Multi-dimensional battery energy storage state analysis method, system, equipment and medium

Abstract

The invention discloses a multi-dimensional battery energy storage state analysis method, system and device and a medium. The method comprises the steps of obtaining first initial data reflecting the health state of a battery to be analyzed; second initial data reflecting the charge state of the to-be-analyzed battery is obtained through calculation based on the electrochemical impedance spectroscopy data of the to-be-analyzed battery and a Kalman filtering method; performing feature extraction on the obtained historical operation data and cycle parameter data of the to-be-analyzed battery, the first initial data and the second initial data to obtain a target battery feature data set; and inputting the target battery characteristic data set into a trained multi-mode battery energy storage state prediction model, and outputting prediction results of the charge state and the health state of the to-be-analyzed battery.

Description

Technical Field

[0001] The present invention relates to the field of energy storage battery technology, and in particular to a multi-dimensional battery energy storage state analysis method, system, device and medium. Background Art

[0002] In response to global warming and climate change, the traditional power industry, which mainly relies on fossil fuel combustion for power generation, is turning to more sustainable power generation methods, such as distributed energy generation, hydropower generation, and bioenergy generation. Energy storage battery technology is an important technology and basic equipment to support the new power system, and is of great significance to promoting green energy transformation, responding to extreme events, ensuring energy supply security, and promoting high-quality development of new energy.

[0003] In recent years, lithium-ion battery energy storage systems have been more widely used. However, due to the lack of accurate prediction and analysis of the overall energy storage status of the battery in existing technologies, it is impossible to timely determine whether there is an abnormality inside the battery energy storage system, and thus it is impossible to ensure the safety and reliability of the battery energy storage system. At present, the operation and maintenance evaluation of battery energy storage systems mainly relies on laboratory-based evaluation methods to evaluate and predict the status of energy storage systems. The means are relatively simple, resulting in low prediction accuracy.

[0004] It can be seen that how to accurately analyze the battery energy storage status to comprehensively ensure the stable operation of the power energy storage system has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a multi-dimensional battery energy storage status analysis method, system, device and medium to solve how to analyze the battery energy storage status based on multiple dimensions to provide stability protection for the power energy storage system.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a multi-dimensional battery energy storage state analysis method, including:

[0007] Acquire first initial data reflecting the health status of the battery to be analyzed;

[0008] Obtaining second initial data reflecting the state of charge of the battery to be analyzed by calculation based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method;

[0009] Performing feature extraction on the acquired historical operation data, cycle parameter data, the first initial data, and the second initial data of the battery to be analyzed to obtain a target battery feature data set;

[0010] The target battery feature data set is input into a trained multimodal battery energy storage state prediction model, and the prediction results of the state of charge and the health state of the battery to be analyzed are output.

[0011] Further, the obtaining of first initial data reflecting the health status of the battery to be analyzed includes:

[0012] Under a preset temperature condition, collecting real-time charge and discharge data of the battery to be analyzed, and constructing a battery equivalent circuit model according to the real-time charge and discharge data;

[0013] Perform parameter identification on the battery to be analyzed according to the battery equivalent circuit model to obtain battery internal parameter data;

[0014] The health state of the battery to be analyzed is analyzed according to the battery internal parameter data to obtain first initial data of the health state.

[0015] Furthermore, the second initial data reflecting the state of charge of the battery to be analyzed is calculated based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method, including:

[0016] Under preset conditions, obtaining electrochemical impedance spectroscopy data of the battery to be analyzed;

[0017] Establishing an electrochemical model based on the electrochemical impedance spectroscopy data, wherein the electrochemical model reflects the relationship between battery impedance and the state of charge of the battery to be analyzed;

[0018] Based on the output result of the electrochemical model, second initial data of the state of charge of the battery to be analyzed is obtained according to the Kalman filtering method.

[0019] Further, the obtaining of electrochemical impedance spectroscopy data of the battery to be analyzed under preset conditions includes:

[0020] Under different ambient temperatures and times, an alternating current signal with a varying frequency is applied to the battery to be analyzed, and the electrochemical impedance spectrum data is acquired in response to the received alternating current signal.

[0021] Furthermore, the obtaining of second initial data of the state of charge of the battery to be analyzed based on the output result of the electrochemical model according to the Kalman filtering method includes:

[0022] Acquire data on the change of the state of charge over time according to the electrochemical impedance spectroscopy data;

[0023] Establishing a charge state transfer equation and a charge observation equation of a Kalman filter based on the state change data and the output result of the electrochemical model;

[0024] The second initial data is acquired according to the charge state transfer equation and the charge observation equation.

[0025] Furthermore, the step of inputting the target battery feature data set into a trained multimodal battery energy storage state prediction model and outputting prediction results of the state of charge and the state of health of the battery to be analyzed includes:

[0026] The target battery characteristic data set is divided into a training set and a test set using a K-fold cross validation method;

[0027] Inputting the training set into a neural network model for training, and testing the neural network model based on the test set to obtain the multimodal battery energy storage state prediction model;

[0028] The target battery feature data set is input into the multimodal battery energy storage state prediction model, and the prediction result is output.

[0029] Furthermore, the acquisition of the cycle parameter data includes:

[0030] Under a preset first cycle number, obtaining first cycle parameter data during a discharge process of the battery;

[0031] Under constant voltage and constant current conditions, the second cycle parameter data of the battery during charging is obtained.

[0032] Another embodiment of the present invention provides a multi-dimensional battery energy storage state analysis system, including:

[0033] An initial health status data acquisition module, used to acquire first initial data reflecting the health status of the battery to be analyzed;

[0034] An initial state of charge data acquisition module, used to calculate and obtain second initial data reflecting the state of charge of the battery to be analyzed based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method;

[0035] A feature extraction module, used for performing feature extraction on the acquired historical operation data, cycle parameter data, the first initial data and the second initial data of the battery to be analyzed, to obtain a target battery feature data set;

[0036] The state prediction module is used to input the target battery feature data set into the trained multimodal battery energy storage state prediction model, and output the prediction results of the charge state and the health state of the battery to be analyzed.

[0037] Another embodiment of the present invention provides a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the multi-dimensional battery energy storage status analysis method as described above is implemented.

[0038] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the multi-dimensional battery energy storage status analysis method as described above is implemented.

[0039] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0040] (1) Perform an initial analysis of the health status and state of charge of the energy storage battery from a multi-dimensional perspective, and dynamically estimate the battery state of charge by combining the Kalman filter algorithm and the battery's electrochemical impedance spectrum data. This can achieve a more accurate estimation of the battery state of charge, thereby improving the performance and reliability of the energy storage battery management system.

[0041] (2) Feature extraction is performed on the historical operating data, cycle parameter data, and initial data of the battery charge and health status. The cycle parameter data can reflect the fluctuations of parameters such as voltage, current, and power during the battery discharge and charging process under multiple cycles. The K-fold cross-validation method is used to divide the data set to train the prediction model, which can improve the accuracy of the model prediction. The constructed multimodal battery energy storage state prediction model can obtain accurate prediction results of the battery charge state and health status. According to the prediction results, the charging and discharging strategy of the energy storage system can be reasonably arranged to ensure the reliability and stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a multi-dimensional battery energy storage state analysis method in one embodiment of the present invention;

[0043] Figure 2 It is an intelligent analysis interface of battery energy storage status in one embodiment of the present invention, including (a): a battery analysis visualization interface and (b): an energy efficiency analysis visualization interface;

[0044] Figure 3 is a structural schematic diagram of a multi-dimensional battery energy storage state analysis system in one embodiment of the present invention;

[0045] Figure 4 It is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. 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.

[0047] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0048] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0049] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0050] It is understandable that the internal state of the battery, SOC and SOH, are two important parameters for evaluating battery performance, which represent the state of charge and health of the battery, respectively. By monitoring SOC, you can know the remaining power of the battery in a timely manner, so as to arrange the charging and use plan reasonably, avoid over-discharge or over-charging of the battery, and extend the service life of the battery. For electric vehicles, hybrid vehicles and other equipment that rely on batteries as a power source, the evaluation of SOC is particularly important. By regularly monitoring and evaluating the battery's SOH, batteries with degraded performance can be discovered and replaced in a timely manner to ensure the stable operation of the system. For application scenarios such as electric vehicles and energy storage systems that rely on batteries as key components, the evaluation of SOH is particularly important.

[0051] An embodiment of the present invention provides a multi-dimensional battery energy storage state analysis method. For details, see Figure 1 , Figure 1 A schematic flow chart showing a multi-dimensional battery energy storage state analysis method in one embodiment of the present invention includes the following steps:

[0052] S1. Acquire first initial data reflecting the health status of a battery to be analyzed.

[0053] In some embodiments of the present invention, the health status of the battery can be calculated by direct measurement, data analysis, incremental capacity analysis (ICA), differential voltage analysis (DVA), and other methods.

[0054] Preferably, in this embodiment, the health status of the battery can be obtained by a parameter identification method.

[0055] Collect the real-time charge and discharge data of the battery, identify the parameters of the battery based on the real-time charge and discharge data, and calculate the battery health status data. It can be understood that the battery charge and discharge data includes the voltage data, current data and temperature data during the battery charge and discharge process. Specifically, the following steps are included:

[0056] First, under preset temperature conditions, real-time charge and discharge data of the battery to be analyzed are collected, and a battery equivalent circuit model is constructed according to the real-time charge and discharge data.

[0057] In some embodiments, the battery may be tested under constant temperature conditions according to a predetermined charge and discharge strategy (such as constant current charging, constant voltage charging, constant current discharging, etc.) to obtain real-time charge and discharge data of the battery to be analyzed.

[0058] Next, the battery to be analyzed is subjected to parameter identification according to the battery equivalent circuit model to obtain battery internal parameter data.

[0059] According to the physical characteristics and application scenarios of the battery to be analyzed, select the appropriate equivalent circuit model structure. Common lithium-ion battery equivalent circuit models include Rint model, Thevenin model, PNGV model, etc. These models usually include components such as internal resistance, capacitance, voltage source, etc., which are used to simulate the electrochemical behavior of the battery.

[0060] Parameter identification is performed according to the selected equivalent circuit model. The result of the model parameter identification, i.e., the internal parameter data of the battery, includes but is not limited to: the internal resistance, polarization resistance, polarization capacitance and open circuit voltage data of the battery.

[0061] It is understandable that in some embodiments of the present invention, during the parameter identification process, an optimization algorithm (such as a genetic algorithm, a least square method / a least square method with a forgetting factor, etc.) can be used to estimate the parameters of the battery equivalent circuit model. The error between the model prediction value and the actual measurement value is also minimized through iterative calculation.

[0062] Preferably, the internal parameters of the battery can be identified by the least square method with a forgetting factor, which can reduce the influence of old data on the current estimation by introducing a forgetting factor, so that the algorithm can better adapt to the dynamic changes of the system.

[0063] Finally, the health status of the battery to be analyzed is analyzed according to the battery internal parameter data to obtain the first initial data of the health status. The first initial data refers to the health status data of the battery to be analyzed obtained by calculation.

[0064] According to the internal parameter data of the battery, the features related to the health status are extracted, including the change of internal resistance, the attenuation of capacity, the enhancement of polarization effect and other features reflecting the health status, so as to obtain the first initial data of the health status of the battery to be analyzed.

[0065] In some real-time methods of the present invention, the health status of the battery can also be analyzed and evaluated through machine learning models and the like to obtain the first initial data.

[0066] S2. Calculate and obtain second initial data reflecting the state of charge of the battery to be analyzed based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method.

[0067] In some embodiments of the present invention, the state of charge of the battery can be calculated by an ampere-hour integration method, an open circuit voltage method, or a model method.

[0068] It is understandable that electrochemical impedance spectroscopy (EIS) is an important electrochemical characterization method, which analyzes and studies the electrode kinetics, double layer, diffusion and other surface behaviors of the system by measuring the change of the target system impedance with a given sine wave frequency. In the estimation of battery state of charge, Kalman filtering can handle nonlinear, time-varying and random characteristics, effectively reduce the influence of noise and error, predict and update the system state in real time, and improve the accuracy and stability of SOC estimation.

[0069] Preferably, in an embodiment of the present invention, the state of charge of the battery is dynamically estimated by combining the Kalman filter algorithm (KF) and the electrochemical impedance spectrum (EIS) data of the battery. Specifically:

[0070] First, under preset conditions, electrochemical impedance spectroscopy data of the battery to be analyzed is obtained; and an electrochemical model is established based on the electrochemical impedance spectroscopy data, wherein the electrochemical model reflects the relationship between battery impedance and the state of charge of the battery to be analyzed.

[0071] In some embodiments of the present invention, it is necessary to collect electrochemical impedance spectroscopy data of the battery at different SOC states so as to accurately reflect the state of charge of the battery.

[0072] Preferably, an alternating current signal with a varying frequency is applied to the battery to be analyzed under different ambient temperatures and times, and the electrochemical impedance spectroscopy data is acquired in response to the received alternating current signal.

[0073] In some embodiments of the present invention, the state of charge can be estimated by building an electrochemical model or an equivalent circuit model of the battery to simulate the electrochemical behavior and electrical characteristics of the battery.

[0074] Preferably, in this embodiment, an electrochemical model of the battery is established based on the electrochemical impedance spectroscopy data. The electrochemical model can output data reflecting the change of the battery impedance with the charge state of the battery to be analyzed. Therefore, it can be understood that in this embodiment, the state change data of the charge state over time (such as battery temperature, aging degree, etc.) is obtained based on the electrochemical impedance spectroscopy data.

[0075] Based on the output result of the electrochemical model, second initial data of the state of charge of the battery to be analyzed is obtained according to the Kalman filtering method.

[0076] This step is the design of the Kalman filter algorithm. In this embodiment, the state variables are defined according to the acquired state change data, and then the state of charge transfer equation and charge observation equation of the Kalman filter are established based on the state change data and the output results of the electrochemical model. The charge state transfer equation describes the change of the battery state of charge over time, while the charge observation equation reflects the output based on the electrochemical model (such as voltage, current and EIS characteristics).

[0077] Finally, the second initial data is obtained according to the state of charge transfer equation and the charge observation equation. It can be understood that by combining the Kalman filter algorithm and the electrochemical impedance spectroscopy data, the advantages of both can be fully utilized to obtain more accurate SOC data.

[0078] S3. Perform feature extraction on the acquired historical operation data, cycle parameter data, first initial data and second initial data of the battery to be analyzed to obtain a target battery feature data set.

[0079] It can be understood that the cycle parameter data generated during the battery's charge and discharge process reflects the dynamic behavior of the battery during the charge and discharge process, the energy conversion efficiency, and the changes in internal parameters. Therefore, feature extraction of the cycle parameter data helps to improve the accuracy of model prediction.

[0080] In the embodiment of the present invention, the cycle parameter data includes data such as charge and discharge capacity, time, voltage and current, temperature, internal resistance and number of cycles.

[0081] In some embodiments of the present invention, the first cycle parameter data of the battery during the discharge process is obtained under a preset first cycle number. Specifically:

[0082] First, you need to set an initial number of cycles as a reference point. This number can be determined based on experimental design or actual needs.

[0083] When the preset first cycle number is reached, the discharge process of the battery is monitored. Professional battery testing equipment or systems can be used to record various parameters during the discharge process with high accuracy.

[0084] The first cycle parameter data is extracted from the discharge process, including but not limited to the discharge capacity (ie, the total amount of electricity released by the battery during the discharge process), the discharge time, the voltage change during the discharge process, the discharge current and the battery temperature.

[0085] Furthermore, in some embodiments of the present invention, the second cycle parameter data of the battery during charging is obtained under constant voltage and constant current.

[0086] Similarly, during the constant voltage and constant current charging process, the charging process is monitored and various key parameters are recorded.

[0087] The second cycle parameter data is extracted from the charging process, including charging capacity (ie, the total amount of electricity received by the battery during the charging process), charging time, voltage change during the charging process, charging current, battery temperature, and energy efficiency.

[0088] It can be understood that in the prediction of battery SOC and SOH, the process of feature processing involves selecting, extracting and transforming raw data to create more informative features and provide better input for the neural network model.

[0089] In the embodiment of the present invention, accurate prediction of battery SOC and SOH needs to consider many factors, including not only cycle parameter data and calculated initial health state and charge state data, but also battery historical operation data.

[0090] The collected data may contain noise or outliers, so preprocessing is required, such as data cleaning, data smoothing, and data normalization. Feature extraction is performed on the preprocessed data. In the embodiment of the present invention, the extracted features include: battery health factor, charge and discharge cycle feature quantity extracted from each charge and discharge cycle, time series features, and statistical features, so as to construct a target battery feature data set.

[0091] The embodiment of the present invention can solve the problems of sparsity and imbalance of internal battery data through the above-mentioned feature processing process, and make the data easier to be learned and understood by the neural network through reasonable feature conversion and standardization methods.

[0092] S4. Input the target battery feature data set into the trained multimodal battery energy storage state prediction model, and output the prediction results of the state of charge and the health state of the battery to be analyzed.

[0093] It is understandable that in some embodiments of the present invention, considering that battery data has time series characteristics, RNN (such as LSTM, GRU) can be selected to build a prediction model. However, other types of neural networks can also be considered, such as a combination of convolutional neural network (CNN) and RNN.

[0094] Furthermore, in some embodiments of the present invention, when dividing the target battery characteristic data set, random division or time series division may be adopted.

[0095] Preferably, in an embodiment of the present invention, the K-fold cross validation method in the time series partitioning method is selected to divide the target battery characteristic data set into a training set and a test set. The selection of K usually depends on the size of the data set and the complexity of the model training.

[0096] Preferably, K may be 5 or 10. Further, the target battery feature data set is randomly divided into K mutually exclusive subsets of similar sizes to perform iterative training and testing of the model.

[0097] Specifically, for each iteration (K times in total), the union of K-1 subsets is selected as the current training set, and the remaining subset is used as the current test set. The training set is input into the neural network model for training, and the neural network model is tested based on the test set, and the performance indicators (such as accuracy, mean square error, etc.) are recorded. According to the results of K iterations, the model with the best average performance can be selected as the final multimodal battery energy storage state prediction model.

[0098] The target battery feature data set is input into the multimodal battery energy storage state prediction model, and the prediction result is output. Specifically, the prediction result includes the state of charge and health state of the battery to be analyzed.

[0099] Based on the prediction results, a battery maintenance log is generated and sent to different terminals for storage or the prediction results are sent to a visualization interface for visual display.

[0100] In some embodiments of the present invention, the battery intelligent analysis interface includes a battery analysis visualization interface and an energy efficiency analysis visualization interface. Figure 2 , Figure 2 It is an intelligent analysis interface of battery energy storage status in one embodiment of the present invention, including (a): a battery analysis visualization interface and (b): an energy efficiency analysis visualization interface.

[0101] As can be seen from (a), the battery analysis visualization interface includes: 1. stack voltage analysis; 2. cluster voltage analysis; 3. single cell voltage analysis.

[0102] As can be seen from (b), the energy efficiency analysis visualization interface includes:

[0103] 1. Comprehensive efficiency: The line chart shows the comprehensive efficiency, which is divided into four time dimensions: the past 7 days (excluding today), the current month (display radio button to customize the month), the current year (display radio button to customize the year), and all (since the power station is connected to the cloud platform). The specific data meanings include:

[0104] a. Comprehensive efficiency: (station power consumption + discharge amount) / charge amount;

[0105] b. System efficiency: discharge amount / charge amount;

[0106] c. Station electricity consumption ratio: This part is hidden when there is no station electricity consumption, and the overall icon is centered (whether the power station has station electricity consumption is mainly determined by whether there is a station electricity meter);

[0107] d. Site ranking (consistent with the time dimension of the chart).

[0108] 2. Discharge achievement rate: The area chart shows the discharge achievement rate, which is divided into four time dimensions: the past 7 days (excluding today), the current month (display radio button to customize the month), the current year (display radio button to customize the year), and all (since the power station is connected to the cloud platform). The specific data meanings include:

[0109] a. Increase the planned discharge capacity of the power station at the entrance, and the discharge achievement rate = actual discharge capacity / planned discharge capacity;

[0110] b. Site ranking (consistent with the time dimension of the chart).

[0111] In summary, the embodiment of the present invention constructs an equivalent circuit model through real-time charging and discharging data to perform parameter identification on the battery to obtain the initial data of the battery health status, and obtains the initial data of the battery state of charge by acquiring the electrochemical impedance spectrum data of the battery in combination with the Kalman filter method; and extracts features from the acquired historical operation data, cycle parameter data, health status and initial data of the state of charge of the battery to obtain a target battery feature data set, and divides the data set through cross-validation to train and test the model, thereby constructing a multimodal battery energy storage state prediction model; the battery state of charge and health status are predicted through the multimodal battery energy storage state prediction model. In the energy storage system, the prediction results of the battery state of charge and health status are analyzed to formulate a reasonable charging and discharging strategy for the energy storage system, thereby improving the safety and stability of the electric energy storage system.

[0112] An embodiment of the present invention provides a multi-dimensional battery energy storage status analysis system. For details, see Figure 3 , Figure 3 The structure diagram of a multi-dimensional battery energy storage state analysis system in one embodiment of the present invention is shown, including:

[0113] An initial health status data acquisition module M1 is used to acquire first initial data reflecting the health status of the battery to be analyzed;

[0114] An initial state of charge data acquisition module M2, used for calculating and obtaining second initial data reflecting the state of charge of the battery to be analyzed based on the electrochemical impedance spectrum data of the battery to be analyzed and the Kalman filter method;

[0115] A feature extraction module M3 is used to extract features from the acquired historical operation data, cycle parameter data, the first initial data and the second initial data of the battery to be analyzed to obtain a target battery feature data set;

[0116] The state prediction module M4 is used to input the target battery feature data set into the trained multi-modal battery energy storage state prediction model, and output the prediction results of the charge state and the health state of the battery to be analyzed.

[0117] like Figure 4 As shown, the embodiment of the present invention further provides a computer device, Figure 4 A structural block diagram of a preferred embodiment of a computer device provided by the present invention, wherein the computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the multi-dimensional battery energy storage status analysis method as described above when executing the computer program.

[0118] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0119] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.

[0120] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory can also be other volatile solid-state storage devices.

[0121] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 4 The structural block diagram is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium may be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0122] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to perform the steps in the multi-dimensional battery energy storage state analysis method of the above embodiment, for example Figure 1 Steps S1 to S4 described in .

[0123] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A multi-dimensional battery energy storage state analysis method, characterized in that: include: Acquire first initial data reflecting the health status of the battery to be analyzed; Obtaining second initial data reflecting the state of charge of the battery to be analyzed by calculation based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method; Performing feature extraction on the acquired historical operation data, cycle parameter data, the first initial data, and the second initial data of the battery to be analyzed to obtain a target battery feature data set; The target battery feature data set is input into a trained multimodal battery energy storage state prediction model, and the prediction results of the state of charge and the health state of the battery to be analyzed are output.

2. The multi-dimensional battery energy storage state analysis method according to claim 1, characterized in that: The obtaining of first initial data reflecting the health status of the battery to be analyzed includes: Under a preset temperature condition, collecting real-time charge and discharge data of the battery to be analyzed, and constructing a battery equivalent circuit model according to the real-time charge and discharge data; Perform parameter identification on the battery to be analyzed according to the battery equivalent circuit model to obtain battery internal parameter data; The health state of the battery to be analyzed is analyzed according to the battery internal parameter data to obtain first initial data of the health state.

3. The multi-dimensional battery energy storage state analysis method according to claim 1, characterized in that: The second initial data reflecting the state of charge of the battery to be analyzed is calculated based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method, including: Under preset conditions, obtaining electrochemical impedance spectroscopy data of the battery to be analyzed; Establishing an electrochemical model based on the electrochemical impedance spectroscopy data, wherein the electrochemical model reflects the relationship between battery impedance and the state of charge of the battery to be analyzed; Based on the output result of the electrochemical model, second initial data of the state of charge of the battery to be analyzed is obtained according to the Kalman filtering method.

4. The multi-dimensional battery energy storage state analysis method according to claim 3, characterized in that: The step of obtaining electrochemical impedance spectroscopy data of the battery to be analyzed under preset conditions includes: Under different ambient temperatures and times, an alternating current signal with a varying frequency is applied to the battery to be analyzed, and the electrochemical impedance spectrum data is acquired in response to the received alternating current signal.

5. The multi-dimensional battery energy storage state analysis method according to claim 3, characterized in that: The step of obtaining the second initial data of the state of charge of the battery to be analyzed based on the output result of the electrochemical model according to the Kalman filtering method includes: Acquire data on the change of the state of charge over time according to the electrochemical impedance spectroscopy data; Establishing a charge state transfer equation and a charge observation equation of a Kalman filter based on the state change data and the output result of the electrochemical model; The second initial data is acquired according to the charge state transfer equation and the charge observation equation.

6. The multi-dimensional battery energy storage state analysis method according to claim 1, characterized in that: The step of inputting the target battery feature data set into a trained multimodal battery energy storage state prediction model and outputting prediction results of the state of charge and the health state of the battery to be analyzed includes: The target battery characteristic data set is divided into a training set and a test set using a K-fold cross validation method; Inputting the training set into a neural network model for training, and testing the neural network model based on the test set to obtain the multimodal battery energy storage state prediction model; The target battery feature data set is input into the multimodal battery energy storage state prediction model, and the prediction result is output.

7. The multi-dimensional battery energy storage state analysis method according to claim 1, characterized in that: The acquisition of the cycle parameter data includes: Under a preset first cycle number, obtaining first cycle parameter data during a discharge process of the battery; Under constant voltage and constant current conditions, the second cycle parameter data of the battery during charging is obtained.

8. A multi-dimensional battery energy storage status analysis system, characterized in that: include: An initial health status data acquisition module, used to acquire first initial data reflecting the health status of the battery to be analyzed; An initial state of charge data acquisition module, used to calculate and obtain second initial data reflecting the state of charge of the battery to be analyzed based on the electrochemical impedance spectroscopy data of the battery to be analyzed and the Kalman filter method; A feature extraction module, used for performing feature extraction on the acquired historical operation data, cycle parameter data, the first initial data and the second initial data of the battery to be analyzed, to obtain a target battery feature data set; The state prediction module is used to input the target battery feature data set into the trained multimodal battery energy storage state prediction model, and output the prediction results of the charge state and the health state of the battery to be analyzed.

9. A computer device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the multi-dimensional battery energy storage status analysis method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the multi-dimensional battery energy storage status analysis method according to any one of claims 1 to 7 is implemented.

Images