. The uniform distribution of temperature is crucial for the long-term stability and safety of the battery, and it can avoid structural damage or performance degradation caused by local overheating and large temperature gradients. A multi-task deep learning model is adopted to predict and optimize the design parameters of the liquid cooling system, the coolant flow rate and the number of channels. Through intelligent adaptive adjustment, the cooling strategy can be dynamically adjusted according to the actual working conditions and environmental changes of the battery, ensuring that the battery system can maintain the best working state in various environments. By precisely controlling the parameters of the liquid cooling system, unnecessary energy consumption can be effectively reduced because the system can avoid overcooling and uneven cooling. The effectiveness of temperature management directly affects the safe operation of the battery. The liquid cooling system can quickly respond to battery temperature changes and perform effective control, thereby reducing the safety risks caused by battery overheating, and further improving the liquid cooling heat dissipation efficiency of the energy storage battery and the thermal management accuracy during the battery discharge process.

[0082] The present application also provides a computer device, which includes a memory and a processor. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor is caused to execute the steps of the energy storage battery temperature management method based on liquid cooling technology in the above embodiments.

[0083] The present application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is caused to execute the steps of the energy storage battery temperature management method based on liquid cooling technology.

[0084] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0086] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A temperature management method for energy storage batteries based on liquid cooling technology, characterized in that, The energy storage battery temperature management method based on liquid cooling technology includes: Initializing the design parameter population of the battery liquid cooling system to generate multiple first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: the initial number of channels and the initial coolant flow rate; Based on the multiple first liquid cooling system design parameter combinations, respectively perform heat dissipation simulation during the discharge process of the target energy storage battery and construct a three-dimensional temperature distribution, obtaining the three-dimensional temperature distribution data of each first liquid cooling system design parameter combination; Construct a first relationship vector between the number of channels and temperature according to the initial number of channels and the three-dimensional temperature distribution data, and construct a second relationship vector between the coolant flow rate and temperature according to the initial coolant flow rate and the three-dimensional temperature distribution data; specifically include: performing feature analysis on the three-dimensional temperature distribution data to obtain multiple temperature distribution features of each first liquid cooling system design parameter combination; calculating the mean value of the multiple temperature distribution features to obtain the feature mean value, and calculating the temperature variation coefficient of the multiple temperature distribution features according to the feature mean value; calculating the variation coefficient of the initial number of channels to obtain the number variation coefficient, and calculating the variation coefficient of the initial coolant flow rate to obtain the flow variation coefficient; calculating the number weight of the initial number of channels and the first weight of the temperature variation coefficient according to the number variation coefficient and the temperature variation coefficient, and calculating the flow weight of the initial coolant flow rate and the second weight of the temperature variation coefficient according to the flow variation coefficient and the temperature variation coefficient; performing vector transformation and vector weighted analysis on the initial number of channels and the multiple temperature distribution features according to the number weight and the first weight to obtain a first relationship vector between the number of channels and temperature; performing vector transformation and vector weighted analysis on the initial coolant flow rate and the multiple temperature distribution features according to the flow weight and the second weight to obtain a second relationship vector between the coolant flow rate and temperature; Input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction to obtain a second liquid cooling system design parameter combination.

2. The temperature management method of the energy storage battery based on the liquid cooling technology according to claim 1, wherein The initializing the design parameter population of the battery liquid cooling system to generate multiple first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: the initial number of channels and the initial coolant flow rate, includes: Defining the channel number threshold and the flow parameter threshold of the battery liquid cooling system; Through the particle swarm optimization algorithm, perform random initialization according to the channel number threshold and the flow parameter threshold to obtain multiple first random values of the channel number and multiple second random values of the coolant flow rate; Combining the multiple first random values and the multiple second random values to generate multiple candidate liquid cooling system design parameter combinations; Respectively calculate the target fitness data of each candidate liquid cooling system design parameter combination and obtain the preset standard fitness data; Calculate the difference data between the target fitness data and the standard fitness data to obtain the target difference data for each candidate liquid cooling system design parameter combination; Calculate the average difference data corresponding to the target difference data of each candidate liquid cooling system design parameter combination, and perform parameter combination selection on the multiple candidate liquid cooling system design parameter combinations according to the average difference data to obtain multiple first liquid cooling system design parameter combinations, where the first liquid cooling system design parameter combinations include: the initial number of channels and the initial coolant flow rate.

3. The temperature management method for an energy storage battery based on liquid cooling technology according to claim 1, wherein Based on the multiple first liquid cooling system design parameter combinations, respectively perform heat dissipation simulation during the discharge process and three-dimensional temperature distribution construction on the target energy storage battery to obtain the three-dimensional temperature distribution data of each first liquid cooling system design parameter combination, including: Based on the multiple first liquid cooling system design parameter combinations, respectively construct a heat dissipation simulation model for the target energy storage battery to obtain a liquid cooling heat dissipation simulation model for each first liquid cooling system design parameter combination; Based on the preset discharge parameter data, perform heat dissipation test during the discharge process and battery temperature data acquisition on the liquid cooling heat dissipation simulation model to obtain the battery temperature data of each liquid cooling heat dissipation simulation model; Perform three-dimensional temperature distribution analysis on multiple temperature data points in the battery temperature data to obtain the three-dimensional space coordinates of each temperature data point; According to the three-dimensional space coordinates of each temperature data point, perform three-dimensional temperature distribution field mapping on the liquid cooling heat dissipation simulation model to obtain the three-dimensional temperature distribution data of each first liquid cooling system design parameter combination.

4. The temperature management method of the energy storage battery based on the liquid cooling technology according to claim 1, characterized in that, Perform feature analysis on the three-dimensional temperature distribution data to obtain multiple temperature distribution features of each first liquid cooling system design parameter combination, including: Search for feature points in the three-dimensional temperature distribution data to obtain multiple initial three-dimensional temperature feature points; Identify neighboring points for the multiple initial three-dimensional temperature feature points respectively to obtain a set of neighboring temperature feature points corresponding to each initial three-dimensional temperature feature point; Construct a temperature feature point distribution map corresponding to each initial three-dimensional temperature feature point based on the set of neighboring temperature feature points; Calculate the clustering center of each temperature feature point distribution map respectively to obtain the target clustering center of each temperature feature point distribution map; Determine the corresponding multiple target three-dimensional temperature feature points according to the target clustering center, and generate multiple temperature distribution features of each first liquid cooling system design parameter combination according to the multiple target three-dimensional temperature feature points.

5. The temperature management method of the energy storage battery based on the liquid cooling technology according to claim 1, characterized in that, Input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction to obtain a second liquid cooling system design parameter combination, including: Construct a multi-task deep learning model, where the multi-task deep learning model includes a first convolutional neural network, a second convolutional neural network, a shared hidden layer, a first Transformer network, a second Transformer network, and an output layer; Input the first relationship vector and the second relationship vector into the multi-task deep learning model for optimal channel number prediction and optimal coolant flow rate prediction, and output the optimal channel number and the optimal coolant flow rate; Generate the second set of design parameters for the battery liquid cooling system based on the optimal number of channels and the optimal coolant flow rate.

6. The temperature management method for an energy storage battery based on liquid cooling technology according to claim 5, characterized in that, Inputting the first relationship vector and the second relationship vector into the multi-task deep learning model for optimal channel number prediction and optimal coolant flow rate prediction, and outputting the optimal channel number and the optimal coolant flow rate, includes: Input the first relationship vector into the first convolutional neural network for convolutional feature operation to obtain a first convolutional vector; Input the second relationship vector into the second convolutional neural network for convolutional feature operation to obtain a second convolutional vector; Perform vector concatenation on the first relationship vector and the second relationship vector to obtain a concatenated relationship vector, and input the concatenated relationship vector into the shared hidden layer for feature extraction to obtain a target feature vector; Input the first convolutional vector and the target feature vector into the first Transformer network for channel number prediction to obtain the optimal channel number, and input the second convolutional vector and the target feature vector into the second Transformer network for coolant flow rate prediction to obtain the optimal coolant flow rate; Integrate and output the optimal channel number and the optimal coolant flow rate through the output layer.

7. A temperature management system for energy storage batteries based on liquid cooling technology, characterized in that, The energy storage battery temperature management system based on liquid cooling technology includes: An initialization module for initializing the design parameter population of the battery liquid cooling system to generate multiple first sets of design parameters for the liquid cooling system, where the first set of design parameters for the liquid cooling system includes: an initial number of channels and an initial coolant flow rate; A simulation module for performing heat dissipation simulation during the discharge process and constructing a three-dimensional temperature distribution for the target energy storage battery based on the multiple first sets of design parameters for the liquid cooling system, to obtain the three-dimensional temperature distribution data for each first set of design parameters for the liquid cooling system; A building module, configured to construct a first relationship vector between the number of channels and temperature based on the initial number of channels and the three-dimensional temperature distribution data, and construct a second relationship vector between the coolant flow rate and temperature based on the initial coolant flow rate and the three-dimensional temperature distribution data; specifically including: performing feature analysis on the three-dimensional temperature distribution data to obtain multiple temperature distribution features of each first liquid cooling system design parameter combination; calculating the mean value of the multiple temperature distribution features to obtain the feature mean value, and calculating the temperature variation coefficient of the multiple temperature distribution features according to the feature mean value; calculating the variation coefficient of the initial number of channels to obtain the number variation coefficient, and calculating the variation coefficient of the initial coolant flow rate to obtain the flow variation coefficient; calculating the number weight of the initial number of channels and the first weight of the temperature variation coefficient according to the number variation coefficient and the temperature variation coefficient, and calculating the flow weight of the initial coolant flow rate and the second weight of the temperature variation coefficient according to the flow variation coefficient and the temperature variation coefficient; performing vector transformation and vector weighted analysis on the initial number of channels and the multiple temperature distribution features according to the number weight and the first weight to obtain a first relationship vector between the number of channels and temperature; performing vector transformation and vector weighted analysis on the initial coolant flow rate and the multiple temperature distribution features according to the flow weight and the second weight to obtain a second relationship vector between the coolant flow rate and temperature; A prediction module, configured to input the first relationship vector and the second relationship vector into a preset multi-task deep learning model for optimal combination parameter prediction to obtain a second liquid cooling system design parameter combination.

8. A computer device, characterized in that, The computer device includes: a memory and at least one processor, and instructions are stored in the memory; The at least one processor invokes the instructions in the memory to cause the computer device to execute the energy storage battery temperature management method based on liquid cooling technology according to any one of claims 1-6.

9. A computer-readable storage medium, on which instructions are stored, characterized in that, When the instructions are executed by the processor, the energy storage battery temperature management method based on liquid cooling technology according to any one of claims 1-6 is implemented.

Images