Remote control method and system of new energy battery

Abstract

The invention relates to the technical field of battery management, and discloses a remote control method and system for a new energy battery, and the method comprises the steps: obtaining a physical topological structure of a target battery, carrying out the digital modeling, extracting a mutual influence factor of a battery cell part, continuously collecting the electrical parameters and temperature data of the battery, and recognizing abnormal information through combining with the influence factor. The abnormal information labeling set is periodically sent to the cloud platform for health state analysis and expected evolution, according to an analysis result, multi-stage gradient management countermeasure analysis is performed, a management strategy is generated, and the management system is deployed to a target battery through wireless data, so that the real-time performance and accuracy of battery management are improved, and the battery management efficiency is improved. The health trend of the battery is analyzed and predicted through the cloud platform, the battery performance is optimized, the service life is prolonged, safe and efficient operation of the battery is ensured, and the problem that the health of the battery cannot be remotely managed in real time in the prior art is solved.

Description

Technical Field

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

[0002] New energy batteries, especially their application in electric vehicles, energy storage systems and other high-performance devices, have become an important part of modern society. With the widespread application of new energy batteries, battery health management and remote monitoring have become increasingly important. The health status of batteries directly affects their performance, lifespan and safety. Batteries will experience the influence of various internal and external factors during long-term use, such as charge and discharge cycles, temperature fluctuations, overcharging, over-discharging, etc. These factors will cause battery capacity decay, increased internal resistance, and even serious problems such as thermal runaway. Traditional battery health management methods mostly rely on regular manual inspections and cannot capture battery health changes and potential failures in real time. Summary of the Invention

[0003] The purpose of the present invention is to provide a remote control method and system for new energy batteries, aiming to solve the problem in the prior art that it is impossible to remotely manage battery health in real time.

[0004] The present invention is implemented as follows: In a first aspect, the present invention provides a remote control method for a new energy battery, comprising: Obtaining the physical topology of a target battery to perform digital modeling of the cell connection relationship of the target battery, and extracting the mutual influence factors of the cell components of the target battery based on the digital modeling; Continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify abnormal information in combination with the mutual influencing factors of the various components of the battery cell to obtain the abnormal information annotation set of the target battery; Sending the abnormal information annotation set to a cloud processing platform at predetermined intervals to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; A multi-level gradient management strategy analysis is performed on the battery health feedback information to generate a battery management strategy and deploy it to the management system of the target battery via wireless data.

[0005] In a second aspect, the present invention provides a remote control system for a new energy battery, which is used to implement a remote control method for a new energy battery according to any one of the first aspects, comprising: An impact analysis module is used to obtain the physical topology of the target battery to perform digital modeling of the cell connection relationship of the target battery, and extract the mutual influence factors of the various components of the cell of the target battery based on the digital modeling; An anomaly annotation module is used to continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify anomaly information in combination with the mutual influence factors of the various components of the battery cell to obtain an anomaly information annotation set of the target battery; a health analysis module, configured to send the abnormal information annotation set to a cloud processing platform at predetermined intervals, so as to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; A countermeasure analysis module is used to perform a multi-level gradient management countermeasure analysis on the battery health feedback information, generate a battery management strategy and deploy it to the management system of the target battery through wireless data.

[0006] The present invention provides a remote control method for a new energy battery, which has the following beneficial effects: The present invention obtains the physical topology of the target battery and performs digital modeling, extracts the mutual influencing factors of the battery components, continuously collects the electrical parameters and temperature data of the battery, identifies abnormal information in combination with the influencing factors, and regularly sends the abnormal information annotation set to the cloud platform for health status analysis and expected evolution. According to the analysis results, a multi-level gradient management countermeasure analysis is performed, and a management strategy is generated. The management strategy is deployed to the management system of the target battery through wireless data, thereby improving the real-time and accuracy of battery management. The cloud platform analyzes and predicts the battery health trend, optimizes battery performance, extends service life, and ensures safe and efficient operation of the battery, thereby solving the problem of the inability to remotely manage battery health in real time in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a schematic diagram of the steps of a remote control method for a new energy battery provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a remote control system for a new energy battery provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. 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.

[0009] The implementation of the present invention is described in detail below with reference to specific embodiments.

[0010] Reference Figure 1 、 Figure 2 As shown, a preferred embodiment of the present invention is provided.

[0011] In a first aspect, the present invention provides a remote control method for a new energy battery, comprising: S1: Obtaining a physical topological structure of a target battery to perform digital modeling of a cell connection relationship of the target battery, and extracting mutual influence factors of various cell components of the target battery based on the digital modeling; S2: Continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify abnormal information in combination with the mutual influencing factors of the various components of the battery cell to obtain an abnormal information annotation set of the target battery; S3: sending the abnormal information annotation set to a cloud processing platform at predetermined intervals to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; S4: Perform a multi-level gradient management strategy analysis on the battery health feedback information, generate a battery management strategy, and deploy it to the management system of the target battery via wireless data.

[0012] Specifically, in step S1 of the embodiment provided by the present invention, 3D scanning technology, CT imaging technology or high-precision CAD design drawings are used to obtain physical structural data of each component inside the battery. These data include the battery cell layout, the connection method of the battery module, and the electrical connection relationship between each cell and module. The relevant data provided by sensors (such as current, voltage, and temperature sensors) and the battery management system (BMS) can be combined with the physical model to supplement the detailed information of the topological structure, and the physical topological model of the battery can be constructed using computer-aided design (CAD) tools or professional simulation software (such as ANSYS, COMSOL, etc.). Through these models, the internal structural layout of the battery, the electrical connection method between the cells, the layout of the cooling system, etc. can be simulated. In order to accurately model the performance, life and failure mode of the battery, it is first necessary to obtain the precise physical structure of the battery. This is the basis for subsequent digital modeling. Accurate physical topology helps in the subsequent modeling of the connection relationship between battery cells, so as to infer the mutual influence factors between components and guide battery health monitoring. Through the precise modeling of the battery physical topology, every detail of the battery can be analyzed in detail, improving the scientific nature of battery design and management. Accurate physical topology can help identify potential failure points and degradation modes, ensuring timely response to various types of battery failures.

[0013] More specifically, according to the physical topology of the battery, the electrical connection mode between the battery cells (such as series connection, parallel connection, etc.) is clarified, and the real-time current, voltage, temperature and other data are obtained through the battery management system (BMS). Combined with the electrical connection diagram inside the battery, the relationship between the battery cells is determined. In the model, the electrical network relationship between the battery cells is established, considering the influence of factors such as current, voltage, and temperature on the battery cells. The battery simulation software (such as MATLAB / Simulink, ANSYS, COMSOL, etc.) is used to digitally model the electrical connection relationship of the battery cells. Through the simulation model, the working state of the battery cell can be simulated, including the distribution of current and voltage, the working state of the thermal management system, etc., considering the battery The feedback relationship between the cell and the battery management system (BMS) simulates the performance of the battery in different working environments. Through digital modeling, it is possible to simulate the electrical behavior of the cell and predict the performance of the battery under different loads and different environments. This provides theoretical support for battery optimization design and fault warning. Clarifying the cell connection relationship helps to identify potential problems of interaction between cells, such as cell imbalance, short circuit or overheating. Through digital modeling of the cell connection relationship, the battery performance can be better optimized and the safety hazards that may be caused by the cell connection can be discovered in the design stage. Digital modeling can help foresee the behavior of the battery under different operating conditions and provide more accurate predictions for battery health monitoring and fault diagnosis.

[0014] More specifically, based on the working principle and topological structure of the battery cell, the electrical and thermal interactions between various components (such as positive and negative electrodes, separators, electrolytes, etc.) are analyzed, and mathematical models (such as electrochemical models, heat conduction models, etc.) are used to quantify these interactions. The real-time data of the battery (such as current, voltage, temperature, etc.) is combined with the model to extract the mutual influencing factors between the battery cell components. These factors may include current distribution, heat distribution, internal resistance, etc. The coupling effects between the various components of the battery cell are analyzed through data-driven modeling methods (such as machine learning or deep learning). This step involves combining the data of the battery management system with the physical model. This allows for more accurate extraction of the influencing factors between components. Extracting the mutual influencing factors of cell components can help identify performance bottlenecks in battery design, such as overheating of certain components, increased internal resistance, etc. Accurately extracting the mutual influencing factors of components can help to comprehensively evaluate the health of the battery and provide a basis for subsequent degradation prediction and fault diagnosis. By extracting the mutual influencing factors of cell components, the battery structure and material selection can be optimized, thereby improving the overall performance and safety of the battery. Based on the extracted mutual influencing factors, the battery degradation mode and the timing of failure can be predicted more accurately, thereby improving the accuracy of the health management system.

[0015] It is understandable that the core steps of the entire process are to obtain the physical topology of the battery and digitally model it, and then fully understand the working status of the battery by analyzing the connection relationship and mutual influencing factors between battery cells. Through these steps, the battery performance can be evaluated more accurately, potential problems can be identified and the design can be optimized. This process is crucial for battery health monitoring, fault prediction and performance optimization, which helps to extend the battery life and improve its safety.

[0016] Specifically, in step S2 of the embodiment provided by the present invention, electrical sensors, temperature sensors, battery management systems (BMS), and other equipment are installed to continuously monitor the battery's electrical and thermal parameters such as voltage, current, and temperature. A high-frequency data acquisition system is configured to record the battery's operating status in real time, including but not limited to charge and discharge current, voltage fluctuations, and temperature changes. A data storage system is configured to ensure that the collected real-time data can be effectively stored for subsequent analysis and processing. High-frequency data acquisition is achieved to ensure that the rapid changes of the battery under different operating conditions can be captured. A reasonable data sampling frequency is set to ensure the timeliness and accuracy of the data to prevent delays in the acquisition system from affecting the monitoring effect. The collection of electrical parameter and temperature data can fully understand the battery's operating status, including the battery's charge and discharge characteristics and temperature changes. These data are the basis for subsequent abnormal information identification and health diagnosis analysis, and provide key features of the battery's operating process. Real-time data collection and storage ensure that all important parameters can be accurately recorded during battery operation, providing support for subsequent fault analysis and early warning. The high-frequency and accurate acquisition system can promptly detect minor abnormalities that occur during battery use, providing more diagnostic basis.

[0017] More specifically, mathematical models and machine learning algorithms (such as neural networks, support vector machines, etc.) are used to process the collected electrical parameters and temperature data to establish a battery anomaly detection model. Combined with the mutual influencing factors of the various components of the battery cell (such as the distribution of current, voltage, temperature, internal resistance changes, etc.), a comprehensive analysis model is constructed to identify potential abnormal conditions during the battery operation (such as overtemperature, overvoltage, overcurrent, increased internal resistance, etc.). The real-time collected data is input into the anomaly detection model, and the current working status of the battery is evaluated through the model. If an anomaly is detected, the system can trigger an alarm and record the specific type of anomaly, time of occurrence, degree of impact, etc. The anomaly detection model is regularly updated and optimized based on the continuously accumulated operating data and abnormal events. In order to adapt to the performance of batteries in different working environments, the incremental learning method in machine learning is applied to gradually improve the model's ability and accuracy in identifying abnormal states. By combining the mutual influencing factors of battery components, it is possible to more accurately judge whether the battery is abnormal, thereby improving the accuracy of abnormality detection. With the help of data-driven analysis methods, some potential problems that are difficult to detect through traditional methods (such as small temperature changes, increased internal resistance, etc.) can be discovered in time. The comprehensive use of physical models and data-driven methods can detect potential abnormalities inside the battery in real time and accurately, avoiding major failures caused by the accumulation of small problems. By timely identifying the abnormal information of the battery, measures can be taken in advance for maintenance, reducing the probability of battery failure, and thus extending the battery life.

[0018] More specifically, detected abnormal events are classified and annotated. Each anomaly should include detailed information such as the timestamp, anomaly type, affected cell components, and anomaly severity. During the annotation process, each event should be recorded in detail to ensure the accuracy and completeness of the anomaly information. An anomaly information annotation set is created, storing all detected abnormal events in chronological order and categorizing them. These annotation sets can be used for subsequent analysis and optimization. Based on historical data, the annotation sets can also be used to train machine learning models to help the models better identify new anomalies in the future. An alarm mechanism is configured for the anomaly information in the annotation set. Once the anomaly information in the annotation set reaches a certain threshold, the system automatically issues an alarm. Anomaly events are annotated and stored in a database, enabling systematic management of battery anomaly information and facilitating subsequent data analysis and processing. The anomaly information annotation set not only provides a basis for fault diagnosis but also provides data support for future performance optimization and design improvements. Through a structured anomaly information annotation set, battery failure modes can be easily tracked and analyzed. The anomaly information annotation set can help timely understand the battery's health status and potential failures, enhance predictive maintenance capabilities, and reduce battery system downtime.

[0019] It is understandable that the core of this process is to identify and mark abnormal information through continuous battery monitoring combined with the mutual influencing factors between battery components. By collecting electrical and temperature data in real time and combining it with advanced anomaly detection technology, potential faults in the battery can be identified in a timely manner and marked, classified and stored. This process not only helps to improve the health management capabilities of the battery system, but also extends the battery life and reduces the risk of failure.

[0020] Specifically, in step S3 of the embodiment provided by the present invention, according to the battery working environment and application scenario, the period of sending the abnormal information annotation set is set (for example, every hour, every day or every week), ensuring that the frequency of data transmission is consistent with the battery operating characteristics and the data processing capabilities of the cloud platform, avoiding data lag or excessive redundancy in data transmission, pre-processing the collected abnormal information annotation set, and packaging it into a standardized data format (such as JSON, CSV, etc.) to ensure that the data structure is consistent and convenient for cloud platform processing, and sending the data to the cloud platform through a secure communication protocol (such as HTTPS, MQTT, etc.) to ensure the security and integrity of the data transmission process, and building a data interface on the cloud platform. The receiving port ensures that the received data can be stored and processed on time, realizes real-time storage and queue management after data reception, ensures that data will not be lost or delayed, and regularly uploads abnormal information annotation sets, so that the cloud platform can obtain the health status and abnormal events of the battery in a timely manner, and maintain the timeliness of the data. After sending the data to the cloud platform, the platform's powerful computing resources can be used for complex analysis and prediction to avoid excessive computing burden on local devices. By uploading data at predetermined time intervals, it can ensure that the cloud obtains the latest status of the battery in real time, providing accurate data for subsequent analysis. Through encrypted transmission and security protocols, it can ensure that data is not tampered with or lost during transmission, thereby ensuring the security of battery data.

[0021] More specifically, the cloud platform uses the uploaded abnormal information annotation set to conduct real-time analysis of the battery's health status. Common analysis methods include model-based analysis, data-driven machine learning analysis, etc. By analyzing the battery's electrical parameters, temperature changes, abnormal events, etc., the current health status of the battery is evaluated to determine whether there are potential risks such as overheating, overvoltage, and increased internal resistance. Advanced health status assessment models (such as state estimation algorithms, health index assessments, etc.) are used in the cloud platform to evaluate the battery status. These models can judge the battery's health level based on historical data and real-time data, and conduct multi-factor analysis based on the battery's working characteristics and external environmental factors to comprehensively evaluate the battery's current status and future trends. Using historical data and trend analysis, the cloud platform can evaluate the battery's health status. The cloud platform uses powerful computing resources and analysis models to process and analyze large amounts of complex data, providing more accurate battery health status assessments. By predicting the evolution of battery health status, it can identify possible battery failures in advance and take measures to avoid accidents in advance. Through real-time data analysis on the cloud platform, a more accurate battery health status assessment can be obtained, potential problems can be discovered in a timely manner, and combined with historical data and models, the battery health trend can be predicted in advance, providing predictive decision support for battery maintenance and management.

[0022] More specifically, based on the analysis results of the cloud platform, a feedback report on the battery health status is generated. The report should include information such as the current battery health index, details of abnormal events, potential failure risks, and future health trend forecasts. The health feedback report can be displayed through a visual interface. Charts, trend charts, and detailed abnormality analysis can help users quickly understand the health status of the battery. Battery health feedback reports are generated regularly and sent to users or operation and maintenance personnel via email, SMS, APP push, etc. to ensure timely acquisition of battery status information. According to changes in the battery health status, the system can automatically trigger an alarm. For example, when the battery health index is lower than the preset threshold, the user or maintenance personnel will be automatically notified to perform maintenance. Or replace, users can view the battery health feedback report through the cloud platform interface, and formulate maintenance plans or take corresponding measures based on the feedback information. The cloud platform can also set up a feedback mechanism, and users can provide feedback on the information in the report to further optimize the analysis model and report content. The health feedback report can help users keep abreast of the battery's health status and make scientific decisions. Through regular health feedback and alarm notifications, effective maintenance can be carried out according to the actual status of the battery to avoid sudden failures. The health feedback report provides detailed battery status information. By obtaining timely feedback on the battery health status, potential problems can be discovered in advance and maintenance can be carried out, thereby extending the battery life and reducing operating costs.

[0023] It is understandable that by regularly sending the abnormal information annotation set to the cloud platform for real-time analysis and expected evolution, and generating health feedback information, it is possible to achieve continuous monitoring, real-time analysis, early warning and fault prediction of the battery health status. This process can help users understand the battery status in a timely manner, provide data support for battery maintenance, management and fault prevention, reduce the risk of sudden failures, and extend battery life.

[0024] Specifically, in step S4 of the embodiment provided by the present invention, the health feedback information of the battery (such as battery voltage, internal resistance, temperature, number of charge and discharge cycles, etc.) is analyzed to identify potential hidden danger factors that may cause battery performance degradation. The potential hidden danger factor is a certain degradation occurring inside the battery, which causes the battery to malfunction during operation. For each potential hidden danger factor, a preliminary management strategy is set. For example, in the case of excessively high battery temperature, the management strategy may be to enhance the cooling system or limit the battery charging power. An impact assessment is performed on each hidden danger factor to generate a first-gradient management strategy to prevent the impact of hidden danger factors on battery health. The first-gradient management strategy can perform preventive management at the early stage of battery health feedback to reduce potential risks. Based on the detailed analysis of battery health feedback information, the effectiveness of the management strategy can be ensured. Through the analysis of potential hidden danger factors, various problems affecting battery health can be accurately identified to avoid the expansion of problems. Effective early management can reduce the incidence of battery failures and improve the reliability of the battery system.

[0025] More specifically, based on the first-level battery management countermeasures, the battery health feedback information is simulated, and the impact of different management countermeasures on potential hidden danger factors after implementation is analyzed. The effects of different countermeasures are speculated through simulation models. For example, if temperature control management countermeasures are adopted, whether the battery temperature can be stabilized within a safe range and whether the battery performance degradation caused by overheating can be prevented. During the analysis process, the effects of different management strategy combinations are considered. There can be multiple solutions for the same hidden danger factor, and each solution may have different effects. For example, if the battery voltage fluctuates greatly, you can choose to limit the charging voltage or enhance the battery voltage stability. These two methods may have different optimization effects. By speculating on the effects of countermeasures, the feasibility and effectiveness of the management strategy in practice can be ensured. Different management solutions may produce different effects in different situations. Speculating on multiple possible results can provide the best solution. Speculating on the effects of potential hidden dangers helps to optimize the management strategy in real time. When the battery operating status changes, the countermeasures can be adjusted in time. By simulating the effects of different strategies, the most appropriate response measures can be selected.

[0026] More specifically, after speculating on the effects of various possible countermeasures, evaluate whether each countermeasure can truly resolve potential hidden dangers. If the effect of a certain strategy does not meet expectations, it can be corrected. The correction may include adjusting the specific implementation steps of the strategy, modifying operating parameters, or taking more suitable alternatives. The corrected potential hidden danger factors are then evaluated to ensure that the corrective measures can effectively reduce battery risks. For example, after correcting the management countermeasures for the problem of excessive battery temperature, re-evaluate whether the battery temperature remains within a safe range and whether the battery performance has returned to normal. Through correction analysis, imperfect strategies can be discovered and corrected in a timely manner to ensure that management strategies are continuously optimized. Correction analysis makes management strategies more flexible and can be dynamically adjusted when faced with complex battery health conditions. Through correction analysis, the accuracy of management strategies is ensured and management errors are reduced. The corrected strategies can more accurately respond to potential hidden dangers and further improve the safety and performance of batteries.

[0027] More specifically, a second level of management countermeasures analysis is conducted based on the corrected potential risk factors. This level is more refined and can address issues that the previous round of countermeasures could not fully resolve. For example, if the revised temperature control countermeasures still do not achieve the expected results, the temperature control methods can be further refined, such as adding heat dissipation devices or optimizing the battery's thermal management system. In the second level, more specific management measures are generated, including hardware adjustments and software optimizations, to ensure battery health management under various conditions. Refined management methods are adopted for each potential risk factor to maximize battery safety and performance. The second level further refines battery health management and can effectively address more complex battery issues. Gradually in-depth management analysis can ensure that battery health is fully protected. Through secondary management analysis, the battery's performance in actual use is more stable. Higher-level management countermeasures can ensure more detailed handling and reduce the occurrence of potential risks.

[0028] More specifically, the above analysis steps are repeated, and the management countermeasures are gradually adjusted and optimized until a sufficient number of gradients are formed. Each round of iteration should be based on the feedback and correction results of the previous round to ensure that the countermeasures are continuously improved. Finally, through the analysis of management countermeasures at multiple gradients, a complete battery management strategy is generated. The strategy should include specific solutions for different hidden danger factors and be able to deal with various battery health issues. Through continuous iteration, the maturity and completeness of the management strategy are ensured. Multiple analyses ensure that the strategy can adapt to changes in battery health and remain effective in a changing working environment. Multiple gradient management countermeasures ensure that all aspects of battery health are fully covered, which improves the adaptability and stability of the system. Each round of analysis and feedback will make the management strategy more and more intelligent, and ultimately achieve intelligent management that fully meets the battery operation requirements.

[0029] More specifically, the final generated battery management strategy is transmitted to the management system of the target battery via wireless data, ensuring that the battery system can remotely receive the latest management instructions. The target battery management system adjusts the battery's charge and discharge control, temperature control and other management parameters according to the received strategy, and the management system provides real-time feedback on the effectiveness of the strategy execution. If an abnormality occurs, the system will make corrections or redeploy a new strategy. Wireless data transmission enables battery management to be performed remotely, greatly improving the convenience and efficiency of operation. Through real-time feedback, the management strategy can be dynamically adjusted according to the actual performance of the battery. Wireless data transmission ensures that battery management can cover remote devices and reduce manual intervention. The real-time feedback mechanism enables the battery management strategy to be continuously optimized according to actual conditions.

[0030] It is understood that this process ensures the gradual improvement and precision of the battery management strategy through multi-level gradient management strategy analysis, correction, optimization, and wireless deployment. Ultimately, the generated battery management strategy can be remotely deployed to optimize the battery's operating status in real time, maximizing battery safety, efficiency, and service life.

[0031] The present invention provides a remote control method for a new energy battery, which has the following beneficial effects: The present invention obtains the physical topology of the target battery and performs digital modeling, extracts the mutual influencing factors of the battery components, continuously collects the electrical parameters and temperature data of the battery, identifies abnormal information in combination with the influencing factors, and regularly sends the abnormal information annotation set to the cloud platform for health status analysis and expected evolution. According to the analysis results, a multi-level gradient management countermeasure analysis is performed, and a management strategy is generated. The management strategy is deployed to the management system of the target battery through wireless data, thereby improving the real-time and accuracy of battery management. The cloud platform analyzes and predicts the battery health trend, optimizes battery performance, extends service life, and ensures safe and efficient operation of the battery, thereby solving the problem of the inability to remotely manage battery health in real time in the existing technology.

[0032] Preferably, the steps of obtaining the physical topology of the target battery to perform digital modeling of the cell connection relationship of the target battery, and extracting the mutual influence factors of the cell components of the target battery based on the digital modeling include: S11: acquiring original design information of a target battery, and collecting structural data of a setting environment of the target battery to obtain working environment information of the target battery; S12: parsing the spatial relationship of various components of the battery cell with respect to the original design information, and converting the parsing result into a standardized information format to obtain the physical topology structure inside the target battery; S13: Digitally modeling each component of the battery cell according to the physical topological structure inside the target battery, and deploying the digital modeling in the same simulation space to connect the electrical relationships, thereby obtaining a digital modeling of the battery; S14: simulating and analyzing current conduction of the digital model of the battery to generate mutual influence factors of various components of the battery cell in the electrical dimension; S15: Simulating and analyzing heat transfer of the digital model of the battery in combination with the working environment information to generate mutual influence factors of various components of the battery cell in the thermal field dimension.

[0033] Specifically, design drawings, electronic circuit diagrams, mechanical structure design information, etc. of the target battery are collected, including the battery cell layout, connection method, shell size, etc. These design information can come from the battery manufacturer's design documents or CAD files to ensure that the physical structure and electrical connection of the battery are accurately reflected. Through sensors or environmental monitoring systems, the working environment data of the battery (such as temperature, humidity, pressure, vibration, etc.) are collected. These environmental information have a direct impact on the performance of the battery. Therefore, it is necessary to understand the working environment of the battery in detail for more accurate modeling. Accurate original design information is the basis of battery digital modeling, ensuring that the model can accurately restore the physical structure of the battery. By collecting working environment data, it can better reflect the impact of the environment on battery performance, enhance the practicality of the simulation, provide detailed and accurate design information and environmental data, and provide high-quality input for subsequent modeling and analysis. Understanding the environment in which the battery is located can make digital modeling more in line with actual usage scenarios and improve the credibility of simulation analysis.

[0034] More specifically, the original design information of the battery is converted into digital data, and the spatial layout and connection relationship between the various components of the battery cell (such as battery cells, battery modules, battery management system (BMS), thermal management system, etc.) are analyzed. Computer-aided design (CAD) tools or 3D modeling software are used to obtain the relative position, connection method and functional area division of each battery component. The spatial layout information of each battery component obtained by analysis is converted into a standardized data format (such as STEP, IGES, STL, etc.) for subsequent digital modeling and simulation, ensuring that the spatial relationship between all components can be expressed and shared in a unified format. The standardized format can ensure the compatibility of data between different simulation platforms and tools, and avoid information loss in data conversion. Through spatial relationship analysis, the layout of each component inside the battery can be clearly understood, providing intuitive structural information for modeling. The standardized analysis results facilitate subsequent digital modeling and simulation, and improve the collaboration efficiency between systems. Accurate modeling of spatial relationships helps to deeply analyze the interactive relationship between battery components and ensure the accuracy of subsequent analysis.

[0035] More specifically, based on standardized design information and spatial relationships, modeling tools (such as ANSYS, COMSOL, etc.) are used to create detailed three-dimensional digital models for each battery component (battery cell, battery unit, battery management system, etc.), ensuring that the geometric dimensions, material properties and connection methods of each component in the model are accurately reflected. The digital models of each battery component are assembled in the same simulation space to ensure that their electrical, thermal, mechanical and other properties can interact and influence each other. Global coupling simulation is performed on the same platform to obtain the relationship between the various components of the battery cell. Deploying all components in the same simulation space can better simulate the electrical and thermal interactions between the battery cells. Digital modeling provides a structured foundation for subsequent electrical and thermal simulations, ensuring that the interaction between the various components can be accurately expressed. Through global modeling, the connection and function between the various components of the battery system can be fully reflected, improving the accuracy and operability of the simulation, and providing a comprehensive digital platform that can perform multi-dimensional analysis such as electrical and thermal, thereby enhancing the versatility of the model.

[0036] More specifically, based on the established digital model, numerical simulation of current conduction (such as finite element analysis) is carried out to analyze the current distribution, conductivity, contact resistance, etc. of the battery under different working conditions, simulate the flow path of current through the internal components of the battery (such as battery cells, conductive connectors, etc.), and calculate the electrical performance of each component. Through the simulation results, the electrical interaction factors between the various components of the battery cell are extracted, including current distribution, voltage changes, battery internal resistance, etc., and how the electrical properties of different components interact with each other and affect the overall performance of the battery are analyzed. The current conduction simulation can reveal the electrical characteristics of the various components of the battery and help evaluate the performance of the battery under working conditions. By analyzing the electrical influencing factors, the connection method between battery components can be optimized and the electrical efficiency of the battery can be improved. The electrical simulation results provide an in-depth analysis of the electrical performance of the battery and can identify potential problems in advance. Based on the electrical influencing factors, the electrical connections inside the battery can be optimized to improve the performance and stability of the battery.

[0037] More specifically, based on the digital model of the battery and combined with working environment information (such as temperature, humidity, etc.), heat transfer simulation is performed. The basic theories of heat conduction, convection and radiation are used to simulate the heat distribution of each component inside the battery, analyze how heat is transferred from one component to another, and evaluate the efficiency of the thermal management system. According to the results of the thermal simulation, the mutual influence factors of the various components of the battery cell in the thermal field dimension are generated, including temperature distribution, heat flux density, thermal stress, etc., and how the various components affect the thermal performance of the battery are analyzed. Hidden dangers that may lead to overheating or thermal runaway are sought. The thermal performance of the battery has a key impact on its safety and life. Through heat transfer simulation, problems in thermal management can be discovered and solved in advance. Analyzing the mutual influence of thermal fields helps to design more effective thermal management strategies, such as radiator design or battery layout adjustment. Heat transfer simulation provides thermal performance data of the battery under different working environments, helps optimize the thermal management design of the battery, and by optimizing the thermal management strategy, avoids battery overheating or overcooling, extends battery life and improves performance.

[0038] It is understandable that this process can comprehensively evaluate all aspects of the battery system, from electrical performance to optimization of the thermal management system, through precise battery digital modeling, electrical and thermal simulation analysis, providing strong support for battery design, optimization and fault warning.

[0039] Preferably, the step of performing current conduction simulation and analysis on the digital modeling of the battery to generate mutual influence factors of various components of the battery cell in the electrical dimension includes: S141: performing current conduction simulation on the target battery under various operating modes based on the battery digital modeling, recording current performance data and voltage performance data of various components of the battery cell to generate electrical conduction simulation information; S142: performing time domain analysis and frequency domain analysis between battery cells on the electrical conduction simulation information to obtain electrical parameter correlation characteristics of various components of the battery cells; S143: Perform multivariate regression analysis based on the electrical parameter correlation characteristics of each component of the battery cell to generate mutual influence factors of each component of the battery cell in the electrical dimension.

[0040] Specifically, a digital battery model is used to simulate current conduction under different operating modes. Operating modes can include charging, discharging, static state, and transient overload. During the simulation process, the electrical characteristics and current transmission paths of different battery cell components (such as the positive electrode, negative electrode, current collector, separator, and casing) are considered. During the simulation, the current performance (such as current density and current distribution) and voltage performance (such as voltage drop and battery cell voltage) of each battery cell component are recorded. The current and voltage data under each operating mode are recorded and summarized in detail for subsequent analysis. The current conduction performance of the battery in different operating modes can vary greatly. Simulating multiple operating modes can fully reflect the electrical characteristics of the battery. By recording current and voltage data, detailed input data is provided for subsequent time domain analysis, frequency domain analysis, and regression analysis. Accurately recording current and voltage data under different operating modes ensures the comprehensiveness and reliability of the simulation data, providing detailed data support for subsequent electrical analysis and ensuring the accuracy of the analysis results.

[0041] More specifically, the data from the current conduction simulation is analyzed by time, and the change patterns of current and voltage over time are studied, with a focus on analyzing the fluctuation characteristics of current and voltage in different time periods, such as the increase and decrease of current during charging and the change of voltage during discharge. The current and voltage responses of the battery under instantaneous overload or frequent load changes are carefully tracked, and the time domain signal is Fourier transformed to analyze the response characteristics of current and voltage at different frequencies, find out the electrical characteristics of the battery in different frequency ranges, identify the response characteristics of the battery components to signals of different frequencies, and evaluate the battery's high frequency (such as instantaneous load) and low frequency (such as normal load). Time domain analysis can evaluate the battery's current and voltage responses in different time periods, helping to analyze the battery's stability and transient response capabilities during the charge and discharge process. Frequency domain analysis can reveal the battery's electrical behavior at different frequencies, helping to identify the battery's electrical resonance and impedance characteristics, and is suitable for high-frequency application environments. Time domain analysis and frequency domain analysis can evaluate the battery's electrical characteristics under dynamic conditions and identify dynamic problems with the battery (such as overheating and transient voltage drops). By combining time domain and frequency domain analysis, the battery's electrical characteristics can be comprehensively analyzed, providing a basis for subsequent electrical optimization design.

[0042] More specifically, the electrical parameters of each component of the battery cell (such as resistance, conductance, capacitance, current density, contact resistance, etc.) are extracted from time domain analysis and frequency domain analysis, and the relationship between these electrical parameters is analyzed. For example, the electrical influence between the positive and negative electrodes, the electrical conduction relationship between the current collector and the battery casing, etc. are analyzed. The multivariate regression analysis method in statistics is used to establish an electrical parameter relationship model between the various components of the battery cell, analyze how the changes in the electrical parameters of each component affect the electrical performance of the entire battery system, calculate the mutual influence factors of each battery cell component, and through regression analysis, find out the influence rules and weights between the electrical performance of each component of the battery cell. Multivariate regression analysis can quantify the mutual influence between each battery cell component and provide a scientific basis for the optimization of electrical performance. Through regression analysis, a mathematical model of the electrical parameters between the various components of the battery cell can be established to provide guidance for subsequent design optimization. Through regression analysis, the electrical interactions and influencing factors between the battery cell components are clarified, which helps to optimize battery design. The generated mutual influence factors can be used as the basis for subsequent battery performance optimization and help identify and solve electrical problems of batteries in different usage scenarios.

[0043] It is understandable that this process comprehensively evaluates the mutual influence of battery cell components in the electrical dimension through current conduction simulation, time domain and frequency domain analysis, and multivariate regression analysis. The specific steps range from simulation of working modes to multi-dimensional analysis of electrical parameters, and finally extracts the mutual influence factors between battery cell components, deeply understands the electrical performance of the battery under different working conditions, and provides a basis for optimized design. These analysis results help to improve the stability, efficiency and life of the battery, and provide strong support for the performance optimization of the battery system.

[0044] Preferably, the step of simulating and analyzing heat transfer of the battery digital modeling in combination with the working environment information to generate mutual influence factors of various components of the battery cell in the thermal field dimension includes: S151: Analyzing the thermal field spatial characteristics of the working environment information, and performing spatial environment constraints on the heat transfer effect on the battery digital modeling according to the analysis results; S152: Performing heat transfer simulation on the digital model of the battery through finite element analysis, recording heat transfer performance data of various components of the battery cell corresponding to various operating modes, to generate heat transfer simulation information; S153: Vectorizing the heat transfer simulation information to obtain a heat transfer characteristic matrix, and constructing an adjacency matrix corresponding to the heat transfer characteristic matrix; S154: Obtain key vector clusters of the heat transfer characteristic matrix through cluster analysis of the adjacency matrix, and calculate the temperature distribution of each component of the battery cell as it changes with working time based on each key vector cluster to determine the mutual influence factors of each component of the battery cell in the thermal field dimension.

[0045] Specifically, working environment data (such as ambient temperature, humidity, airflow, radiation, etc.) is collected and, based on this data, the thermal field characteristics of the battery's exterior and interior are analyzed to determine heat conduction boundary conditions, such as the heat exchange pattern between the battery's exterior and the environment, the thermal conductivity and heat capacity of each battery cell component, etc. Based on the spatial characteristics of the thermal field, the heat transfer boundary conditions for the battery digital modeling are set, and the influence of the battery's external environment (such as air cooling, liquid cooling, or natural heat dissipation) is considered. The battery model is spatially restricted based on the thermal field characteristics to ensure that the model can reflect the heat transfer of the battery in the actual working environment. Heat transfer restrictions related to the working environment are added to the digital modeling, such as the direction of heat flow and the distribution of heat sources. Analyzing the thermal field characteristics of the working environment can help establish a heat exchange model between the battery's interior and external environment, ensuring that the digital modeling is consistent with the actual situation. Through spatial environmental restrictions, the thermal response of the battery in different environments can be simulated, providing accurate heat transfer data for subsequent analysis. This step can accurately consider the impact of the external environment on battery heat transfer, ensure the accuracy of thermal simulation, and provide reasonable heat transfer boundary conditions for finite element analysis, thereby improving simulation accuracy.

[0046] More specifically, finite element analysis (FEA) is used to simulate heat transfer in battery models. The simulation considers the thermal behavior of different battery components (such as the positive electrode, negative electrode, separator, and current collector) and different operating modes (such as charging, discharging, static, and overload). Heat transfer mechanisms such as heat conduction, convection, and radiation are considered during the simulation process, simulating the temperature changes and heat flow distribution of each battery component. Under different operating modes, the thermal transfer performance data of each battery component, including temperature, heat flow, and thermal conductivity, is recorded. The thermal behavior of different components under various operating modes is summarized to generate heat transfer simulation information. The finite element method can accurately simulate complex heat transfer processes, especially considering the internal geometry of the battery and its components and different operating modes. The heat transfer characteristics under different operating modes vary significantly. Recording thermal data under different modes helps to fully understand the battery's thermal behavior. Finite element analysis provides highly accurate heat transfer simulation data, ensuring a comprehensive understanding of the battery's thermal behavior. The generated heat transfer simulation information provides rich data support for subsequent analysis and helps identify thermal management issues of the battery system under different operating conditions.

[0047] More specifically, the heat transfer simulation data (such as temperature, heat flow, etc.) is converted into vector form for subsequent data processing and analysis, and the heat transfer behavior of each battery component is represented as a vector to ensure that the heat transfer relationship between the components can be expressed in the mathematical model. The heat transfer characteristics of each component (such as heat flux density, temperature change, etc.) are composed into a heat transfer feature matrix. Each element in the matrix represents the heat transfer relationship between two components. The matrix elements are filled according to the degree of thermal coupling between the components. The heat transfer feature matrix is ​​converted into an adjacency matrix. The elements in the adjacency matrix represent the strength of the heat transfer relationship between the components (such as thermal coupling strength). Each node of the adjacency matrix represents a battery component, and the edges in the matrix represent the heat transfer path. Vectorization can convert complex heat transfer information into a mathematical model for subsequent analysis. The feature matrix and adjacency matrix can clearly express the heat transfer relationship between the components, providing a basis for subsequent cluster analysis. By vectorization and constructing the feature matrix, complex heat transfer data is simplified and structured, which is convenient for further analysis and optimization. The adjacency matrix clearly shows the heat transfer coupling relationship between the components, helping to identify the key heat transfer paths in the system.

[0048] More specifically, cluster analysis is performed on the adjacency matrix to identify key vector clusters in the heat transfer feature matrix. These clusters represent components or combinations of components that play an important role in heat transfer. Cluster analysis can use algorithms such as K-means, hierarchical clustering, or spectral clustering to identify the main heat flow paths and key components in heat transfer. Based on the clustering results, the temperature distribution of each component in the battery cell is analyzed over time. Through time-stepping simulation, the temperature evolution of each component in the battery cell under different operating modes is calculated. The calculation results will provide detailed information on battery thermal management and help identify the key components and time patterns of temperature changes. Cluster analysis can extract key vector clusters from complex heat transfer information and focus on the most important heat transfer paths. Calculating temperature changes over time can help discover potential problems in battery thermal management and optimize battery design. Cluster analysis can effectively identify key components and paths in heat transfer, providing a basis for battery thermal management optimization. Through temperature distribution calculation, the temperature evolution of different battery components can be predicted, the thermal management system can be optimized, and the battery life can be extended.

[0049] It is understandable that this process, through heat transfer simulation and analysis, combined with environmental characteristics and working modes, gradually conducts heat transfer simulation, data vectorization, cluster analysis and temperature calculation, and finally determines the mutual influence factors of various components of the battery cell in the thermal field dimension. This series of analysis methods can comprehensively evaluate the thermal management performance of the battery under different working environments, help optimize the battery design, and improve its thermal stability and efficiency.

[0050] Preferably, the step of continuously collecting the operating electrical parameters and temperature monitoring data of the target battery, and identifying abnormal information in combination with the mutual influence factors of the components of the battery cell to obtain the abnormal information annotation set of the target battery includes: S21: Continuously collect the operating electrical parameters and temperature monitoring data of the target battery through the pre-transmitted electrical monitoring module and temperature sensing module, and assign a timestamp to the collected operating electrical parameters and temperature monitoring data; S22: Arranging the operating electrical parameters and temperature monitoring data at each moment in time sequence according to the timestamp, and aligning the operating electrical parameters and temperature monitoring data at each moment according to the timestamp to obtain battery monitoring information; S23: Constructing corresponding electrical characteristic curves, temperature characteristic curves, and electrical-temperature mapping characteristic curves based on the battery monitoring information; S24: performing characteristic analysis of the electrical characteristic curve in terms of curve trend, curve fluctuation, and curve period, and evaluating the conformity of the characteristic analysis results with respect to the spatiotemporal correlation of electrical conduction based on the mutual influence factors of the components of the battery cell in the electrical dimension, so as to obtain an electrical anomaly index at each moment; S25: performing curvature calculation and second-order derivative analysis on the temperature characteristic curve, and evaluating the conformity of the temporal and spatial correlation of thermal field transmission on the analysis results based on the mutual influence factors of the components of the battery cell in the thermal field dimension, so as to obtain the thermal field anomaly index at each moment; S26: performing consistency analysis on the electrical anomaly index and the thermal field anomaly index at each moment to construct an anomaly evaluation consistency curve, and performing curve matching processing on the anomaly evaluation consistency curve according to the electrical-temperature mapping characteristic curve to obtain the curve matching degree at each moment; S27: Annotate the battery monitoring information for abnormal situations according to the curve matching degree at each moment to generate an abnormal information annotation set.

[0051] Specifically, during the operation of the target battery, the electrical monitoring module and the temperature sensing module are used to continuously collect the battery's operating electrical parameters (such as voltage, current, power, etc.) and temperature monitoring data (such as cell temperature, ambient temperature, etc.). For each collected working electrical parameter and temperature monitoring data, a corresponding timestamp is added to ensure the time sequence and timeliness of the data. The assignment of timestamps can ensure that the electrical parameters and temperature data are compared and analyzed within the same time frame, ensuring the time sequence and consistency of the data. Real-time collection and labeling of timestamp data helps to analyze the performance of the battery at different time points and capture potential abnormal behaviors. Timestamps ensure the synchronization of various data sources, facilitating subsequent time series analysis. Real-time data collection and timestamp assignment provide sufficient time information support for subsequent abnormal information identification.

[0052] More specifically, the working electrical parameters and temperature monitoring data at each time point are arranged in timestamp order to ensure that the time sequence of the data is consistent. The working electrical parameters and temperature monitoring data from different sources are aligned to ensure that the electrical and temperature data at the same time point are matched during analysis. Arranging and aligning the data in chronological order can ensure that the relationship between electrical parameters and temperature data is correctly reflected in the subsequent analysis process. The alignment process can ensure the information integrity of each data source at the same time point, which is conducive to more accurate modeling and analysis. Through time series arrangement and data alignment, accurate comparison of battery monitoring data can be achieved, supporting subsequent abnormality analysis, ensuring the alignment of electrical and temperature data at the time point, and providing accurate data for further feature extraction.

[0053] More specifically, based on electrical monitoring data (such as current, voltage, etc.), the battery's electrical characteristic curve is constructed to describe the battery's electrical performance under different working conditions. Based on the temperature monitoring data, the battery's temperature characteristic curve is constructed to reflect the temperature changes of various battery components at different time points. The electrical monitoring data is combined with the temperature data to construct a mapping characteristic curve between electrical and temperature to show how electrical changes affect the battery's temperature distribution. By constructing electrical, temperature, and electrical-temperature mapping curves, the battery's operating characteristics can be analyzed from multiple dimensions. These curves provide a basis for subsequent abnormal behavior analysis and help discover abnormal patterns of the battery. The electrical characteristics, temperature characteristics, and electrical-temperature mapping curves can provide a comprehensive perspective for subsequent abnormality detection and optimization. Through these characteristic curves, changes in the battery during operation can be effectively tracked, facilitating abnormality detection.

[0054] More specifically, the electrical characteristic curve is subjected to trend analysis (changing trend of voltage and current), fluctuation analysis (fluctuation amplitude of electrical parameters), and periodic analysis (periodic change of electrical parameters). Based on the mutual influence factors of the various components of the battery cell, the correlation of the electrical characteristic analysis results in the time and space dimensions is evaluated. According to the analysis results, the electrical anomaly index is calculated at each moment, which indicates the degree of abnormality of the battery's electrical behavior at the current moment. Analyzing the curve trend, fluctuation and periodic change helps to identify abnormal fluctuations in battery operation. Based on the mutual influence factors between components, the temporal and spatial correlation of electrical behavior is evaluated, which helps to accurately identify the source of the anomaly. Through the calculation of the electrical anomaly index, abnormal behavior in the battery system can be discovered in time, and a reference can be provided for subsequent maintenance. Based on the comprehensive analysis of the electrical characteristic curve, the abnormal mode of the battery system can be captured, and the accuracy of the early warning can be improved.

[0055] More specifically, the curvature of the temperature characteristic curve is calculated to identify the accelerated change points of temperature change to judge abnormal temperature changes. The second-order derivative analysis of the temperature characteristic curve is performed to capture the acceleration and change trend of temperature change. According to the heat transfer influencing factors of each component of the battery cell, the spatiotemporal correlation between temperature change and thermal field transfer is evaluated, and the thermal field anomaly index is calculated. The curvature and second-order derivative can accurately identify the rate of change and abnormal fluctuation of temperature, providing sensitivity for thermal anomaly detection. Based on the spatiotemporal correlation of thermal field transfer, the abnormal degree of battery temperature is evaluated. Through curvature and second-order derivative analysis, abnormal trends of battery temperature changes can be discovered in time, helping to discover potential thermal management problems early. The calculation of the thermal field anomaly index provides accurate data support for thermal management optimization.

[0056] More specifically, a consistency analysis is performed on the electrical anomaly index and the thermal field anomaly index to check whether there are correlated abnormal behaviors between the two at the same time. Based on the results of the consistency analysis, an abnormality assessment consistency curve is constructed to reflect the synchronization of electrical and thermal field abnormal behaviors. According to the electrical-temperature mapping characteristic curve, the abnormality assessment consistency curve is matched and processed, and the curve matching degree at each moment is calculated. The consistency analysis can combine electrical and thermal abnormal behaviors to provide a full range of abnormality assessments. Through curve matching, the severity of battery abnormalities can be judged more accurately. Combining electrical and thermal field abnormalities can comprehensively evaluate the health status of the battery and predict potential failures in advance, thereby improving the consistency and accuracy of abnormality assessments and helping to effectively identify potential abnormal situations.

[0057] More specifically, the degree of curve matching determines whether an abnormality exists. If the degree of matching is low, it is marked as an abnormal situation. The marked abnormal situation and the corresponding time point are recorded in the abnormal information annotation set to facilitate subsequent analysis and tracking. Anomaly annotation helps record abnormal conditions in battery operation, providing data support for subsequent analysis and processing. Through abnormal annotation, the system can be warned of potential problems in real time. The abnormal annotation set can obtain battery abnormal information in real time and respond in advance. The abnormal information annotation set supports battery health monitoring, fault diagnosis, and optimization.

[0058] Preferably, the step of sending the abnormal information annotation set to a cloud processing platform at predetermined intervals to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information includes: S31: Dual monitoring of the abnormal information annotation set at the current moment in terms of the frequency and quantity of abnormal situation annotations is performed to obtain a risk weight of the abnormal information annotation set, and determining whether the abnormal information annotation set at the current moment needs to be sent in advance based on the risk weight; S32: When the time from the last sending reaches a predetermined time, the abnormal information annotation set is sent to the cloud processing platform; S33: Performing real-time analysis and multi-scale periodic evolution of the battery health status on the abnormal information annotation set using a pre-trained LSTM long short-term memory network model to obtain the battery health assessment result displayed by the abnormal information annotation set corresponding to the target battery in the current time period, as well as theoretical evolution information displayed in several future time periods; S34: tracing the degradation factors of the target battery according to the theoretical evolution information displayed in the time period of each scale, so as to obtain the potential hidden danger factors of the target battery at the current moment; S35: Perform confidence verification on the potential hidden danger factor according to the battery health assessment result to generate battery health feedback information.

[0059] Specifically, the frequency and quantity analysis of the abnormal information annotation set at each moment is performed. The frequency analysis checks the number of occurrences of abnormal situations, while the quantity analysis focuses on the types and number of abnormal situations. The risk weight of each annotation set is calculated based on the monitored frequency and quantity information combined with the set rules. Annotation sets with high risk weights indicate that the battery health is poor and there may be potential risks. If the risk weight of the abnormal information annotation set at a certain moment exceeds the set threshold, the early sending mechanism is triggered to send the abnormal annotation information at that moment to the cloud platform. Through the dual monitoring of frequency and quantity, potential abnormal situations can be discovered in time, and possible battery failures can be warned in advance. The calculation of risk weights can dynamically evaluate the current health status of the battery and ensure the timely processing of abnormal data. Through dual monitoring, it is possible to more accurately judge whether the battery is in a risky state, improve the system's response speed to abnormalities, determine whether to send in advance based on the risk weight, reduce unnecessary network load, and optimize the data transmission process.

[0060] More specifically, a fixed time interval is set. When the current time reaches the predetermined time threshold from the last transmission, the sending mechanism is triggered, and the abnormal information annotation set at the current moment is sent to the cloud processing platform through the network for further health status analysis and expected evolution. Data transmission at the predetermined time interval can ensure that the abnormal information is transmitted to the cloud platform in time for subsequent analysis. Scheduled transmission reduces unnecessary frequent sending operations and improves the efficiency of data transmission. Sending at a predetermined time ensures real-time performance while avoiding excessively frequent data transmission, ensuring that data is sent to the cloud platform for analysis in a timely manner, and ensuring that the battery health status can be regularly evaluated.

[0061] More specifically, the abnormal information annotation set at the current moment is input into the trained LSTM model, which can process time series data and perform real-time evaluation of the battery health status. The LSTM model not only analyzes the health status at the current moment, but also performs multi-scale periodic evolution predictions, that is, predicts the health changes of the battery in a period of time in the future, outputs the current battery health assessment results, and displays the predicted information of the battery health status in different time scales in the future. The LSTM model can process complex time series data and effectively capture the changing trend of the battery health status. Through multi-scale analysis, it can predict the battery health in different time spans and foresee potential problems in time. The long and short-term memory characteristics of LSTM enable the historical status of the battery to affect future predictions, thereby improving the accuracy of health status assessment. Multi-scale evolution analysis can predict the health changes of the battery in a certain period of time in the future and identify potential failure risks in advance.

[0062] More specifically, based on the future battery health evolution information predicted by the LSTM model, the degradation factors that may lead to the deterioration of battery health are analyzed. These factors may include temperature, charging cycles, over-discharge, etc. The results of traceability analysis are used to identify the potential hidden dangers of the current battery and find out the root causes of battery degradation. By tracing the degradation factors, the causes of changes in battery health can be traced and the hidden dangers of battery degradation can be discovered in time. Tracing analysis can deeply understand the key factors affecting battery health and support more effective prevention and maintenance measures. Through traceability analysis, potential battery problems can be accurately identified, providing a basis for subsequent maintenance and optimization. By understanding the degradation factors, measures can be taken in advance to reduce the occurrence of battery failures.

[0063] More specifically, confidence verification is performed on potential hidden danger factors to evaluate whether they actually affect battery health. The reliability of hidden dangers is verified based on probability models or other statistical methods, and battery health feedback information is generated based on the confidence verification results. The feedback information includes the current health status of the battery, potential hidden dangers, and possible future health evolution trends. Confidence verification can improve the accuracy of health assessment results and ensure the reliability of hidden danger identification. By generating battery health feedback, comprehensive battery health status information can be provided to users or maintenance teams. Through confidence verification, the accuracy and effectiveness of battery health feedback can be ensured. Battery health feedback not only includes the current status, but also includes future evolution trends, providing strong support for decision-making.

[0064] It is understandable that the entire process combines electrical and thermal field monitoring information through data collection, risk assessment, LSTM prediction, degradation factor analysis and confidence verification, providing all-round support for battery health monitoring. This method can not only monitor the battery status in real time, but also predict future health changes of the battery, providing the battery management system with intelligent and accurate health assessment and maintenance recommendations.

[0065] Preferably, the step of tracing the degradation factors of the target battery according to the theoretical evolution information displayed in the time period of each scale to obtain the potential hidden danger factors of the target battery at the current moment includes: S341: extracting abnormal features from the theoretical evolution information displayed within the time period of each scale to obtain a predicted abnormality list, and performing abnormal pattern analysis on the predicted abnormality list to generate semantic expression information corresponding to the predicted abnormality list based on the analysis results; S342: Performing a battery health degradation analysis on the target battery according to the predicted anomaly list and the semantic expression information to generate a battery health degradation curve; S343: Deploying parameters for a pre-built battery degradation model based on the battery health assessment result, and matching the expected battery health degradation curve to obtain a degradation deviation characteristic value of the target battery; S344: performing a correlation analysis on the degradation deviation characteristic value with various preset degradation factors based on a pre-built battery health degradation knowledge base, so as to assign a deviation characteristic contribution degree to each preset degradation factor; S345: Combining various preset degradation factors for several rounds based on their deviation characteristic contributions, and analyzing the synergistic feasibility of the combinations to ultimately obtain potential hidden danger factors of the target battery at the current moment.

[0066] Specifically, based on the battery health evolution data within the multi-scale time period output by the LSTM model, abnormal features are extracted. For example, possible features include sudden changes in battery health indicators and trends that deviate from normal trajectories. The extracted abnormal features are summarized to form a predicted abnormality list, indicating abnormal situations that may exist at different time scales. The abnormal patterns in the predicted abnormality list are analyzed to identify the regularities and patterns of the abnormalities. For example, whether a specific abnormality is related to specific operating conditions (such as charging speed, temperature, etc.) is determined. Based on the analysis results, the predicted abnormality pattern is converted into understandable semantic expression information. This information makes it easier for users or maintenance personnel to understand the causes and trends of the abnormalities. By extracting abnormal features and analyzing abnormal patterns, key issues in battery health changes can be more accurately identified. Semantic expression enables technicians or decision makers to quickly understand the potential causes and possible impacts of abnormalities, helping to make better decisions. Multi-scale abnormal feature extraction can accurately capture abnormal fluctuations in battery health status and detect potential problems in advance. By generating semantic expression information, the readability and operability of abnormal information are enhanced, facilitating communication with other systems or personnel.

[0067] More specifically, the key abnormal features and semantic expression information obtained from the predicted abnormality list are used to perform battery health expected decline analysis. This analyzes how the battery will decline over time under future operating conditions. Based on the analysis results, a battery health expected decline curve is drawn to reflect the changes in the battery's health status at different time points. Through expected decline analysis, the battery's health decline trend can be identified in advance, helping the battery management system to take optimization measures in advance. The decline curve provides a quantitative representation of battery decline, which facilitates the evaluation of battery health changes in long-term operation. The generated battery health expected decline curve can more accurately predict future battery health changes and provide data support for battery maintenance and replacement. Through the expected decline curve, the battery management system can make maintenance, replacement and other decisions based on accurate data to reduce invalid operations.

[0068] More specifically, based on the results of the battery health assessment, the parameters of the battery degradation model are adjusted or deployed. The model has been pre-built based on a large amount of historical data to simulate the battery degradation process. The health expected degradation curve is matched with the degradation model, and the deviation between the two is analyzed to obtain the degradation deviation characteristic value. By deploying the parameters of the health assessment results with the pre-built degradation model, the accuracy and practical relevance of the model can be ensured. The matching process can effectively reveal the difference between the actual battery degradation process and the theoretical model, providing key data for subsequent analysis. By matching the actual health data with the degradation model, it is ensured that the model can accurately reflect the degradation characteristics of the battery. The degradation deviation characteristic value helps to further quantify the anomalies in the degradation process and guide subsequent maintenance and prediction.

[0069] More specifically, based on the battery health degradation knowledge base, the relationship between the degradation deviation characteristic value and different degradation factors is analyzed. The degradation factors may include temperature fluctuations, overcharging, depth of discharge, etc. According to the analysis results, corresponding deviation characteristic contribution degrees are assigned to each degradation factor, indicating the contribution degree of each factor to battery degradation. Correlation analysis can help the system fully understand which factors have the greatest impact on battery degradation, so as to better manage battery health. By assigning deviation characteristic contribution degrees, the role of each degradation factor can be quantitatively evaluated, providing a basis for optimizing management strategies. Analyzing the contribution of each degradation factor makes the battery degradation analysis more comprehensive and provides accurate data support for battery management. According to the contribution degrees of various degradation factors, battery use and maintenance strategies can be optimized to extend battery life.

[0070] More specifically, several rounds of combination analysis are performed based on the contribution of the deviation characteristics of various degradation factors. Each round of combination analysis considers the combined effects of different degradation factors, conducts a collaborative feasibility analysis on each factor combination, and evaluates whether the combined effects of different degradation factors can effectively explain the potential hidden dangers of the battery. Ultimately, by combining the effects of various degradation factors, the potential hidden danger factors that may exist in the battery at the current moment are identified. Through multiple rounds of combination analysis, the combined effects of different degradation factors can be more comprehensively considered, avoiding the misleading effects of a single factor. Through collaborative feasibility analysis, the hidden danger factors of the battery can be accurately identified, providing strong support for battery health management. Combination analysis and collaborative feasibility analysis help to reveal potential health hazards of batteries and improve management accuracy. The identified potential hidden danger factors will help decision makers to carry out more targeted maintenance and optimization, improving the efficiency and safety of battery use.

[0071] It's clear that through this series of steps, the system can comprehensively analyze the various factors affecting battery degradation based on battery health assessment, degradation modeling, correlation analysis, and potential risk identification, ultimately achieving accurate battery health warning and management. This process effectively combines data analysis, predictive models, and knowledge base analysis, providing a scientific basis for long-term battery health management.

[0072] Preferably, the steps of performing a multi-level gradient management strategy analysis on the battery health feedback information, generating a battery management strategy, and deploying the strategy to the management system of the target battery via wireless data include: S41: performing a first-level management countermeasure analysis based on each potential risk factor in the battery health feedback information to generate a first-level battery management countermeasure; S42: Based on the first-level battery management countermeasures, the battery health feedback information is subjected to an estimation of the effect of potential hidden danger factors that are inconsistent with expectations, so as to obtain several possible countermeasure effects; S43: performing a correction analysis of potential hidden danger factors on the target battery based on the effects of various possible countermeasures, and performing a second-level management countermeasure analysis based on the corrected potential hidden danger factors to generate a second-level battery management countermeasure; S44: Repeat the above steps to obtain battery management strategies with several gradients that meet the requirements, which together constitute a battery management strategy, and deploy it to the management system of the target battery via wireless data to remotely manage the target battery.

[0073] Specifically, various potential hidden danger factors are identified from the battery health feedback information, such as battery overcharging, excessive temperature, excessive depth of discharge, etc., and corresponding preliminary management countermeasures are formulated for each potential hidden danger factor. For example, for the overcharging problem, the countermeasure is to adjust the charging strategy or limit the charging time; for the problem of excessive temperature, it will involve optimizing the heat dissipation design or adjusting the working environment, etc. The effectiveness of the formulated first-tier countermeasures is evaluated to determine whether they can effectively reduce the hidden danger factors and improve battery health. Through the analysis of battery health feedback information, potential battery problems can be identified early and preliminary management countermeasures can be taken to avoid the expansion of problems. The first-tier management countermeasures are usually simpler and easy to implement quickly, which helps to effectively intervene in battery health in the early stages. Through the first-tier management countermeasures, potential problems can be effectively identified and eliminated, and the probability of serious battery failures can be reduced. Management countermeasures for preliminary problems can respond quickly and deal with possible battery health problems in a timely manner.

[0074] More specifically, the first-gradient management countermeasures are applied to the battery health feedback information to infer their possible effects. This includes simulating various changes that may occur in potential hidden danger factors after the implementation of management countermeasures. Based on the inferred effects, several possible countermeasure effects are generated. For example, a certain management countermeasure may achieve good results in temperature control, but poor results in charging speed control. Different management countermeasures may have different effects on different hidden danger factors. By inferring their effects, the success probability of the preliminary countermeasures can be evaluated more clearly. By simulating different effect scenarios, multiple estimates can be made before the countermeasures are implemented to avoid risks caused by substandard countermeasure effects. Effect inference can provide multiple solutions to help select the optimal strategy and ensure that the management countermeasures can produce good results in practice. Through effect inference, potential management risks can be understood in advance, providing more sufficient data support for subsequent decision-making.

[0075] More specifically, based on the effectiveness of the first-tier management countermeasures, the changes in the potential hidden danger factors of the battery during actual operation are analyzed and corrected. For example, if the overcharging problem is not effectively resolved, further measures such as reducing charging frequency or strengthening battery monitoring are taken. Based on the corrected hidden danger factors, new and more detailed management countermeasures are formulated. For example, if the overtemperature problem is not fundamentally resolved, a more sophisticated temperature control system may be required, or a transition to a lower power charging strategy may be required during the battery charging process. Based on the corrected potential hidden danger factors, second-tier management countermeasures are generated. These countermeasures are generally more complex and detailed than those in the first tier. Because battery health issues may change during the implementation of management countermeasures, the hidden danger factors need to be corrected and the management strategies adjusted according to the new conditions. Through deeper analysis and optimization, the second-tier countermeasures can more effectively solve problems that the first-tier countermeasures cannot fully solve. Through the second-tier countermeasure analysis, more personalized intervention can be carried out for each hidden danger factor, improving management accuracy. By correcting and refining the management countermeasures, the battery health can be better controlled, the battery life can be extended, and the operational stability can be improved.

[0076] More specifically, the above-mentioned gradient analysis process is repeated until the generated battery management strategy meets the required number of gradients. In each cycle, the battery health feedback information and management strategies will be further analyzed and optimized, and the management strategies of different gradients will be integrated to form a comprehensive battery management strategy. The strategies of each gradient will play a different role in the overall strategy and work together to manage the health of the battery. Through multiple cycles, the management strategies can be gradually corrected and optimized at each stage to ensure that the final strategy can cope with various problems that the battery may encounter. Multi-gradient management strategies can cover a wider range of battery health problems and ensure that the battery can be effectively managed under various working conditions. Through multi-gradient analysis and adjustment, the final battery management strategy can cope with different battery health problems and provide comprehensive solutions. After multiple iterations of management strategies, it can not only solve current problems, but also effectively prevent future battery health problems.

[0077] More specifically, the battery management strategy obtained through multi-gradient analysis is transmitted to the management system of the target battery through the wireless communication network to ensure that the strategy can be applied to battery management in real time. Through the battery management system, the battery health management strategy is remotely implemented. The system can monitor the battery status in real time and adjust it according to the preset management strategy to ensure that the battery always maintains the best condition during operation. Wireless data deployment can ensure that the management strategy can be applied to the target battery quickly and in real time to meet the needs of remote monitoring and management. Through remote management, a lot of manual operation costs can be saved and the efficiency and accuracy of battery management can be improved. Wireless data deployment makes battery management more efficient and real-time, and can be managed anywhere. Through remote management, maintenance costs can be reduced and overall operational efficiency can be improved.

[0078] It's clear that the above steps enable a refined battery health management system. Through multi-level, gradient management strategy analysis and remote deployment, we ensure battery health over the long term and promptly adjust management strategies to address potential issues. Ultimately, battery management strategies are implemented wirelessly, providing an efficient, flexible, and intelligent battery management solution.

[0079] Reference Figure 2 As shown, in a second aspect, the present invention provides a remote control system for a new energy battery, which is used to implement a remote control method for a new energy battery according to any one of the first aspects, comprising: An impact analysis module is used to obtain the physical topology of the target battery to perform digital modeling of the cell connection relationship of the target battery, and extract the mutual influence factors of the various components of the cell of the target battery based on the digital modeling; An anomaly annotation module is used to continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify anomaly information in combination with the mutual influence factors of the various components of the battery cell to obtain an anomaly information annotation set of the target battery; a health analysis module, configured to send the abnormal information annotation set to a cloud processing platform at predetermined intervals, so as to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; A countermeasure analysis module is used to perform a multi-level gradient management countermeasure analysis on the battery health feedback information, generate a battery management strategy and deploy it to the management system of the target battery through wireless data.

[0080] In this embodiment, for the specific implementation of each module in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A remote control method for a new energy battery, characterized in that: include: Obtaining the physical topology of a target battery to perform digital modeling of the cell connection relationship of the target battery, and extracting the mutual influence factors of the cell components of the target battery based on the digital modeling; Continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify abnormal information in combination with the mutual influencing factors of the various components of the battery cell to obtain the abnormal information annotation set of the target battery; Sending the abnormal information annotation set to a cloud processing platform at predetermined intervals to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; A multi-level gradient management strategy analysis is performed on the battery health feedback information to generate a battery management strategy and deploy it to the management system of the target battery via wireless data.

2. The remote control method for a new energy battery according to claim 1, characterized in that: The steps of obtaining the physical topology of the target battery, performing digital modeling of the cell connection relationship of the target battery, and extracting the mutual influence factors of the cell components of the target battery based on the digital modeling include: Acquiring original design information of a target battery and collecting structural data of a setting environment of the target battery to obtain working environment information of the target battery; Analyzing the spatial relationship between components of the battery cell based on the original design information, and converting the analysis results into a standardized information format to obtain the internal physical topology of the target battery; Digitally modeling the components of the battery cell according to the physical topological structure inside the target battery, and deploying the digital models in the same simulation space to connect the electrical relationships to obtain a digital model of the battery; Simulating and analyzing the current conduction of the digital model of the battery to generate mutual influence factors of various components of the battery cell in the electrical dimension; The heat transfer of the battery digital model is simulated and analyzed in combination with the working environment information to generate the mutual influence factors of the components of the battery cell in the thermal field dimension.

3. The remote control method of the new energy battery according to claim 2, characterized in that: The steps of performing current conduction simulation and analysis on the digital model of the battery to generate mutual influence factors of various components of the battery cell in the electrical dimension include: Based on the battery digital modeling, current conduction simulation is performed on the target battery under various operating modes, and current performance data and voltage performance data of each component of the battery cell are recorded to generate electrical conduction simulation information; Performing time domain analysis and frequency domain analysis on the electrical conduction simulation information between battery cells to obtain electrical parameter correlation characteristics of various components of the battery cells; Multivariate regression analysis is performed based on the correlation characteristics of the electrical parameters of each component of the battery cell to generate the mutual influence factors of each component of the battery cell in the electrical dimension.

4. The remote control method of the new energy battery according to claim 2, characterized in that: The steps of simulating and analyzing heat transfer of the battery digital modeling in combination with the working environment information to generate mutual influence factors of various components of the battery cell in the thermal field dimension include: Analyzing the thermal field spatial characteristics of the working environment information, and performing spatial environmental restrictions on the heat transfer effect on the battery digital modeling based on the analysis results; Performing heat transfer simulation on the digital model of the battery through finite element analysis, recording heat transfer performance data of various components of the battery cell corresponding to various operating modes, and generating heat transfer simulation information; Vectorizing the heat transfer simulation information to obtain a heat transfer characteristic matrix, and constructing an adjacency matrix corresponding to the heat transfer characteristic matrix; By clustering the adjacency matrix, the key vector clusters of the heat transfer characteristic matrix are obtained, and based on each key vector cluster, the temperature distribution of each component of the battery cell is calculated as it changes with the working time, so as to determine the mutual influence factors of each component of the battery cell in the thermal field dimension.

5. The remote control method of the new energy battery according to claim 1, characterized in that: The steps of continuously collecting the operating electrical parameters and temperature monitoring data of the target battery, and identifying abnormal information in combination with the mutual influencing factors of the various components of the battery cell to obtain the abnormal information annotation set of the target battery include: Continuously collect the target battery's operating electrical parameters and temperature monitoring data through the pre-transmitted electrical monitoring module and temperature sensing module, and assign a timestamp to the collected operating electrical parameters and temperature monitoring data; Arrange the working electrical parameters and temperature monitoring data at each moment in time sequence according to the timestamp, and align the working electrical parameters and temperature monitoring data at each moment according to the timestamp to obtain battery monitoring information; Constructing corresponding electrical characteristic curves, temperature characteristic curves, and electrical-temperature mapping characteristic curves based on the battery monitoring information; Performing characteristic analysis on the electrical characteristic curve for curve trend, curve fluctuation, and curve period, and evaluating the conformity of the characteristic analysis results with the spatiotemporal correlation of electrical conduction based on the mutual influence factors of the components of the battery cell in the electrical dimension, so as to obtain the electrical anomaly index at each moment; Performing curvature calculation and second-order derivative analysis on the temperature characteristic curve, and evaluating the conformity of the temporal and spatial correlation of thermal field transmission on the analysis results based on the mutual influence factors of the various components of the battery cell in the thermal field dimension, so as to obtain the thermal field anomaly index at each moment; Performing consistency analysis on the electrical anomaly index and the thermal field anomaly index at each moment to construct an anomaly evaluation consistency curve, and performing curve matching processing on the anomaly evaluation consistency curve according to the electrical-temperature mapping characteristic curve to obtain the curve matching degree at each moment; The battery monitoring information is annotated with abnormal situations according to the curve matching degree at each moment to generate an abnormal information annotation set.

6. The remote control method of the new energy battery according to claim 1, characterized in that: The steps of sending the abnormal information annotation set to a cloud processing platform at predetermined intervals to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information include: Perform dual-condition monitoring of the abnormal situation annotation frequency and quantity of the abnormal information annotation set at the current moment to obtain the risk weight of the abnormal information annotation set, and determine whether the abnormal information annotation set at the current moment needs to be sent in advance based on the risk weight; When the time from the last sending reaches a predetermined time, the abnormal information annotation set is sent to the cloud processing platform; The pre-trained LSTM long short-term memory network model is used to perform real-time analysis and multi-scale periodic evolution of the battery health status of the abnormal information annotation set, thereby obtaining the battery health assessment results displayed by the abnormal information annotation set corresponding to the target battery in the current time period, as well as the theoretical evolution information displayed in several future time periods; Tracing the degradation factors of the target battery according to the theoretical evolution information displayed in the time period of each scale to obtain the potential hidden danger factors of the target battery at the current moment; The confidence level of the potential hidden danger factor is verified based on the battery health assessment result to generate battery health feedback information.

7. The remote control method of the new energy battery according to claim 6, characterized in that: The steps of tracing the degradation factors of the target battery according to the theoretical evolution information displayed in the time period of each scale to obtain the potential hidden danger factors of the target battery at the current moment include: Extracting abnormal features from the theoretical evolution information displayed within the time period of each scale to obtain a predicted abnormality list, and performing abnormal pattern analysis on the predicted abnormality list to generate semantic expression information corresponding to the predicted abnormality list based on the analysis results; Performing a battery health decline analysis on the target battery according to the predicted anomaly list and the semantic expression information to generate a battery health decline curve; Deploying parameters of a pre-built battery degradation model based on the battery health assessment result, and matching the battery health expected degradation curve to obtain a degradation deviation characteristic value of the target battery; performing a correlation analysis of the degradation deviation characteristic value with various preset degradation factors according to a pre-built battery health degradation knowledge base, so as to assign a deviation characteristic contribution degree to each preset degradation factor; Based on the deviation characteristic contribution of each preset degradation factor, various preset degradation factors are combined for several rounds, and the synergistic feasibility of the combination is analyzed to finally obtain the potential hidden danger factors of the target battery at the current moment.

8. The remote control method for a new energy battery according to claim 6, characterized in that: The steps of performing a multi-level gradient management strategy analysis on the battery health feedback information, generating a battery management strategy, and deploying the strategy to the management system of the target battery via wireless data include: Performing a first-level management countermeasure analysis based on each potential risk factor in the battery health feedback information to generate a first-level battery management countermeasure; Based on the first-level battery management countermeasures, the battery health feedback information is subjected to an estimation of the effect of potential hidden danger factors not being consistent with expectations, so as to obtain several possible countermeasure effects; Based on the effects of various possible countermeasures, a corresponding potential hidden danger factor correction analysis is performed on the target battery, and a second-level management countermeasure analysis is performed based on the corrected potential hidden danger factors to generate a second-level battery management countermeasure; Repeat the above steps to obtain several battery management strategies with the required number of gradients, which together constitute a battery management strategy and are deployed to the management system of the target battery via wireless data to remotely manage the target battery.

9. A remote control system for new energy batteries, characterized in that: A remote control method for a new energy battery according to any one of claims 1 to 8, comprising: An impact analysis module is used to obtain the physical topology of the target battery to perform digital modeling of the cell connection relationship of the target battery, and extract the mutual influence factors of the various components of the cell of the target battery based on the digital modeling; An anomaly annotation module is used to continuously collect the operating electrical parameters and temperature monitoring data of the target battery, and identify anomaly information in combination with the mutual influence factors of the various components of the battery cell to obtain an anomaly information annotation set of the target battery; a health analysis module, configured to send the abnormal information annotation set to a cloud processing platform at predetermined intervals, so as to perform real-time analysis and expected evolution of the battery health status on the abnormal information annotation set to generate battery health feedback information; A countermeasure analysis module is used to perform a multi-level gradient management countermeasure analysis on the battery health feedback information, generate a battery management strategy and deploy it to the management system of the target battery through wireless data.

Images