Energy storage battery health status monitoring method, system and storage medium

Abstract

The present invention relates to the technical field of energy storage batteries, and in particular to a method, system and storage medium for monitoring the health status of energy storage batteries. The method comprises the following steps: obtaining material composition data of the energy storage battery; analyzing the interaction between components at the electrochemical level of the energy storage battery according to the material composition data, and predicting the interface behavior to obtain interface behavior prediction data; simulating the electrochemical impedance spectrum according to the interface behavior prediction data, and mapping the internal state and performance of the battery under different conditions to obtain battery characteristic diagram data; performing state simulation analysis on the battery performance degradation behavior under different charge and discharge states according to the battery characteristic diagram data to obtain degradation behavior simulation data; establishing a battery health status evolution model according to the operating parameters corresponding to different operating conditions and the degradation behavior simulation data; the present invention utilizes multi-source sensors and advanced data analysis technology to achieve real-time monitoring without affecting the normal operation of the battery.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage batteries, and in particular to a method, system and storage medium for monitoring the health status of an energy storage battery. Background Art

[0002] Energy storage batteries are devices that can store electrical energy and release it when needed. They play an increasingly important role in modern energy systems, especially in the field of renewable energy. Energy storage battery health status monitoring is a technical means to evaluate and manage the health status of battery systems to ensure that they operate within the normal range and optimize their performance and life. The state of health (SOH) of energy storage batteries refers to the relative level of the battery's current performance and capacity compared to its new state. SOH is usually expressed as a percentage, with 100% representing the state of a brand new battery. As the use time increases, the SOH will gradually decrease.

[0003] However, traditional methods for monitoring the health status of energy storage batteries often have the following problems: Limitations of non-invasive measurement technology: Many health status monitoring methods require interrupting the normal operation of the battery, which is unacceptable in some applications; for example, in an uninterruptible power supply (UPS) system, it is difficult to conduct a comprehensive health status assessment without affecting system operation. Real-time electrochemical impedance spectroscopy (EIS) measurement: EIS measurement usually takes a long time and is difficult to achieve real-time monitoring; for example, in a fast charging station, it is impossible to use EIS technology to evaluate the battery health status in real time; it mainly relies on simple parameters such as voltage and current, and it is difficult to fully reflect the battery health status. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a method and system for monitoring the health status of an energy storage battery to solve at least one of the above technical problems.

[0005] To achieve the above object, a method for monitoring the health status of an energy storage battery comprises the following steps:

[0006] Step S1: obtaining material composition data of the energy storage battery; analyzing the interaction between components at the electrochemical level of the energy storage battery according to the material composition data, and predicting the interface behavior, thereby obtaining interface behavior prediction data; performing electrochemical impedance spectroscopy simulation according to the interface behavior prediction data, and mapping the internal state and performance of the battery under different conditions, thereby obtaining battery characteristic diagram data;

[0007] Step S2: performing state simulation analysis on the battery performance degradation behavior under different charge and discharge states according to the battery characteristic diagram data, thereby obtaining degradation behavior simulation data; establishing a battery health state evolution model according to the operating parameters corresponding to different operating conditions and the degradation behavior simulation data;

[0008] Step S3: obtaining battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extracting features from the battery operation data, and performing health status prediction and evaluation based on state features and a battery health status evolution model, thereby obtaining health status evaluation data;

[0009] Step S4: obtaining heat distribution data inside the energy storage battery; constructing a thermal management model according to the heat distribution data; simulating the heat flow behavior inside the battery according to the thermal management model by a finite element analysis method, and performing electrochemical-thermal coupling correction to obtain heat flow path diagram data;

[0010] Step S5: Perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain optimized battery management strategy data, wherein the multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

[0011] The present invention can more accurately predict the behavior of the electrode-electrolyte interface by analyzing the composition of battery materials and their electrochemical properties, which helps to identify potential interface failure mechanisms such as gas evolution and deposition, thereby preventing possible failures in advance. The simulation of electrochemical impedance spectroscopy (EIS) provides a performance map of the battery under different operating conditions, helping researchers understand the dynamic response of the battery and its sensitivity to material and structural changes. This mapping can provide a reference for subsequent state monitoring and performance optimization. By simulating the degradation behavior of the battery under different charge and discharge states, the degradation mode of the battery under various working conditions can be identified. This prediction provides important data support for battery life management and helps to detect and prevent battery degradation in advance in actual use. This model integrates the degradation behavior simulation data with the actual operating parameters, and can provide dynamic and accurate evaluation criteria for real-time monitoring and prediction of the battery health status, helping to detect abnormal changes in the battery at an early stage. Through the data collected by multi-source sensors (such as voltage, current, temperature, etc.), the system can monitor the operating status of the battery in real time, and detect possible problems with the battery in a timely manner through feature extraction and health status assessment models, providing early warning functions. Combined with multiple sensor data, the evaluation model can comprehensively analyze the health status of the battery, including mechanical stress, electrochemical performance, and thermal characteristics. This comprehensive evaluation provides a reliable basis for battery management decisions. The thermal management model simulates the thermal flow behavior inside the battery to help identify the hot spots and temperature gradients of the battery under different operating conditions; this is crucial to improve the thermal stability and safety of the battery, extend the battery life, and reduce the risk of failure caused by overheating. By coupling the electrochemical behavior with the thermal behavior, the system can more accurately simulate the battery state in actual operation, identify and optimize the key factors affecting battery performance, and achieve more efficient battery management. By performing multi-dimensional coupling analysis of thermal management data and health status assessment data (such as thermal-electric coupling, spatiotemporal dynamic characteristics prediction, etc.), the system can generate more comprehensive and efficient battery management strategies that can not only improve the overall performance of the battery, but also extend its service life. Through the quantitative analysis of parameter sensitivity, the system can identify the factors that have the greatest impact on battery performance and help optimize the design and operating conditions, which is of great significance in the development of high-performance and durable energy storage batteries. Through the implementation of this method, the health status monitoring and management of energy storage batteries will be more accurate and efficient. Systematic analysis and multi-dimensional coupling between each step will help to achieve a comprehensive understanding and control of the battery from material composition to operating status, and optimize the safety, reliability and life of the battery. This method is not only suitable for laboratory research, but also has a wide range of practical application potential, especially in the fields of smart grids, renewable energy storage systems and electric vehicles.

[0012] The present invention also provides a system for monitoring the health status of an energy storage battery, which is used to execute the above-mentioned method for monitoring the health status of an energy storage battery. The system for monitoring the health status of an energy storage battery comprises:

[0013] The battery characteristics prediction module is used to obtain the material composition data of the energy storage battery; analyze the interaction between the components at the electrochemical level of the energy storage battery based on the material composition data, and predict the interface behavior to obtain the interface behavior prediction data; perform electrochemical impedance spectrum simulation based on the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain the battery characteristic diagram data;

[0014] The degradation behavior modeling module is used to simulate and analyze the battery performance degradation behavior under different charging and discharging conditions according to the battery characteristic diagram data, so as to obtain degradation behavior simulation data; and to establish a battery health state evolution model according to the operating parameters corresponding to different working conditions and the degradation behavior simulation data;

[0015] The real-time status assessment module is used to obtain battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extract features from battery operation data, and perform health status prediction and assessment based on status features and battery health status evolution model, thereby obtaining health status assessment data;

[0016] Thermal behavior analysis module, used to obtain the thermal distribution data inside the energy storage battery; build a thermal management model based on the thermal distribution data; simulate the thermal flow behavior inside the battery according to the thermal management model through the finite element analysis method, and perform electrochemical-thermal coupling correction to obtain thermal flow path diagram data;

[0017] The multi-dimensional optimization strategy module is used to perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain the optimized battery management strategy data. The multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

[0018] The present invention can deeply understand the behavior and performance of materials in batteries by acquiring material composition data of energy storage batteries and analyzing the interaction between components at the electrochemical level. This provides accurate basic data for subsequent prediction and management. The simulation of electrochemical impedance spectrum and battery performance mapping under different conditions can predict the interface behavior of the battery in actual use in advance, avoid potential performance degradation or failure, and thus improve the safety and reliability of the battery. By analyzing the battery characteristic diagram data, the performance degradation behavior under different charge and discharge states can be simulated. This simulation helps to identify and predict the attenuation characteristics of the battery during use in advance, thereby extending the battery life. By establishing a health state evolution model, the health state changes of the battery under different working conditions can be continuously monitored. This provides a scientific basis for real-time management and maintenance and helps to formulate more effective maintenance strategies. The battery operation data is collected by multi-source sensors, and the battery status can be monitored in real time in combination with feature extraction technology. This real-time monitoring helps to discover potential problems in a timely manner and take corresponding preventive measures. The current health state of the battery can be accurately predicted by evaluating the state characteristics and health state evolution model. This provides accurate data support for the continuous optimization and management of the battery and reduces the risk of failure. By acquiring and analyzing the thermal distribution data of energy storage batteries and building a thermal management model, the thermal management strategy of the battery can be optimized to avoid performance degradation or safety problems caused by overheating. Through electrochemical-thermal coupling correction, the thermal flow behavior inside the battery can be simulated more accurately. This coupling analysis provides a more refined optimization direction for thermal management and helps to extend the service life of the battery. Through multi-dimensional coupling analysis, including thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis, the battery management strategy can be optimized from multiple angles. This comprehensive optimization can balance different performance indicators and find the best management solution. Through multi-dimensional optimization strategies, key bottlenecks in the system can be identified and solved, the robustness and operating efficiency of the battery management system can be improved, and the battery can be ensured to work stably and efficiently under different conditions of use. Through the collaborative work of these modules, comprehensive management from material property prediction, performance degradation simulation, real-time health status monitoring to thermal behavior analysis and multi-dimensional optimization can be achieved throughout the life cycle of the energy storage battery; this systematic approach not only improves the safety and reliability of the battery, but also extends the battery life and reduces operation and maintenance costs.

[0019] The present invention also provides a storage medium for monitoring the health status of an energy storage battery, comprising:

[0020] Memory for storing computer programs;

[0021] The processor is used to implement the steps of the above-mentioned energy storage battery health status monitoring method when executing the computer program. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0023] Figure 1 A schematic diagram of the steps of the method for monitoring the health status of an energy storage battery according to the present invention;

[0024] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0025] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0026] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for monitoring the health status of an energy storage battery, the method comprising the following steps:

[0030] Step S1: obtaining material composition data of the energy storage battery; analyzing the interaction between components at the electrochemical level of the energy storage battery according to the material composition data, and predicting the interface behavior, thereby obtaining interface behavior prediction data; performing electrochemical impedance spectroscopy simulation according to the interface behavior prediction data, and mapping the internal state and performance of the battery under different conditions, thereby obtaining battery characteristic diagram data;

[0031] Step S2: performing state simulation analysis on the battery performance degradation behavior under different charge and discharge states according to the battery characteristic diagram data, thereby obtaining degradation behavior simulation data; establishing a battery health state evolution model according to the operating parameters corresponding to different operating conditions and the degradation behavior simulation data;

[0032] Step S3: obtaining battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extracting features from the battery operation data, and performing health status prediction and evaluation based on state features and a battery health status evolution model, thereby obtaining health status evaluation data;

[0033] Step S4: obtaining heat distribution data inside the energy storage battery; constructing a thermal management model according to the heat distribution data; simulating the heat flow behavior inside the battery according to the thermal management model by a finite element analysis method, and performing electrochemical-thermal coupling correction to obtain heat flow path diagram data;

[0034] Step S5: Perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain optimized battery management strategy data, wherein the multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

[0035] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for monitoring the health status of an energy storage battery according to the present invention. In this example, the method for monitoring the health status of an energy storage battery includes the following steps:

[0036] Step S1: obtaining material composition data of the energy storage battery; analyzing the interaction between components at the electrochemical level of the energy storage battery according to the material composition data, and predicting the interface behavior, thereby obtaining interface behavior prediction data; performing electrochemical impedance spectroscopy simulation according to the interface behavior prediction data, and mapping the internal state and performance of the battery under different conditions, thereby obtaining battery characteristic diagram data;

[0037] The embodiment of the present invention collects material composition data of energy storage batteries, including chemical composition and structural information of positive electrode materials, negative electrode materials, electrolytes, separators, etc. Computational chemistry methods (such as density functional theory or molecular dynamics simulation) are used to analyze the interaction between these materials to determine the mutual influence between positive and negative electrode materials and electrolytes; predict possible reaction behaviors at the material interface, such as the formation of SEI film, decomposition reaction, etc. Combined with the interface behavior prediction data, the electrochemical impedance spectroscopy (EIS) simulation tool is used to simulate the internal electrochemical state of the battery under different working conditions (such as temperature, SOC level). Map the battery performance under different conditions, and generate battery characteristic diagram data to characterize the impact of material characteristics on battery performance under different operating conditions.

[0038] Step S2: performing state simulation analysis on the battery performance degradation behavior under different charge and discharge states according to the battery characteristic diagram data, thereby obtaining degradation behavior simulation data; establishing a battery health state evolution model according to the operating parameters corresponding to different operating conditions and the degradation behavior simulation data;

[0039] The embodiment of the present invention uses the battery characteristic diagram data to simulate the degradation of battery performance under different charge and discharge conditions (such as different discharge rates and SOC cycle ranges) and analyze the key degradation mechanisms in the battery life cycle. The degradation behavior simulation data is combined with the operating parameters under different working conditions (such as temperature, load current, and charge and discharge rate) to construct a battery health state evolution model to describe the performance change trend of the battery in long-term use.

[0040] Step S3: obtaining battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extracting features from the battery operation data, and performing health status prediction and evaluation based on state features and a battery health status evolution model, thereby obtaining health status evaluation data;

[0041] During the operation of the battery, the embodiment of the present invention uses multiple sensors to collect data such as the battery's voltage, current, temperature, gas concentration, and mechanical stress. The collected battery operation data is preprocessed, including denoising, normalization, outlier detection, etc., to ensure the accuracy and availability of the data. The statistical features, time series features, and spectrum features of the preprocessed data are extracted using time domain and frequency domain analysis methods. Based on the extracted state features and the previously constructed health state evolution model, the health state is predicted and evaluated in real time to obtain the battery health state evaluation data for monitoring the current health state of the battery.

[0042] Step S4: obtaining heat distribution data inside the energy storage battery; constructing a thermal management model according to the heat distribution data; simulating the heat flow behavior inside the battery according to the thermal management model by a finite element analysis method, and performing electrochemical-thermal coupling correction to obtain heat flow path diagram data;

[0043] The embodiment of the present invention uses infrared thermal imaging technology or other thermal measurement equipment to obtain the heat distribution data inside and on the surface of the energy storage battery; based on the heat distribution data, a three-dimensional thermal management model is constructed using the finite element analysis method (FEA) to analyze the thermal conduction, convection and radiation behavior inside the battery. Based on the three-dimensional thermal management model, the thermal flow behavior inside the battery is simulated, including the analysis of the flow of cooling medium and heat transfer characteristics; electrochemical-thermal coupling factors (such as heat generation during charging and discharging) are introduced to correct the preliminary heat flow path data to obtain more accurate heat flow path diagram data.

[0044] Step S5: Perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain optimized battery management strategy data, wherein the multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

[0045] The embodiment of the present invention aligns the heat flow path diagram data with the health status assessment data in time and space, quantifies the correlation between the change in heat distribution and the degradation of battery performance, and obtains thermal-electric coupling correlation data. Using machine learning models such as time convolutional networks, a dynamic characteristic prediction model is constructed based on the time-space aligned thermal-electric data to predict the thermal distribution and health status of the battery for a period of time in the future. Through methods such as Sobol sensitivity analysis, the parameter sensitivity of the thermal management model is quantified to identify the key factors affecting battery performance; based on a multi-objective optimization algorithm (such as NSGA-II), the multi-dimensional coupling analysis data is optimized and solved to generate an optimized battery management strategy to improve the overall performance and safety of the battery.

[0046] The present invention can more accurately predict the behavior of the electrode-electrolyte interface by analyzing the composition of battery materials and their electrochemical properties, which helps to identify potential interface failure mechanisms such as gas evolution and deposition, thereby preventing possible failures in advance. The simulation of electrochemical impedance spectroscopy (EIS) provides a performance map of the battery under different operating conditions, helping researchers understand the dynamic response of the battery and its sensitivity to material and structural changes. This mapping can provide a reference for subsequent state monitoring and performance optimization. By simulating the degradation behavior of the battery under different charge and discharge states, the degradation mode of the battery under various working conditions can be identified. This prediction provides important data support for battery life management and helps to detect and prevent battery degradation in advance in actual use. This model integrates the degradation behavior simulation data with the actual operating parameters, and can provide dynamic and accurate evaluation criteria for real-time monitoring and prediction of the battery health status, helping to detect abnormal changes in the battery at an early stage. Through the data collected by multi-source sensors (such as voltage, current, temperature, etc.), the system can monitor the operating status of the battery in real time, and detect possible problems with the battery in a timely manner through feature extraction and health status assessment models, providing early warning functions. Combined with multiple sensor data, the evaluation model can comprehensively analyze the health status of the battery, including mechanical stress, electrochemical performance, and thermal characteristics. This comprehensive evaluation provides a reliable basis for battery management decisions. The thermal management model simulates the thermal flow behavior inside the battery to help identify the hot spots and temperature gradients of the battery under different operating conditions; this is crucial to improve the thermal stability and safety of the battery, extend the battery life, and reduce the risk of failure caused by overheating. By coupling the electrochemical behavior with the thermal behavior, the system can more accurately simulate the battery state in actual operation, identify and optimize the key factors affecting battery performance, and achieve more efficient battery management. By performing multi-dimensional coupling analysis of thermal management data and health status assessment data (such as thermal-electric coupling, spatiotemporal dynamic characteristics prediction, etc.), the system can generate more comprehensive and efficient battery management strategies that can not only improve the overall performance of the battery, but also extend its service life. Through the quantitative analysis of parameter sensitivity, the system can identify the factors that have the greatest impact on battery performance and help optimize the design and operating conditions, which is of great significance in the development of high-performance and durable energy storage batteries. Through the implementation of this method, the health status monitoring and management of energy storage batteries will be more accurate and efficient. Systematic analysis and multi-dimensional coupling between each step will help to achieve a comprehensive understanding and control of the battery from material composition to operating status, and optimize the safety, reliability and life of the battery. This method is not only suitable for laboratory research, but also has a wide range of practical application potential, especially in the fields of smart grids, renewable energy storage systems and electric vehicles.

[0047] Preferably, step S1 comprises the following steps:

[0048] Step S11: Acquire material composition data of the energy storage battery, including positive electrode material data, negative electrode material data, electrolyte data, and separator data;

[0049] Step S12: Calculating the band structure and state density of the electrode materials of the positive and negative electrode materials of the energy storage battery according to the material composition data based on density functional theory, thereby obtaining electronic energy level distribution data;

[0050] Step S13: simulating the atomic structure of the electrode / electrolyte interface according to the electronic energy level distribution data, thereby obtaining the interface atomic configuration data;

[0051] Step S14: constructing a molecular dynamics model of the electrode / electrolyte interface according to the material composition data and the electronic energy level distribution data; simulating the diffusion behavior of ions at the interface according to the interface atomic configuration data and the molecular dynamics model to obtain ion migration data;

[0052] Step S15: predicting charge transfer at the interface, solid electrolyte interface formation and growth behavior according to the ion migration data and the interface atomic configuration data, thereby generating interface behavior prediction data;

[0053] Step S16: Perform electrochemical impedance spectroscopy simulation based on the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain battery characteristic diagram data.

[0054] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in the embodiment of the present invention, step S1 includes the following steps:

[0055] Step S11: Acquire material composition data of the energy storage battery, including positive electrode material data, negative electrode material data, electrolyte data, and separator data;

[0056] The embodiment of the present invention obtains the material composition information of the key components of the energy storage battery, including the chemical composition, physical properties and structural characteristics of the positive electrode material, the negative electrode material, the electrolyte and the separator; the material data can be obtained through literature review, experimental testing or material database (such as Materials Project).

[0057] Step S12: Calculating the band structure and state density of the electrode materials of the positive and negative electrode materials of the energy storage battery according to the material composition data based on density functional theory, thereby obtaining electronic energy level distribution data;

[0058] The embodiment of the present invention uses density functional theory to calculate the electronic structure of the positive and negative electrode materials of the battery, especially the band structure and density of states (DOS); selects a suitable exchange-correlation function (such as PBE or HSE06), and performs structural optimization to ensure the accuracy of the calculation results. According to the calculation results, the electronic energy level distribution data of the material is obtained. These data are used to understand the electronic conduction characteristics of the material at the electrode / electrolyte interface, which has an important influence on the electrochemical performance of the battery.

[0059] Step S13: simulating the atomic structure of the electrode / electrolyte interface according to the electronic energy level distribution data, thereby obtaining the interface atomic configuration data;

[0060] The embodiment of the present invention uses energy level distribution data and atomic-level structural models to simulate the atomic configuration of the interface between the electrode material and the electrolyte. The simulation process takes into account the chemical reaction, phase change and crystal structure change at the interface, and uses the first principle or classical molecular dynamics method to simulate. The atomic arrangement of the electrode / electrolyte interface is optimized to find the lowest energy configuration and ensure the stability of the interface.

[0061] Step S14: constructing a molecular dynamics model of the electrode / electrolyte interface according to the material composition data and the electronic energy level distribution data; simulating the diffusion behavior of ions at the interface according to the interface atomic configuration data and the molecular dynamics model to obtain ion migration data;

[0062] The embodiment of the present invention constructs a molecular dynamics model of the electrode / electrolyte interface based on the above energy level distribution and interface atomic configuration data; the model should take into account the electrochemical and physical properties of the interface material, including charge distribution, interface binding energy, etc. Molecular dynamics is used to simulate the diffusion behavior of ions at the electrode / electrolyte interface, focusing on analyzing the migration path and diffusion coefficient of ions near the interface; the simulation conditions should cover ion migration under different temperatures, concentrations and electric fields to fully characterize the electrochemical behavior at the interface.

[0063] Step S15: predicting charge transfer at the interface, solid electrolyte interface formation and growth behavior according to the ion migration data and the interface atomic configuration data, thereby generating interface behavior prediction data;

[0064] The embodiment of the present invention predicts the charge transfer behavior at the interface based on ion migration data and interface atomic configuration; this includes the accumulation of interface charge, the formation of interface potential, etc.; simulates the formation and growth behavior of the solid electrolyte interface (SEI) layer, and evaluates its impact on battery performance. All simulation results are integrated to generate interface behavior prediction data; these data can be used for subsequent battery electrochemical performance analysis.

[0065] Step S16: Perform electrochemical impedance spectroscopy simulation based on the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain battery characteristic diagram data.

[0066] The embodiment of the present invention uses the aforementioned interface behavior prediction data to perform electrochemical impedance spectroscopy (EIS) simulation. EIS simulation can be used to analyze the electrochemical impedance characteristics of the battery at different frequencies; the simulation results help identify key parameters such as charge transfer resistance and ion migration impedance inside the battery. The EIS simulation results under different conditions are mapped to the state and performance inside the battery to generate battery characteristic diagram data; these characteristic diagrams can help understand the behavior of the battery under different operating conditions and are used to optimize design and performance prediction.

[0067] The present invention ensures the accuracy of subsequent simulation and calculation by obtaining detailed material data of the positive electrode, negative electrode, electrolyte and separator of the energy storage battery. Understanding the composition and characteristics of each material is the basis for building a battery model, which helps to deeply analyze the physical and chemical behavior inside the battery. Density functional theory (DFT) calculations can reveal the electronic structure of electrode materials, especially the band structure and state density. This helps to understand the conductivity, reactivity and interaction of electrode materials with electrolytes under different electrochemical conditions. Through the electronic energy level distribution data, researchers can optimize the composition and structure of materials to improve the conductivity and overall performance of batteries. This is crucial for designing efficient and stable energy storage materials. Simulating the atomic structure between electrodes and electrolytes can provide a basis for understanding the microscopic behavior of the electrode / electrolyte interface. This is of great significance for predicting electrode stability and battery life. By understanding the atomic configuration of the interface, researchers can adjust materials or battery processes, optimize the stability and performance of the electrode / electrolyte interface, and reduce the occurrence of adverse reactions. By simulating the diffusion behavior of ions at the electrode / electrolyte interface through molecular dynamics models, the ion migration path and rate at the interface can be predicted. This is crucial for optimizing the ionic conductivity and overall efficiency of batteries. Understanding the interfacial behavior during ion migration helps design battery materials with higher ionic conductivity and lower interfacial impedance, thereby improving the charge and discharge efficiency of the battery. By predicting the charge transfer, formation of the solid electrolyte interface and its growth behavior, the key factors affecting battery performance can be identified and controlled. This prediction helps design batteries with higher efficiency and longer life. Understanding the charge transfer at the interface and the behavior of the solid electrolyte interface can effectively inhibit adverse reactions at the battery interface, such as increased interface resistance or abnormal growth of the SEI (solid electrolyte interface) layer, thereby improving the stability of the battery. Electrochemical impedance spectroscopy (EIS) simulation can map the internal state and performance of the battery under different conditions to generate a battery characteristic map. This map can provide researchers with tools to gain in-depth understanding of battery behavior and help identify performance bottlenecks and optimization directions. Through the battery characteristic map, the dynamic response of the battery under various operating conditions can be comprehensively analyzed, covering multi-scale information from the material level to the interface level, which helps to develop more efficient and longer-lasting energy storage systems. These steps provide in-depth analysis tools for the design and optimization of energy storage batteries through systematic multi-scale modeling and simulation. Through in-depth research on materials, interfaces and electrochemical behaviors, it is possible to identify and control the key factors that affect battery performance, thereby optimizing battery performance and extending battery life. Especially in the development of high-efficiency batteries, this approach can provide strong support for optimizing material selection, designing more stable electrode / electrolyte interfaces, and improving overall battery efficiency.

[0068] Preferably, step S16 comprises the following steps:

[0069] Step S161: generalizing the interface behavior prediction data from the atomic scale and the molecular scale to the macro scale, and establishing a multi-scale model connecting the microscopic mechanism and the macroscopic performance, thereby obtaining cross-scale battery material performance prediction data;

[0070] The embodiment of the present invention first analyzes the interface behavior prediction data (including charge transfer, ion migration, etc.), and generalizes it from the atomic scale (such as the charge distribution of individual atoms) to the molecular scale (such as intermolecular interaction force and binding energy); uses molecular dynamics simulation tools to convert atomic-level parameters (such as diffusion coefficient, charge density) into parameters that can describe intermolecular interactions. The molecular-scale data is generalized to the macroscopic scale, and a continuous medium mechanics model (such as finite element analysis) is used to describe the behavior of the overall battery material; a multi-scale model connecting microscopic mechanisms (such as interfacial electrochemical reactions) and macroscopic performance (such as overall battery resistance and capacity) is established. This model can combine data from multiple physical scales for prediction. The multi-scale model is used to predict the performance of battery materials across scales. The model can comprehensively consider the impact of changes in microstructure on macroscopic performance (such as energy density, cycle life, etc.), thereby obtaining cross-scale battery material performance prediction data.

[0071] Step S162: identifying electrochemical process information of the interface behavior prediction data, and determining circuit elements for each process, thereby obtaining an equivalent circuit model;

[0072] The embodiment of the present invention identifies various electrochemical processes inside the battery, including charge transfer, ion diffusion, interface resistance, etc., based on the interface behavior prediction data; for each electrochemical process, the corresponding circuit elements are determined, such as resistance (R), capacitance (C), inductance (L), etc. The identified electrochemical process is mapped to the equivalent circuit model, which simplifies the complex electrochemical behavior of the battery into a combination of a group of circuit elements, and can more intuitively represent the relationship between different electrochemical processes; the equivalent circuit model is simulated using simulation software to ensure that the model can accurately reflect the actual electrochemical behavior.

[0073] Step S163: simulating the battery impedance response at different frequencies according to the equivalent circuit model to obtain a theoretical EIS spectrum; and analyzing the contribution of different battery groups to the EIS characteristics on the theoretical EIS spectrum to obtain impedance distribution data;

[0074] Based on the constructed equivalent circuit model, the embodiment of the present invention simulates the battery impedance response at different frequencies to generate a theoretical electrochemical impedance spectrum (EIS); by adjusting the frequency range, the characteristic performance of different electrochemical processes (such as interfacial charge transfer and bulk ion diffusion) in the EIS spectrum is observed. The theoretical EIS spectrum is deeply analyzed to evaluate the contribution of different battery components to the overall EIS characteristics, which includes separating the impedance components of each electrochemical process by fitting and decomposing the EIS curve to obtain detailed impedance distribution data. These data help to understand the internal electrochemical processes of the battery under different working conditions and provide a reference for optimizing battery performance.

[0075] Step S164: Perform a virtual experiment on the energy storage battery based on the battery material performance prediction data and the impedance distribution data, simulate the battery behavior under different working conditions, calculate and record the key performance indicators under each condition, and generate a mapping relationship between the battery performance and the working conditions, thereby obtaining the battery characteristic diagram data.

[0076] The embodiment of the present invention uses battery material performance prediction data and impedance distribution data to establish a virtual experimental environment on a computer, which can simulate the behavior of the battery under different working conditions; the virtual experiment includes setting different charge and discharge rates, temperatures, number of cycles and other conditions to comprehensively evaluate the performance of the battery. In the virtual experiment, the key performance indicators under each working condition, such as battery capacity, internal resistance, cycle life, etc., are calculated and recorded, and these key indicators are matched with the working conditions to generate a mapping relationship between battery performance and working conditions. Based on the results of the virtual experiment, battery characteristic diagram data is generated, which shows the performance of the battery under various conditions and can be used to optimize battery design and operation strategies.

[0077] The present invention can more comprehensively predict the performance of battery materials under actual working conditions by extending the interface behavior prediction data at the atomic scale and molecular scale to the macro scale and establishing a cross-scale model. In this way, the microscopic mechanism that affects the macroscopic performance of the battery can be identified, and the material selection and battery design can be guided. The cross-scale model can connect the microscopic mechanism and the macroscopic performance, thereby helping researchers to optimize the design of battery materials and improve the overall performance of the battery, such as energy density, cycle life and safety. By identifying the electrochemical processes in the interface behavior prediction data, determining the corresponding circuit elements for each process, and constructing an equivalent circuit model, the complex electrochemical process can be effectively simplified. This model can more intuitively describe the electrochemical behavior of the battery, which is easy to analyze and understand. The equivalent circuit model can quickly simulate the electrochemical response of the battery under different conditions, which helps to accelerate the battery design process and help engineers quickly evaluate the battery performance. By simulating the battery impedance response at different frequencies through the equivalent circuit model and generating a theoretical EIS spectrum, it can help researchers to deeply understand the impedance characteristics of the battery. By analyzing the contribution of different battery groups to the EIS characteristics, different impedance sources inside the battery can be identified, such as the impedance of the electrode interface, the material body and the electrolyte. Impedance distribution data helps researchers optimize the design of battery components and reduce unfavorable impedance sources, thereby improving the overall efficiency and stability of the battery. By simulating battery behavior under different working conditions through virtual experiments, battery performance can be predicted in the early stage of the experiment; this method not only saves time and resources, but also can find potential problems before actual testing. By recording key performance indicators under each working condition and generating a mapping relationship between battery performance and working conditions, researchers can better understand how batteries perform under different working conditions. This helps optimize the design and control strategy of batteries to meet the needs of different application scenarios. These steps can comprehensively and deeply predict and optimize the performance of energy storage batteries by constructing cross-scale models from micro to macro, simplifying equivalent circuit models of electrochemical processes, simulating electrochemical impedance spectra, and finally conducting virtual experiments. In this way, researchers can better understand the internal behavior of batteries, optimize material selection and design strategies, and improve the overall performance and stability of batteries. This comprehensive analysis method is of great significance for the development of efficient and long-lasting energy storage batteries.

[0078] Preferably, step S2 comprises the following steps:

[0079] Step S21: constructing a battery performance degradation model based on the performance parameter data set, wherein the battery performance degradation model includes a capacity attenuation model, an internal resistance growth model, and a power attenuation model;

[0080] Step S22: using the battery performance degradation model to simulate the battery performance under different charge and discharge conditions, simulating the cycle performance of the battery under different charge and discharge depths, rates and temperatures, so as to obtain degradation behavior simulation data;

[0081] Step S23: extracting the characteristics of capacity attenuation rate, internal resistance growth rate and power attenuation rate from the degradation behavior simulation data, thereby obtaining degradation characteristic data;

[0082] Step S24: establishing a battery health status indicator system according to the degradation characteristic data, and constructing a battery health status assessment model based on a fuzzy logic model;

[0083] Step S25: constructing a battery health state evolution model that can predict the changing trend of the battery health state under different working conditions based on the battery health state assessment model and the degradation behavior simulation data.

[0084] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment of the present invention, step S2 includes the following steps:

[0085] Step S21: constructing a battery performance degradation model based on the performance parameter data set, wherein the battery performance degradation model includes a capacity attenuation model, an internal resistance growth model, and a power attenuation model;

[0086] The embodiment of the present invention collects historical data of key performance parameters including battery capacity, internal resistance, power output, etc. These data can come from laboratory tests, monitoring data in actual use, or public battery performance databases; the data set is preprocessed, including noise removal, data smoothing, and outlier processing to ensure the accuracy and consistency of the data. Establish a mathematical model for predicting the change of battery capacity with cycle number, discharge depth, and temperature; the model can be based on empirical formulas, physical models, or machine learning methods. Construct a model to describe the growth of battery internal resistance over time or cycle number. Usually, the growth of internal resistance is caused by electrolyte decomposition, polarization, and accumulation of reaction products on the electrode surface; the model can use polynomial fitting, exponential decay model, or modeling method based on physical mechanism. Establish a model for the change of battery power output over time and usage conditions, mainly considering the power loss caused by increased internal resistance and capacity decay; the model can be based on the transient response of the battery, the charge and discharge characteristic curve, or a simulation-based method.

[0087] Step S22: using the battery performance degradation model to simulate the battery performance under different charge and discharge conditions, simulating the cycle performance of the battery under different charge and discharge depths, rates and temperatures, so as to obtain degradation behavior simulation data;

[0088] The embodiment of the present invention sets up a simulation environment based on the constructed capacity attenuation model, internal resistance growth model and power attenuation model; selects different charge and discharge conditions for simulation, including different charge and discharge depth (DOD), rate (C-rate), temperature and other variables. Use simulation tools (such as MATLAB / Simulink or battery simulation software) to simulate the long-term cycle performance of the battery under these conditions; record the changes in capacity, internal resistance and power of each cycle to obtain detailed degradation behavior simulation data.

[0089] Step S23: extracting the characteristics of capacity attenuation rate, internal resistance growth rate and power attenuation rate from the degradation behavior simulation data, thereby obtaining degradation characteristic data;

[0090] The embodiment of the present invention analyzes the degradation behavior simulation data and calculates key degradation characteristics such as capacity attenuation rate, internal resistance growth rate, and power attenuation rate; these characteristic values ​​reflect the degradation speed and degree of the battery under different usage conditions. The extracted degradation characteristic data are classified and stored to form a characteristic data set for subsequent analysis and model building.

[0091] Step S24: establishing a battery health status indicator system according to the degradation characteristic data, and constructing a battery health status assessment model based on a fuzzy logic model;

[0092] According to the degradation characteristic data, the embodiment of the present invention defines a set of battery state of health (SOH) indicators, including capacity retention rate, internal resistance increase ratio, power retention rate, etc. These indicators will serve as the basis for battery health status assessment. Based on fuzzy logic theory, a battery health status assessment model is constructed. The model input is degradation characteristic data (such as capacity decay rate, internal resistance growth rate), and the output is a comprehensive health status score (such as a value between 0 and 1, indicating the quality of the health status); define fuzzy rules and membership functions so that the model can handle nonlinear relationships and uncertainties; use partial degradation data to verify and optimize the fuzzy logic model to ensure the accuracy and robustness of the assessment results.

[0093] Step S25: constructing a battery health state evolution model that can predict the changing trend of the battery health state under different working conditions based on the battery health state assessment model and the degradation behavior simulation data.

[0094] The embodiment of the present invention performs time series analysis on the output of the health status assessment model, and combines the degradation behavior simulation data to construct a battery health status change trend model; uses time series models such as autoregressive moving average (ARMA) or long short-term memory network (LSTM) for prediction, and simulates the evolution of health status over time under different working conditions. The health status evolution model is trained using historical data, and the prediction accuracy of the model is evaluated using a cross-validation method; the model parameters are optimized, such as selecting appropriate lag periods, fitting functions, and regularization parameters to improve the prediction performance of the model. The impact of different operating condition changes (such as charge and discharge rates, temperature, and number of cycles) on the evolution of the battery health status is analyzed and integrated into the evolution model; by simulating different usage scenarios, a trend graph of the battery health status changing with the operating conditions is generated. According to the battery operation data collected in actual use, the health status evolution model is regularly updated to maintain the accuracy and real-time performance of the model.

[0095] The present invention can systematically analyze the performance degradation behavior of the battery in long-term use by constructing a battery performance degradation model including a capacity decay model, an internal resistance growth model and a power decay model. This model can comprehensively consider multiple influencing factors and provide a comprehensive understanding of the battery performance changes. Using the degradation model, the performance changes of the battery under different use conditions can be more accurately predicted, helping designers to identify potential degradation problems in advance and take corresponding measures to extend the battery life. By simulating the battery performance under different charge and discharge conditions (such as charge and discharge depth, rate, temperature, etc.) using the degradation model, the degradation behavior of the battery in various working environments can be evaluated. This helps to identify the impact of different working conditions on battery life and optimize the use strategy. The simulation results can provide data support for engineers and designers to help them optimize the design and use strategy of the battery to maximize the working life and performance of the battery. By extracting degradation feature data such as capacity decay rate, internal resistance growth rate and power decay rate, the degradation behavior of the battery can be accurately quantified. These quantitative data can be used as key indicators of battery health status and provide a basis for subsequent health assessment. The extraction of degradation feature data enables the health status assessment model to more accurately reflect the actual state of the battery and provide more reliable health assessment results. By establishing a battery health status assessment model based on fuzzy logic, it is possible to comprehensively consider multiple degradation feature data and assess the overall health status of the battery. The fuzzy logic model can handle uncertainty and ambiguity, making the assessment more flexible and accurate.

[0096] Providing dynamic assessment of health status: This assessment model can not only provide the current health status of the battery, but also dynamically track changes in battery health, providing a reference for maintenance and care. By constructing a battery health status evolution model, the health status change trend of the battery under different working conditions can be predicted. This model can help users understand the performance of the battery in future use and take preventive measures to extend the battery life. The evolution model can provide guidance for battery usage strategies and maintenance plans to ensure that the battery can maintain optimal performance throughout its life cycle and reduce performance degradation or failures caused by degradation. Through these steps, the degradation behavior of energy storage batteries can be comprehensively analyzed and predicted, and their health status can be evaluated. This method can not only quantify the degradation process of the battery, but also predict its future performance changes, providing important support for optimizing battery design, formulating usage strategies, and extending battery life. This is of great significance to improving the reliability and efficiency of energy storage systems.

[0097] Preferably, step S25 comprises the following steps:

[0098] Step S251: constructing a time series prediction model of the battery health state based on the autoregressive integrated moving average model according to the battery health state assessment model;

[0099] The embodiment of the present invention collects historical output data of the battery health status assessment model, including indicators such as health status score, capacity retention rate, and internal resistance change; organizes these data into a time series form to capture the changing trend of the battery health status over time. The autoregressive integrated moving average model (ARIMA) is selected as the time series prediction model. The ARIMA model combines the autoregressive (AR) and moving average (MA) parts, and can process non-stationary data through difference (I); according to the characteristics of the time series (such as seasonality and trend), the parameters of the ARIMA model are set, including the autoregressive order (p), the difference order (d), and the moving average order (q); the model parameters are determined by data fitting, so that the model can effectively capture the patterns and trends in the historical data. Use the constructed ARIMA model to make a preliminary prediction of the battery health status in the future period to obtain the predicted time series data.

[0100] Step S252: training and verifying the time series prediction model according to the degradation behavior simulation data, and optimizing the model parameters, thereby obtaining the time series model data;

[0101] The embodiment of the present invention uses degradation behavior simulation data to train the ARIMA model and adjusts the model parameters to minimize the prediction error. During the training process, the rolling window method or cross-validation method is used to ensure that the model has good prediction performance for data in different time periods. The model is applied to a test data set that has not participated in the training to evaluate its prediction accuracy and robustness. Common time series evaluation indicators such as root mean square error (RMSE) and mean absolute error (MAE) are used to quantify the performance of the model. Through grid search or other optimization methods, the parameter combination of the ARIMA model is further adjusted to find the optimal (p, d, q) value; ensure that the model can stably reflect the evolution trend of the health status in long-term predictions, and obtain the final time series model data.

[0102] Step S253: constructing a multi-factor health state evolution model based on the operating parameters corresponding to different operating conditions according to the time series model data, and extracting the impact of the operating condition change on the health state evolution, thereby obtaining the multi-factor evolution model data;

[0103] The embodiment of the present invention designs a multi-factor health state evolution model based on the time series model data and combined with the operating parameters of different working conditions (such as charge and discharge rate, temperature, number of cycles, etc.); the model should be able to comprehensively consider the impact of various factors on the health state of the battery, and simulate the future state based on time series prediction. Through sensitivity analysis or regression analysis, the impact of different working conditions on the evolution of the health state is quantified, and the key influencing factors are extracted. These influencing factors are combined with time series data to construct a complete multi-factor health state evolution model. Use a multivariate time series model (such as VAR or LSTM) to predict the health state, and compare the prediction results under different working conditions; record the specific impact of each working condition on the health state to obtain the multi-factor evolution model data.

[0104] Step S254: performing uncertainty analysis on the multi-factor evolution model data by using the Monte Carlo method, and performing confidence interval evaluation on the model prediction results, thereby obtaining uncertainty analysis data;

[0105] The embodiment of the present invention performs Monte Carlo simulation on the multi-factor evolution model data, simulates a variety of possible operating condition change scenarios, and generates a series of prediction results; through a large number of random sampling, the uncertainty of the model's response to the evolution of health status under different operating conditions is evaluated. The Monte Carlo simulation results are analyzed to calculate the confidence interval of the health status prediction under different time points and operating conditions; the evaluation of the confidence interval can help identify the credibility and potential risks of the prediction results and obtain uncertainty analysis data.

[0106] Step S255: performing model correction based on robustness and accuracy on the multi-factor evolution model data according to the uncertainty analysis data, thereby obtaining a battery health state evolution model.

[0107] The embodiment of the present invention uses uncertainty analysis data to identify parts of the multi-factor evolution model with low robustness or large prediction deviations; by adjusting the model structure or parameters, the model's robustness to changes in different operating conditions is enhanced, reducing prediction errors. The multi-factor evolution model is corrected using an iterative method, and each correction is verified using the Monte Carlo method to ensure that the model's prediction performance is improved after correction; the model is continuously optimized until the health status prediction results under different operating conditions reach the expected accuracy and stability, ultimately forming an accurate battery health status evolution model.

[0108] The present invention can capture the changing law of battery health status over time through a time series prediction model based on an autoregressive integrated moving average model (ARIMA). The ARIMA model can effectively process the trend and seasonal characteristics in time series data, thereby providing accurate health status prediction. The construction of this model enables the battery health status to be dynamically monitored, and early warning is given when an abnormality or significant degradation is about to occur, which helps to take maintenance measures in time and extend the battery life. By using degradation behavior simulation data to train and verify the time series prediction model and optimize the model parameters, the accuracy of the prediction model can be significantly improved. Model training helps to better adapt it to the changes in the actual battery health status. The optimized model can better adapt to the prediction of battery health status under different working conditions, so that the model can provide reliable prediction results in a variety of operating environments. This step can include the operating parameters of the battery under different working conditions into the analysis by constructing a multi-factor health status evolution model, so as to more comprehensively understand the influence of various factors on the battery health status. In this way, the health status changes of the battery under complex working conditions can be predicted more accurately. The multi-factor model can extract the influence of working condition changes on the battery health status, so that users can adjust the operation strategy according to the actual use conditions to maximize battery performance and life. Through the Monte Carlo method, uncertainty analysis of the multi-factor evolution model can quantify the potential errors of the model prediction results and provide confidence intervals. This makes the prediction results not only have clear values, but also include possible error ranges, thereby improving the reliability of the prediction. Uncertainty analysis and confidence interval evaluation can help users make decisions more confidently when facing model predictions, understand the reliability of the prediction results, and make adjustments when necessary. Through robustness and accuracy-based corrections, it can be ensured that the multi-factor evolution model remains highly accurate and stable in the face of different operating conditions and uncertainties. The corrected model can better cope with various challenges in practical applications. The final optimized battery health state evolution model can provide more accurate prediction results, helping users to better manage the use of batteries and avoid unnecessary losses or risks. Through these steps, a highly accurate and robust battery health state evolution model can be constructed to predict the health state changes of batteries under different operating conditions. This process not only improves the accuracy of the prediction, but also takes into account the robustness and uncertainty of the model, making the prediction results more reliable. This is of great significance for optimizing battery management strategies, extending battery life, and ensuring the stable operation of the system.

[0109] Preferably, step S3 comprises the following steps:

[0110] Step S31: collecting battery operation data through multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data;

[0111] The embodiment of the present invention installs a multi-source sensor network, including a voltage sensor, a current sensor, a temperature sensor, a gas concentration sensor (such as an H2 or O2 sensor), and a strain sensor, for monitoring the mechanical stress during battery operation; sets the sampling frequency and data transmission interval of the sensor to ensure that rapid changes during operation can be captured without excessively increasing the amount of data; collects data from each sensor in real time and transmits it to a data storage system to form a real-time operation data set of the battery.

[0112] Step S32: performing preprocessing including denoising, normalization and outlier detection on the battery operation data, thereby obtaining a battery operation data set;

[0113] The embodiment of the present invention utilizes filtering technology (such as low-pass filtering, mean filtering, etc.) to denoise the data collected by the sensor and eliminate random noise and interference in the sensor signal; and selects appropriate filter parameters to retain effective signal features in the data. The data of each sensor is normalized to eliminate the scale differences between different data dimensions so that the data can be analyzed and processed on the same scale; common methods such as minimum-maximum normalization and Z-score normalization are used to select a suitable normalization method according to the data characteristics. Statistical methods or machine learning algorithms are used to detect outliers in the operating data, such as sudden high temperatures or short-term current anomalies; the detected outliers are marked, corrected or removed to ensure the accuracy of the data.

[0114] Step S33: extracting features including statistical features, time series features and spectrum features from the battery operation data set using time domain analysis and frequency domain analysis methods, thereby obtaining a multi-dimensional feature vector;

[0115] The embodiment of the present invention calculates the basic statistical characteristics of operating data such as voltage, current, temperature, etc., such as mean, variance, skewness, kurtosis, etc.; extracts time domain characteristics such as autocorrelation and sliding average of the time series to capture the time dynamic characteristics of the data. The time series data is converted to the frequency domain through Fourier transform (FFT) to analyze the intensity and distribution of each frequency component; extract frequency domain features such as spectrum center, spectrum energy, main frequency, etc., for analyzing periodic or oscillatory behavior. The extracted time domain and frequency domain features are combined to form a multidimensional feature vector for subsequent dimensionality reduction and health status estimation.

[0116] Step S34: performing dimensionality reduction processing on the multi-dimensional feature vector through an autoencoder, and constructing a data-driven health state estimator based on the dimensionality reduction features and the battery health state evolution model;

[0117] The embodiment of the present invention uses an autoencoder to reduce the dimensionality of a multi-dimensional feature vector. An autoencoder is an unsupervised neural network that can learn a low-dimensional representation of feature data. By training the autoencoder, the main feature distribution of the data is learned, and a feature vector after dimensionality reduction is generated. Using the feature vector after dimensionality reduction as input, a data-driven health state estimator is constructed according to the battery health state evolution model. The health state estimator can use supervised learning methods, such as support vector machines (SVM), random forests (RF) or deep neural networks (DNN), and is trained and verified through historical data.

[0118] Step S35: using the health state estimator to estimate the current health state of the battery in real time, and recording the health state estimation result, so as to obtain health state estimation data;

[0119] The embodiment of the present invention inputs the currently collected feature vector into the health state estimator in real time to estimate the current health state of the battery, such as remaining capacity, internal resistance change, thermal stability, etc.; compares the estimated result with the historical state to determine the changing trend of the health state. The health state result of each estimation is recorded in the data storage system to form a series of health state estimation data; these data are used for subsequent time series prediction analysis.

[0120] Step S36: Perform a time series-based prediction of the battery health state within a future period of time on the health state estimation data, and perform a confidence interval evaluation to obtain health state evaluation data.

[0121] The embodiment of the present invention uses a time series prediction model (such as ARIMA, LSTM, etc.) based on historical health status estimation data to predict the battery health status in the future; the prediction results include health status estimation values ​​at future time points, such as remaining life, internal resistance growth trend, etc. The prediction results are evaluated by confidence intervals, and the confidence of the prediction results at different time points is determined by analyzing the uncertainty of the prediction. The evaluation results are used to guide the battery operation strategy and maintenance decisions.

[0122] The present invention can fully grasp the operation of the battery under different states by collecting various battery operation data such as voltage, current, temperature, gas concentration and mechanical stress. This provides rich basic data for subsequent health status analysis. Multi-source sensors can monitor various operating parameters of the battery in real time to ensure accurate control of the battery state, especially the operation under harsh working conditions. Through preprocessing steps such as denoising, normalization and outlier detection, noise and outliers in the data can be effectively removed to improve the quality and reliability of the data. This makes subsequent analysis more accurate. Normalization processing converts data from different sources and magnitudes into a unified standard, which helps to perform more consistent analysis in subsequent feature extraction and model construction. Through time domain analysis and frequency domain analysis methods, rich features can be extracted from the battery operation data set, including statistical features, time series features and spectral features. These features provide a comprehensive information basis for health status estimation. The feature extraction process can reveal the key behavior patterns and trends in battery operation, providing important support for accurate prediction of health status. By reducing the dimensionality of multidimensional feature vectors through autoencoders, the data dimension can be reduced while retaining important information, thereby reducing computational complexity and resource consumption. The data-driven health state estimator built based on dimensionality reduction features and battery health state evolution model can more accurately reflect the current state of the battery and improve the accuracy and robustness of the estimation. Using the health state estimator, the current health state of the battery can be estimated in real time, potential faults or performance degradation can be discovered in time, and a basis for rapid response can be provided. Recording health state estimation data accumulates valuable historical data for subsequent health state analysis, trend prediction, and fault diagnosis. By performing time series analysis on health state estimation data, the health state changes of the battery in the future can be predicted, which helps to do maintenance and management work in advance. Confidence interval evaluation can quantify the reliability of the prediction results, so that the prediction not only has a specific value, but also provides a possible error range, thereby improving the credibility of the prediction. Through these steps, a comprehensive and accurate energy storage battery health state monitoring and prediction system can be built. This system can not only monitor the current state of the battery in real time, but also make accurate future state predictions based on rich multi-source data, and provide reliable confidence interval evaluation. This multi-dimensional monitoring and prediction provides strong support for the health management and fault warning of energy storage batteries, which helps to extend the battery life and improve the reliability and safety of the system.

[0123] Preferably, step S4 comprises the following steps:

[0124] Step S41: using infrared thermal imaging technology to obtain thermal distribution data on the surface and inside of the energy storage battery;

[0125] The embodiment of the present invention selects an infrared thermal imaging device that is suitable for the battery size and resolution requirements to ensure that it can capture the thermal distribution on the surface and inside of the battery; calibrates the device, sets a suitable sampling frequency and thermal imaging range to ensure the accuracy of the data. The battery is placed in a test environment, and the surface and inside of the battery under different charging and discharging conditions are continuously monitored using infrared thermal imaging equipment to record thermal distribution data; during the experiment, the ambient temperature and heat dissipation conditions are controlled to ensure the repeatability of the experimental conditions and the consistency of the data.

[0126] Step S42: Analyze the geometric structure and thermophysical parameters of each component inside the battery according to the heat distribution data, so as to construct a three-dimensional heat conduction model;

[0127] The embodiment of the present invention obtains the geometric shape and arrangement of each component inside the battery (such as electrodes, diaphragms, electrolytes, etc.) based on the actual physical structure of the battery, and establishes a three-dimensional geometric model of the battery through three-dimensional scanning or CAD model; obtains the thermophysical parameters of the battery material (such as thermal conductivity, specific heat capacity, density, etc.), which can be measured experimentally or referenced by literature data; combines the thermophysical parameters with the geometric structure to establish a thermal conduction model of each component inside the battery. The three-dimensional geometric structure of the battery is meshed using the finite element method to generate a mesh model suitable for thermal conduction analysis; the thermophysical parameters are assigned to the corresponding mesh units, and a three-dimensional heat conduction model is constructed to simulate the temperature distribution during the heat flow process inside the battery.

[0128] Step S43: simulating the flow and heat transfer characteristics of the cooling medium based on computational fluid dynamics according to the three-dimensional heat conduction model, thereby obtaining a cooling system model; coupling the cooling system model and the three-dimensional heat conduction model to construct a complete thermal management model;

[0129] The embodiment of the present invention simulates the flow and heat transfer characteristics of the cooling medium (such as liquid coolant or air) based on the three-dimensional heat conduction model, analyzes the heat transfer effect of the cooling system at different flow rates, flow rates and coolant temperatures; determines the key parameters of the cooling system, such as flow channel design, coolant flow rate, etc., and generates a cooling system model. The cooling system model is coupled with the three-dimensional heat conduction model to form a complete battery thermal management model, simulating the interaction between the heat flow and the cooling medium during the actual operation of the battery; through repeated simulation and optimization, the optimal cooling system design parameters are determined to achieve the best thermal management effect.

[0130] Step S44: simulating the heat flow behavior inside the battery according to the thermal management model by using a finite element analysis method to obtain preliminary heat flow path data;

[0131] The embodiment of the present invention uses the finite element analysis method to perform detailed heat flow simulation on the coupled thermal management model, predict the temperature distribution and heat flow path of each area inside the battery, analyze the temperature gradient inside the battery, the location of hot spots and their evolution over time, and generate preliminary heat flow path data. The simulation results are experimentally verified by comparing the actual measured heat distribution data with the simulation data, adjusting the model parameters to ensure the accuracy of the simulation results.

[0132] Step S45: introducing an electrochemical reaction heat source term into the thermal management model, and establishing an electrochemical-thermal coupling model based on heat generation and distribution during the charging and discharging process;

[0133] The embodiment of the present invention calculates the corresponding heat generation rate according to the electrochemical reaction characteristics of the battery during the charge and discharge process. This heat source term includes reaction heat, Joule heat, polarization heat, etc. The electrochemical reaction heat source term is introduced into the thermal management model to construct an electrochemical-thermal coupling model. This model can more accurately reflect the heat generation and distribution of the battery during actual use.

[0134] Step S46: using the electrochemical-thermal coupling model to correct the preliminary heat flow path data by electrochemical-thermal coupling, thereby obtaining heat flow path diagram data.

[0135] The embodiment of the present invention uses the electrochemical-thermal coupling model to correct the preliminary heat flow path data, especially to optimize key features such as hot spots, temperature gradients, and heat dissipation paths; simulate the corrected heat flow path, and analyze the thermal management effect of the battery under different working conditions. Based on the corrected model data, the final heat flow path diagram is generated to provide a detailed description of the heat flow inside the battery; the path diagram can be used to further optimize the battery design, improve the cooling system, extend the battery life, and improve safety.

[0136] The infrared thermal imaging technology of the present invention can obtain the heat distribution data on the surface and inside of the energy storage battery without contact. This high-resolution temperature detection method can quickly identify possible overheating areas inside the battery and prevent thermal runaway. By acquiring the heat distribution data in real time, the temperature change of the battery under different working conditions can be dynamically tracked, providing real and reliable basic data for subsequent thermal management modeling. According to the heat distribution data, the geometric structure and thermophysical parameters of each component inside the battery are analyzed, and a three-dimensional heat conduction model reflecting the real situation of the battery can be constructed. This model helps to accurately simulate the heat flow and temperature distribution inside the battery. The three-dimensional heat conduction model can take into account the different thermal conductivities and geometric shapes of each component inside the battery, provide a more comprehensive thermal management analysis, and help identify potential thermal management problems. By simulating the flow and heat transfer characteristics of the cooling medium through computational fluid dynamics (CFD), it can help optimize the design of the cooling system so that it can effectively dissipate heat and improve the heat dissipation efficiency of the battery. The cooling system model is coupled with the three-dimensional heat conduction model to construct a complete thermal management model, so that the interaction between the cooling system and the battery thermal management can be comprehensively considered, thereby improving the overall thermal management performance of the battery. By simulating the thermal management model through finite element analysis (FEA), the heat flow path inside the battery can be predicted. The preliminary heat flow path data provides a basis for subsequent electrochemical-thermal coupling analysis; the preliminary simulation can help identify possible hot spots or insufficient cooling areas inside the battery, and provide important information for further optimizing the thermal management strategy. Introducing the heat source term of the electrochemical reaction in the thermal management model can more accurately reflect the heat generation and distribution of the battery during the charging and discharging process. This is crucial for analyzing the internal thermal stress of the battery and preventing overheating. The electrochemical-thermal coupling model can consider the impact of the chemical reaction inside the battery on the heat flow, making the model closer to the actual working state of the battery and improving the accuracy of the thermal management simulation. Using the electrochemical-thermal coupling model to correct the preliminary heat flow path data can correct the errors caused by ignoring the heat source of the electrochemical reaction, making the final heat flow path diagram more accurate. The corrected heat flow path diagram data provides a more reliable basis for optimizing the thermal management strategy of the battery, and can help design more effective cooling and thermal management solutions, extend the service life of the battery, and improve its safety and reliability. Through these steps, a comprehensive thermal management model for energy storage batteries can be constructed, which comprehensively improves the thermal management effect of batteries from the material composition and geometric structure of the battery to the design of the cooling system and the consideration of electrochemical reactions. This multi-level and multi-faceted thermal management measure can not only effectively prevent thermal runaway of the battery, but also optimize the working efficiency and safety performance of the battery and extend its service life.

[0137] Preferably, step S5 comprises the following steps:

[0138] Step S51: aligning the heat flow path diagram data with the health status assessment data in time and space, thereby obtaining time-space aligned thermo-electric data; and quantifying the correlation between the thermal distribution change and the battery performance degradation according to the time-space aligned thermo-electric data by using the Pearson correlation coefficient, thereby obtaining thermo-electric coupling correlation data;

[0139] The embodiment of the present invention performs spatiotemporal alignment of the heat flow path diagram data and the health status assessment data. The specific operation includes aligning the two data sets in the time dimension and the space dimension. The time dimension alignment includes synchronizing the timestamps of the thermal data and the battery health status data, and the space dimension alignment is based on the thermal distribution of different positions inside the battery and the health status of the corresponding position. The aligned thermal distribution data is fused with the battery performance data to generate a comprehensive data set - spatiotemporal aligned thermal-electric data. The spatiotemporal aligned thermal-electric data is analyzed to calculate the Pearson correlation coefficient between the thermal distribution change (such as temperature gradient, hot spot location, etc.) and the battery performance degradation (such as capacity decay, internal resistance increase). Based on the calculation result of the Pearson correlation coefficient, the correlation between the thermal distribution and the battery performance degradation is quantified to obtain the thermal-electric coupling correlation data, which reveals the degree of influence of thermal effects on battery performance.

[0140] Step S52: constructing a spatiotemporal dynamic characteristic prediction model based on the spatiotemporal aligned thermal-electric data based on the time convolution network, and jointly predicting the thermal distribution and health status in the future period, thereby obtaining spatiotemporal dynamic characteristic prediction data;

[0141] The embodiment of the present invention is based on a temporal convolutional network (TCN) to construct a spatiotemporal dynamic characteristics prediction model. TCN can process time series data and capture the temporal and spatial correlations in the data. The model is trained using spatiotemporal aligned thermal-electric data. The input of the model is the thermal distribution and health status data for a period of time in the past, and the output is a joint prediction of the thermal distribution and battery health status for a period of time in the future. The trained model is verified, and the prediction performance of the model is evaluated using a test set. The verification indicators may include mean square error (MSE), mean absolute error (MAE), etc. Using the verified model, the thermal distribution and health status of the battery in the future are predicted to generate spatiotemporal dynamic characteristics prediction data. These prediction data provide trend analysis of future battery performance and thermal effects.

[0142] Step S53: performing sensitivity analysis on the thermal management model and the spatiotemporally aligned thermal-electrical data by using the Sobol sensitivity analysis method to obtain parameter sensitivity quantification data;

[0143] The embodiment of the present invention selects the Sobol sensitivity analysis method, which can effectively quantify the impact of input parameters on model output; sensitivity analysis is performed on the thermal management model and the time-space aligned thermal-electric data, and the input parameters (such as thermophysical parameters, electrochemical reaction parameters, etc.) are changed to observe their impact on the model output (such as temperature distribution, health state change), and obtain parameter sensitivity quantitative data. Analyze the Sobol sensitivity results to determine which parameters have the greatest impact on battery thermal management and health state, and these parameters will become the key variables for subsequent optimization.

[0144] Step S54: construct a multi-objective optimization problem based on the thermal-electric coupling correlation data, the spatiotemporal dynamic characteristics prediction data, and the parameter sensitivity quantification data, and perform multi-objective optimization solution through NSGA-II to obtain optimized battery management strategy data.

[0145] The embodiment of the present invention sets a multi-objective optimization problem based on the thermal-electric coupling correlation data, spatiotemporal dynamic characteristics prediction data and parameter sensitivity quantification data. The optimization objectives may include minimizing battery performance degradation, maximizing thermal management efficiency, etc.; a multi-objective optimization model is constructed using the above data, and the objective function and constraints are driven by thermal-electric coupling, dynamic prediction, and sensitivity analysis results. The non-dominated sorting genetic algorithm II (NSGA-II) is used to solve the multi-objective optimization problem. NSGA-II performs well in multi-objective optimization problems and can effectively find the Pareto optimal solution set; NSGA-II is run to generate multiple optimization solutions, and the optimal battery management strategy is selected based on these solutions, and finally the optimized battery management strategy data is obtained. These strategies extend the battery life and improve the overall performance on the basis of balancing performance and thermal management efficiency.

[0146] The present invention can ensure the consistency of thermal-electric data in time and space dimensions by aligning the heat flow path diagram data with the health status assessment data in time and space, making the data analysis more accurate and comprehensive. Quantifying the correlation between the change in heat distribution and the degradation of battery performance through the Pearson correlation coefficient helps to clarify the specific relationship between battery thermal management problems and performance degradation, which can provide guidance for subsequent optimization and help identify key influencing factors. Using a temporal convolutional network to construct a spatiotemporal dynamic characteristic prediction model can effectively capture the time series characteristics of heat distribution and battery health status, and realize the joint prediction of future heat distribution and battery health status. Through accurate prediction data, measures can be taken in advance to avoid possible overheating or performance degradation problems, and more proactive battery management and maintenance can be achieved. The Sobol sensitivity analysis method can quantify the impact of different parameters on battery thermal management and health status, and identify the parameters that are most sensitive to system performance. This provides a clear direction for optimization design and makes the optimization process more efficient. Through sensitivity analysis, it is possible to ensure that the model is robust in key parameters, reduce the impact of potential uncertainties on the results, and thus improve the overall reliability and accuracy of the model. By constructing a multi-objective optimization problem, multiple objectives of thermal management and battery health status can be considered simultaneously to ensure the best balance between different objectives; the NSGA-II algorithm can effectively solve this multi-objective optimization problem and obtain the optimal battery management strategy. By integrating thermal-electric coupling correlation data, spatiotemporal dynamic characteristics prediction data, and parameter sensitivity quantification data, the optimized battery management strategy can better adapt to different working conditions and needs, and provide a more personalized and efficient management solution. These steps achieve in-depth optimization of energy storage battery management strategies through the organic combination of thermal-electric coupling analysis, dynamic characteristics prediction, sensitivity analysis, and multi-objective optimization; this can not only accurately predict and prevent potential thermal management problems, but also achieve the best balance between performance and safety, and improve the overall service life and efficiency of the battery. This method is of great significance for achieving efficient and reliable energy storage system management.

[0147] The present invention also provides a system for monitoring the health status of an energy storage battery, which is used to execute the above-mentioned method for monitoring the health status of an energy storage battery. The system for monitoring the health status of an energy storage battery comprises:

[0148] The battery characteristics prediction module is used to obtain the material composition data of the energy storage battery; analyze the interaction between the components at the electrochemical level of the energy storage battery based on the material composition data, and predict the interface behavior to obtain the interface behavior prediction data; perform electrochemical impedance spectrum simulation based on the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain the battery characteristic diagram data;

[0149] The degradation behavior modeling module is used to simulate and analyze the battery performance degradation behavior under different charging and discharging conditions according to the battery characteristic diagram data, so as to obtain degradation behavior simulation data; and to establish a battery health state evolution model according to the operating parameters corresponding to different working conditions and the degradation behavior simulation data;

[0150] The real-time status assessment module is used to obtain battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extract features from battery operation data, and perform health status prediction and assessment based on status features and battery health status evolution model, thereby obtaining health status assessment data;

[0151] Thermal behavior analysis module, used to obtain the thermal distribution data inside the energy storage battery; build a thermal management model based on the thermal distribution data; simulate the thermal flow behavior inside the battery according to the thermal management model through the finite element analysis method, and perform electrochemical-thermal coupling correction to obtain thermal flow path diagram data;

[0152] The multi-dimensional optimization strategy module is used to perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain the optimized battery management strategy data. The multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

[0153] The present invention can deeply understand the behavior and performance of materials in batteries by acquiring material composition data of energy storage batteries and analyzing the interaction between components at the electrochemical level. This provides accurate basic data for subsequent prediction and management. The simulation of electrochemical impedance spectrum and battery performance mapping under different conditions can predict the interface behavior of the battery in actual use in advance, avoid potential performance degradation or failure, and thus improve the safety and reliability of the battery. By analyzing the battery characteristic diagram data, the performance degradation behavior under different charge and discharge states can be simulated. This simulation helps to identify and predict the attenuation characteristics of the battery during use in advance, thereby extending the battery life. By establishing a health state evolution model, the health state changes of the battery under different working conditions can be continuously monitored. This provides a scientific basis for real-time management and maintenance and helps to formulate more effective maintenance strategies. The battery operation data is collected by multi-source sensors, and the battery status can be monitored in real time in combination with feature extraction technology. This real-time monitoring helps to discover potential problems in a timely manner and take corresponding preventive measures. The current health state of the battery can be accurately predicted by evaluating the state characteristics and health state evolution model. This provides accurate data support for the continuous optimization and management of the battery and reduces the risk of failure. By acquiring and analyzing the thermal distribution data of energy storage batteries and building a thermal management model, the thermal management strategy of the battery can be optimized to avoid performance degradation or safety problems caused by overheating. Through electrochemical-thermal coupling correction, the thermal flow behavior inside the battery can be simulated more accurately. This coupling analysis provides a more refined optimization direction for thermal management and helps to extend the service life of the battery. Through multi-dimensional coupling analysis, including thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis, the battery management strategy can be optimized from multiple angles. This comprehensive optimization can balance different performance indicators and find the best management solution. Through multi-dimensional optimization strategies, key bottlenecks in the system can be identified and solved, the robustness and operating efficiency of the battery management system can be improved, and the battery can be ensured to work stably and efficiently under different conditions of use. Through the collaborative work of these modules, comprehensive management from material property prediction, performance degradation simulation, real-time health status monitoring to thermal behavior analysis and multi-dimensional optimization can be achieved throughout the life cycle of the energy storage battery; this systematic approach not only improves the safety and reliability of the battery, but also extends the battery life and reduces operation and maintenance costs.

[0154] The present invention also provides a storage medium for monitoring the health status of an energy storage battery, comprising:

[0155] Memory for storing computer programs;

[0156] The processor is used to implement the steps of the above-mentioned energy storage battery health status monitoring method when executing the computer program.

[0157] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0158] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for monitoring the health status of an energy storage battery, characterized in that: The following steps are involved: Step S1: obtaining material composition data of the energy storage battery; analyzing the interaction between components at the electrochemical level of the energy storage battery according to the material composition data, and predicting the interface behavior, thereby obtaining interface behavior prediction data; performing electrochemical impedance spectrum simulation according to the interface behavior prediction data, and mapping the internal state and performance of the battery under different conditions, thereby obtaining battery characteristic diagram data. Step S1 is specifically as follows: Step S11: Acquire material composition data of the energy storage battery, including positive electrode material data, negative electrode material data, electrolyte data, and separator data; Step S12: Calculating the band structure and state density of the electrode materials of the positive and negative electrode materials of the energy storage battery according to the material composition data based on density functional theory, thereby obtaining electronic energy level distribution data; Step S13: simulating the atomic structure of the electrode / electrolyte interface according to the electronic energy level distribution data, thereby obtaining the interface atomic configuration data; Step S14: constructing a molecular dynamics model of the electrode / electrolyte interface according to the material composition data and the electronic energy level distribution data; simulating the diffusion behavior of ions at the interface according to the interface atomic configuration data and the molecular dynamics model to obtain ion migration data; Step S15: predicting charge transfer at the interface, solid electrolyte interface formation and growth behavior according to the ion migration data and the interface atomic configuration data, thereby generating interface behavior prediction data; Step S16: Perform electrochemical impedance spectroscopy simulation according to the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain battery characteristic diagram data. Step S16 is specifically as follows: Step S161: generalizing the interface behavior prediction data from the atomic scale and the molecular scale to the macro scale, and establishing a multi-scale model connecting the microscopic mechanism and the macroscopic performance, thereby obtaining cross-scale battery material performance prediction data; Step S162: identifying electrochemical process information of the interface behavior prediction data, and determining circuit elements for each process, thereby obtaining an equivalent circuit model; Step S163: simulating the battery impedance response at different frequencies according to the equivalent circuit model to obtain a theoretical EIS spectrum; and analyzing the contribution of different battery groups to the EIS characteristics on the theoretical EIS spectrum to obtain impedance distribution data; Step S164: Performing a virtual experiment of the energy storage battery according to the battery material performance prediction data and the impedance distribution data, simulating the battery behavior under different working conditions, calculating and recording the key performance indicators under each condition, and generating a mapping relationship between the battery performance and the working conditions, thereby obtaining battery characteristic diagram data; Step S2: performing state simulation analysis on the battery performance degradation behavior under different charge and discharge states according to the battery characteristic diagram data, thereby obtaining degradation behavior simulation data; establishing a battery health state evolution model according to the operating parameters corresponding to different operating conditions and the degradation behavior simulation data; Step S3: Acquire battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration, and mechanical stress data; Extract features from battery operation data, and perform health status prediction and evaluation based on status features and battery health status evolution model to obtain health status evaluation data; Step S4: Acquire heat distribution data inside the energy storage battery; A thermal management model is constructed according to the thermal distribution data; the thermal flow behavior inside the battery is simulated according to the thermal management model by a finite element analysis method, and electrochemical-thermal coupling correction is performed to obtain thermal flow path diagram data. Step S4 is specifically as follows: Step S41: using infrared thermal imaging technology to obtain thermal distribution data on the surface and inside of the energy storage battery; Step S42: Analyze the geometric structure and thermophysical parameters of each component inside the battery according to the heat distribution data, so as to construct a three-dimensional heat conduction model; Step S43: simulating the flow and heat transfer characteristics of the cooling medium based on computational fluid dynamics according to the three-dimensional heat conduction model, thereby obtaining a cooling system model; coupling the cooling system model and the three-dimensional heat conduction model to construct a complete thermal management model; Step S44: simulating the heat flow behavior inside the battery according to the thermal management model by using a finite element analysis method to obtain preliminary heat flow path data; Step S45: introducing an electrochemical reaction heat source term into the thermal management model, and establishing an electrochemical-thermal coupling model based on heat generation and distribution during the charging and discharging process; Step S46: using an electrochemical-thermal coupling model to perform electrochemical-thermal coupling correction on the preliminary heat flow path data, thereby obtaining heat flow path diagram data; Step S5: Perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain optimized battery management strategy data, wherein the multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

2. The method for monitoring the health status of an energy storage battery according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: constructing a battery performance degradation model based on the performance parameter data set, wherein the battery performance degradation model includes a capacity attenuation model, an internal resistance growth model, and a power attenuation model; Step S22: using the battery performance degradation model to simulate the battery performance under different charge and discharge conditions, simulating the cycle performance of the battery under different charge and discharge depths, rates and temperatures, so as to obtain degradation behavior simulation data; Step S23: extracting the capacity attenuation rate, internal resistance growth rate and power attenuation rate characteristics of the degradation behavior simulation data, thereby obtaining degradation characteristic data; Step S24: establishing a battery health status indicator system according to the degradation characteristic data, and constructing a battery health status assessment model based on a fuzzy logic model; Step S25: constructing a battery health state evolution model that can predict the changing trend of the battery health state under different working conditions based on the battery health state assessment model and the degradation behavior simulation data.

3. The method for monitoring the health status of an energy storage battery according to claim 2, characterized in that: Step S25 includes the following steps: Step S251: constructing a time series prediction model of the battery health state based on the autoregressive integrated moving average model according to the battery health state assessment model; Step S252: training and verifying the time series prediction model according to the degradation behavior simulation data, and optimizing the model parameters, thereby obtaining the time series model data; Step S253: constructing a multi-factor health state evolution model based on the operating parameters corresponding to different operating conditions according to the time series model data, and extracting the impact of the operating condition change on the health state evolution, thereby obtaining the multi-factor evolution model data; Step S254: performing uncertainty analysis on the multi-factor evolution model data by using the Monte Carlo method, and performing confidence interval evaluation on the model prediction results, thereby obtaining uncertainty analysis data; Step S255: performing model correction based on robustness and accuracy on the multi-factor evolution model data according to the uncertainty analysis data, thereby obtaining a battery health state evolution model.

4. The method for monitoring the health status of an energy storage battery according to claim 3, characterized in that: Step S3 includes the following steps: Step S31: collecting battery operation data through multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; Step S32: performing preprocessing including denoising, normalization and outlier detection on the battery operation data, thereby obtaining a battery operation data set; Step S33: extracting features including statistical features, time series features and spectrum features from the battery operation data set using time domain analysis and frequency domain analysis methods, thereby obtaining a multi-dimensional feature vector; Step S34: performing dimensionality reduction processing on the multi-dimensional feature vector through an autoencoder, and constructing a data-driven health state estimator based on the dimensionality reduction features and the battery health state evolution model; Step S35: using the health state estimator to estimate the current health state of the battery in real time, and recording the health state estimation result, so as to obtain health state estimation data; Step S36: predict the battery health status within a future period of time based on the health status estimation data based on the time series, and perform confidence interval evaluation to obtain health status evaluation data.

5. The method for monitoring the health status of an energy storage battery according to claim 4, characterized in that: Step S5 includes the following steps: Step S51: aligning the heat flow path diagram data with the health status assessment data in time and space, thereby obtaining time-space aligned thermo-electric data; and quantifying the correlation between the thermal distribution change and the battery performance degradation according to the time-space aligned thermo-electric data by using the Pearson correlation coefficient, thereby obtaining thermo-electric coupling correlation data; Step S52: constructing a spatiotemporal dynamic characteristic prediction model based on the spatiotemporal aligned thermal-electric data based on the time convolution network, and jointly predicting the thermal distribution and health status in the future period, thereby obtaining spatiotemporal dynamic characteristic prediction data; Step S53: performing sensitivity analysis on the thermal management model and the spatiotemporally aligned thermal-electrical data by using the Sobol sensitivity analysis method to obtain parameter sensitivity quantification data; Step S54: construct a multi-objective optimization problem based on the thermal-electric coupling correlation data, the spatiotemporal dynamic characteristics prediction data, and the parameter sensitivity quantification data, and perform multi-objective optimization solution through the non-dominated sorting genetic algorithm II to obtain the optimized battery management strategy data.

6. A storage battery health status monitoring system, characterized in that: Used to execute the energy storage battery health status monitoring method according to claim 1, the energy storage battery health status monitoring system comprises: The battery characteristics prediction module is used to obtain the material composition data of the energy storage battery; analyze the interaction between the components at the electrochemical level of the energy storage battery based on the material composition data, and predict the interface behavior to obtain the interface behavior prediction data; perform electrochemical impedance spectrum simulation based on the interface behavior prediction data, and map the internal state and performance of the battery under different conditions to obtain the battery characteristic diagram data; The degradation behavior modeling module is used to simulate and analyze the battery performance degradation behavior under different charging and discharging conditions according to the battery characteristic diagram data, so as to obtain degradation behavior simulation data; and to establish a battery health state evolution model according to the operating parameters corresponding to different working conditions and the degradation behavior simulation data; The real-time status assessment module is used to obtain battery operation data collected by multi-source sensors, including voltage, current, temperature, gas concentration and mechanical stress data; extract features from battery operation data, and perform health status prediction and assessment based on status features and battery health status evolution model, thereby obtaining health status assessment data; Thermal behavior analysis module, used to obtain the thermal distribution data inside the energy storage battery; build a thermal management model based on the thermal distribution data; simulate the thermal flow behavior inside the battery according to the thermal management model through the finite element analysis method, and perform electrochemical-thermal coupling correction to obtain thermal flow path diagram data; The multi-dimensional optimization strategy module is used to perform multi-dimensional coupling analysis on the thermal flow path diagram data and the health status assessment data to obtain the optimized battery management strategy data. The multi-dimensional coupling analysis includes thermal-electric coupling correlation analysis, spatiotemporal dynamic characteristics prediction analysis, and parameter sensitivity quantification analysis.

7. A storage medium for monitoring the health status of an energy storage battery, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the method for monitoring the health status of an energy storage battery as described in any one of claims 1 to 5 when executing the computer program.

Images