Attenuation analysis method and system for electrochemical performance of energy storage batteries based on cloud computing

Abstract

The present application discloses a method and system for analyzing the attenuation of electrochemical performance of energy storage batteries based on cloud computing, which relates to the field of cloud computing technology. The method includes: decomposing and constructing a parameter relationship tree based on the historical attenuation cases of electrochemical performance of energy storage batteries; performing node task decomposition and matching according to the parameter relationship tree and the cloud computing distribution structure to obtain the cloud computing task relationship; obtaining the mathematical model of each cloud computing node based on the cloud computing task relationship; uploading the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain the limit cycle; performing stability analysis on the limit cycle to determine its stability; analyzing the sensitivity of various factors to the performance attenuation parameters based on the stability of the limit cycle to obtain the limit cycle influencing factors and influencing coefficients; and performing electrochemical performance attenuation prediction analysis in combination with the application environment and charge and discharge parameters of the energy storage battery. The technical effect of reducing analysis costs, improving analysis efficiency and accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and in particular to a method and system for analyzing the attenuation of electrochemical performance of energy storage batteries based on cloud computing. Background Art

[0002] With the improvement of social activities, the demand for electricity in modern society is also increasing, which has promoted the development of energy storage technology. Energy storage batteries are an important component of electric energy storage technology. In the actual deployment process, as the use time of energy storage batteries increases, the electrochemical performance of energy storage batteries will gradually decay. Traditional battery decay analysis methods mainly rely on experimental data and theoretical models, and there are technical problems such as high data acquisition cost, low analysis efficiency, and inaccurate results. Summary of the invention

[0003] The purpose of this application is to provide a method and system for analyzing the attenuation of electrochemical performance of energy storage batteries based on cloud computing, so as to solve the technical problems of high data acquisition cost, low analysis efficiency and inaccurate results in the prior art.

[0004] In view of the above technical problems, the present application provides a method and system for analyzing the attenuation of the electrochemical performance of energy storage batteries based on cloud computing.

[0005] In a first aspect, the present application provides a method for analyzing the attenuation of electrochemical performance of energy storage batteries based on cloud computing, wherein the method comprises:

[0006] Based on the historical attenuation cases of electrochemical performance of energy storage batteries, the electrochemical performance types and parameter relationships are decomposed and a parameter relationship tree is constructed;

[0007] Perform node task decomposition and matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets, and corresponding cloud computing nodes;

[0008] Based on the cloud computing task relationship, obtaining a mathematical model of each cloud computing node;

[0009] Uploading the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain limit cycles;

[0010] Performing stability analysis on the limit cycle to determine the stability of the limit cycle;

[0011] Based on the limit cycle stability, the sensitivity of each factor to the performance attenuation parameter is analyzed to obtain the limit cycle influencing factors and influencing coefficients;

[0012] According to the influencing factors and influencing coefficients of the limit cycle, combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation of the energy storage battery is predicted and analyzed.

[0013] In a second aspect, the present application also provides a cloud computing-based energy storage battery electrochemical performance attenuation analysis system, wherein the system comprises:

[0014] An electrochemical performance analysis module, which is used to decompose the electrochemical performance type and parameter relationship based on the historical attenuation cases of the electrochemical performance of the energy storage battery, and to construct a parameter relationship tree;

[0015] A cloud computing task matching module, the cloud computing task matching module is used to perform node task decomposition matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets and corresponding cloud computing nodes;

[0016] A mathematical model acquisition module, the mathematical model acquisition module is used to acquire a mathematical model of each cloud computing node based on the cloud computing task relationship;

[0017] A limit cycle analysis module, wherein the limit cycle analysis module is used to upload the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain a limit cycle;

[0018] A limit cycle stability analysis module, wherein the limit cycle stability analysis module is used to perform stability analysis on the limit cycle to determine the stability of the limit cycle;

[0019] An attenuation sensitivity analysis module, which is used to analyze the sensitivity of various factors to performance attenuation parameters based on the limit cycle stability, and obtain limit cycle influencing factors and influencing coefficients;

[0020] The performance prediction module is used to predict and analyze the electrochemical performance attenuation of the energy storage battery based on the limit cycle influencing factors and influencing coefficients combined with the application environment and charging and discharging parameters of the energy storage battery.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] Through the historical attenuation cases of electrochemical performance of energy storage batteries, the electrochemical performance type and parameter relationship are decomposed to construct a parameter relationship tree; node tasks are matched according to the parameter relationship tree and the cloud computing distribution structure to obtain cloud computing task relationships, including data acquisition parameters, operation targets and corresponding cloud computing nodes; based on the cloud computing task relationship, the mathematical model of each cloud computing node is obtained and uploaded to the cloud platform for limit cycle analysis and identification to obtain the limit cycle; stability analysis is performed on the limit cycle to determine its stability; the sensitivity of various factors to performance attenuation parameters is analyzed to obtain the limit cycle influencing factors and influencing coefficients; combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation of the energy storage battery is predicted and analyzed. The technical effect of reducing analysis costs, improving analysis efficiency and accuracy is achieved.

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly illustrate the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The embodiments of the present invention and the following brief description are illustrated in conjunction with the accompanying drawings, which are described as follows:

[0025] Figure 1 A schematic diagram of the process of the attenuation analysis method of the electrochemical performance of energy storage batteries based on cloud computing in this application;

[0026] Figure 2 This is a schematic diagram of the structure of the attenuation analysis system of the electrochemical performance of energy storage batteries based on cloud computing in this application.

[0027] Explanation of the accompanying drawings: electrochemical performance analysis module 11, cloud computing task matching module 12, mathematical model acquisition module 13, limit cycle analysis module 14, limit cycle stability analysis module 15, attenuation sensitivity analysis module 16, performance prediction module 17. DETAILED DESCRIPTION

[0028] The present application solves the technical problems faced by the prior art, such as high data acquisition cost, low analysis efficiency and inaccurate results, by providing a method and system for analyzing the attenuation of the electrochemical performance of energy storage batteries based on cloud computing.

[0029] The solution in the embodiment of the present technology, in order to solve the above problems, adopts the following overall ideas:

[0030] Based on historical attenuation cases, the type of electrochemical performance and parameter relationship are first decomposed to construct a parameter relationship tree; then, according to the parameter relationship tree and cloud computing structure, the task is decomposed and matched to determine the data acquisition parameters, operation targets and corresponding cloud computing nodes; then, the mathematical model of each cloud computing node is obtained and uploaded to the cloud platform for limit cycle analysis and identification to obtain the limit cycle; the stability of the limit cycle is analyzed to determine its stability; finally, the sensitivity of each factor to the performance attenuation parameter is analyzed to obtain the influence coefficient, and the electrochemical performance attenuation is predicted and analyzed in combination with the application environment and charge and discharge parameters. This can reduce the analysis cost, improve the analysis efficiency and achieve accurate technical effects.

[0031] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the drawings and specific implementation methods of the specification. It should be noted that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that for the sake of ease of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0032] Embodiment 1

[0033] like Figure 1 As shown, the present application provides a method for analyzing the attenuation of electrochemical performance of energy storage batteries based on cloud computing, the method comprising:

[0034] Based on the historical attenuation cases of electrochemical performance of energy storage batteries, the electrochemical performance types and parameter relationships are decomposed and a parameter relationship tree is constructed;

[0035] Among them, the electrochemical performance degradation type refers to the type of performance degradation exhibited by the battery during use, such as battery capacity degradation, charge and discharge rate degradation, cycle life degradation, etc. The parameter relationship tree is a hierarchical model used to show the logical relationship between electrochemical performance degradation categories and influencing factors.

[0036] In some embodiments, the electrochemical performance type and parameter relationship decomposition based on the historical attenuation cases of the electrochemical performance of the energy storage battery and the construction of the parameter relationship tree include:

[0037] Based on the historical attenuation cases of electrochemical performance of energy storage batteries, determine the type of electrochemical performance attenuation, including battery capacity, charge and discharge rate, and cycle life attenuation;

[0038] According to the electrochemical performance attenuation category, an influencing factor analysis is performed to determine the influencing factors of each electrochemical performance attenuation category, wherein the influencing factors are parameters that cause the electrochemical performance attenuation category to occur, including ambient temperature, ambient humidity, charge and discharge power, diaphragm quality, number of charges, and internal resistance;

[0039] The electrochemical performance decay analysis target is taken as the top event, and the parameter relationship tree is established according to the correspondence between the electrochemical performance decay category and the influencing factor.

[0040] Optionally, based on historical attenuation cases of the electrochemical performance of the energy storage battery, the type of electrochemical performance attenuation is determined, including battery capacity attenuation, that is, the available capacity of the battery gradually decreases; charge and discharge rate attenuation, that is, the maximum charge and discharge rate of the battery gradually decreases; cycle life attenuation, that is, the life of the battery gradually decreases during the cyclic charge and discharge process.

[0041] Exemplarily, by traversing a plurality of historical attenuation cases, statistical analysis is performed on attenuation type data in the historical attenuation cases, thereby obtaining the electrochemical performance attenuation type.

[0042] Optionally, the influencing factor is the cause or factor that causes the electrochemical performance to decay, and is characterized by a variety of index parameters, including ambient temperature, ambient humidity, charge and discharge power, diaphragm quality, charge times, internal resistance, etc.

[0043] Furthermore, taking the electrochemical performance degradation analysis target as the top event, a parameter relationship tree is established based on the correspondence between the degradation category and the influencing factor. The parameter relationship tree shows the logical relationship between the electrochemical performance degradation category and the influencing factor, which helps to understand the cause of electrochemical performance degradation.

[0044] Exemplarily, the parameter relationship tree has a hierarchical structure, in which the top-level node is the electrochemical performance attenuation type, that is, the electrochemical performance attenuation analysis target is used as the top-level node of the parameter relationship tree, the secondary nodes are the influencing factors corresponding to each electrochemical performance attenuation type, and the leaf nodes are specific influencing factor parameters.

[0045] Through the above parameter relationship tree structure, the various categories of electrochemical performance degradation and their corresponding influencing factors can be clearly displayed, so as to gain an in-depth understanding of the causes and mechanisms of battery performance degradation, making it easier to take corresponding measures to improve and optimize battery performance.

[0046] Perform node task decomposition and matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets, and corresponding cloud computing nodes;

[0047] Optionally, the task requirements in the parameter relationship tree are matched with the cloud computing distribution structure to determine the best node to execute the task in the cloud computing environment. Specifically, it involves a comprehensive evaluation of factors such as the computing power, storage capacity, network connection, and cost of each node to select the cloud computing task relationship.

[0048] The cloud computing distribution structure refers to the distribution of cloud computing resources in the cloud computing network. Cloud computing resources include computing performance indicators such as the number, location, and processing power of distributed cloud computing nodes. Node task decomposition and matching refers to decomposing the electrochemical performance attenuation analysis target of the top-level node into multiple decomposition tasks to facilitate decentralized parallel processing of tasks, thereby improving analysis efficiency. Multiple decomposition tasks are assigned to the appropriate cloud computing nodes through node task decomposition and matching.

[0049] Through the above steps, the electrochemical performance decay analysis task is effectively matched with cloud computing resources, making full use of the advantages of cloud computing resources to improve analysis efficiency and accuracy.

[0050] In some embodiments, performing node task decomposition matching according to the parameter relationship tree and the cloud computing distribution structure to obtain the cloud computing task relationship includes:

[0051] The electrochemical performance attenuation category in the parameter relationship tree is used as the operation target of the node attenuation analysis task, and according to the corresponding relationship between the electrochemical performance attenuation category and the influencing factor, the influencing factor is used as the data acquisition parameter;

[0052] Decomposing the computational load and acquisition equipment characteristics according to the node attenuation analysis task and data acquisition parameters, and determining the computational processing demand characteristics;

[0053] Acquire a cloud computing distribution structure, analyze the load of each edge computing node of the cloud computing and the collection characteristics of the edge device based on the cloud computing distribution structure, and establish a cloud computing node computing characteristic;

[0054] According to the computing processing requirement characteristics and the computing characteristics of the cloud computing node, a matching degree is calculated, and a matching relationship between the node attenuation analysis task and the cloud computing node is determined based on the calculated matching degree;

[0055] A matching relationship between the node attenuation analysis task, the data collection task and the cloud computing node is established to obtain the cloud computing task relationship.

[0056] Optionally, the electrochemical performance attenuation category is used as the operation target of the node attenuation analysis task, and the influencing factor is used as the data collection parameter according to the correspondence between the attenuation category and the influencing factor. In other words, the electrochemical performance attenuation category is used as the decomposition task of the node attenuation analysis task, so as to convert the complex node attenuation analysis task into multiple simple tasks corresponding to a single attenuation type, so as to facilitate the adaptive analysis and processing of the cloud computing node. Among them, the influencing factor is the target of data collection, and the value of the influencing factor obtained through collection contains the attenuation status of the target energy storage battery.

[0057] Specifically, the computational load and acquisition equipment characteristics are decomposed according to the node attenuation analysis task and data acquisition parameters to determine the computational processing requirement characteristics. The computational load is the amount of calculation required to complete the node attenuation analysis task. The acquisition equipment characteristics characterize the characteristics or performance that the equipment used to collect data needs to have.

[0058] Furthermore, the cloud computing distribution structure is obtained, and based on the distribution structure, the load of each edge computing node of the cloud computing and the collection characteristics of the edge device are analyzed to establish the computing characteristics of the cloud computing node. The edge computing node refers to the cloud computing node located at the edge of the network. Different cloud computing nodes have different processing capabilities and resources. The load is the current workload level of the edge computing node; the collection characteristics of the edge device are the performance characteristics of the edge device in data collection. The above-mentioned load and collection characteristics together constitute the computing characteristics of the cloud computing node to describe the characteristics of the cloud computing node processing tasks.

[0059] Optionally, a matching degree is calculated based on the computing processing demand characteristics and the computing characteristics of the cloud computing node, and the matching relationship between the node attenuation analysis task and the cloud computing node is determined based on the matching degree obtained by the calculation. Thus, a matching relationship between the node attenuation analysis task, the data collection task and the cloud computing node is established, and a cloud computing task relationship is obtained.

[0060] Among them, the matching degree calculation is used to evaluate the matching degree between the node attenuation analysis task and the cloud computing node. Exemplarily, the matching degree is the coverage of multiple characteristic indicators in the computing characteristics of the cloud computing node to multiple characteristic indicators in the computing processing requirement characteristics, and the coverage has a central constraint. In other words, it should be ensured that the computing processing requirement characteristics are a true subset of the computing characteristics of the cloud computing node, and the overflow of the computing characteristics of the cloud computing node is as small as possible, so as to maximize the use of cloud computing capabilities and cloud computing resources while meeting the task processing requirements and reduce the waste of computing power.

[0061] Optionally, the matching relationship between the node attenuation analysis task and the cloud computing node is determined based on the calculated matching degree to obtain the cloud computing task relationship. In this way, the reasonable allocation and efficient processing of the electrochemical performance attenuation analysis task is achieved, the advantages of cloud computing resources are fully utilized, and the analysis efficiency and accuracy are improved.

[0062] Based on the cloud computing task relationship, obtaining a mathematical model of each cloud computing node;

[0063] Among them, the mathematical model of each cloud computing node is a mathematical expression or a set of equations corresponding to the hierarchical tasks of each node obtained based on empirical analysis or experiments. The mathematical model of each cloud computing node represents the mapping relationship between the influencing factors and the attenuation information of each electrochemical performance attenuation category.

[0064] Uploading the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain limit cycles;

[0065] In some embodiments, uploading the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain the limit cycle includes:

[0066] Based on the mathematical model of each cloud computing node, a time-series dynamic analysis of the data of each electrochemical performance attenuation category is performed to obtain the time-series trend relationship between each data acquisition parameter and the electrochemical performance;

[0067] Construct a phase plane diagram based on the collected data of the cloud computing nodes, the temporal trend relationship between each data collection parameter and the electrochemical performance;

[0068] According to the phase plane diagram, a closed loop identification model is used to identify a limit cycle, where the limit cycle is an isolated closed curve, wherein the closed loop identification model includes a convolution kernel trained with closed loop features.

[0069] Optionally, based on the mathematical model of each cloud computing node, a time-series dynamic analysis of the data of each electrochemical performance attenuation category is performed, and the changing trend of the electrochemical performance attenuation category over time is analyzed to obtain the time-series trend relationship between each data acquisition parameter and the electrochemical performance.

[0070] Furthermore, based on the collected data of the cloud computing nodes and the time-series trend relationship, a phase plane diagram is constructed, which visualizes the change trend of the electrochemical performance over time. Specifically, the phase plane diagram is a high-dimensional diagram in a multi-dimensional coordinate system, in which the dimensional axes represent different data collection parameters, and the curve represents the change trend of the electrochemical performance over time.

[0071] Optionally, the limit cycle in the phase plane diagram is identified based on a closed loop identification model. A closed loop is an isolated closed curve that represents the stable state of the electrochemical performance of the target energy storage battery in the phase space. Exemplarily, the closed loop identification model includes a convolution kernel trained with closed loop features to extract closed loop features, thereby more accurately identifying the limit cycle.

[0072] Performing stability analysis on the limit cycle to determine the stability of the limit cycle;

[0073] Exemplarily, by studying the evolution trajectory of the electrochemical properties of the target energy storage battery under different initial conditions, it is determined whether the target energy storage battery has a stable equilibrium point or periodic solution. First, the nonlinear dynamic equation of the target energy storage battery system is determined, that is, the mathematical model of the above-mentioned cloud computing node. Then, the limit cycle is substituted into the nonlinear dynamic equation of the system to obtain a set of nonlinear equations about the state variables of the system, and the nonlinear equations are solved by numerical or analytical methods to obtain a set of solutions on the circular orbit. Furthermore, the stability of the solution is determined by linearization analysis, Lyapunov function and other methods.

[0074] Optionally, if the solution is stable, that is, the system has a stable periodic solution on the limit cycle, then it means that the electrochemical performance of the target energy storage battery is in a steady-state change. In other words, the electrochemical performance of the target energy storage battery is in a normal decay state; correspondingly, if the solution is unstable, that is, the system does not have a stable periodic solution on the limit cycle, then it means that the electrochemical performance of the target energy storage battery decays abnormally and the target energy storage battery may be damaged.

[0075] Based on the limit cycle stability, the sensitivity of each factor to the performance attenuation parameter is analyzed to obtain the limit cycle influencing factors and influencing coefficients;

[0076] In some embodiments, based on the limit cycle stability, the sensitivity of each factor to the performance degradation parameter is analyzed to obtain the limit cycle influencing factors and influencing coefficients, including:

[0077] When the stability of the limit cycle cannot meet the preset conditions, performing parameter change analysis on the limit cycle;

[0078] According to the change amount, change direction and time series characteristics of each parameter, the influence relationship analysis of the limit cycle is performed to determine the influence coefficient of each parameter;

[0079] Screening is performed based on the influence coefficient of each parameter to determine the limit cycle influence factor, where the limit cycle influence factor is one or more parameters whose influence coefficient reaches a preset threshold.

[0080] Optionally, first, a change analysis of each parameter is performed to obtain changes in the performance attenuation parameters, which are characterized by the change amount, change direction and variable time series characteristics of each parameter.

[0081] Furthermore, based on the correlation analysis method or regression model, the change amount, change direction and time series characteristics of each parameter are analyzed, the influence relationship analysis of the limit cycle is performed, the influence of each parameter on the performance attenuation parameter is calculated, and the influence coefficient of each parameter is generated. Optionally, the influence coefficient is represented as a vector. In other words, the influence coefficient includes a positive and negative sign part and a numerical part. The larger the absolute value of the influence coefficient, the greater the influence of the corresponding parameter on the performance. The positive and negative of the influence coefficient represent the direction of the influence.

[0082] Optionally, according to the size of the influence coefficient, the influence coefficient of each parameter is traversed and screened. The parameters whose influence coefficient reaches the preset threshold are extracted as the limit cycle influencing factors, and the limit cycle influencing factors have a significant impact on the stability of the limit cycle. Among them, the preset threshold is a certain standard set to determine whether the influence coefficient of the parameter reaches a significant level.

[0083] Through the above analysis, we can understand the contribution of each factor to the system performance and provide optimization direction for optimizing system performance.

[0084] According to the influencing factors and influencing coefficients of the limit cycle, combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation of the energy storage battery is predicted and analyzed.

[0085] In some embodiments, based on the limit cycle influencing factors and influencing coefficients, combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation prediction analysis of the energy storage battery includes:

[0086] Collect the charging and discharging parameters of the energy storage battery and the application environment parameters through the node collection device and send them to the cloud platform;

[0087] Constructing an attenuation analysis model according to the limit cycle influencing factors and influencing coefficients;

[0088] The attenuation analysis model is used to analyze the impact of the charging and discharging parameters and the application environment parameters, and the timing cycle relationship is located according to the parameter impact relationship to obtain attenuation prediction information.

[0089] Optionally, the charging and discharging parameters and application environment parameters of the energy storage battery are collected through the node collection device and sent to the cloud platform for storage and processing. The node collection device refers to a device deployed around or inside the energy storage battery for collecting data, and exemplary includes temperature sensors, humidity sensors, voltmeters, ammeters, etc.

[0090] Among them, the charge and discharge parameters are the key parameters of the energy storage battery during the charge and discharge process, such as voltage, current, temperature, discharge rate, cut-off voltage, etc. The application environment parameters refer to the environmental conditions of the energy storage battery, such as temperature, humidity, light, etc.

[0091] Optionally, based on the influencing factors of the limit cycle and their influencing coefficients, combined with the charging and discharging parameters and application environment parameters of the energy storage battery, an attenuation analysis model is established. Exemplarily, the attenuation analysis model is constructed based on statistical methods, machine learning methods, or deep learning methods, etc., and is used to predict the attenuation of the electrochemical performance of the energy storage battery.

[0092] Optionally, constructing the attenuation analysis model also includes constructing a mathematical model using statistical methods, linear regression methods, nonlinear regression methods or other mathematical modeling methods.

[0093] Preferably, a decay analysis model is constructed based on a machine learning method or a deep learning method. First, an appropriate machine learning model or a deep learning model is selected, and then the selected model is trained using historical charge and discharge parameters, historical application environment parameters, and associated history as decay information training data. During the training process, the model parameters are adjusted according to the influencing factors and their coefficients to ensure that the model can accurately reflect the influence of the influencing factors on the decay of electrochemical performance. Then, the trained model is evaluated using methods such as cross-validation and validation sets to verify the performance and accuracy of the model. If the model performance meets the prediction requirements, the model is stored as a decay analysis model.

[0094] Furthermore, the established attenuation analysis model is used to analyze the impact of charge and discharge parameters and application environment parameters. The attenuation analysis model performs impact analysis based on the mapping relationship between the learned charge and discharge parameters and application environment parameters and the degree of electrochemical performance attenuation. Among them, the timing cycle relationship is located according to the parameter influence relationship, that is, the timing cycle relationship of different parameter changes on electrochemical performance attenuation is determined. This helps to predict the performance change trend of the battery under different working conditions.

[0095] In some embodiments, the method further comprises:

[0096] Tracing the influencing parameters according to the attenuation prediction information to determine the abnormal influencing parameters;

[0097] Perform compensation analysis based on the abnormal influencing parameters and the influence coefficients of the parameters to determine the compensation amount of the abnormal influencing parameters;

[0098] The battery charging and discharging compensation control is performed according to the compensation amount of the abnormal influencing parameter.

[0099] Optionally, analyze the attenuation prediction information to locate the key parameters that cause the electrochemical performance of the energy storage battery to decay. Then, analyze multiple key parameters to find the actual parameters related to the abnormal conditions described in the attenuation prediction information. In other words, by identifying the parameters that are abnormal compared to the historical parameter state, the abnormal influencing parameters are determined. Exemplarily, the abnormal categories of the abnormal influencing parameters include deviation, fluctuation, mutation, periodic change, trend change, etc.

[0100] Optionally, a compensation analysis is performed based on the abnormal influencing parameters and the influence coefficients of each parameter to determine the compensation amount of the abnormal influencing parameters, including determining the size and direction of the compensation amount. That is to say, by determining the compensation amount of the abnormal influencing parameters, the degree and direction of adjustment of the abnormal influencing parameters can be obtained, thereby ensuring that the impact on the performance of the energy storage battery is minimized or eliminated.

[0101] In summary, the attenuation analysis method of the electrochemical performance of energy storage batteries based on cloud computing provided by the present invention has the following technical effects:

[0102] Based on the historical attenuation cases of the electrochemical performance of energy storage batteries, the electrochemical performance type and parameter relationship are decomposed to construct a parameter relationship tree; the node task is decomposed and matched according to the parameter relationship tree and the cloud computing distribution structure to obtain the cloud computing task relationship, where the cloud computing task relationship includes data acquisition parameters, operation targets and corresponding cloud computing nodes; based on the cloud computing task relationship, the mathematical model of each cloud computing node is obtained; the mathematical model of each cloud computing node is uploaded to the cloud platform for limit cycle analysis and identification to obtain the limit cycle; the stability of the limit cycle is analyzed to determine the stability of the limit cycle; based on the stability of the limit cycle, the sensitivity of each factor to the performance attenuation parameters is analyzed to obtain the limit cycle influencing factors and influencing coefficients; based on the limit cycle influencing factors and influencing coefficients, the energy storage battery electrochemical performance attenuation is predicted and analyzed in combination with the application environment and charging and discharging parameters of the energy storage battery. This can reduce the analysis cost, improve the analysis efficiency and achieve accurate technical effects.

[0103] Embodiment 2

[0104] Based on the same concept as the attenuation analysis method of the electrochemical performance of the energy storage battery based on cloud computing in the embodiment, Figure 2 As shown, the present application also provides a cloud computing-based energy storage battery electrochemical performance attenuation analysis system, the system comprising:

[0105] The electrochemical performance analysis module 11 is used to decompose the electrochemical performance type and parameter relationship based on the historical attenuation cases of the electrochemical performance of the energy storage battery, and to construct a parameter relationship tree;

[0106] A cloud computing task matching module 12 is used to perform node task decomposition matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets and corresponding cloud computing nodes;

[0107] A mathematical model acquisition module 13, used to acquire a mathematical model of each cloud computing node based on the cloud computing task relationship;

[0108] A limit cycle analysis module 14 is used to upload the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain a limit cycle;

[0109] A limit cycle stability analysis module 15, used to perform stability analysis on the limit cycle to determine the stability of the limit cycle;

[0110] The attenuation sensitivity analysis module 16 is used to analyze the sensitivity of various factors to the performance attenuation parameters based on the limit cycle stability, and obtain the limit cycle influencing factors and influencing coefficients;

[0111] The performance prediction module 17 is used to predict and analyze the electrochemical performance attenuation of the energy storage battery based on the limit cycle influencing factors and influencing coefficients combined with the application environment and charging and discharging parameters of the energy storage battery.

[0112] Furthermore, the electrochemical performance analysis module 11 also includes:

[0113] The attenuation type acquisition unit is used to determine the electrochemical performance attenuation type according to the historical attenuation cases of the electrochemical performance of the energy storage battery, including battery capacity, charge and discharge rate, and cycle life attenuation;

[0114] An influencing factor analysis unit, used to perform influencing factor analysis according to the electrochemical performance attenuation category, and determine the influencing factors of each electrochemical performance attenuation category, wherein the influencing factors are parameters causing the electrochemical performance attenuation category to occur, including ambient temperature, ambient humidity, charge and discharge power, diaphragm quality, number of charges, and internal resistance;

[0115] The parameter relationship tree establishing unit is used to establish the parameter relationship tree based on the correspondence between the electrochemical performance attenuation category and the influencing factor by taking the electrochemical performance attenuation analysis target as the top event.

[0116] Furthermore, the cloud computing task matching module 12 also includes:

[0117] A data acquisition parameter unit, used to use the electrochemical performance attenuation category in the parameter relationship tree as the operation target of the node attenuation analysis task, and according to the correspondence between the electrochemical performance attenuation category and the influencing factor, use the influencing factor as the data acquisition parameter;

[0118] An operation and processing requirement characteristic unit, used to perform operation and collection equipment characteristic decomposition according to the node attenuation analysis task and data collection parameters, and determine the operation and processing requirement characteristics;

[0119] A computing feature construction unit is used to obtain a cloud computing distribution structure, analyze the load of each edge computing node of the cloud computing and the collection characteristics of the edge device based on the cloud computing distribution structure, and establish a computing feature of the cloud computing node;

[0120] A matching degree calculation unit, configured to perform matching degree calculation according to the computing processing requirement characteristics and the computing characteristics of the cloud computing node, and determine a matching relationship between the node attenuation analysis task and the cloud computing node based on the matching degree obtained by calculation;

[0121] The task relationship acquisition unit is used to establish a matching relationship between the node attenuation analysis task, the data collection task and the cloud computing node, and obtain the cloud computing task relationship.

[0122] Furthermore, the limit cycle analysis module 14 also includes:

[0123] A time-series dynamic analysis unit, for performing a time-series dynamic analysis of data of each electrochemical performance attenuation category based on the mathematical model of each cloud computing node, and obtaining a time-series trend relationship between each data acquisition parameter and the electrochemical performance;

[0124] The phase plane unit is used to construct a phase plane diagram based on the collected data of the cloud computing node, the temporal trend relationship between each data collection parameter and the electrochemical performance;

[0125] A limit cycle identification unit is used to identify limit cycles according to the phase plane diagram using a closed loop identification model, wherein the limit cycle is an isolated closed curve, wherein the closed loop identification model includes a convolution kernel trained with closed loop features.

[0126] Furthermore, the attenuation sensitivity analysis module 16 also includes:

[0127] A parameter change analysis unit, used for performing parameter change analysis on the limit cycle when the limit cycle stability fails to meet a preset condition;

[0128] A unit, used to analyze the influence relationship of the limit cycle according to the change amount, change direction and time series characteristics of each parameter, and determine the influence coefficient of each parameter;

[0129] The coefficient screening unit is used to screen based on the influence coefficients of the parameters to determine the limit cycle influence factors, where the limit cycle influence factors are one or more parameters whose influence coefficients reach a preset threshold.

[0130] Furthermore, the performance prediction module 17 includes:

[0131] The parameter collection unit is used to collect the charging and discharging parameters of the energy storage battery and the application environment parameters through the node collection device and send them to the cloud platform;

[0132] An attenuation analysis model initialization unit, used to construct an attenuation analysis model according to the limit cycle influencing factors and influencing coefficients;

[0133] The impact analysis unit is used to perform impact analysis on the charging and discharging parameters and application environment parameters through the attenuation analysis model, and locate the timing cycle relationship according to the parameter impact relationship to obtain attenuation prediction information.

[0134] Furthermore, the performance prediction module 17 also includes:

[0135] An influencing parameter tracing unit, used to trace the influencing parameters according to the attenuation prediction information and determine abnormal influencing parameters;

[0136] A compensation analysis unit, used to perform compensation analysis according to the abnormal influencing parameters and the influence coefficients of the parameters, and determine the compensation amount of the abnormal influencing parameters;

[0137] The compensation charging and discharging unit is used to perform battery charging and discharging compensation control according to the compensation amount of the abnormal influencing parameter.

[0138] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the cloud computing-based energy storage battery electrochemical performance attenuation analysis system described in embodiment two. For the sake of brevity of the specification, no further elaboration is given here.

[0139] It should be understood that the embodiments disclosed in this application and the above description can enable those skilled in the art to use this application to implement this application. At the same time, this application is not limited to the above-mentioned embodiments, and obvious modifications, combinations and substitutions of the embodiments mentioned in this application also fall within the scope of protection of this application.

Claims

1. Attenuation analysis method of electrochemical performance of energy storage batteries based on cloud computing, It is characterized in that The method comprises: Based on the historical attenuation cases of electrochemical performance of energy storage batteries, the electrochemical performance types and parameter relationships are decomposed and a parameter relationship tree is constructed; Perform node task decomposition and matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets, and corresponding cloud computing nodes; Based on the cloud computing task relationship, obtaining a mathematical model of each cloud computing node; Uploading the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain limit cycles; Performing stability analysis on the limit cycle to determine the stability of the limit cycle; Based on the limit cycle stability, the sensitivity of each factor to the performance attenuation parameter is analyzed to obtain the limit cycle influencing factors and influencing coefficients; According to the influencing factors and influencing coefficients of the limit cycle, combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation of the energy storage battery is predicted and analyzed; The method of decomposing the electrochemical performance type and parameter relationship based on the historical attenuation cases of the electrochemical performance of the energy storage battery and constructing a parameter relationship tree includes: Based on the historical attenuation cases of electrochemical performance of energy storage batteries, determine the type of electrochemical performance attenuation, including battery capacity, charge and discharge rate, and cycle life attenuation; According to the electrochemical performance attenuation category, an influencing factor analysis is performed to determine the influencing factors of each electrochemical performance attenuation category, wherein the influencing factors are parameters that cause the electrochemical performance attenuation category to occur, including ambient temperature, ambient humidity, charge and discharge power, diaphragm quality, number of charges, and internal resistance; Taking the electrochemical performance attenuation analysis target as the top event, and establishing the parameter relationship tree according to the correspondence between the electrochemical performance attenuation category and the influencing factor; The node task decomposition and matching is performed according to the parameter relationship tree and the cloud computing distribution structure to obtain the cloud computing task relationship, including: The electrochemical performance attenuation category in the parameter relationship tree is used as the operation target of the node attenuation analysis task, and according to the corresponding relationship between the electrochemical performance attenuation category and the influencing factor, the influencing factor is used as the data acquisition parameter; Decomposing the computational load and acquisition equipment characteristics according to the node attenuation analysis task and data acquisition parameters, and determining the computational processing demand characteristics; Acquire a cloud computing distribution structure, analyze the load of each edge computing node of the cloud computing and the collection characteristics of the edge device based on the cloud computing distribution structure, and establish a cloud computing node computing characteristic; According to the computing processing requirement characteristics and the computing characteristics of the cloud computing node, a matching degree is calculated, and a matching relationship between the node attenuation analysis task and the cloud computing node is determined based on the calculated matching degree; Establishing a matching relationship between the node attenuation analysis task, the data collection task and the cloud computing node to obtain the cloud computing task relationship; The mathematical model of each cloud computing node is uploaded to the cloud platform for limit cycle analysis and identification to obtain the limit cycle, including: Based on the mathematical model of each cloud computing node, a time-series dynamic analysis of the data of each electrochemical performance attenuation category is performed to obtain the time-series trend relationship between each data acquisition parameter and the electrochemical performance; Construct a phase plane diagram based on the collected data of the cloud computing nodes, the temporal trend relationship between each data collection parameter and the electrochemical performance; According to the phase plane diagram, a closed loop identification model is used to identify a limit cycle, where the limit cycle is an isolated closed curve, wherein the closed loop identification model includes a convolution kernel trained with closed loop features.

2. The method according to claim 1, It is characterized in that Based on the limit cycle stability, the sensitivity of each factor to the performance attenuation parameter is analyzed to obtain the limit cycle influencing factors and influencing coefficients, including: When the stability of the limit cycle cannot meet the preset conditions, performing parameter change analysis on the limit cycle; According to the change amount, change direction and time series characteristics of each parameter, the influence relationship analysis of the limit cycle is performed to determine the influence coefficient of each parameter; Screening is performed based on the influence coefficient of each parameter to determine the limit cycle influence factor, where the limit cycle influence factor is one or more parameters whose influence coefficient reaches a preset threshold.

3. The method according to claim 2, It is characterized in that According to the influencing factors and influencing coefficients of the limit cycle, combined with the application environment and charging and discharging parameters of the energy storage battery, the electrochemical performance attenuation of the energy storage battery is predicted and analyzed, including: Collect the charging and discharging parameters of the energy storage battery and the application environment parameters through the node collection device and send them to the cloud platform; Constructing an attenuation analysis model according to the limit cycle influencing factors and influencing coefficients; The attenuation analysis model is used to analyze the impact of the charging and discharging parameters and the application environment parameters, and the timing cycle relationship is located according to the parameter impact relationship to obtain attenuation prediction information.

4. The method according to claim 3, It is characterized in that The method further comprises: Tracing the influencing parameters according to the attenuation prediction information to determine the abnormal influencing parameters; Perform compensation analysis based on the abnormal influencing parameters and the influence coefficients of the parameters to determine the compensation amount of the abnormal influencing parameters; The battery charging and discharging compensation control is performed according to the compensation amount of the abnormal influencing parameter.

5. Attenuation analysis system of electrochemical performance of energy storage batteries based on cloud computing, It is characterized in that The system is used to implement the attenuation analysis method of electrochemical performance of energy storage batteries based on cloud computing according to any one of claims 1 to 4, and the system comprises: An electrochemical performance analysis module, which is used to decompose the electrochemical performance type and parameter relationship based on the historical attenuation cases of the electrochemical performance of the energy storage battery, and to construct a parameter relationship tree; A cloud computing task matching module, the cloud computing task matching module is used to perform node task decomposition matching according to the parameter relationship tree and the cloud computing distribution structure to obtain a cloud computing task relationship, wherein the cloud computing task relationship includes data collection parameters, computing targets and corresponding cloud computing nodes; A mathematical model acquisition module, the mathematical model acquisition module is used to acquire a mathematical model of each cloud computing node based on the cloud computing task relationship; A limit cycle analysis module, wherein the limit cycle analysis module is used to upload the mathematical model of each cloud computing node to the cloud platform for limit cycle analysis and identification to obtain a limit cycle; A limit cycle stability analysis module, wherein the limit cycle stability analysis module is used to perform stability analysis on the limit cycle to determine the stability of the limit cycle; An attenuation sensitivity analysis module, which is used to analyze the sensitivity of various factors to performance attenuation parameters based on the limit cycle stability, and obtain limit cycle influencing factors and influencing coefficients; The performance prediction module is used to predict and analyze the electrochemical performance attenuation of the energy storage battery based on the limit cycle influencing factors and influencing coefficients combined with the application environment and charging and discharging parameters of the energy storage battery.

Images