Energy storage battery temperature control early warning method and system

Abstract

The present invention relates to the technical field of battery temperature control and early warning technology, and in particular to a method and system for temperature control and early warning of energy storage batteries. The method comprises the following steps: obtaining an internal structure diagram of the energy storage battery; performing internal space layout analysis and inter-unit physical connection analysis on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology structure model; obtaining real-time temperature monitoring parameters of the energy storage battery; performing dynamic temperature distribution visualization rendering on the three-dimensional battery topology structure model based on the real-time temperature monitoring parameters of the energy storage battery, thereby constructing thermal state portraits of multiple unit areas; performing multi-period battery operation simulation on the thermal state portraits of the multiple unit areas, and performing sliding time window temperature change trend prediction to obtain the temperature change prediction trend of each area; performing continuous abnormal temperature rise trend detection on the temperature change prediction trend of each area, thereby generating abnormal temperature rise trend characteristics. The present invention achieves safe and efficient battery temperature control and early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of battery temperature control and early warning technology, and in particular to a temperature control and early warning method and system for an energy storage battery. Background Art

[0002] Energy storage batteries, as a key component of modern energy systems, are widely used in power storage, smart grids, mobile power supplies, and other fields, carrying the important task of power conversion and storage. With the rapid development of new energy and energy storage technologies, energy storage batteries are playing an increasingly significant role in power regulation, load balancing, and emergency power supply. However, during the long and frequent charge and discharge process, energy storage batteries often generate significant heat due to internal chemical reactions, external load changes, and environmental factors. If battery temperature is not effectively controlled, it can lead to degraded battery performance, reduced charge and discharge efficiency, and even safety incidents such as overheating, fire, or explosion.

[0003] Traditional battery temperature control technologies rely primarily on simple temperature monitoring and heat dissipation designs, using physical heat dissipation and temperature control systems to prevent battery overheating. However, these methods often fail to consider the temperature variations of batteries under different operating conditions and their long-term impact on battery life and safety. Furthermore, they lack sufficient intelligent early warning capabilities and are unable to effectively predict the timing and causes of temperature anomalies, making it difficult to take effective measures before abnormal temperature rises occur.

[0004] With the increasing complexity of energy storage battery applications and the increasing demand for battery safety, traditional temperature control technologies can no longer meet the accuracy and real-time requirements of temperature control warnings in modern energy storage systems. Therefore, there is an urgent need to develop an energy storage battery temperature control warning method that integrates advanced monitoring technology, predictive analysis technology, and intelligent warning mechanisms. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a temperature control early warning method and system for energy storage batteries to solve at least one of the above technical problems.

[0006] To achieve the above objectives, the present invention provides a temperature control and early warning method for an energy storage battery, comprising the following steps:

[0007] Step S1: Obtaining an internal structure diagram of the energy storage battery; performing internal space layout analysis and inter-unit physical connection analysis on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model;

[0008] Step S2: obtaining real-time temperature monitoring parameters of the energy storage battery; performing dynamic temperature distribution visualization rendering on the three-dimensional battery topology model according to the real-time temperature monitoring parameters of the energy storage battery, thereby constructing thermal state portraits of multiple unit areas;

[0009] Step S3: performing multi-period battery operation simulation on the thermal state portraits of the multiple unit areas, and performing sliding window temperature change trend prediction to obtain the temperature change prediction trend of each area;

[0010] Step S4: Continuously detecting abnormal temperature rise trends in the temperature change forecast situation of each region, thereby generating abnormal temperature rise trend features; and generating temperature anomaly warning signals based on the abnormal temperature rise trend features;

[0011] Step S5: performing dynamic temperature rise diffusion evolution based on the temperature abnormality warning signal, and then making a battery abnormality fault diagnosis decision to obtain a battery abnormality fault diagnosis result;

[0012] Step S6: Obtain the historical work log of the energy storage battery; conduct in-depth mining of the load status of each scene in the historical work log of the energy storage battery, and optimize the dynamic temperature control parameters according to the battery abnormal fault diagnosis results to build a dynamic battery temperature control engine.

[0013] The present invention accurately constructs a three-dimensional topological structure model of the battery by analyzing the internal structure of the energy storage battery and the connection relationship between the cells. This provides a basis for subsequent temperature distribution and thermal status monitoring, ensuring that the temperature monitoring system accurately maps various areas inside the battery. By obtaining real-time temperature data and combining it with the three-dimensional battery topological structure model for visual rendering, the temperature distribution of each unit area of the battery is fully displayed, so that temperature anomalies can be discovered in time to avoid overheating or uneven cooling of the battery. Through multi-period battery operation simulation, the temperature change trend of the battery under different working conditions is predicted. Combined with the temperature change trend prediction of the sliding window, the early signs of temperature anomalies are effectively captured, which helps to take preventive measures in advance to prevent battery overheating or performance degradation. Through continuous monitoring of the temperature change trend, the abnormal temperature rise trend of the battery cell is detected in time to avoid battery overheating or uneven cooling. High temperature can cause safety hazards. Based on the early warning signal generated by the abnormal temperature rise trend, the operator is reminded in real time to take necessary measures, such as adjusting the battery load, starting the cooling system, etc., to ensure that the battery is in a safe operating temperature range. Through the dynamic evolution analysis of the battery temperature rise diffusion, the temperature anomaly source can be more accurately located to diagnose battery faults, which helps to identify battery faults such as short circuit, overheating, unit damage, etc., and reduce the probability of faults. Through in-depth mining of the historical work logs of energy storage batteries, the performance of batteries in different working environments and load conditions can be understood, which helps to identify historical factors that lead to temperature anomalies. According to the abnormal fault diagnosis results of the battery and the analysis of the historical work logs, the battery temperature control strategy is adjusted, the temperature control parameters are optimized, and the operating temperature of the battery is dynamically adjusted to ensure that the battery works in the safest and most efficient state, further extending the battery life.

[0014] Preferably, step S1 includes the following steps:

[0015] Step S11: performing CT scanning on the target energy storage battery to obtain an internal structure diagram of the energy storage battery;

[0016] Step S12: Perform deep visual recognition on the internal structure diagram of the energy storage battery and mark each battery cell;

[0017] Step S13: performing precise positioning calculation of the internal space of each battery cell to extract the internal space coordinates of each battery cell;

[0018] Step S14: performing internal space layout analysis based on the internal space coordinates of each battery cell to generate battery space layout features;

[0019] Step S15: performing inter-cell physical connection analysis on each battery cell to obtain a topological connection relationship of the battery cells;

[0020] Step S16: reconstructing the battery space layout characteristics in three dimensions based on the topological connection relationship of the battery cells to construct a three-dimensional battery topological structure model.

[0021] The present invention uses CT scanning imaging technology to non-destructively obtain a detailed structural diagram of the internal structure of the energy storage battery, including the arrangement, size and shape of the battery cells. Compared with traditional disassembly or external scanning methods, CT scanning can provide more accurate and comprehensive internal battery information. Through deep visual recognition technology, each battery cell inside the energy storage battery can be automatically and accurately identified. This technology can identify the shape, size and relative position of the battery cell, reduce manual intervention, improve accuracy and efficiency, and accurately locate each battery cell to obtain the spatial coordinates of the battery cell. This is the core step in constructing a three-dimensional topological structure model. Through the precise calculation of spatial coordinates, errors are eliminated and the model is ensured to be spatially accurate. Accuracy: By analyzing the layout of the spatial coordinates of the battery cells, the relative positions, arrangement methods and heat flow channels between the battery cells are identified. The generated battery spatial layout characteristics help to understand the working environment and performance of the battery. By analyzing the physical connections between the battery cells, it is clear how each battery cell is connected to each other, including electrical connections and thermal connections. This is crucial for understanding the electrical performance, heat conduction and load balancing inside the battery. According to the spatial layout characteristics and topological connection relationships of the battery cells, the three-dimensional structure is reconstructed to generate a complete and accurate three-dimensional battery topology structure model. This three-dimensional model provides an intuitive and accurate foundation for the subsequent temperature control and early warning system.

[0022] Preferably, step S2 includes the following steps:

[0023] Step S21: Acquire real-time temperature monitoring parameters of the energy storage battery based on multiple sensors;

[0024] Step S22: Calculating the internal position of each sensor node one by one based on the multi-sensor to obtain the internal space coordinates of the battery of each sensor node;

[0025] Step S23: performing spatial temperature distribution mining on the real-time temperature monitoring parameters of the energy storage battery according to the internal spatial coordinates of the battery of each sensor node to obtain the temperature distribution characteristics of each battery cell;

[0026] Step S24: dividing the three-dimensional battery topology model into multiple battery unit regions, thereby generating multiple unit region models;

[0027] Step S25: Based on the temperature distribution characteristics of each battery cell, dynamic temperature distribution visualization rendering is performed on the multiple unit area models, thereby constructing thermal state portraits of the multiple unit areas.

[0028] This invention uses multi-sensor technology to simultaneously monitor temperature at key locations throughout the battery system. Multiple sensors cover different battery regions, ensuring comprehensive temperature data and avoiding inaccurate temperature monitoring due to errors or failures in a single sensor. By calculating the internal position of each sensor node, the spatial coordinates of each sensor within the battery can be accurately determined. This ensures that temperature data is correctly mapped to the actual battery location, avoiding temperature data deviations caused by inaccurate positioning. Spatial temperature distribution mining enables early detection of temperature anomalies, providing an important basis for early warning systems. Furthermore, analyzing the temperature characteristics of different cells helps optimize battery cell layout, cooling systems, and thermal management designs. By partitioning the three-dimensional battery topology model into multiple cell regions, the battery is divided into several distinct zones, facilitating further analysis of the temperature conditions in each zone. This partitioning is based on factors such as the battery's physical structure, temperature distribution characteristics, and load requirements, making the analysis more targeted. By combining the temperature distribution characteristics of each cell with the three-dimensional model for dynamic visualization, the thermal status of different battery zones is displayed in real time. This thermal status visualization provides operators with an intuitive temperature monitoring view, making it easier to identify areas experiencing overheating or temperature imbalances. Dynamic thermal status visualization can reveal abnormal temperature areas in advance, helping to identify potential safety risks early, such as battery cell overheating and large temperature differences. This helps to take timely measures to prevent failures or accidents caused by temperature runaway.

[0029] Preferably, the specific steps of step S25 are:

[0030] Perform real-time temperature distribution change analysis on the temperature distribution characteristics of each battery cell to generate real-time temperature distribution change data;

[0031] Perform discrete fitting of time series temperature values on real-time temperature distribution change data to construct the temperature distribution change curve of each battery cell;

[0032] Perform temperature positioning matching on the temperature distribution change curve of each battery cell and multiple unit area models to obtain the matching temperature curve relationship of each unit area;

[0033] Visualize the temperature distribution of multiple unit area models based on the matching temperature curve relationship of each unit area, thereby obtaining the temperature distribution thermal map of multiple unit areas;

[0034] Dynamic temperature change rendering is performed on the temperature distribution thermodynamic map of multiple unit areas to construct thermal state portraits of multiple unit areas.

[0035] The present invention analyzes the temperature distribution characteristics of each battery cell in real time and timely captures the fluctuation of battery temperature under different working conditions. This helps to track the temperature change trend in real time and ensure that the temperature remains within a safe range during the operation of the battery. Through discrete fitting of time series temperature values, the real-time temperature data is converted into a smooth temperature change curve. This curve can intuitively show the temperature change of each battery cell at different time points, which is convenient for analysis and early warning. By matching the temperature change curve of each battery cell with the temperature positioning of the multi-cell regional model, it is ensured that the temperature change of each region is consistent with the temperature data of the actual environment. This step provides accurate guidance for subsequent thermodynamic analysis. The positioning and data of the battery system are used to generate a temperature distribution thermogram of each unit area through the visualization of the temperature distribution. This makes the temperature distribution and changes more intuitive, and the operator can quickly identify which areas have higher temperatures or larger temperature differences, so as to take timely treatment measures. By dynamically rendering the temperature change of the thermograms of multiple unit areas, the process of temperature distribution changing over time is displayed, forming a dynamic thermal state portrait. This dynamic image helps the operator understand the temperature state change trend of the battery system in real time. The dynamic thermal state portrait can display sudden changes or anomalies in the temperature change process, helping to timely discover potential safety hazards, such as local overheating, uneven cooling, etc., and to issue early warnings and take preventive measures.

[0036] Preferably, the specific steps of step S3 are:

[0037] Step S31: defining multiple operating conditions of the battery pack;

[0038] Step S32: performing multi-period battery operation simulation on thermal state portraits of multiple unit areas according to multiple operating conditions of the battery pack to collect multi-period operation simulation data;

[0039] Step S33: performing temperature change trend analysis on each region of the multi-period simulation data to obtain temperature change trend characteristics of each region;

[0040] Step S34: performing sliding window temperature change situation prediction based on the temperature change trend characteristics of each area to obtain the temperature change prediction situation of each area.

[0041] The present invention defines multiple operating conditions to simulate the performance of the battery pack under different loads, temperatures, working pressures and other conditions. This helps to comprehensively evaluate the thermal management capabilities of the battery pack under various working scenarios and ensure that the temperature control warning system can cope with various complex working conditions in actual applications. Through multi-period simulation, the temperature changes of the battery pack in different time periods and different working conditions can be obtained. These data can reflect the temperature fluctuations of the battery during long-term operation and help to gain a deeper understanding of the thermal management performance of the battery. The multi-period operation simulation can simulate the temperature response of the battery under different working conditions, ensuring that the system can provide effective temperature control warnings even under extreme working conditions to avoid battery overheating. The risk of high or too low temperature is eliminated by analyzing the temperature change trend of each area of the simulation data one by one, and accurately obtaining the temperature fluctuation characteristics of each unit area in different time periods. This helps to identify which areas have large temperature changes and which areas have temperature hotspots. The sliding window temperature change trend prediction method uses the existing temperature change trend to predict the temperature change in the future. In this way, the impending temperature anomaly can be discovered in advance, providing sufficient response time for the temperature control warning system. Through temperature change prediction, it can identify the temperature abnormality trend of battery cells or areas in the future, such as overheating, uneven heat dissipation, etc., thereby providing sufficient time for the battery management system to intervene.

[0042] Preferably, the specific steps of step S32 are:

[0043] Based on the real-time temperature monitoring parameters of the energy storage battery, the temperature difference between adjacent cells is mined for each battery cell to obtain the temperature change relationship between adjacent cells;

[0044] Based on the temperature change relationship between adjacent cells, the heat transfer evolution between battery cells is analyzed to obtain the heat transfer law of battery cells;

[0045] Calculate the cooling efficiency of energy storage batteries;

[0046] Performing a quantitative analysis of the heat transfer rules of the battery cells and the cooling efficiency of the energy storage battery under multiple operating conditions of the battery pack, thereby generating battery operating characteristics under different operating conditions;

[0047] Based on the battery operation characteristics of different working conditions, multi-period battery operation simulation is performed on the thermal state portraits of multiple unit areas to collect multi-period operation simulation data.

[0048] The present invention reveals the heat transfer effect between different battery cells by exploring the correlation between the temperature difference changes between adjacent cells. This helps to deeply understand how heat is transferred between cells in the battery pack, especially which cells have a greater impact on temperature changes. Through the temperature change relationship between battery cells, a heat transfer evolution model between battery cells is constructed, which helps to understand and predict the heat propagation mode and rate between cells in the battery pack, provide a basis for optimizing cooling design, calculate the cooling efficiency, clarify the performance of the cooling system in the battery pack, and judge whether it can effectively take away the heat of the battery cells and maintain the system temperature within a safe range. By analyzing the heat transfer laws and cooling methods of battery cells under various working conditions, the present invention also reveals the heat transfer effect between different battery cells. Quantitative analysis of cooling efficiency can evaluate the thermal performance of batteries in different operating environments. This analysis helps to optimize the thermal management strategy of batteries under different working conditions. Analysis under different working conditions helps to understand the thermal response of batteries under extreme working conditions (such as high load or low temperature), ensuring that the batteries can maintain stable operation under various working conditions and will not cause performance degradation or safety hazards due to temperature problems. Through multi-period simulation, the temperature data of battery packs under various working conditions in different time periods are collected. Such data provides sufficient information for subsequent temperature control predictions. Simulation under different working conditions can more accurately simulate the various situations encountered by battery packs in actual operation, thereby improving the adaptability and accuracy of the simulation model.

[0049] Preferably, the specific steps of step S4 are:

[0050] Step S41: Calculating the temperature change rate for the predicted temperature change situation of each region to generate the temperature change situation rate of each region;

[0051] Step S42: analyzing the temperature fluctuation range of each region based on the temperature change prediction trend to obtain the temperature fluctuation range of each region;

[0052] Step S43: identifying temperature rise deviations based on the temperature change rate of each region and the temperature change fluctuation range of each region, and marking the temperature change deviation regions;

[0053] Step S44: performing continuous abnormal temperature rise trend detection on the temperature change deviation area based on a preset temperature rise deviation threshold, thereby generating an abnormal temperature rise trend feature;

[0054] Step S45: generating a temperature abnormality warning signal based on the abnormal temperature rise trend characteristics.

[0055] By calculating the temperature change rate, the present invention can timely understand the temperature change rate of each area, which helps to quickly identify those areas with rapid temperature changes, facilitates quick response and measures, and the calculation of the temperature change rate enables the system to capture areas where the temperature changes too quickly and promptly discover existing overheating or uneven heat dissipation problems, which provides a data basis for taking cooling, cooling or load adjustment measures in advance. By analyzing the temperature change fluctuation range of each area, the amplitude and change trend of the temperature fluctuation can be clarified, so as to identify areas with large temperature fluctuations or too high temperatures, thereby avoiding the battery being affected by unstable temperature. The analysis of the temperature change fluctuation range helps to optimize the battery's heat dissipation system. For areas with large fluctuations, cooling is strengthened, radiators are added, etc. to maintain the battery temperature stability. By combining the temperature change rate and the temperature change fluctuation range, areas where temperature changes deviate from the normal trend can be accurately identified, which helps to discover potential temperature as early as possible. Abnormalities can be detected to avoid failures caused by local overheating. By marking the temperature change deviation area, the problem can be concentrated in a specific area, which is convenient for targeted adjustments and optimization, such as enhancing cooling or adjusting workload. By continuously monitoring the temperature change deviation area, the trend of abnormal temperature rise can be tracked in real time to ensure that a response is made before the temperature exceeds the standard. Detecting the temperature rise trend in advance can help reduce the occurrence of system overheating and safety accidents. The preset temperature rise deviation threshold helps to set the warning line. Once the temperature changes beyond the set range, the system can immediately generate an alarm signal and automatically trigger temperature control measures to avoid temperature out of control. By generating temperature abnormality warning signals, the system can automatically detect and prompt operators to take measures, reduce reliance on human intervention, and improve the response speed of the system. The temperature abnormality warning signal helps operators to deal with problems such as rapid temperature rise or uneven temperature in the battery pack in a timely manner to prevent the problem from deteriorating to the point of causing equipment damage or danger.

[0056] Preferably, the specific steps of step S5 are:

[0057] Step S51: locating the abnormal temperature starting point based on the abnormal temperature warning signal, thereby marking the abnormal temperature rise starting unit;

[0058] Step S52: performing abnormal temperature rise evolution path analysis on the abnormal temperature rise starting unit based on the three-dimensional battery topology model to generate multiple abnormal temperature rise evolution paths;

[0059] Step S53: performing dynamic temperature rise diffusion evolution based on multiple abnormal temperature rise evolution paths, thereby generating a diffusion prediction trend of the abnormal starting unit;

[0060] Step S54: making a battery abnormal fault diagnosis decision based on the diffusion prediction trend of the abnormal starting unit to obtain a battery abnormal fault diagnosis result.

[0061] The present invention can accurately identify the starting unit of temperature abnormality through temperature abnormality early warning signal, ensuring that the problem can be discovered and handled in time from the source. This step helps to avoid the spread of temperature rise due to failure to identify abnormality in time, affecting the entire battery pack. Marking the starting unit of abnormal temperature rise provides a clear target for subsequent thermal management and fault diagnosis, which can quickly track the problem area, reduce unnecessary intervention, and optimize processing efficiency. By analyzing the evolution path of the starting unit of temperature rise, we can gain an in-depth understanding of how temperature abnormality propagates inside the battery pack, which units are affected, and which areas become hot spots of temperature rise. This helps to predict the thermal response of the entire system. Diffusion prediction based on multiple abnormal temperature rise evolution paths can predict the further expansion trend of abnormal temperature rise, helping The management system accurately grasps the dynamic changes in temperature evolution, which provides a scientific basis for subsequent temperature control decisions. Through the diffusion prediction trend, it can determine in advance which areas will have temperature anomalies in the future, and adjust the cooling system or battery load in time to avoid further deterioration of the problem and enhance the safety and reliability of the system. By combining the diffusion prediction trend with the battery fault diagnosis model, automated fault identification and processing decisions are achieved. The system can automatically determine whether abnormal temperature rise will cause a fault and generate an alarm in advance to avoid human delays. According to the fault diagnosis results, it can accurately determine whether the battery is facing the risk of failure, helping operation and maintenance personnel to take timely preventive measures, such as shutting down some modules, adjusting the cooling system, reducing the battery load, etc., to avoid more serious faults.

[0062] Preferably, the specific steps of step S6 are:

[0063] Step S61: Obtaining the historical working log of the energy storage battery;

[0064] Step S62: performing multiple operation scenario identification on the energy storage battery historical work log to obtain multiple battery operation scenarios;

[0065] Step S63: performing in-depth mining of the load status of each of the multiple battery operation scenarios, thereby generating a load status feature for each operation scenario;

[0066] Step S64: Dynamically transfer learning is performed on the load state characteristics of each operating scenario to generate a deep representation of the battery load state;

[0067] Step S65: Optimize dynamic temperature control parameters based on the battery load state depth characterization and battery abnormal fault diagnosis results to build a dynamic battery temperature control engine to execute battery temperature control warning and temperature control parameter decision-making.

[0068] The present invention identifies different battery operating scenarios and understands the performance of the battery under different environmental and load conditions. This helps to build a comprehensive model covering various operating conditions experienced by the battery (such as high load, low temperature, high temperature, etc.). This scenario recognition helps to evaluate the performance of the battery under diverse operating conditions and ensure that the battery can maintain an efficient and safe working state under various actual operating conditions. By deeply mining the load status of each scenario, the load characteristics and temperature control requirements of each scenario can be accurately identified. Under different operating loads, the temperature distribution and heat dissipation requirements of the battery will be different. This step helps to accurately locate the thermal management requirements under different working conditions. Dynamic transfer learning allows the model to extract experience from past scenarios and migrate it to new operating scenarios, which helps the battery in facing Under different loads and working conditions, it can make adaptive adjustments, thereby improving the intelligence level of the system. Based on the in-depth characterization of the load status and fault diagnosis results, the system can dynamically adjust the temperature control parameters and optimize the battery's heat dissipation, cooling and load management strategies, thereby minimizing the occurrence of temperature anomalies and ensuring the temperature stability of the battery under different load conditions. The dynamic temperature control engine can monitor the battery temperature in real time and adjust the temperature control strategy in time according to load changes, providing automated temperature control warnings and decisions, which helps to improve the safety of the energy storage system and reduce battery failures caused by temperature control problems. The dynamic optimization of temperature control parameters ensures that the battery can always maintain the best working state. According to changes in load status, the battery's temperature control system responds at any time, extending the battery life and improving the efficiency of the system.

[0069] In this specification, a temperature control and early warning system for an energy storage battery is provided, which is used to execute the temperature control and early warning method for an energy storage battery as described above, including:

[0070] The topology module is used to obtain the internal structure diagram of the energy storage battery; perform internal space layout analysis and physical connection analysis between units on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model;

[0071] The visualization rendering module is used to obtain the real-time temperature monitoring parameters of the energy storage battery; based on the real-time temperature monitoring parameters of the energy storage battery, the dynamic temperature distribution visualization rendering of the three-dimensional battery topology model is performed to construct the thermal state portrait of multiple unit areas;

[0072] The multi-period simulation module is used to simulate the battery operation in multiple periods based on the thermal state profiles of multiple unit areas and to predict the temperature change trend over a sliding window to obtain the predicted temperature change trend for each area.

[0073] The abnormal warning module is used to continuously detect abnormal temperature rise trends in the temperature change forecast situation of each area, thereby generating abnormal temperature rise trend characteristics; and generate temperature abnormality warning signals based on the abnormal temperature rise trend characteristics;

[0074] The diagnosis and decision module is used to dynamically analyze the temperature rise diffusion evolution based on the temperature abnormality warning signal, and then make a battery abnormality fault diagnosis decision to obtain the battery abnormality fault diagnosis result;

[0075] The dynamic temperature control optimization module is used to obtain the historical work logs of the energy storage battery; it deeply mines the load status of each scenario in the historical work logs of the energy storage battery, and optimizes the dynamic temperature control parameters based on the abnormal battery fault diagnosis results to build a dynamic battery temperature control engine.

[0076] By acquiring the internal structure diagram of the energy storage battery and performing a detailed analysis, the present invention can accurately construct a three-dimensional topological model of the battery. This allows for an accurate understanding of the layout and physical connection relationships of each battery cell, facilitating subsequent thermal state analysis and fault location. It clarifies the physical connection relationships between battery cells and provides a clear structural view for the battery's thermal management system, ensuring that the specific layout of the battery module is taken into account during design and optimization, improving battery heat dissipation efficiency and performance. The present invention monitors and renders the battery's temperature distribution in real time, generating a thermal state profile that makes the battery's temperature status clear at a glance. Through dynamic rendering, the battery's thermal changes can be observed in real time, allowing temperature anomalies to be quickly discovered. The thermal state profile accurately identifies the areas and trends of temperature anomalies, providing an intuitive basis for subsequent temperature control optimization and fault detection, ensuring that temperature changes are responded to promptly. Through multi-period simulation, battery temperature changes in different operating time periods can be simulated to predict battery temperature fluctuations in future time periods. Combined with the temperature change trend prediction of the sliding window, potential temperature control problems can be identified in advance. The temperature prediction information provided by this module helps to adjust the battery's operating strategy (such as load distribution, cooling adjustment, etc.) in real time, ensuring that the battery always remains within a safe temperature range and reducing the risk of failure. Real-time monitoring can detect abnormal temperature rise trends in a timely manner to ensure that early warnings can be issued before problems occur. This early warning mechanism can effectively avoid battery damage or safety accidents caused by excessively high temperatures. The identification of abnormal temperature rise trend characteristics enables the early warning system to not only rely on simple temperature thresholds, but also to identify potential fault sources from more complex temperature change patterns, thereby improving the accuracy of early warnings. Based on the early warning signal, through diffusion evolution analysis, it can track the process of temperature anomalies spreading from the source to other areas, accurately determine the root cause of the temperature rise anomaly, and perform fault diagnosis. Through accurate diagnostic decisions, it can quickly identify whether the battery is Faults can be detected and countermeasures can be formulated (such as shutting down certain modules, adjusting the load, increasing cooling, etc.) to prevent further expansion of the fault. Through in-depth mining of historical work logs, the load status characteristics in different scenarios can be identified to provide the necessary adjustment basis for the temperature control system. This helps to dynamically optimize the temperature control parameters and achieve the best operation of the temperature control system under various working conditions. The constructed dynamic battery temperature control engine can automatically adjust the battery temperature control strategy (such as cooling intensity, load distribution, etc.) according to the load, working conditions and fault diagnosis results in real time, thereby effectively avoiding over-high or under-temperature conditions, extending battery life and improving system efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 This is a schematic flow chart of the steps of a temperature control and early warning method for an energy storage battery according to the present invention;

[0078] Figure 2 Detailed implementation flow chart of step S1;

[0079] Figure 3 Detailed implementation flow chart of step S2;

[0080] Figure 4 Schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION

[0081] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0082] This application provides a method and system for temperature control and early warning of energy storage batteries. The execution entities of the method and system include, but are not limited to, mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc., which can be considered as general computing nodes of this application. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0083] See also Figures 1 to 4 The present invention provides a temperature control and early warning method for an energy storage battery, the temperature control and early warning method for an energy storage battery comprising the following steps:

[0084] Step S1: Obtaining an internal structure diagram of the energy storage battery; performing internal space layout analysis and inter-unit physical connection analysis on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model;

[0085] Step S2: obtaining real-time temperature monitoring parameters of the energy storage battery; performing dynamic temperature distribution visualization rendering on the three-dimensional battery topology model according to the real-time temperature monitoring parameters of the energy storage battery, thereby constructing thermal state portraits of multiple unit areas;

[0086] Step S3: performing multi-period battery operation simulation on the thermal state portraits of the multiple unit areas, and performing sliding window temperature change trend prediction to obtain the temperature change prediction trend of each area;

[0087] Step S4: Continuously detecting abnormal temperature rise trends in the temperature change forecast situation of each region, thereby generating abnormal temperature rise trend features; and generating temperature anomaly warning signals based on the abnormal temperature rise trend features;

[0088] Step S5: performing dynamic temperature rise diffusion evolution based on the temperature abnormality warning signal, and then making a battery abnormality fault diagnosis decision to obtain a battery abnormality fault diagnosis result;

[0089] Step S6: Obtain the historical work log of the energy storage battery; conduct in-depth mining of the load status of each scene in the historical work log of the energy storage battery, and optimize the dynamic temperature control parameters according to the battery abnormal fault diagnosis results to build a dynamic battery temperature control engine.

[0090] The present invention accurately constructs a three-dimensional topological structure model of the battery by analyzing the internal structure of the energy storage battery and the connection relationship between the cells. This provides a basis for subsequent temperature distribution and thermal status monitoring, ensuring that the temperature monitoring system accurately maps various areas inside the battery. By obtaining real-time temperature data and combining it with the three-dimensional battery topological structure model for visual rendering, the temperature distribution of each unit area of the battery is fully displayed, so that temperature anomalies can be discovered in time to avoid overheating or uneven cooling of the battery. Through multi-period battery operation simulation, the temperature change trend of the battery under different working conditions is predicted. Combined with the temperature change trend prediction of the sliding window, the early signs of temperature anomalies are effectively captured, which helps to take preventive measures in advance to prevent battery overheating or performance degradation. Through continuous monitoring of the temperature change trend, the abnormal temperature rise trend of the battery cell is detected in time to avoid battery overheating or uneven cooling. High temperature can cause safety hazards. Based on the early warning signal generated by the abnormal temperature rise trend, the operator is reminded in real time to take necessary measures, such as adjusting the battery load, starting the cooling system, etc., to ensure that the battery is in a safe operating temperature range. Through the dynamic evolution analysis of the battery temperature rise diffusion, the temperature anomaly source can be more accurately located to diagnose battery faults, which helps to identify battery faults such as short circuit, overheating, unit damage, etc., and reduce the probability of faults. Through in-depth mining of the historical work logs of energy storage batteries, the performance of batteries in different working environments and load conditions can be understood, which helps to identify historical factors that lead to temperature anomalies. According to the abnormal fault diagnosis results of the battery and the analysis of the historical work logs, the battery temperature control strategy is adjusted, the temperature control parameters are optimized, and the operating temperature of the battery is dynamically adjusted to ensure that the battery works in the safest and most efficient state, further extending the battery life.

[0091] In the embodiment of the present invention, see Figure 1 , is a schematic flow chart of the steps of a temperature control and early warning method for an energy storage battery according to the present invention. In this example, the steps of the temperature control and early warning method for an energy storage battery include:

[0092] Step S1: Obtaining an internal structure diagram of the energy storage battery; performing internal space layout analysis and inter-unit physical connection analysis on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model;

[0093] In this embodiment, the source of the internal structure diagram is determined. The sources include design drawings, technical manuals, CAD files or existing engineering models provided by the manufacturer. Identify the specific model and specifications of the battery to ensure that the obtained drawings are consistent with the actual battery. If the required internal structure diagram exists in a digital format (such as PDF, CAD file), use professional software (such as AutoCAD, SolidWorks) to open and extract the relevant content. If necessary, contact the manufacturer to obtain a high-definition internal structure diagram to ensure that the details of the drawing are clearly visible. Identify the layout of the battery cells in the internal structure diagram, including the relative positions of the battery cells, conductive connections, cooling pipes and other auxiliary components. Record the size and position relationship of each component for use in three-dimensional modeling. Use computer-aided design (CAD) software to measure and analyze the extracted structure diagram to ensure that the spatial layout of each component meets the design standards. Use the measurement tools in the application software to record the spacing between battery cells, connection methods and layout of the cooling system. Organize the internal space layout analysis results to form a layout analysis report containing key dimensions, spacing and layout features to provide a reference for subsequent modeling. Identify the physical connections between each battery cell in the internal structural diagram, including the electrical connections, mechanical fastenings, and thermal conduction paths. Record the material properties (e.g., electrical conductivity, thermal conductivity) and design details of each connection. Use finite element analysis (FEA) software (e.g., ANSYS, COMSOL) to simulate the connections between battery cells and analyze the strength and thermal conductivity of the connections. Set simulation parameters, such as material properties, load conditions, and boundary conditions, to assess the reliability of the connections. Record the performance analysis results for each connection, including important parameters such as electrical impedance, thermal impedance, and structural strength. Organize the physical connection analysis results into a report providing detailed information on the connection characteristics. Select an appropriate 3D modeling tool (e.g., SolidWorks, CATIA, Autodesk Inventor) to construct a 3D topological structural model. Build the 3D model step by step based on the internal space layout and physical connection analysis results. First, create the battery cell geometry, then add connectors and the cooling system. Ensure that each component of the model conforms to the actual size and connection method to lay the foundation for subsequent thermal and electrical analyses. After the model is built, the software's validation tools are used to check its completeness and accuracy, ensuring no missing or incorrect connections. Preliminary functional testing is performed to ensure the model is suitable for subsequent analysis and optimization. The 3D battery topology model construction process is organized, including the internal spatial layout, physical connection analysis, and model construction steps. The final 3D model file is generated and stored alongside the analysis results for easy subsequent use and modification.

[0094] Step S2: obtaining real-time temperature monitoring parameters of the energy storage battery; performing dynamic temperature distribution visualization rendering on the three-dimensional battery topology model according to the real-time temperature monitoring parameters of the energy storage battery, thereby constructing thermal state portraits of multiple unit areas;

[0095] In this embodiment, the real-time temperature monitoring device and its data source are determined, which usually include a sensor network (such as thermocouples, infrared sensors) and a data acquisition system (such as a data logger, PLC system). The type of monitoring parameters is determined, including the temperature of each battery cell, the ambient temperature, the charge and discharge status, etc. The temperature sensor is connected using data acquisition software (such as LabVIEW, MATLAB), and the temperature data is collected in real time. The data collection frequency is ensured to meet the needs of dynamic analysis, for example, once per second. The data storage format of the acquisition system is set (such as CSV, JSON), and the accuracy and completeness of the data are ensured. The collected real-time temperature data is analyzed. Clean the data, remove outliers and noise, ensure the quality of the data set, use statistical methods (such as median filtering, Z-score outlier detection) for processing, standardize the processed data, ensure the comparability of different sensor data, and ensure the accuracy of the three-dimensional battery topology model. The model should include all battery cells and their physical connections. Use CAD software (such as SolidWorks, CATIA) to open the model for confirmation, check the scale and unit of the model, and ensure that it matches the real-time temperature data. Map the acquired real-time temperature monitoring parameters to the three-dimensional model according to the number and position of the battery cell. Use Python's NumPy and P The ANDAS library processes data and generates a temperature distribution matrix for each unit. It uses interpolation methods (such as linear interpolation and cubic interpolation) to smooth the temperature data on the surface of the 3D model to obtain a finer temperature distribution. It uses visualization tools (such as Paraview, MATLAB's surf function, and Blender) to dynamically render the 3D model, set the temperature color mapping (such as heat map) to ensure that different temperature ranges are represented by different colors, set visualization parameters such as viewing angle, lighting, and shadow effects to enhance the visualization effect, make the temperature distribution clear at a glance, and set a dynamic update mechanism so that the visualization results can reflect the temperature data in real time. Changes, by writing scripts to regularly read temperature data and update the model, ensure that the visualization interface is user-friendly and can easily switch between different perspectives and display modes, record the dynamic rendering results as video or animation files for subsequent analysis and display, use tools such as FFmpeg for video encoding to ensure video quality and smoothness, generate static images (such as PNG, JPEG format), which are used to display thermal status portraits in reports and documents, analyze the generated thermal status portraits, identify temperature abnormalities and hotspots, evaluate the thermal management performance of the battery, record the temperature change trend of each unit, and analyze the temperature distribution characteristics under different working conditions to provide a basis for subsequent optimization.

[0096] Step S3: performing multi-period battery operation simulation on the thermal state portraits of the multiple unit areas, and performing sliding window temperature change trend prediction to obtain the temperature change prediction trend of each area;

[0097] In this embodiment, based on the constructed three-dimensional battery topology model and real-time thermal state portrait, suitable thermal simulation software (such as ANSYS Fluent, COMSOL Multiphysics) is selected to perform multi-period thermal simulation. Determine the simulation parameters, including the battery's thermophysical properties (such as thermal conductivity, specific heat capacity), environmental conditions (such as external temperature, wind speed) and operating conditions (such as charge and discharge rate, load change). According to the battery's working cycle, set the simulation period (such as 1 hour, 2 hours), and subdivide each period (such as performing a simulation calculation every 10 minutes). Record the battery state changes in each period, such as power output and ambient temperature changes during charging and discharging. Start the simulation software, enter the set initial conditions and boundary conditions, and run the multi-period thermal simulation. Ensure that the software can handle complex heat conduction and convection problems and accurately simulate the temperature distribution inside the battery. Monitor the calculation progress during the simulation process to ensure that the temperature changes in each unit area can be updated and recorded in a timely manner. Select a suitable time series prediction model (such as ARIMA, LSTM, SVR) to perform sliding window temperature change trend prediction. Determine the input characteristics and output targets of the model based on data characteristics and prediction requirements. Determine sliding window settings, such as the window size (e.g., 10 minutes, 30 minutes) and the sliding step size (e.g., 1 minute, 5 minutes), to achieve high-frequency temperature forecasts. Preprocess the recorded temperature change data, including normalization, detrending, and seasonal decomposition, to improve the accuracy of the forecast model. Generate training and test sets to ensure data representativeness and diversity for model training and evaluation. Use the training set to train the forecast model, adjusting model hyperparameters (e.g., learning rate, regularization term) to optimize performance. Use cross-validation to evaluate the model's performance on the test set to ensure the model's generalization across different datasets. Apply the sliding window forecast model to real-time temperature data to generate temperature change forecasts for future periods. Update the model inputs each time new data arrives, and calculate future temperature changes in real time. Record the temperature change forecast results for each region and compare them with actual monitoring data to analyze the accuracy and reliability of the forecasts. Use visualization tools (e.g., Matplotlib, Tableau) to generate visualization charts of the temperature change forecast, displaying temperature change trends and warning thresholds for each region. Organize temperature change prediction results and analysis reports, record the temperature prediction situation and risk points of each area, and provide a basis for subsequent fault warning and thermal management.

[0098] Step S4: Continuously detecting abnormal temperature rise trends in the temperature change forecast situation of each region, thereby generating abnormal temperature rise trend features; and generating temperature anomaly warning signals based on the abnormal temperature rise trend features;

[0099] In this embodiment, the judgment criteria for temperature anomaly are set. Generally, the temperature is defined as exceeding the normal operating range (such as being higher than a certain threshold, such as 45°C) or the temperature change rate exceeds a preset value (such as more than 2°C per minute) as abnormal temperature rise. A time window (such as 5 minutes, 10 minutes) is determined, and temperature changes are monitored within the window to capture abnormal trends in a short period of time. The temperature change prediction status data of each area is collected, including real-time temperature values, predicted values and their change trends, to ensure that the data can reflect the real-time dynamics of temperature. The temperature data from different areas are integrated to form a comprehensive data set for subsequent analysis, and suitable anomaly detection algorithms are selected, such as control charts, Z-score method or machine learning models (such as Isolation Forest, One-Class SVM) is used to detect the temperature rise trend. The control chart method is used to draw a control chart of temperature changes to monitor whether the temperature exceeds the control range in real time. A script (such as Python) is written to implement the anomaly detection algorithm. The temperature data of each area is monitored in real time and a threshold is set. If the data exceeds the threshold, it is marked as abnormal. At the end of each time window, the statistical features such as the temperature average and standard deviation in the window are calculated to facilitate subsequent abnormal trend analysis. The abnormal temperature rise events detected in each area are recorded, including the occurrence time, duration, and excess amplitude. An abnormal log is generated for subsequent analysis and tracking. According to the abnormal temperature rise events monitored, relevant features are extracted, such as abnormal duration, temperature change rate, abnormal amplitude, etc. Feature vectors are designed, including the combination of these features. Statistical analysis methods are used to analyze the relationship between the abnormal temperature rise trend characteristics and the battery operating status, and their impact on battery safety is evaluated. If there is enough historical data, machine learning methods (such as decision trees and random forests) are used to analyze the abnormal trend features. The model is trained to identify potential abnormal patterns, with training and test sets set. The accuracy of the model is evaluated through cross-validation. Based on the abnormal temperature rise trend characteristics, the trigger threshold of the temperature anomaly warning signal is set. For example, a warning signal is issued when the temperature in a certain area exceeds the set threshold for 5 consecutive minutes. A multi-level warning mechanism is set, such as green (normal), yellow (caution), red (critical), etc., to reflect different risk levels. An early warning system is developed to monitor the temperature changes in each area in real time and generate corresponding early warning signals based on the set thresholds. Alarm systems, SMS notifications, or visual dashboards are used to ensure that the early warning system can respond in a timely manner and record detailed information for each warning event, including time, area, temperature changes, etc. The performance of the early warning system is regularly checked, the accuracy and timeliness of the warning signals are analyzed, feedback data is collected, the early warning mechanism is optimized, the probability of false alarms and missed alarms is reduced, a summary report is formed, recording the entire process of abnormal temperature rise trend detection, feature generation, and early warning signal generation, and improvement suggestions are put forward.

[0100] Step S5: performing dynamic temperature rise diffusion evolution based on the temperature abnormality warning signal, and then making a battery abnormality fault diagnosis decision to obtain a battery abnormality fault diagnosis result;

[0101] In this embodiment, a suitable thermal diffusion model is selected, such as a one-dimensional heat conduction equation or a more complex two-dimensional or three-dimensional thermal diffusion model, to simulate the diffusion process of the temperature anomaly. The model parameters, including thermal conductivity, specific heat capacity, ambient temperature, initial temperature distribution, etc., are determined. These parameters are set according to the physical properties of the battery material and experimental data. Boundary conditions (such as adiabatic and constant temperature) are set according to the actual operating conditions of the battery, and initial conditions are set to ensure that the model can accurately reflect the operating state of the battery. In the model, the initial temperature of a battery cell is set to the identified abnormal temperature, and the temperature of other cells is set to the normal operating temperature. Numerical simulation software (such as COMSOL Multiphysics and ANSYS) is used to simulate the dynamic temperature rise and diffusion evolution. A suitable solver is selected, ensuring that it can handle multi-dimensional heat conduction problems. The simulation is started, and the temperature change over time is gradually calculated to observe how the temperature anomaly diffuses between the battery cells. The temperature distribution at each time step is recorded to ensure that the dynamic process of temperature change can be captured. The simulation time step is set (such as per second or per minute). In order to more accurately capture the temperature evolution process, record the simulation results, including the temperature changes of each unit at different time points, generate a temperature distribution map, intuitively display the temperature rise diffusion trend, and output the results in a visual format (such as animation, heat map) for easy analysis and display. Select an appropriate fault diagnosis algorithm, such as a model-based method (such as Kalman filter, state observer) or a data-based method (such as machine learning classifier, such as support vector machine, decision tree). According to the specific operating status and historical data of the battery, design a suitable fault diagnosis model, extract fault features from the temperature rise diffusion simulation results, such as temperature change rate, abnormal area, duration and temperature peak, etc. These features will be used as input data for fault diagnosis, and standardize the extracted features to ensure that the contribution of different features in the model is balanced. If a machine learning model is used, it is necessary to use historical fault data to train the model and evaluate the performance of the model through cross-validation to ensure that the model has good generalization ability. Record the model's accuracy, recall rate, F1 score and other evaluation indicators to evaluate the effectiveness of the model in fault diagnosis.

[0102] Step S6: Obtain the historical work log of the energy storage battery; conduct in-depth mining of the load status of each scene in the historical work log of the energy storage battery, and optimize the dynamic temperature control parameters according to the battery abnormal fault diagnosis results to build a dynamic battery temperature control engine.

[0103] In this embodiment, the storage location of the historical work log of the energy storage battery is determined, including a database (such as SQL Server, MySQL), a file system (such as CSV, JSON format) or cloud storage, and key data fields in the log are identified, such as charge and discharge status, temperature data, current, voltage, operating time and fault records. The historical work log is exported using a data extraction tool (such as Python script, SQL query), ensuring that the extracted data contains a complete time range, usually covering at least the complete working cycle of the battery. A standard data extraction format is established to ensure that the field names and data types are consistent for subsequent analysis. The extracted data is cleaned to remove duplicate records and missing values to ensure the accuracy and completeness of the data. Integrity, use the Pandas library for data processing, standardize key indicators such as temperature, voltage and current for subsequent analysis and comparison, identify different battery operation scenarios based on the data in the historical work log, such as normal charge and discharge, overload, low-temperature operation, etc., clarify the characteristic indicators of each scenario, such as current, temperature and charge and discharge rate, set feature extraction methods for each scenario, such as using statistical methods such as mean, variance, maximum and minimum to describe the load state, use data mining tools (such as Python's Scikit-learn library) to analyze historical data, extract the load state characteristics of each scenario, and use cluster analysis methods (such as K-Means) to group similar scenarios. For each scenario, a load status characteristic report is generated, including temperature change trends, charge and discharge efficiency, and risk points. The load status characteristics of each scenario are sorted out to form a detailed analysis report, recording the scenario characteristics and the corresponding load status to facilitate subsequent dynamic temperature control parameter optimization. The previous battery abnormal fault diagnosis results are combined with the scenario load status to identify the temperature control requirements in different operating scenarios. Under high load conditions, more stringent temperature control strategies are required. The relationship between battery temperature changes and fault occurrence in each scenario is recorded to help optimize temperature control parameters. According to historical data and fault diagnosis results, optimization goals are set, such as maximizing charge and discharge efficiency, minimizing temperature fluctuations, or reducing the occurrence rate of faults, to determine dynamic temperature control parameters. The scope of dynamic temperature control is as follows: for example, setting temperature control thresholds, cooling rates, and heating rates; selecting appropriate optimization algorithms (such as genetic algorithms and particle swarm optimization) for dynamic temperature control parameter optimization; setting the input (such as current temperature and load status) and output (such as temperature control strategy) of the optimization model; running the optimization algorithm to generate the best dynamic temperature control strategy to ensure that the battery maintains the optimal operating temperature under different load conditions; based on the optimization results, designing the structure and function of the dynamic battery temperature control engine, including real-time temperature monitoring, control algorithms, and feedback mechanisms, to ensure that the engine can respond to the battery's operating status and environmental changes in real time, and maintain battery safety and efficiency by adjusting cooling and heating strategies; developing temperature control engine software, integrating temperature monitoring systems, control algorithms, and user interfaces;Ensure that the software can process real-time data and respond quickly. Test the performance of the dynamic temperature control engine in an experimental environment and record its response time, temperature control accuracy, and performance under different load conditions.

[0104] In this embodiment, refer to Figure 2 , is a flowchart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0105] Step S11: performing CT scanning on the target energy storage battery to obtain an internal structure diagram of the energy storage battery;

[0106] Step S12: Perform deep visual recognition on the internal structure diagram of the energy storage battery and mark each battery cell;

[0107] Step S13: performing precise positioning calculation of the internal space of each battery cell to extract the internal space coordinates of each battery cell;

[0108] Step S14: performing internal space layout analysis based on the internal space coordinates of each battery cell to generate battery space layout features;

[0109] Step S15: performing inter-cell physical connection analysis on each battery cell to obtain a topological connection relationship of the battery cells;

[0110] Step S16: reconstructing the battery space layout characteristics in three dimensions based on the topological connection relationship of the battery cells to construct a three-dimensional battery topological structure model.

[0111] In this embodiment, a high-resolution X-ray computed tomography (CT) device is selected to ensure that the internal structure with high details can be captured. The device should have a slice thickness of at least 1 mm and a spatial resolution of up to 0.5 mm. The outside of the energy storage battery is cleaned to ensure that there is no dust or other substances that affect the imaging quality. The battery is fixed on the sample stage of the CT scanner to avoid movement during the scanning process. An appropriate scanning protocol is set, including voltage (such as 120 kV), current (such as 200 μA) and scanning time (such as 10 minutes) to ensure image clarity and detailed visualization. The scanning program is executed and multiple slice images are recorded. According to the scanning results, it is usually necessary to obtain 360-degree slices to ensure full coverage of the energy storage battery. The internal structure of the cell is processed by filtering back projection (FBP) and iterative reconstruction algorithms to process the raw data obtained from the scan to generate a complete three-dimensional image. Software (such as CT scan-specific analysis software) is used to process the data to generate a high-quality internal structure map. Image processing software (such as OpenCV) is used to remove noise and enhance the internal structure map to improve recognition accuracy. Gaussian blur and edge detection algorithms are applied, and threshold segmentation (such as Otsu algorithm) is used to separate the battery cell from the background to ensure the accuracy of the subsequent recognition process. Convolutional neural network (CNN) is used for image recognition. A pre-trained model (such as ResNet or U-Net) is selected for fine-tuning to adapt to the characteristics of the battery cell. Through the model, the image is automatically Automatically mark each battery cell and output the marking result map to ensure that each cell has a unique ID for subsequent analysis and use. Determine the origin and axis of the three-dimensional coordinate system. Usually, the geometric center of the battery is selected as the origin. The X, Y, and Z axes point to the length, width, and height of the battery respectively. By traversing the pixel points of each battery cell, its geometric center coordinates are calculated. For each battery cell, the formula is used to calculate its center of mass position to obtain the three-dimensional coordinates. The internal space coordinates of each battery cell are recorded in the database to ensure the accuracy of the data and the convenience of subsequent analysis. Determine the layout features that need to be analyzed, such as the distance between battery cells, the arrangement method (such as straight line, matrix), space utilization, etc. Use the Euclidean distance formula to calculate the distance between each battery cell. The distance between battery cells is used to evaluate the effectiveness of the layout, the ratio of the total occupied volume to the available volume of the battery's internal space is calculated, the rationality of the spatial layout is evaluated, and the connection relationship between battery cells is defined, including electrical connection and mechanical connection. Electrical connection is usually achieved through wires or welds, while mechanical connection involves the physical position and support of the cell. A topological model of the battery cell is constructed using graph theory methods, each cell is regarded as a node in the graph, and the connection is regarded as an edge. By analyzing the actual layout of the battery cells, the connection relationship is extracted, a topological connection matrix is generated, and the connection status of each cell is recorded. A suitable 3D reconstruction algorithm is selected, such as voxel reconstruction or patch-based modeling technology, to ensure that the spatial layout and connection relationship of the battery cells can be accurately reflected.The extracted layout features and topological connection relationships are used as input to generate a 3D model of the battery using 3D modeling software (such as Blender or MeshLab). The generated 3D model is visualized to ensure that it is consistent with the actual physical structure. The accuracy of the 3D model is verified by comparing it with the CT scan image.

[0112] In this embodiment, refer to Figure 3 , is a flowchart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0113] Step S21: Acquire real-time temperature monitoring parameters of the energy storage battery based on multiple sensors;

[0114] Step S22: Calculating the internal position of each sensor node one by one based on the multi-sensor to obtain the internal space coordinates of the battery of each sensor node;

[0115] Step S23: performing spatial temperature distribution mining on the real-time temperature monitoring parameters of the energy storage battery according to the internal spatial coordinates of the battery of each sensor node to obtain the temperature distribution characteristics of each battery cell;

[0116] Step S24: dividing the three-dimensional battery topology model into multiple battery unit regions, thereby generating multiple unit region models;

[0117] Step S25: Based on the temperature distribution characteristics of each battery cell, dynamic temperature distribution visualization rendering is performed on the multiple unit area models, thereby constructing thermal state portraits of the multiple unit areas.

[0118] In this embodiment, suitable temperature sensors, such as thermocouples, RTDs (resistance temperature detectors), or digital temperature sensors (such as DS18B20), are selected and evaluated based on their accuracy, response time, and operating range. The number and arrangement of sensors are determined to cover all key areas of the energy storage battery, ensuring that each area is monitored by at least one sensor. Sensors are properly arranged inside and outside the battery module to ensure that temperature changes in the battery are monitored. Sensors are placed at the top, bottom, and middle of the battery. The position and number of each sensor are recorded for subsequent data analysis and processing. A data acquisition system is developed, using a microcontroller (such as Arduino or Raspberry Pi) to connect each sensor, periodically read temperature data, and set a data acquisition frequency, such as collecting temperature data once every second, to ensure real-time monitoring of temperature changes. The collected temperature data is sent to a central server or cloud platform via wireless transmission (such as Wi-Fi or Bluetooth) for storage and processing, ensuring the stability and security of data transmission. An encryption protocol is used to protect the integrity of the data. A position calibration scheme is designed to determine how to calculate the coordinates of the sensor inside the battery, using a three-dimensional coordinate system (X, Y,Z) to represent the position of each sensor, set the reference point of each sensor, such as the center point of the battery module, in order to perform relative position calculations, collect the actual installation position data of each sensor, including the distance and direction between the sensor and the reference point, and record them as relative coordinates. Use three-dimensional measurement tools (such as laser rangefinders) to ensure the accuracy of the position data, use geometric calculation methods to determine the spatial coordinates of each sensor, use basic three-dimensional coordinate formulas, combine the relative position data of the sensor, calculate its absolute coordinates, organize the calculation results into a data table, record the unique identifier of each sensor and its corresponding spatial coordinates, integrate the real-time temperature monitoring parameters with the spatial coordinates of the sensor, and form a table containing sensor ID, temperature value and spatial coordinates, clean the data, remove invalid or abnormal temperature readings, ensure data accuracy, format the integrated data into a form suitable for analysis, such as using a data frame (DataFrame) structure to facilitate subsequent processing, select a suitable temperature distribution analysis algorithm, such as interpolation, heat map generation, or Kriging interpolation (Kriging), to visualize the temperature distribution, set the spatial range of the analysis to ensure coverage of the entire battery module, use the selected algorithm to analyze the data, generate a temperature distribution model inside the battery, use Python's SciPy or Matplotlib library for data visualization, and record the temperature distribution characteristics of each battery cell, including the mean and maximum temperature. , minimum value and standard deviation, use computer-aided design (CAD) software (such as SolidWorks or AutoCAD) to build a three-dimensional battery topology model to ensure that the model accurately reflects the actual shape of the battery, determine the boundaries and connection methods of the battery cells in the model, record the characteristics of each battery cell, set regional division standards according to the function, thermal state or physical location of the battery cell, divide the battery cell according to its thermal performance or cooling efficiency, determine the number and shape of the divisions, ensure that each area can be analyzed independently and is representative, use regional division algorithms (such as Voronoi diagram or K-means clustering) to divide the three-dimensional model, generate multiple battery cell area models, and record the boundaries of each area To facilitate subsequent analysis and processing, select a suitable visualization rendering tool (such as Blender, Unity, or VTK) and build a visualization environment. Ensure that the rendering tool supports dynamic data visualization and has good graphics rendering performance. Set rendering parameters based on the temperature distribution characteristics of each battery cell, including color mapping, temperature range, and dynamic change rate. Design visual effects, such as displaying high-temperature areas in red and low-temperature areas in blue, to facilitate identification of temperature anomalies. Input temperature data into the visualization tool for dynamic rendering. Use real-time data streams to update rendering parameters and display temperature changes over time. Record rendering results, including thermal state portraits at different time points, for subsequent analysis and reporting.

[0119] In this embodiment, the specific steps of step S25 are:

[0120] Perform real-time temperature distribution change analysis on the temperature distribution characteristics of each battery cell to generate real-time temperature distribution change data;

[0121] Perform discrete fitting of time series temperature values on real-time temperature distribution change data to construct the temperature distribution change curve of each battery cell;

[0122] Perform temperature positioning matching on the temperature distribution change curve of each battery cell and multiple unit area models to obtain the matching temperature curve relationship of each unit area;

[0123] Visualize the temperature distribution of multiple unit area models based on the matching temperature curve relationship of each unit area, thereby obtaining the temperature distribution thermal map of multiple unit areas;

[0124] Dynamic temperature change rendering is performed on the temperature distribution thermodynamic map of multiple unit areas to construct thermal state portraits of multiple unit areas.

[0125] In this embodiment, a multi-sensor architecture is used to ensure that the temperature of each battery cell can be recorded regularly. The sensors should be installed in key locations of the battery and ensure that they work properly. The frequency of data collection is set, for example, once per second, to ensure that subtle changes in temperature can be captured. A microcontroller (such as Arduino or Raspberry Pi) is used. Pi) for data collection, transmit data to the server in real time via wireless network, use MQTT protocol to effectively process real-time data streams, store the collected temperature data in a time series database (such as InfluxDB) for subsequent analysis and query, use Python's Pandas library to analyze temperature data in real time, calculate the mean, maximum and minimum temperature of each battery cell, and monitor temperature change trends, set monitoring indicators, such as when the temperature change rate exceeds a certain threshold (such as more than 5°C per minute), record it as an abnormality, use Matplotlib or Plotly to generate a real-time temperature distribution graph to show the temperature change of each battery cell, help real-time monitoring and decision-making, and form a visual report of real-time temperature change data to facilitate analysis and troubleshooting by engineers, clean real-time temperature data, remove outliers and noise, ensure data accuracy, use Z-score or IQR method to detect and remove abnormal data points, sort temperature data by timestamp, create a time series dataset for subsequent analysis, and select an appropriate fitting algorithm, such as polynomial fitting or spline interpolation (spline Interpolation) is used to construct the temperature variation curve of each battery cell. The scipy.interpolate module in Python's SciPy library is used for discretization. The selected fitting algorithm is applied to fit the temperature time series data of each battery cell to generate a temperature variation curve. The fitting parameters, including the coefficients of the fitting function and the goodness of fit (R 2 value) to evaluate the fitting effect.

[0126] Use Matplotlib to generate a temperature change curve for each battery cell, showing the change in temperature over time, which is convenient for subsequent analysis and comparison. A graphical report of the temperature distribution change is formed and provided to relevant personnel for evaluation. The standard for temperature matching is determined, and a similarity measurement method such as mean square error (MSE) or dynamic time warping (DTW) is set to evaluate the similarity between curves. The matching threshold is set. If the MSE is less than a certain value (such as 0.5), the two temperature curves are considered to match. Use Python to implement the curve matching algorithm, match the temperature change curve of the battery cell with the model of each unit area, calculate the similarity, record the matching results, and generate the matching temperature curve relationship for each unit area, including the matching battery cell ID and area ID. Analyze the matching results, identify the best matching unit area, evaluate the accuracy and stability of the matching, and adjust the parameters of the matching algorithm based on the analysis results to improve the matching effect and accuracy. Select a suitable visualization tool (such as Matplotlib, Seaborn or Plotly) to generate the temperature distribution heat map, and ensure that the selected tool supports multidimensional data Visualize and process temperature data from different battery cells. Set the color mapping of the heat map based on the matching temperature curve relationship of each area, ensuring that high-temperature areas are displayed in red and low-temperature areas are displayed in blue. Set the temperature range and resolution to clearly display the temperature distribution of each unit area. Use the selected visualization tool to generate temperature distribution heat maps of multiple unit areas to display the temperature characteristics of each area. Record the generated heat map data for subsequent analysis and monitoring. Select a dynamic rendering tool (such as Unity, Blender, or OpenGL) to ensure support for real-time data streaming and dynamic effects. Set the rendering environment and configure the necessary libraries and dependencies to ensure that the tool can run efficiently. Set the dynamic rendering parameters based on the heat map data, including rendering speed, temperature change range, and visual effects (such as animated transition effects). Design visual effects to make the temperature change process intuitive and easy to understand, such as displaying temperature changes through gradient colors. Input the heat map data into the dynamic rendering tool to generate dynamic images of the thermal status of multiple unit areas to display the temperature change process. Record key data during the rendering process for analysis and reporting.

[0127] In this embodiment, refer to Figure 4 , is a flowchart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0128] Step S31: defining multiple operating conditions of the battery pack;

[0129] Step S32: performing multi-period battery operation simulation on thermal state portraits of multiple unit areas according to multiple operating conditions of the battery pack to collect multi-period operation simulation data;

[0130] Step S33: performing temperature change trend analysis on each region of the multi-period simulation data to obtain temperature change trend characteristics of each region;

[0131] Step S34: performing sliding window temperature change situation prediction based on the temperature change trend characteristics of each area to obtain the temperature change prediction situation of each area.

[0132] In this embodiment, according to the application scenarios of the battery pack (such as electric vehicles, energy storage systems, etc.), multiple key operating environment parameters are identified, including temperature, humidity, load type, charge and discharge rate, etc. Different operating conditions are set, such as high temperature, high load, low temperature, etc., to ensure that various situations encountered by the battery pack in actual applications are covered. The defined operating conditions are classified into normal operating conditions, extreme operating conditions and critical operating conditions, and each operating condition is described in detail, including its impact on battery performance. Specific parameter ranges are formulated for each operating condition. Under high temperature conditions, the temperature range is set to 40°C to 60°C, and the load is set to 1C rate. All defined operating conditions are organized into documents, including the name of each condition, parameter range, expected impact and other information. Ensure that the document is clear and easy to understand for subsequent simulation and analysis personnel. Invite experts in related fields to review the defined operating conditions to ensure that they meet the actual application requirements and correct any deficiencies. Adjustments are made based on feedback, and the definitions of multiple operating conditions are finally confirmed. Use battery simulation software (such as MATLAB / Simulink, COMSOL Multiphysics, or ANSYS) to build a thermal model of the battery pack to ensure that the model reflects the battery's thermal behavior and electrochemical properties. Set model parameters, including the battery's thermal conductivity, specific heat capacity, and exothermic reactions, to ensure accurate simulation results. Based on the defined operating conditions, set the simulation model's input parameters, including the battery pack's initial temperature, charge and discharge strategies, and external environmental conditions (such as heat dissipation). Ensure that each operating condition is reflected in the simulation to facilitate comparison of battery performance under different operating conditions. Run the simulation model for multiple time periods (e.g., 0-1 hour, 1-2 hours, 2-3 hours), recording the temperature changes of each battery cell during each time period. After each time period, save the simulation results, including data such as the temperature distribution and heat flux density for each region. Export the simulation results to a database or file system to ensure data traceability and integrity. Use CSV or JSON format to record data for later analysis. Combine simulation results from different time periods into a single dataset to ensure a complete record of temperature changes in each region. Clean the data to remove invalid or abnormal temperature records to ensure accurate data analysis. Select an appropriate trend analysis method, such as linear regression, moving average, or exponential smoothing, to identify temperature trends. Determine the time window for analysis; for example, use data from the past three time periods for trend analysis to obtain a smooth curve. Use Python's Pandas and NumPy libraries to perform trend analysis on the integrated data, calculating the average temperature change, maximum, and minimum values for each region. Record the temperature trend characteristics of each region, such as whether the temperature is rising, falling, or stable. Use Matplotlib or Seaborn to generate a temperature trend chart to display the temperature changes in each region, facilitating subsequent decision-making and analysis.Organize the results into a report for easy sharing and discussion with the team. Select an appropriate time series forecasting model, such as ARIMA (autoregressive integrated moving average model), LSTM (long short-term memory network), or SARIMA (seasonal ARIMA). Train the model based on historical temperature change data to ensure that the model can capture the trend and periodicity of temperature changes. Determine the parameters of the model, such as the p, d, and q values in the ARIMA model, or the number of network layers and nodes in the LSTM. Use methods such as grid search to optimize parameter selection. Apply the sliding window method to the trained model to predict temperature for each region. Use data from the past five time periods to predict temperature changes for the next time period. Record the predicted values for each region, including the predicted temperature and confidence interval, to assess the reliability of the forecast. Verify the accuracy of the forecast model by comparing the predicted temperature with the actual temperature (if any), and calculate the forecast error (such as MSE or MAE). Use visualization tools to display the forecast results and compare the predicted curve with the actual temperature curve to facilitate analysis and adjustment of the model.

[0133] In this embodiment, the specific steps of step S32 are:

[0134] Based on the real-time temperature monitoring parameters of the energy storage battery, the temperature difference between adjacent cells is mined for each battery cell to obtain the temperature change relationship between adjacent cells;

[0135] Based on the temperature change relationship between adjacent cells, the heat transfer evolution between battery cells is analyzed to obtain the heat transfer law of battery cells;

[0136] Calculate the cooling efficiency of energy storage batteries;

[0137] Performing a quantitative analysis of the heat transfer rules of the battery cells and the cooling efficiency of the energy storage battery under multiple operating conditions of the battery pack, thereby generating battery operating characteristics under different operating conditions;

[0138] Based on the battery operation characteristics of different working conditions, multi-period battery operation simulation is performed on the thermal state portraits of multiple unit areas to collect multi-period operation simulation data.

[0139] In this example, an established multi-sensor temperature monitoring system is used to collect real-time temperature data for each battery cell. The data is collected at a frequency of, for example, once per second to capture subtle temperature changes. The data is stored in a database (such as InfluxDB) for subsequent analysis. The temperature data for each battery cell is integrated with the data of its neighboring cells to form a data framework containing temperature, timestamp, and location. The data is cleaned to remove missing and outliers to ensure the accuracy of the analysis results. Statistical methods such as the Pearson Correlation Coefficient or Spearman Rank Correlation are used to analyze temperature differences between neighboring cells. A correlation threshold is set, for example, a correlation coefficient greater than 0.7 is considered as a strong correlation to screen out significant temperature change relationships, calculate the correlation of the temperature data of each pair of adjacent cells, record the correlation value and change trend of each cell pair, generate a report, and show the correlation of the temperature difference changes between adjacent cells and its statistical analysis results to facilitate subsequent research and decision-making. Select a suitable heat transfer model, such as a one-dimensional heat conduction equation or a two-dimensional heat transfer model to reflect the heat transfer characteristics between battery cells, build a model in MATLAB or Python, set initial conditions and boundary conditions, such as the initial temperature of the battery cell and the external environment temperature, run the heat transfer model, simulate the heat transfer process in different time periods, and record the temperature of each battery cell at different time points. Changes, set the simulation time step, for example, update the temperature distribution every 1 minute, analyze the temperature change trend during the heat transfer process, record the temperature response and heat transfer rate of each unit, generate a heat transfer law report, and show the heat transfer relationship and evolution characteristics between different battery cells. The cooling efficiency is defined by comparing the actual temperature of the battery cell with the theoretical temperature (such as ambient temperature), determine the source of the ambient temperature and theoretical temperature, ensure the accuracy of the data, integrate the actual temperature data, ambient temperature data and theoretical temperature data of the battery cell to form the data set required for calculation, analyze the cooling efficiency changes under different working conditions, identify the main factors affecting the cooling efficiency (such as load, environmental conditions, etc.), and generate cooling efficiency data. Cooling efficiency analysis report is used to facilitate subsequent optimization of the cooling system. Different test scenarios are set according to the previously defined multiple operating conditions, such as high temperature and high load, low temperature and low load, etc., to ensure that all application scenarios are covered. Specific parameters are defined for each operating condition, such as temperature range, charge and discharge rate, and cooling method. The battery pack is operated under different operating conditions, and the temperature data, cooling efficiency data, and heat transfer law data of the battery cells are collected. Statistical analysis methods (such as variance analysis ANOVA) are used to compare the data under different operating conditions, quantify the impact of each operating condition on battery performance, and organize the quantitative analysis results of different operating conditions, such as forming a summary of the temperature distribution, cooling efficiency, and heat transfer characteristics under each operating condition. Reporting and visualizing results facilitates understanding and communication. Based on the battery operating characteristics obtained in the previous steps, update the simulation model's input parameters, such as adjusting the thermal conductivity and heat capacity, to reflect the actual conditions under different operating conditions. Set new initial simulation conditions to ensure consistency with actual operating conditions. Perform multiple simulation periods in the updated model, recording the temperature changes of the battery cells during each period. Set the simulation time range, such as from startup to full charge and discharge, and record temperature data every minute. Record the simulation results in a database or file to ensure data integrity for subsequent analysis. Use visualization tools to generate thermal state images to display the temperature distribution of the battery cells at different time periods.

[0140] In this embodiment, step S4 includes the following steps:

[0141] Step S41: Calculating the temperature change rate for the predicted temperature change situation of each region to generate the temperature change situation rate of each region;

[0142] Step S42: analyzing the temperature fluctuation range of each region based on the temperature change prediction trend to obtain the temperature fluctuation range of each region;

[0143] Step S43: identifying temperature rise deviations based on the temperature change rate of each region and the temperature change fluctuation range of each region, and marking the temperature change deviation regions;

[0144] Step S44: performing continuous abnormal temperature rise trend detection on the temperature change deviation area based on a preset temperature rise deviation threshold, thereby generating an abnormal temperature rise trend feature;

[0145] Step S45: generating a temperature abnormality warning signal based on the abnormal temperature rise trend characteristics.

[0146] In this embodiment, the temperature change data of each region within a specified time period is extracted from the previous temperature prediction results. The timestamps of the data are ensured to be continuous and the units are consistent (minutes). The temperature change data of each region are iteratively calculated to calculate the temperature change rate of each time period. The temperature change rate data of each region is recorded and a rate analysis report is generated, including statistical information such as the average value, maximum value, and minimum value of the rate. The temperature change rate formula is: Among them, R tis the temperature change rate, ΔT is the temperature change amount, and Δt is the time interval. Use Matplotlib or Seaborn to generate a temperature change rate graph to show the temperature change rate changes in different regions for easy analysis and comparison. The temperature fluctuation range is usually defined as the difference between the maximum and minimum temperature changes in a period of time, W = T max - T min, W is the fluctuation range, T max is the highest temperature in the time period, T min is the lowest temperature. The maximum, minimum and change conditions of the temperature in each area within the specified time are extracted from the temperature forecast data and organized into a data frame for statistical analysis. The data of each area are traversed and the above fluctuation range formula is applied to calculate the temperature fluctuation range of each area. The fluctuation range of each area is recorded and an analysis report is generated, including the average value, maximum value and minimum value of the fluctuation range. The temperature fluctuation range of each area is displayed using a bar chart or box plot to make the analysis results more intuitive. The deviation identification standard is set according to the temperature change rate and fluctuation range. When the temperature change rate exceeds a certain threshold (such as 2℃ / min) and the temperature change fluctuation range exceeds a certain threshold (such as 5℃), it is marked as a temperature change deviation area. The temperature change rate and fluctuation range data are integrated together to form a comprehensive data frame. The data of each area are traversed to check whether the deviation identification standard is met. If the conditions are met, the area is marked as a temperature change deviation area, the marking results are recorded, and a deviation identification report is generated, which includes a list of deviation areas and their related features. Based on the abnormal temperature rise detection results, a temperature rise deviation threshold (such as a 3°C over-range) is set to detect abnormal trends. The marked deviation areas are continuously monitored, and their temperature changes are checked in real time. The temperature data for each time period is recorded. A sliding window method is applied to calculate the temperature change within each time period to check whether it exceeds the set threshold. If the temperature exceeds the threshold, the event is recorded and an abnormal temperature rise trend feature report is generated, including information such as the time, area, and temperature change of the anomaly. A time series graph is used to display the temperature trend, highlighting abnormal temperature rise events to help analysts quickly understand the temperature changes. Warning signal standards are set based on the abnormal temperature rise detection results. For example, if the temperature exceeds the threshold in three consecutive detections, a warning signal is triggered. The recorded abnormal temperature rise trend is monitored. If the set warning conditions are met, a temperature anomaly warning signal is generated, and the warning event is recorded, recording the time, area, and temperature change information. A response mechanism for the warning signal is determined, such as sending an alarm email or text message or automatically starting the cooling system. The generated warning signal is visualized and a warning report is formed to facilitate timely response and processing by relevant personnel.

[0147] In this embodiment, step S5 includes the following steps:

[0148] Step S51: locating the abnormal temperature starting point based on the abnormal temperature warning signal, thereby marking the abnormal temperature rise starting unit;

[0149] Step S52: performing abnormal temperature rise evolution path analysis on the abnormal temperature rise starting unit based on the three-dimensional battery topology model to generate multiple abnormal temperature rise evolution paths;

[0150] Step S53: performing dynamic temperature rise diffusion evolution based on multiple abnormal temperature rise evolution paths, thereby generating a diffusion prediction trend of the abnormal starting unit;

[0151] Step S54: making a battery abnormal fault diagnosis decision based on the diffusion prediction trend of the abnormal starting unit to obtain a battery abnormal fault diagnosis result.

[0152] In this embodiment, the temperature abnormality warning signal data is collected to ensure that all abnormal temperature rise records, timestamps and corresponding battery cell positions are included, and data from different monitoring systems (such as temperature sensors, data acquisition systems, etc.) are integrated to form a complete data set. According to the characteristics of the abnormal temperature rise, the starting point identification standard is set, and the time point when the temperature first exceeds the set threshold is selected as the abnormal starting point. The threshold is set to 3°C for accurate identification. The collected abnormal temperature rise data is traversed to find the battery cells whose temperature exceeds the threshold for the first time, and the specific location and time of these cells are recorded. Each abnormal temperature rise starting cell is marked, and a report is generated, including the ID, location and abnormal temperature of the abnormal starting cell. The abnormal temperature rise starting unit is displayed using a thermal map or 3D model to help engineers and analysts quickly identify the problem area. Computer-aided design (CAD) software or simulation tools (such as ANSYS and COMSOL Multiphysics) are used to build a three-dimensional topological structure model of the battery pack to ensure that the model can accurately reflect the layout and connection relationship of the battery cells. According to the position of the abnormal temperature rise starting unit and the heat transfer characteristics between adjacent units, the standard for evolution path analysis is set, and the adjacent heat transfer coupling units are selected as the temperature rise propagation path. The three-dimensional model is thermally simulated by the simulation tool to simulate the diffusion process of the abnormal temperature rise and record the diffusion process from the abnormal starting unit to the adjacent units. The temperature change path of the adjacent unit is used to generate multiple abnormal temperature rise evolution paths, record the temperature change information, propagation rate and time of each path, and use 3D visualization tools to display the evolution path of abnormal temperature rise, helping analysts to deeply understand the temperature rise propagation mechanism, establish a dynamic temperature rise diffusion model, select a suitable numerical model (such as a finite element model) to describe the change of temperature over time, and consider the physical properties of the material such as thermal conductivity and specific heat capacity, define the standard of the diffusion path, based on the identified abnormal temperature rise evolution path, combined with the heat conduction characteristics of the adjacent units, predict the diffusion trend of the temperature rise, apply the constructed diffusion model, perform temperature diffusion simulation at different time steps (such as every 1 minute), and record the temperature change. Calculate the temperature distribution at each time point and generate diffusion prediction trend data. Use heat maps or dynamic charts to display the dynamic temperature rise diffusion evolution, and intuitively display the temperature changes at different time points. According to the temperature rise diffusion prediction trend, set the fault diagnosis standard. If the temperature in a certain area continues to exceed the threshold (such as 5°C) within the specified time, it can be determined as a potential fault. Analyze the diffusion prediction trend data, identify the area where the temperature continues to rise within the set time period, and determine whether it meets the fault diagnosis standard. Record the diagnosis results, including the ID of the fault area, temperature changes and time information. Organize the fault diagnosis results to form a comprehensive report with detailed information on the abnormal fault area to facilitate subsequent processing and decision support.

[0153] In this embodiment, step S6 includes the following steps:

[0154] Step S61: Obtaining the historical working log of the energy storage battery;

[0155] Step S62: performing multiple operation scenario identification on the energy storage battery historical work log to obtain multiple battery operation scenarios;

[0156] Step S63: performing in-depth mining of the load status of each of the multiple battery operation scenarios, thereby generating a load status feature for each operation scenario;

[0157] Step S64: Dynamically transfer learning is performed on the load state characteristics of each operating scenario to generate a deep representation of the battery load state;

[0158] Step S65: Optimize dynamic temperature control parameters based on the battery load state depth characterization and battery abnormal fault diagnosis results to build a dynamic battery temperature control engine to execute battery temperature control warning and temperature control parameter decision-making.

[0159] In this embodiment, the content of the historical work log is determined, which generally includes the battery's charge and discharge records, temperature monitoring data, operating time, load status, and fault records, etc. The data storage location is identified, such as a database, file system, or cloud storage. Data extraction tools (such as SQL queries and Python scripts) are used to extract the required work logs from relevant data sources, ensuring that the extracted time range includes the complete working cycle of the battery. The collected data should include timestamps, charge and discharge status, temperature changes, and any relevant event records. The extracted data is cleaned to remove duplicate records and missing values to ensure data consistency and integrity. Key indicators such as temperature and load are standardized to facilitate subsequent analysis. According to the battery usage, Define operating scenarios, such as normal charging and discharging, overload, low-temperature operation, high-temperature operation, etc., and clarify the characteristic indicators of each scenario, such as the battery charging rate, discharge rate, temperature range and load type. Use data mining and machine learning techniques (such as cluster analysis and classification algorithms) to analyze historical work logs to identify different operating scenarios. Use the K-Means clustering algorithm to cluster according to characteristics such as battery temperature, load and charge and discharge status to identify various operating scenarios. Assign labels to each identified operating scenario for subsequent analysis, record the characteristics and number of data samples for each scenario, determine the key indicators of load status, such as instantaneous load, battery charge and discharge efficiency, temperature change rate, etc., and select appropriate statistical methods. (such as mean, variance, maximum, minimum) to describe the load characteristics, analyze each scenario one by one, extract its load status indicators, use Python's Pandas library to group and process the data, calculate each key indicator, record the load characteristics of each scenario, including load change trends and stability, etc., organize the load status characteristics of each operating scenario, and form a data report containing key indicators, statistical information and charts for each scenario to prepare for subsequent dynamic transfer learning, ensure that the data is clear and available, design a transfer learning framework, select a suitable model (such as convolutional neural network CNN, long short-term memory network LSTM) to process the battery load status characteristics, set the source task (historical data) and the target task (real-time data) The relationship between them is used to better transfer knowledge. The load state feature data in the historical work log is used to train the model. Appropriate training parameters (such as learning rate and batch size) are set. The performance of the model is evaluated using the cross-validation method to ensure that the model can effectively learn and identify the load state features. The deep representation is extracted from the trained model to form a feature vector of the battery load state for subsequent analysis and application. The deep representation of each scene is recorded and a representation result report is formed. According to the deep representation of the battery load state and the fault diagnosis results, the standard for temperature control parameter optimization is set, the temperature range (such as 15℃-35℃) and the load change rate are set, and the optimization algorithm (such as genetic algorithm and particle swarm optimization algorithm) is used to optimize the temperature control parameters.Ensure optimal battery temperature control under various load conditions. Set optimization goals, such as maximizing charge and discharge efficiency or minimizing temperature fluctuations. Build a dynamic temperature control engine based on the optimization results, integrate an automatic temperature control system and early warning mechanism to monitor and adjust battery temperature in real time, and develop control algorithms to ensure that the temperature control system can quickly respond to load and environmental changes.

[0160] In this embodiment, a temperature control and early warning system for an energy storage battery is provided, which is used to execute the temperature control and early warning method for an energy storage battery as described above, including:

[0161] The topology module is used to obtain the internal structure diagram of the energy storage battery; perform internal space layout analysis and physical connection analysis between units on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model;

[0162] The visualization rendering module is used to obtain the real-time temperature monitoring parameters of the energy storage battery; based on the real-time temperature monitoring parameters of the energy storage battery, the dynamic temperature distribution visualization rendering of the three-dimensional battery topology model is performed to construct the thermal state portrait of multiple unit areas;

[0163] The multi-period simulation module is used to simulate the battery operation in multiple periods based on the thermal state profiles of multiple unit areas, and to predict the temperature change trend over a sliding window to obtain the predicted temperature change trend for each area.

[0164] The abnormal warning module is used to continuously detect abnormal temperature rise trends in the temperature change forecast situation of each area, thereby generating abnormal temperature rise trend characteristics; and generate temperature abnormality warning signals based on the abnormal temperature rise trend characteristics;

[0165] The diagnosis and decision module is used to dynamically analyze the temperature rise diffusion evolution based on the temperature abnormality warning signal, and then make a battery abnormality fault diagnosis decision to obtain the battery abnormality fault diagnosis result;

[0166] The dynamic temperature control optimization module is used to obtain the historical work logs of the energy storage battery; it deeply mines the load status of each scenario in the historical work logs of the energy storage battery, and optimizes the dynamic temperature control parameters based on the abnormal battery fault diagnosis results to build a dynamic battery temperature control engine.

[0167] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0168] The foregoing description is intended only to provide specific embodiments of the present invention, which are intended to enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest manner consistent with the principles and novel features disclosed herein.

Claims

1. A temperature control and early warning method for energy storage batteries, characterized in that: The following steps are involved: Step S1: Obtaining an internal structure diagram of the energy storage battery; performing internal space layout analysis and inter-unit physical connection analysis on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model; Step S2: obtaining real-time temperature monitoring parameters of the energy storage battery; performing dynamic temperature distribution visualization rendering on the three-dimensional battery topology structure model according to the real-time temperature monitoring parameters of the energy storage battery, thereby constructing thermal state portraits of multiple unit areas; Step S3: performing multi-period battery operation simulation on the thermal state portraits of the multiple unit areas, and performing sliding window temperature change trend prediction to obtain the temperature change prediction trend of each area; Step S4: Detecting the continuous abnormal temperature rise trend for the temperature change prediction situation in each region, thereby generating abnormal temperature rise trend features; Generate temperature anomaly warning signals based on abnormal temperature rise trend characteristics; Step S5: performing dynamic temperature rise diffusion evolution based on the temperature abnormality warning signal, and then making a battery abnormality fault diagnosis decision to obtain a battery abnormality fault diagnosis result; Step S6: Obtain the historical work log of the energy storage battery; conduct in-depth mining of the load status of each scenario in the historical work log of the energy storage battery, and optimize the dynamic temperature control parameters according to the battery abnormal fault diagnosis results to build a dynamic battery temperature control engine; Among them, the specific steps of step S3 are: Step S31: defining multiple operating conditions of the battery pack; Step S32: performing multi-period battery operation simulation on thermal state portraits of multiple unit areas according to multiple operating conditions of the battery pack to collect multi-period operation simulation data; Step S33: performing temperature change trend analysis on each region of the multi-period simulation data to obtain temperature change trend characteristics of each region; Step S34: performing sliding window temperature change situation prediction based on the temperature change trend characteristics of each area to obtain the temperature change prediction situation of each area; The specific steps of step S32 are: Based on the real-time temperature monitoring parameters of the energy storage battery, the temperature difference between adjacent cells is mined for each battery cell to obtain the temperature change relationship between adjacent cells; Based on the temperature change relationship between adjacent cells, the heat transfer evolution between battery cells is analyzed to obtain the heat transfer law of battery cells; Calculate the cooling efficiency of energy storage batteries; Performing a quantitative analysis of the heat transfer rules of the battery cells and the cooling efficiency of the energy storage battery under multiple operating conditions of the battery pack, thereby generating battery operating characteristics under different operating conditions; Based on the battery operation characteristics of different working conditions, multi-period battery operation simulation is performed on the thermal state portraits of multiple unit areas to collect multi-period operation simulation data.

2. The energy storage battery temperature control and early warning method according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: performing CT scanning on the target energy storage battery to obtain an internal structure diagram of the energy storage battery; Step S12: Perform deep visual recognition on the internal structure diagram of the energy storage battery and mark each battery cell; Step S13: performing precise positioning calculation of the internal space of each battery cell to extract the internal space coordinates of each battery cell; Step S14: performing internal space layout analysis based on the internal space coordinates of each battery cell to generate battery space layout features; Step S15: performing inter-cell physical connection analysis on each battery cell to obtain a topological connection relationship of the battery cells; Step S16: reconstructing the battery space layout characteristics in three dimensions based on the topological connection relationship of the battery cells to construct a three-dimensional battery topological structure model.

3. The energy storage battery temperature control and early warning method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Acquire real-time temperature monitoring parameters of the energy storage battery based on multiple sensors; Step S22: Calculating the internal position of each sensor node one by one based on the multi-sensor to obtain the internal space coordinates of the battery of each sensor node; Step S23: performing spatial temperature distribution mining on the real-time temperature monitoring parameters of the energy storage battery according to the internal spatial coordinates of the battery of each sensor node to obtain the temperature distribution characteristics of each battery cell; Step S24: dividing the three-dimensional battery topology model into multiple battery unit regions, thereby generating multiple unit region models; Step S25: Based on the temperature distribution characteristics of each battery cell, dynamic temperature distribution visualization rendering is performed on the multiple unit area models, thereby constructing thermal state portraits of the multiple unit areas.

4. The energy storage battery temperature control and early warning method according to claim 3, characterized in that: The specific steps of step S25 are: Perform real-time temperature distribution change analysis on the temperature distribution characteristics of each battery cell to generate real-time temperature distribution change data; Perform discrete fitting of time series temperature values on real-time temperature distribution change data to construct the temperature distribution change curve of each battery cell; Perform temperature positioning matching on the temperature distribution change curve of each battery cell and multiple unit area models to obtain the matching temperature curve relationship of each unit area; Visualize the temperature distribution of multiple unit area models based on the matching temperature curve relationship of each unit area, thereby obtaining the temperature distribution thermal map of multiple unit areas; Dynamic temperature change rendering is performed on the temperature distribution thermodynamic map of multiple unit areas to construct thermal state portraits of multiple unit areas.

5. The energy storage battery temperature control and early warning method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: Calculating the temperature change rate for the predicted temperature change situation of each region to generate the temperature change situation rate of each region; Step S42: analyzing the temperature fluctuation range of each region based on the temperature change prediction trend to obtain the temperature fluctuation range of each region; Step S43: identifying temperature rise deviations based on the temperature change rate of each region and the temperature change fluctuation range of each region, and marking the temperature change deviation regions; Step S44: performing continuous abnormal temperature rise trend detection on the temperature change deviation area based on a preset temperature rise deviation threshold, thereby generating an abnormal temperature rise trend feature; Step S45: generating a temperature abnormality warning signal based on the abnormal temperature rise trend characteristics.

6. The energy storage battery temperature control and early warning method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: locating the abnormal temperature starting point based on the abnormal temperature warning signal, thereby marking the abnormal temperature rise starting unit; Step S52: performing abnormal temperature rise evolution path analysis on the abnormal temperature rise starting unit based on the three-dimensional battery topology model to generate multiple abnormal temperature rise evolution paths; Step S53: performing dynamic temperature rise diffusion evolution based on multiple abnormal temperature rise evolution paths, thereby generating a diffusion prediction trend of the abnormal starting unit; Step S54: making a battery abnormal fault diagnosis decision based on the diffusion prediction trend of the abnormal starting unit to obtain a battery abnormal fault diagnosis result.

7. The energy storage battery temperature control and early warning method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Obtaining the historical working log of the energy storage battery; Step S62: performing multiple operation scenario identification on the energy storage battery historical work log to obtain multiple battery operation scenarios; Step S63: performing in-depth mining of the load status of each of the multiple battery operation scenarios, thereby generating a load status feature for each operation scenario; Step S64: Dynamically transfer learning is performed on the load state characteristics of each operating scenario to generate a deep representation of the battery load state; Step S65: Optimize dynamic temperature control parameters based on the battery load state depth characterization and battery abnormal fault diagnosis results to build a dynamic battery temperature control engine to execute battery temperature control warning and temperature control parameter decision-making.

8. A temperature control and warning system for energy storage batteries, characterized in that: The method for executing the temperature control and early warning method for the energy storage battery according to claim 1 comprises: The topology module is used to obtain the internal structure diagram of the energy storage battery; perform internal space layout analysis and physical connection analysis between units on the internal structure diagram of the energy storage battery to construct a three-dimensional battery topology model; The visualization rendering module is used to obtain the real-time temperature monitoring parameters of the energy storage battery; based on the real-time temperature monitoring parameters of the energy storage battery, the dynamic temperature distribution visualization rendering of the three-dimensional battery topology model is performed to construct the thermal state portrait of multiple unit areas; The multi-period simulation module is used to simulate the battery operation in multiple periods based on the thermal state profiles of multiple unit areas and to predict the temperature change trend over a sliding window to obtain the predicted temperature change trend for each area. The abnormal warning module is used to continuously detect abnormal temperature rise trends in the temperature change forecast situation of each area, thereby generating abnormal temperature rise trend characteristics; and generate temperature abnormality warning signals based on the abnormal temperature rise trend characteristics; The diagnosis and decision module is used to dynamically analyze the temperature rise diffusion evolution based on the temperature abnormality warning signal, and then make a battery abnormality fault diagnosis decision to obtain the battery abnormality fault diagnosis result; A dynamic temperature control optimization module is used to obtain the historical work logs of energy storage batteries. This module conducts in-depth mining of the load status of each scenario in the historical work logs of energy storage batteries and optimizes dynamic temperature control parameters based on the results of abnormal battery fault diagnosis to build a dynamic battery temperature control engine. The multi-period simulation module is used to perform multi-period battery operation simulation on the thermal state portraits of multiple unit areas and perform sliding window temperature change situation prediction to obtain the temperature change prediction situation of each area, specifically for: Define multiple operating conditions for the battery pack; Performing multi-period battery operation simulation on thermal state portraits of multiple unit areas according to multiple operating conditions of the battery pack to collect multi-period operation simulation data; The temperature change trend of each region is analyzed on the multi-period simulation data to obtain the temperature change trend characteristics of each region; According to the temperature change trend characteristics of each area, the sliding window temperature change situation is predicted to obtain the temperature change prediction situation of each area; The specific steps of performing multi-period battery operation simulation on thermal state portraits of multiple unit areas according to multiple operating conditions of the battery pack to collect multi-period operation simulation data are as follows: Based on the real-time temperature monitoring parameters of the energy storage battery, the temperature difference between adjacent cells is mined for each battery cell to obtain the temperature change relationship between adjacent cells; Based on the temperature change relationship between adjacent cells, the heat transfer evolution between battery cells is analyzed to obtain the heat transfer law of battery cells; Calculate the cooling efficiency of energy storage batteries; Performing a quantitative analysis of the heat transfer rules of the battery cells and the cooling efficiency of the energy storage battery under multiple operating conditions of the battery pack, thereby generating battery operating characteristics under different operating conditions; Based on the battery operation characteristics of different working conditions, multi-period battery operation simulation is performed on the thermal state portraits of multiple unit areas to collect multi-period operation simulation data.

Images