Lithium battery life monitoring and health state autonomous protection system and method

Abstract

The invention relates to the technical field of electromagnetic measurement, and discloses a lithium battery life monitoring and health state autonomous protection system and method, and the system comprises a data collection module, a trend consistency discrimination module, a health assessment report generation module, a health deviation degree verification module, a deterioration risk deduction module, and an autonomous protection strategy generation module. The method comprises the following steps: collecting lithium battery operation multi-dimensional electrical parameters, and eliminating abnormal fluctuations through a time sequence window to obtain a time sequence correlation parameter set; generating an initial health assessment report based on health state feature matching analysis, and verifying the initial health assessment report with historical data to obtain a health deviation degree; worsening risk deduction is carried out in combination with the parameter trend change rate, optimized health assessment and life early warning are output, and corresponding autonomous protection strategies are matched and started according to the optimization health assessment and life early warning; according to the invention, the life monitoring and health state autonomous protection efficiency of the lithium battery can be improved.

Description

Technical Field

[0001] This invention relates to the field of electromagnetic measurement technology, and in particular to a lithium battery life monitoring and health status autonomous protection system and method. Background Technology

[0002] In the field of lithium battery life monitoring and health status protection, existing technologies have significant shortcomings in data acquisition and processing. They often struggle to effectively purify and filter multi-dimensional electrical parameters collected during operation, failing to accurately remove random and abnormal fluctuations in data. This leads to interference and bias in the parameter data upon which subsequent analysis relies. Consequently, the health status feature matching analysis based on this data lacks reliability, and the generated health assessment results fail to accurately reflect the actual operating conditions of the lithium battery, thus affecting the accurate judgment of the battery's health status.

[0003] Meanwhile, existing technologies are ineffective in predicting health status risks and implementing protection strategies. Most fail to comprehensively extrapolate the degree of health status deviation and the rate of parameter trend change, making it difficult to identify lithium battery health degradation risks in advance, resulting in insufficient timeliness and accuracy in lifespan warnings. Furthermore, existing protection strategies are mostly fixed settings, lacking adaptation to specific health problems and risk levels of lithium batteries. They cannot autonomously match targeted protection schemes, leading to delayed or unsuitable protection measures, failing to effectively slow down battery aging, and thus failing to provide sufficient assurance for the safe and stable operation of lithium batteries. Summary of the Invention

[0004] This invention provides a lithium battery life monitoring and health status autonomous protection system and method to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a lithium battery life monitoring and health status autonomous protection system, characterized in that the system includes a data acquisition module, a trend consistency analysis module, a health assessment report generation module, a health deviation verification module, a deterioration risk prediction module, and an autonomous protection strategy generation module, wherein: The data acquisition module is used to collect the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery, and obtain a multi-dimensional electrical parameter dataset of the lithium battery. The trend consistency analysis module is used to compare the parameter trends of adjacent time windows based on a preset time window and the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, so as to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery. The health assessment report generation module is used to perform matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state, so as to obtain an initial health status assessment report of the lithium battery. The health deviation verification module is used to verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery during the same period, so as to obtain the health status deviation of the lithium battery. The degradation risk simulation module is used to perform degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, and to obtain the optimized battery health status assessment report and life risk warning information of the lithium battery. The autonomous protection strategy generation module is used to select the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the life risk warning information.

[0006] In a preferred embodiment, when the data acquisition module collects the battery terminal voltage, charging and discharging current, and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery, it is specifically used for: The real-time electrical signals of the lithium battery are collected through the electrical signal transmission link during the operation of the lithium battery; The real-time electrical signal is subjected to multi-level anti-interference filtering and purification to obtain the pure electrical signal of the lithium battery; Based on the parameter characteristics of the pure electrical signal, the signal amplitude of the pure electrical signal is accurately captured; Based on the signal amplitude, wavelet transform is performed on the pure electrical signal to obtain characteristic signals of the battery terminal voltage, charging and discharging current and internal resistance change rate in the lithium battery; Based on the electrical parameter storage specifications of the lithium battery, the feature signals are standardized and calibrated to obtain a multi-dimensional electrical parameter dataset of the lithium battery.

[0007] In a preferred embodiment, when the trend consistency analysis module performs a consistency comparison of parameter trends in adjacent time windows based on a preset time window and the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, in order to eliminate random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery, it is specifically used for: Based on the temporal distribution characteristics of the multidimensional electrical parameter dataset, the multidimensional electrical parameter dataset is adaptively divided into temporal windows to obtain continuous temporal windows in the multidimensional electrical parameter dataset and parameter subsets corresponding to the temporal windows. By using the least squares method, the parameter subset is trend-fitted to obtain the trend curve and trend feature vector of the parameter subset; Based on the trend feature vectors of adjacent time series windows, the trend curve is quantified to obtain the trend consistency coefficient of the adjacent time series windows. The formula for calculating the trend consistency coefficient is as follows: ; In the formula, This represents the trend consistency coefficient. This represents the dimension of the trend feature vector. The first element in the trend feature vector represents the... Preset weights for each feature, This represents the first trend feature vector in the previous time series window. One portion, This represents the first trend eigenvector in the next time series window. One component; Identify adjacent time-series windows where the trend consistency coefficient exceeds a preset consistency threshold, and mark the adjacent time-series windows as abnormal time-series windows of the lithium battery; Based on the parameter subset corresponding to the abnormal time series window, random abnormal fluctuation data in the multi-dimensional electrical parameter dataset are removed to obtain the time series correlation parameter set of the lithium battery.

[0008] In a preferred embodiment, when the trend consistency analysis module performs the process of removing random abnormal fluctuation data from the multi-dimensional electrical parameter dataset based on the parameter subset corresponding to the abnormal time series window to obtain the time series correlation parameter set of the lithium battery, it is specifically used for: Extract the parameter change magnitude of the parameter subset in the abnormal time series window; The abnormal causes of the parameter changes are determined to distinguish the abnormal types of the parameter subset; Based on the aforementioned anomaly type, the parameter subset marked as random fluctuation is precisely filtered out to obtain the preliminary filtered parameter subset set of the lithium battery. The time-series continuity of the parameter subset after initial screening is verified to obtain the time-series associated parameter set of the lithium battery.

[0009] In a preferred embodiment, when the health assessment report generation module performs matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state to obtain an initial health state assessment report for the lithium battery, it is specifically used for: The time-series correlation parameter set is mapped to the standard electrical parameter feature library of the lithium battery to obtain the sensitivity of the electrical parameters in the time-series correlation parameter set to the health status of the lithium battery. The sensitivity is prioritized, and electrical parameters with a sensitivity higher than a preset sensitivity threshold are retained to obtain the key feature parameters of the time-series correlation parameter set; The key feature parameters are matched and compared with the corresponding feature ranges in the standard electrical parameter feature library in a dimension-by-dimensional manner to obtain the multi-dimensional matching results of the key feature parameters. Based on the failure mechanism of the lithium battery and the sensitivity, the influence weight of the key characteristic parameters is determined; Based on the aforementioned influence weights, the multi-dimensional matching results are weighted and comprehensively evaluated to obtain a preliminary health assessment result for the lithium battery. According to the preset report format specifications, the preliminary health assessment results are standardized and integrated to obtain the initial health status assessment report of the lithium battery.

[0010] In a preferred embodiment, the health deviation verification module, when performing a consistency verification between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the health status deviation of the lithium battery, is specifically used for: The initial health status assessment report is decomposed into dimensions to obtain the multi-dimensional assessment results of the initial health status assessment report; Based on the historical health status database of the lithium battery, retrieve the historical health status assessment data corresponding to the current monitoring cycle of the lithium battery, and align the parameter dimensions and statistical calibers of the multi-dimensional assessment results with those of the historical health status assessment data. Calculate the evaluation difference value for the aligned parameter dimensions, wherein the calculation formula for the evaluation difference value is as follows: ; In the formula, Indicates the first Evaluation difference values ​​for each parameter dimension, This indicates the current monitoring cycle number of the lithium battery. Evaluation values ​​for each parameter dimension, This indicates the first [item] in the historical health status assessment data. Evaluation values ​​for each parameter dimension; Based on the influence weights of the aforementioned parameter dimensions, the evaluation difference values ​​are weighted and fused to obtain the comprehensive deviation coefficient of the lithium battery. The comprehensive deviation coefficient is mapped to a preset deviation level range to determine the degree of deviation of the health status of the lithium battery.

[0011] In a preferred embodiment, when the degradation risk simulation module performs degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation from the health status and the trend change rate of the time-series correlation parameter set, and obtains an optimized battery health status assessment report and lifespan risk warning information for the lithium battery, it is specifically used for: A time-series change rate analysis is performed on the key feature parameters in the time-series correlation parameter set to obtain a set of trend change rates of the key feature parameters; Based on the set of the degree of deviation from the health status and the rate of change of the trend, the risk coefficient of the deterioration of the health status of the lithium battery is calculated; Based on the aforementioned deterioration risk coefficient and combined with the risk level classification rules for lithium batteries, the deterioration tendency type of the lithium battery is determined to obtain the deterioration tendency type of the lithium battery. Based on the aforementioned deterioration tendency type, a risk situation simulation is performed on the health status of the lithium battery to obtain the deterioration trend of the health status of the lithium battery. Based on the deterioration trend of the health status, the initial health status assessment report is supplemented and corrected to obtain the optimized battery health status assessment report of the lithium battery. Based on the risk level corresponding to the deterioration risk coefficient, the corresponding lifespan risk warning information in the optimized battery health status assessment report is marked.

[0012] In a preferred embodiment, the formula for calculating the deterioration risk coefficient is as follows: ; In the formula, This represents the risk coefficient of deterioration. This represents the comprehensive deviation coefficient corresponding to the degree of deviation from the stated health status. This represents the preset trend influence coefficient. This indicates the number of the key feature parameters. Indicates the first The deterioration of key feature parameters affects the weights. Indicates the first The rate of change of the trend of each key characteristic parameter.

[0013] In a preferred embodiment, when the autonomous protection strategy generation module performs the task of selecting the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the lifespan risk warning information, it is specifically used for: The optimized battery health status assessment report is subjected to structured analysis to obtain the analysis results of the health problems of the lithium battery; Extract the risk level and risk impact range from the lifespan risk warning information to obtain the risk characteristic information of the lithium battery; Based on the health problem analysis results and risk characteristic information, the corresponding battery protection strategies in the preset battery protection control strategy library are selected to obtain the candidate protection strategy set for the lithium battery. The suitability of the candidate protection strategy set is verified by adaptation simulation to obtain the suitability score of the candidate protection strategy set; The battery protection strategy with the highest compatibility score is adopted as the autonomous protection strategy for the lithium battery.

[0014] To address the aforementioned problems, this invention also provides a method for monitoring the lifespan and autonomously protecting the health status of lithium batteries, the method comprising: S1. Collect the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery. S2. Based on a preset time window, and combined with the changing trend characteristics of the parameters in the multi-dimensional electrical parameter dataset, the consistency of the parameter trends in adjacent time windows is compared to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset, thereby obtaining the time-series associated parameter set of the lithium battery. S3. Based on the electrical parameter characteristics of the lithium battery in a healthy state, perform matching and correlation analysis on the key feature parameters in the time-series correlation parameter set to obtain the initial health status assessment report of the lithium battery. S4. Verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the degree of deviation of the health status of the lithium battery. S5. Based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, the deterioration risk of the health status of the lithium battery in subsequent operating cycles is deduced, and the optimized battery health status assessment report and life risk warning information of the lithium battery are obtained. S6. Based on the optimized battery health status assessment report and the life risk warning information, select the corresponding autonomous protection strategy from the preset battery protection control strategy library.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention purifies electrical signals through multi-level anti-interference filtering and wavelet transform, eliminates random abnormal data by comparing the trend consistency of time-series windows, and determines the degree of health deviation by verifying with historical data from the same period. Multiple steps ensure the reliability of parameters, and combined with weighted evaluation of key feature parameters, the health status assessment is more in line with the actual working conditions of the battery.

[0016] 2. This invention infers the risk of deterioration by analyzing the degree of health deviation and the rate of change of parameter trends, and accurately outputs lifespan warnings; it selects suitable solutions from a preset strategy library and verifies them through simulation, matching targeted autonomous protection strategies to avoid deterioration risks in advance, delay battery aging, and improve operational safety and service life. Attached Figure Description

[0017] Figure 1 This is a system architecture diagram of a lithium battery life monitoring and health status autonomous protection system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating a method for monitoring the lifespan and autonomously protecting the health status of a lithium battery, as provided in an embodiment of the present invention.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0021] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0022] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0023] In practice, the server-side equipment deployed in a lithium battery life monitoring and health status autonomous protection system may consist of one or more devices. This lithium battery life monitoring and health status autonomous protection system can be implemented as: a business instance, a virtual machine, or hardware devices. For example, this lithium battery life monitoring and health status autonomous protection system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this lithium battery life monitoring and health status autonomous protection system can be understood as software deployed on a cloud node, used to provide a lithium battery life monitoring and health status autonomous protection system to various user terminals. Alternatively, this lithium battery life monitoring and health status autonomous protection system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, this lithium battery life monitoring and health status autonomous protection system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide a lithium battery life monitoring and health status autonomous protection system to various user terminals.

[0024] In terms of implementation, a lithium battery life monitoring and health status autonomous protection system and a user terminal are mutually compatible. That is, if the lithium battery life monitoring and health status autonomous protection system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the lithium battery life monitoring and health status autonomous protection system is implemented as a website, then the user terminal is implemented as a webpage; or if the lithium battery life monitoring and health status autonomous protection system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0025] like Figure 1 The figure shown is a system architecture diagram of a lithium battery life monitoring and health status autonomous protection system provided in an embodiment of the present invention.

[0026] The lithium battery life monitoring and health status autonomous protection system 100 described in this invention can be installed on a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the lithium battery life monitoring and health status autonomous protection system 100 may include a data acquisition module 101, a trend consistency analysis module 102, a health assessment report generation module 103, a health deviation verification module 104, a deterioration risk prediction module 105, and an autonomous protection strategy generation module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0027] In this embodiment of the invention, in a lithium battery life monitoring and health status autonomous protection system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the lithium battery life monitoring and health status autonomous protection system provided by this embodiment of the invention, without modifying the program code, the applicability of the lithium battery life monitoring and health status autonomous protection system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the lithium battery life monitoring and health status autonomous protection system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0028] The following describes the components and workflow of a lithium battery life monitoring and health status autonomous protection system, using specific embodiments as examples: The data acquisition module 101 is used to acquire the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery, and obtain a multi-dimensional electrical parameter dataset of the lithium battery. In this embodiment of the invention, when the data acquisition module collects the battery terminal voltage, charging and discharging current, and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery, it is specifically used for: The real-time electrical signals of the lithium battery are collected through the electrical signal transmission link during the operation of the lithium battery; The real-time electrical signal is subjected to multi-level anti-interference filtering and purification to obtain the pure electrical signal of the lithium battery; Based on the parameter characteristics of the pure electrical signal, the signal amplitude of the pure electrical signal is accurately captured; Based on the signal amplitude, wavelet transform is performed on the pure electrical signal to obtain characteristic signals of the battery terminal voltage, charging and discharging current and internal resistance change rate in the lithium battery; Based on the electrical parameter storage specifications of the lithium battery, the feature signals are standardized and calibrated to obtain a multi-dimensional electrical parameter dataset of the lithium battery.

[0029] The specific process of acquiring the real-time electrical signal of the lithium battery through the electrical signal transmission link during lithium battery operation is as follows: a complete electrical signal transmission link is constructed based on the signal transmission wires led out from the lithium battery electrodes. This link is directly connected to the signal receiving port of the signal acquisition module. The signal acquisition module continuously receives the electrical signals transmitted in the transmission link, synchronously tracks the changes in the operating state of the lithium battery, records the transmission feedback information of the electrical signals in the link in real time, and finally forms a real-time electrical signal that can reflect the real-time operating state of the lithium battery.

[0030] The specific process of performing multi-stage anti-interference filtering and purification on the real-time electrical signal to obtain the pure electrical signal of the lithium battery is as follows: First, a passive filtering method is used, employing a filter circuit composed of capacitors and inductors to perform the first stage of processing on the received real-time electrical signal, filtering out power frequency interference signals mixed in the real-time electrical signal. Then, an active filtering method is used, employing a filter circuit built with operational amplifiers to perform the second stage of processing on the electrical signal after the first stage of processing, filtering out high-frequency noise interference present in the electrical signal. Finally, a signal shaping method is used to perform the third stage of processing on the electrical signal after the first two stages of filtering, regulating the amplitude fluctuation range of the electrical signal, so that the waveform of the electrical signal remains stable and continuous. The electrical signal obtained after the above three stages of processing is the pure electrical signal of the lithium battery.

[0031] Based on the parameter characteristics of the pure electrical signal, the specific process of accurately capturing the signal amplitude of the pure electrical signal is as follows: for the obtained pure electrical signal, scan its waveform changes segment by segment, identify the peak interval and stable interval in the waveform, lock the specific position of the waveform peak in the stable interval, and extract the signal intensity value corresponding to the position. This value is the signal amplitude of the pure electrical signal.

[0032] The specific process of performing wavelet transform on the pure electrical signal based on the signal amplitude to obtain the characteristic signals of the battery terminal voltage, charging and discharging current, and internal resistance change rate in the lithium battery is as follows: using the captured signal amplitude as the reference value for wavelet transform, the waveform of the pure electrical signal is divided into segments according to the intervals corresponding to the amplitude. Each segment of the waveform is scaled, stretching the waveform segments with higher amplitudes to highlight their feature details and compressing the waveform segments with lower amplitudes to retain their basic information. Then, each segment of the scaled waveform is translated to make the feature points of each segment of the waveform accurately correspond to the preset feature recognition intervals. By performing targeted feature extraction on the transformed waveform, feature signals that can reflect the change law of the lithium battery terminal voltage, feature signals that can reflect the change law of the lithium battery charging and discharging current, and feature signals that can reflect the change law of the lithium battery internal resistance change rate are selected respectively.

[0033] Based on the lithium battery's electrical parameter storage specifications, the specific process of standardizing and calibrating the feature signals to obtain the multi-dimensional electrical parameter dataset of the lithium battery is as follows: According to the preset lithium battery electrical parameter storage specifications, which clearly define the signal format, data recording order, feature identification rules, and information storage duration of the electrical parameters, the three types of feature signals extracted are formatted according to the specifications, and the recording duration, signal sampling interval, and feature information labeling position of each type of feature signal are unified. Then, the three types of feature signals are integrated in an orderly manner according to a preset combination order. The integrated set containing three types of feature information—lithium battery terminal voltage, charging and discharging current, and internal resistance change rate—is the multi-dimensional electrical parameter dataset of the lithium battery.

[0034] The beneficial effects are as follows: by relying on the lithium battery electrode signal transmission link to collect real-time electrical signals, the real-time acquisition and accurate recording of signals reflecting the operating status of the lithium battery are ensured. Through multi-level anti-interference filtering and purification processing consisting of passive filtering, active filtering and signal shaping, power frequency interference and high-frequency noise in the real-time electrical signals are effectively filtered out, signal waveform fluctuations are regulated, and a stable and continuous pure electrical signal is obtained. Based on the parameter characteristics of the pure electrical signal, the signal amplitude is accurately captured, providing a reliable reference value for subsequent signal transformation. Using this amplitude value as a reference, scaling and translation operations are performed on the pure electrical signal, which can accurately extract the characteristic signals reflecting the lithium battery terminal voltage, charging and discharging current and internal resistance change rate. According to the lithium battery electrical parameter storage specifications, the characteristic signals are standardized and calibrated in a standardized manner and integrated in an orderly manner, finally forming a dataset containing multiple key electrical parameters, which can fully meet the needs of subsequent comprehensive analysis of the lithium battery operating status.

[0035] The trend consistency analysis module 102 is used to compare the parameter trends of adjacent time windows based on a preset time window and the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, so as to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery. In this embodiment of the invention, when the trend consistency analysis module performs a consistency comparison of parameter trends in adjacent time windows based on a preset time window and combined with the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, in order to eliminate random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery, it is specifically used for: Based on the temporal distribution characteristics of the multidimensional electrical parameter dataset, the multidimensional electrical parameter dataset is adaptively divided into temporal windows to obtain continuous temporal windows in the multidimensional electrical parameter dataset and parameter subsets corresponding to the temporal windows. By using the least squares method, the parameter subset is trend-fitted to obtain the trend curve and trend feature vector of the parameter subset; Based on the trend feature vectors of adjacent time series windows, the trend curve is quantified to obtain the trend consistency coefficient of the adjacent time series windows. The formula for calculating the trend consistency coefficient is as follows: ; In the formula, This represents the trend consistency coefficient. This represents the dimension of the trend feature vector. The first element in the trend feature vector represents the... Preset weights for each feature, This represents the first trend feature vector in the previous time series window. One portion, This represents the first trend eigenvector in the next time series window. One component; Identify adjacent time-series windows where the trend consistency coefficient exceeds a preset consistency threshold, and mark the adjacent time-series windows as abnormal time-series windows of the lithium battery; Based on the parameter subset corresponding to the abnormal time series window, random abnormal fluctuation data in the multi-dimensional electrical parameter dataset are removed to obtain the time series correlation parameter set of the lithium battery.

[0036] When the trend consistency analysis module executes the parameter subset corresponding to the abnormal time series window to remove random abnormal fluctuation data from the multi-dimensional electrical parameter dataset and obtain the time series correlation parameter set of the lithium battery, it is specifically used for: Extract the parameter change magnitude of the parameter subset in the abnormal time series window; The abnormal causes of the parameter changes are determined to distinguish the abnormal types of the parameter subset; Based on the aforementioned anomaly type, the parameter subset marked as random fluctuation is precisely filtered out to obtain the preliminary filtered parameter subset set of the lithium battery. The time-series continuity of the parameter subset after initial screening is verified to obtain the time-series associated parameter set of the lithium battery.

[0037] Based on the temporal distribution characteristics of the multi-dimensional electrical parameter dataset, the specific process of adaptively dividing the multi-dimensional electrical parameter dataset into temporal windows to obtain continuous temporal windows and parameter subsets corresponding to the temporal windows is as follows: Analyze the temporal arrangement pattern of the multi-dimensional electrical parameter dataset, determine the dense and sparse intervals of electrical parameter changes over time in the dataset, use the density of electrical parameter changes as the basis for window division, set shorter windows in dense intervals and longer windows in sparse intervals, so that the electrical parameter data in each window can fully reflect the parameter change characteristics within the corresponding time period. The continuous time interval formed after the division is the temporal window, and the electrical parameter data contained in each temporal window is the parameter subset corresponding to that temporal window.

[0038] The specific process of obtaining the trend curve and trend feature vector of the parameter subset by trend fitting using the least squares method is as follows: each electrical parameter data point in the parameter subset is mapped to a time-varying coordinate system, and the curvature and extension direction of the curve are adjusted so that the curve can fit all data points in the parameter subset to the greatest extent, minimizing the deviation of each data point from the curve. The smooth curve formed after fitting is the trend curve of the parameter subset. The core features such as the direction characteristics and curvature of the trend curve are extracted and transformed into the corresponding feature expression form, which is the trend feature vector of the parameter subset.

[0039] The specific process of quantifying the trend consistency of the trend curves based on the trend feature vectors of adjacent time series windows to obtain the trend consistency coefficient of the adjacent time series windows is as follows: compare the trend feature vectors corresponding to two adjacent time series windows, analyze whether the trends of the two feature vectors are the same, whether the fluctuation amplitudes are similar, and whether the change rhythms are matched. Based on the results of the comparison, the consistency of the trend curves of adjacent time series windows is quantified, and the result of this quantification is the trend consistency coefficient of the adjacent time series windows.

[0040] The dimension of the trend feature vector is determined from the trend feature vectors corresponding to adjacent time windows. This trend feature vector is the product of trend fitting of a subset of parameters, and its dimension is the number of features contained in the vector.

[0041] The trend eigenvector of the first The preset weights of each feature are pre-set based on the degree of influence of lithium battery electrical parameters on the analysis of operating status. This degree of influence is determined by combining the priority of each electrical parameter during normal operation of the lithium battery.

[0042] The first trend eigenvector in the previous time series window Each component is extracted from the trend feature vector corresponding to the previous time series window, which is obtained by trend fitting of the parameter subset of the previous time series window.

[0043] The first trend feature vector in the next time series window Each component is extracted from the trend feature vector corresponding to the next time series window obtained from the division. This trend feature vector is obtained by trend fitting of the parameter subset of the next time series window.

[0044] The formula for calculating the trend consistency coefficient is used to calculate the trend consistency coefficient of adjacent time series windows. The specific process is as follows: first, obtain the absolute value of the difference between the corresponding components in the trend feature vector of the previous time series window and the next time series window; then, calculate the ratio between the absolute value and the larger value of the two components; next, multiply the ratio by the preset weight of the corresponding feature; then, accumulate the multiplication results of all components. The final result is the trend consistency coefficient, which is an indicator used to quantify the consistency of trend curves of adjacent time series windows.

[0045] The smaller the difference between the corresponding components of the trend feature vectors of two adjacent time series windows, the smaller the ratio of the absolute value of the difference of the corresponding components to the larger value, the smaller the result after multiplying by the preset weight, the smaller the cumulative value of the result of multiplying all components, and the smaller the trend consistency coefficient, indicating that the trend curves of adjacent time series windows are more consistent.

[0046] When the difference between the corresponding components of the trend feature vectors of two adjacent time series windows is greater, the ratio of the absolute value of the difference of the corresponding components to the larger value is greater, the result after multiplying by the preset weight is also greater, the cumulative value of the result of multiplying all components is also greater, and the trend consistency coefficient is also greater, indicating that the trend curves of adjacent time series windows are less consistent.

[0047] The specific process of identifying adjacent time-series windows whose trend consistency coefficient exceeds a preset consistency threshold and marking them as abnormal time-series windows of the lithium battery is as follows: the calculated trend consistency coefficient of the adjacent time-series windows is compared one by one with the preset consistency threshold, adjacent time-series windows with trend consistency coefficient values ​​higher than the preset consistency threshold are selected, and these selected adjacent time-series windows are uniformly marked as abnormal time-series windows of the lithium battery.

[0048] The specific process for extracting the parameter change amplitude of the parameter subset within the abnormal time series window is as follows: First, the parameter subset corresponding to the abnormal time series window is locked. Then, the initial and final values ​​of the electrical parameter data within this subset are determined. The range and degree of difference between the initial and final values ​​are analyzed. The comprehensive representation of this range and degree of difference is the parameter change amplitude of the parameter subset within the abnormal time series window. The specific process for determining the abnormal cause of the parameter change amplitude to distinguish the abnormal type of the parameter subset involves combining the change patterns of electrical parameters during normal operation of the lithium battery. The rate, direction, and duration of change corresponding to the parameter change amplitude are analyzed. It is determined whether the parameter change amplitude is caused by random factors during lithium battery operation or by fault factors within the lithium battery itself. Based on the determination result, the abnormal situation of the parameter subset is divided into different categories, which are the abnormal types of the parameter subset.

[0049] Based on the aforementioned anomaly type, the specific process of precisely filtering out the parameter subsets marked as random fluctuations to obtain the preliminary set of parameter subsets for the lithium battery is as follows: according to the anomaly type determination result, the parameter subsets marked as random fluctuations are filtered out, and these parameter subsets are removed one by one from the multi-dimensional electrical parameter dataset. After the removal is completed, the set formed by integrating all the remaining parameter subsets is the preliminary set of parameter subsets for the lithium battery.

[0050] The specific process of performing time-series continuity verification on the initially screened parameter subset set to obtain the time-series associated parameter set of the lithium battery is as follows: check whether the time-series windows corresponding to each parameter subset in the initially screened parameter subset set are continuous in time sequence; for positions with time breakpoints, confirm whether there are any missing valid parameter subsets at the breakpoints; if not, retain the current state of the breakpoint; if so, supplement the corresponding valid parameter subsets; the parameter subset set with complete time-series association formed after verification and necessary supplementation is the time-series associated parameter set of the lithium battery.

[0051] The beneficial effects are that by dividing the time-series features of the fitting electrical parameters through an adaptive time-series window, a reliable trend curve and feature vector are obtained by fitting with the least squares method, abnormal time-series windows are accurately identified by using the trend consistency coefficient, the abnormality type is distinguished by tracing the cause of the abnormality, and after filtering out the subset of random fluctuation parameters, a complete set of time-series related parameters is formed by time-series continuity verification, which meets the needs of accurate analysis of the operating status of lithium batteries.

[0052] The health assessment report generation module 103 is used to perform matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state, so as to obtain an initial health status assessment report of the lithium battery. In this embodiment of the invention, when the health assessment report generation module performs matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state to obtain an initial health state assessment report for the lithium battery, it is specifically used for: The time-series correlation parameter set is mapped to the standard electrical parameter feature library of the lithium battery to obtain the sensitivity of the electrical parameters in the time-series correlation parameter set to the health status of the lithium battery. The sensitivity is prioritized, and electrical parameters with a sensitivity higher than a preset sensitivity threshold are retained to obtain the key feature parameters of the time-series correlation parameter set; The key feature parameters are matched and compared with the corresponding feature ranges in the standard electrical parameter feature library in a dimension-by-dimensional manner to obtain the multi-dimensional matching results of the key feature parameters. Based on the failure mechanism of the lithium battery and the sensitivity, the influence weight of the key characteristic parameters is determined; Based on the aforementioned influence weights, the multi-dimensional matching results are weighted and comprehensively evaluated to obtain a preliminary health assessment result for the lithium battery. According to the preset report format specifications, the preliminary health assessment results are standardized and integrated to obtain the initial health status assessment report of the lithium battery.

[0053] The specific process of mapping the time-series correlation parameter set to the standard electrical parameter feature library of the lithium battery to obtain the sensitivity of the electrical parameters in the time-series correlation parameter set to the health status of the lithium battery is as follows: The standard electrical parameter feature library of the lithium battery is pre-constructed based on electrical parameter data corresponding to different health statuses throughout the entire life cycle of the lithium battery. It includes the correlation between various types of electrical parameters and health status. Each electrical parameter in the time-series correlation parameter set is matched with the same type of electrical parameter in the standard electrical parameter feature library, and the degree of correlation between the change of the electrical parameter and the change of health status is analyzed. This degree of correlation is the sensitivity of the electrical parameters in the time-series correlation parameter set to the health status of the lithium battery.

[0054] The specific process of prioritizing the sensitivity and retaining electrical parameters with a sensitivity higher than a preset sensitivity threshold to obtain the key feature parameters of the time-series correlation parameter set is as follows: the sensitivity corresponding to each electrical parameter is arranged in descending order of value. The preset sensitivity threshold is pre-set in conjunction with the core focus dimension of lithium battery health status determination. Electrical parameters with a sensitivity value higher than the threshold are selected, and these selected electrical parameters are the key feature parameters of the time-series correlation parameter set.

[0055] The specific process of performing a dimension-by-dimensional matching and comparison between the key feature parameters and the corresponding feature ranges in the standard electrical parameter feature library to obtain the multi-dimensional matching results of the key feature parameters is as follows: retrieve the feature range of the same type of electrical parameter corresponding to each key feature parameter from the standard electrical parameter feature library. This feature range includes the normal range, warning range, and abnormal range of the parameter under the healthy state of the lithium battery. Match the actual value of the key feature parameter with these ranges one by one to determine the range in which the parameter is located. Integrate the range correspondence results of all key feature parameters, and the resulting set is the multi-dimensional matching result of the key feature parameters.

[0056] The specific process for determining the influence weight of the key characteristic parameters based on the failure mechanism and sensitivity of the lithium battery is as follows: The failure mechanism of the lithium battery includes the mechanism by which different abnormal electrical parameters cause the performance of the lithium battery to decline or fail. Combining the sensitivity of each key characteristic parameter, parameters with high sensitivity and more direct impact on the health of the lithium battery in the failure mechanism are assigned higher weight values, while parameters with low sensitivity and weaker impact in the failure mechanism are assigned lower weight values, thereby determining the influence weight of each key characteristic parameter.

[0057] The specific process of performing a weighted comprehensive evaluation on the multi-dimensional matching results based on the aforementioned influence weights to obtain the preliminary health assessment result of the lithium battery is as follows: according to preset rules, the interval results corresponding to each key feature parameter in the multi-dimensional matching results are converted into evaluation scores; each evaluation score is multiplied by the influence weight corresponding to the key feature parameter to obtain the weighted evaluation value of each parameter; the weighted evaluation values ​​of all key feature parameters are summarized; and the lithium battery health status level corresponding to the summarized result is determined to be the preliminary health assessment result of the lithium battery.

[0058] The process of standardizing and integrating the preliminary health assessment results according to the preset report format specifications to obtain the initial health status assessment report of the lithium battery is as follows: The preset report format specifications clarify the structural modules of the health status assessment report, including key characteristic parameters, multi-dimensional matching results, preliminary health assessment level and corresponding explanatory content. The preliminary health assessment results are filled in according to these modules, and the expression and layout order of the content are unified. The document formed after filling and layout is the initial health status assessment report of the lithium battery.

[0059] The beneficial effects are that by mapping the time-series correlation parameter set to the standard electrical parameter feature library of lithium batteries to obtain sensitivity, after screening highly sensitive key parameters, the results matched with the standard feature range are combined with the failure mechanism to determine the influence weight of key parameters, and the weighted evaluation is used to obtain the preliminary health judgment result. The results are then integrated into a standardized health assessment report in a specific format to meet the health assessment needs of lithium batteries.

[0060] The health deviation verification module 104 is used to verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery during the same period, so as to obtain the health status deviation of the lithium battery. In this embodiment of the invention, when the health deviation verification module performs a consistency verification between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the health status deviation of the lithium battery, it is specifically used for: The initial health status assessment report is decomposed into dimensions to obtain the multi-dimensional assessment results of the initial health status assessment report; Based on the historical health status database of the lithium battery, retrieve the historical health status assessment data corresponding to the current monitoring cycle of the lithium battery, and align the parameter dimensions and statistical calibers of the multi-dimensional assessment results with those of the historical health status assessment data. Calculate the evaluation difference value for the aligned parameter dimensions, wherein the calculation formula for the evaluation difference value is as follows: ; In the formula, Indicates the first Evaluation difference values ​​for each parameter dimension, This indicates the current monitoring cycle number of the lithium battery. Evaluation values ​​for each parameter dimension, This indicates the first [item] in the historical health status assessment data. Evaluation values ​​for each parameter dimension; Based on the influence weights of the aforementioned parameter dimensions, the evaluation difference values ​​are weighted and fused to obtain the comprehensive deviation coefficient of the lithium battery. The comprehensive deviation coefficient is mapped to a preset deviation level range to determine the degree of deviation of the health status of the lithium battery.

[0061] The specific process of decomposing the initial health status assessment report into multiple dimensions to obtain the multi-dimensional assessment results of the initial health status assessment report is as follows: The initial health status assessment report contains different content modules such as the interval matching status of key feature parameters and the preliminary health judgment level. The content corresponding to these modules is extracted separately, and the content corresponding to each module is the assessment result of one dimension. The assessment results of all dimensions are integrated to obtain the multi-dimensional assessment results of the initial health status assessment report.

[0062] Based on the historical health status database of the lithium battery, the specific process of retrieving historical health status assessment data corresponding to the current monitoring cycle of the lithium battery and aligning the parameter dimensions and statistical calibers of the multi-dimensional assessment results with those of the historical health status assessment data is as follows: The historical health status database of the lithium battery is a collection storing health status assessment data of the lithium battery in previous monitoring cycles. The current monitoring cycle for health assessment is determined, and the historical health status assessment data corresponding to this cycle is retrieved from the database. Each parameter dimension in the multi-dimensional assessment results is matched one-to-one with the same type of parameter in the historical data. At the same time, the statistical time range and data calculation method of the two are unified to complete the alignment of parameter dimensions and statistical calibers.

[0063] The specific process for calculating the evaluation difference value of the aligned parameter dimension is as follows: for each aligned parameter dimension, obtain the value corresponding to that dimension in the multi-dimensional evaluation results and the value corresponding to that dimension in the historical health status evaluation data, and calculate the difference between these two values. This difference is the evaluation difference value of that parameter dimension after alignment.

[0064] When calculating the evaluation difference value of the corresponding parameter dimension, the evaluation value of the corresponding parameter dimension of the current monitoring cycle of the lithium battery involved in the evaluation difference value of the corresponding parameter dimension is extracted from the multi-dimensional evaluation results obtained after the initial health status evaluation report is decomposed into dimensions. The multi-dimensional evaluation results are the product of the initial health status evaluation report after dimensional decomposition.

[0065] The evaluation values ​​of the corresponding parameter dimensions involved in the historical health status evaluation data are extracted from the historical health status database of lithium batteries, which are historical health status evaluation data corresponding to the current monitoring cycle. Furthermore, the historical health status evaluation data has been aligned with the parameter dimensions and statistical calibers of the multi-dimensional evaluation results.

[0066] The calculation process of this formula is as follows: First, obtain the absolute value of the difference between the evaluation value of the corresponding parameter dimension in the current monitoring cycle of the lithium battery and the evaluation value of the corresponding parameter dimension in the historical health status evaluation data. Then, perform a ratio operation between this absolute value and the evaluation value of the corresponding parameter dimension in the historical health status evaluation data. The result obtained is the evaluation difference value of the corresponding parameter dimension. This evaluation difference value is used to reflect the difference in the evaluation status of the same parameter dimension in the current monitoring cycle and the historical cycle.

[0067] Under the calculation logic of this formula, the smaller the difference between the evaluation value of the corresponding parameter dimension in the current monitoring cycle of the lithium battery and the evaluation value of the corresponding parameter dimension in the historical health status evaluation data, the smaller the absolute value of the difference, the smaller its ratio to the historical evaluation value, and the smaller the corresponding evaluation difference value, indicating that the evaluation status of the parameter dimension in the current monitoring cycle and the historical cycle is smaller.

[0068] The larger the difference between the assessment value of the corresponding parameter dimension in the current monitoring period of the lithium battery and the assessment value of the corresponding parameter dimension in the historical health status assessment data, the larger the absolute value of the difference, the larger its ratio to the historical assessment value, and the larger the corresponding assessment difference value, indicating that the assessment status of this parameter dimension in the current monitoring period is greater than that in the historical period.

[0069] The specific process of weighting and fusing the evaluation difference values ​​based on the influence weights of the parameter dimensions to obtain the comprehensive deviation coefficient of the lithium battery is as follows: the influence weight of the parameter dimension is the weight value previously determined for the key feature parameters. For the evaluation difference value of each parameter dimension, it is multiplied by the influence weight corresponding to that parameter dimension to obtain the weighted difference value of that dimension. The weighted difference values ​​of all parameter dimensions are summarized, and the summed result is the comprehensive deviation coefficient of the lithium battery.

[0070] The specific process of mapping the comprehensive deviation coefficient to a preset deviation level range to determine the degree of deviation of the health status of the lithium battery is as follows: the preset deviation level range is a coefficient range corresponding to different degrees of deviation, including the intervals corresponding to slight deviation, moderate deviation, and severe deviation. The comprehensive deviation coefficient is compared with these intervals one by one to determine the interval in which the coefficient is located. The degree of deviation corresponding to the interval is the degree of deviation of the health status of the lithium battery.

[0071] The beneficial effects include the dimensional decomposition of the initial health status assessment report, resulting in a clear and multi-dimensional assessment result. By retrieving historical assessment data for the corresponding period from the lithium battery historical health status database and aligning the parameter dimensions and statistical calibers, the effectiveness and accuracy of data comparison can be ensured. The calculated assessment difference values ​​of the aligned parameter dimensions can intuitively reflect the changes in the current and historical health status. By combining the influence weights of the parameter dimensions to perform weighted fusion of the assessment difference values, a comprehensive deviation coefficient reflecting the overall change in the lithium battery health status can be obtained. Mapping the comprehensive deviation coefficient to a preset deviation level range can accurately determine the degree of deviation in the lithium battery health status, providing a reliable basis for the comprehensive assessment of the lithium battery health status.

[0072] The degradation risk simulation module 105 is used to perform degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, and obtain the optimized battery health status assessment report and life risk warning information of the lithium battery. In this embodiment of the invention, when the degradation risk simulation module performs degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation from the health status and the trend change rate of the time-series correlation parameter set, and obtains an optimized battery health status assessment report and lifespan risk warning information for the lithium battery, it is specifically used for: A time-series change rate analysis is performed on the key feature parameters in the time-series correlation parameter set to obtain a set of trend change rates of the key feature parameters; Based on the set of the degree of deviation from the health status and the rate of change of the trend, the risk coefficient of the deterioration of the health status of the lithium battery is calculated; Based on the aforementioned deterioration risk coefficient and combined with the risk level classification rules for lithium batteries, the deterioration tendency type of the lithium battery is determined to obtain the deterioration tendency type of the lithium battery. Based on the aforementioned deterioration tendency type, a risk situation simulation is performed on the health status of the lithium battery to obtain the deterioration trend of the health status of the lithium battery. Based on the deterioration trend of the health status, the initial health status assessment report is supplemented and corrected to obtain the optimized battery health status assessment report of the lithium battery. Based on the risk level corresponding to the deterioration risk coefficient, the corresponding lifespan risk warning information in the optimized battery health status assessment report is marked.

[0073] The formula for calculating the risk of deterioration is as follows: ; In the formula, This represents the risk coefficient of deterioration. This represents the comprehensive deviation coefficient corresponding to the degree of deviation from the stated health status. This represents the preset trend influence coefficient. This indicates the number of the key feature parameters. Indicates the first The deterioration of key feature parameters affects the weights. Indicates the first The rate of change of the trend of each key characteristic parameter.

[0074] The comprehensive deviation coefficient corresponding to the degree of deviation from the health status is a product obtained by weighting and fusing the assessment difference values ​​based on the influence weights of the parameter dimensions. This comprehensive deviation coefficient is used to map to a preset deviation level range to determine the degree of deviation from the health status. The preset trend influence coefficient is a fixed value set in advance based on the operating characteristics of the lithium battery and the degree of influence of the trend of lithium battery health deterioration. The number of key feature parameters is the number of key feature parameters retained after sensitivity screening in the time-series correlation parameter set. These key feature parameters are electrical parameters with sensitivity higher than a preset sensitivity threshold.

[0075] No. The weighting of the deterioration impact of each key characteristic parameter is set based on the degree of influence of the key characteristic parameter on the health deterioration of the lithium battery. This degree of influence is determined by the corresponding weight value in conjunction with the failure mechanism of the lithium battery. The rate of change of a key feature parameter is the rate of change of the corresponding key feature parameter extracted from the set of trend change rates obtained after analyzing the rate of change of key feature parameters in the set of time-series correlation parameters.

[0076] This formula is used to calculate the risk coefficient of deterioration of the health status of lithium batteries. The specific process is as follows: for each key characteristic parameter, the corresponding deterioration impact weight is multiplied by the trend change rate. The multiplication results of all key characteristic parameters are accumulated. The accumulated result is multiplied by the preset trend impact coefficient. The result is then multiplied by the comprehensive deviation coefficient corresponding to the degree of deviation of the health status. The final result is the deterioration risk coefficient, which is used to reflect the degree of risk of the lithium battery health status developing in a bad direction.

[0077] When the comprehensive deviation coefficient corresponding to the degree of deviation from the health status increases, the deterioration risk coefficient also increases, indicating a higher risk of deterioration in the lithium battery's health status. Similarly, when the preset trend influence coefficient increases, the deterioration risk coefficient also increases, indicating a higher risk of deterioration in the lithium battery's health status. Furthermore, when the cumulative sum of the product of the deterioration influence weights corresponding to key characteristic parameters and the trend change rate increases, the deterioration risk coefficient also increases, indicating a higher risk of deterioration in the lithium battery's health status.

[0078] When any one of the following decreases: the comprehensive deviation coefficient corresponding to the degree of deviation from the health status, the preset trend influence coefficient, or the cumulative result of the product of the deterioration influence weight and the trend change rate corresponding to the key characteristic parameters, the deterioration risk coefficient will decrease accordingly, indicating that the risk of deterioration of the health status of the lithium battery is lower.

[0079] The specific process of performing time-series change rate analysis on key feature parameters in the time-series correlation parameter set to obtain the trend change rate set of key feature parameters is as follows: the key feature parameters are the core electrical parameters retained in the time-series correlation parameter set after sensitivity screening. For each key feature parameter, the specific value corresponding to it in each continuous time-series window contained in the time-series correlation parameter set is extracted. The correlation between the change magnitude of the parameter value and the corresponding time interval between two adjacent time-series windows is analyzed to determine the rate of change of each key feature parameter over time. The set formed by summarizing and organizing the rate of change of all key feature parameters is the trend change rate set of key feature parameters.

[0080] The specific process for calculating the deterioration risk coefficient of lithium battery health status based on the set of deviation degree and trend change rate is as follows: the deviation degree is the result determined by mapping the comprehensive deviation coefficient to a preset deviation level range; the trend change rate set is the set of the rate of change of key characteristic parameters; by combining the severity of the deviation degree and the rate of change of the trend, these two types of information are integrated to obtain a result that reflects the risk level of lithium battery health status developing in a bad direction. This result is the deterioration risk coefficient of lithium battery health status.

[0081] Based on the deterioration risk coefficient and combined with the risk level classification rules for lithium batteries, the specific process of determining the deterioration tendency type of lithium batteries is as follows: the risk level classification rules are pre-set rules based on the different rates and ranges of health deterioration of lithium batteries. The calculated deterioration risk coefficient is matched one by one with the corresponding risk intervals in the rules. Based on the matching results, the specific category of the current health status deterioration of the lithium battery is determined, and this category is the deterioration tendency type of the lithium battery.

[0082] Based on the type of deterioration tendency, the risk situation of the health status of lithium batteries is extrapolated to obtain the specific process of the deterioration trend of the health status of lithium batteries. The type of deterioration tendency is a specific category of the health deterioration of lithium batteries. Based on the deterioration speed and development characteristics corresponding to the type, the changes of key characteristic parameters of lithium batteries and the development trend of the degree of deviation of health status in subsequent continuous time periods are extrapolated. The result of integrating and sorting out the information of these extrapolated development trends is the deterioration trend of the health status of lithium batteries.

[0083] The specific process of supplementing and correcting the initial health status assessment report based on the trend of deterioration in the health status of the lithium battery is as follows: the initial health status assessment report is a health assessment document that has been standardized and integrated. The deduced trend of deterioration in the health status is added to the corresponding content module of the report. At the same time, the health status description in the report that does not match the current deterioration trend is corrected. The complete document formed after the supplementation and correction is the optimized battery health status assessment report of the lithium battery.

[0084] The specific process of marking the corresponding lifespan risk warning information in the optimized battery health status assessment report based on the risk level corresponding to the deterioration risk coefficient is as follows: the risk level corresponding to the deterioration risk coefficient is a level matched from the risk level classification rules. According to the warning content requirements corresponding to the level, the lifespan risk warning content matching the risk level is marked in the designated prompt area of ​​the optimized battery health status assessment report. This prompt content is the corresponding lifespan risk warning information in the optimized battery health status assessment report.

[0085] The beneficial effect is that by analyzing the rate of change of key characteristic parameters in the time-series correlation parameter set, it is possible to clearly identify how quickly each key characteristic parameter changes over time. The resulting set of trend change rates provides a precise basis for subsequent risk analysis. By combining the degree of deviation from the health status with this set of trend change rates, the risk level of the health status deteriorating can be comprehensively reflected, accurately indicating the health risk level of the lithium battery.

[0086] The autonomous protection strategy generation module 106 is used to select the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the life risk warning information.

[0087] In this embodiment of the invention, when the autonomous protection strategy generation module performs the task of selecting the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the lifespan risk warning information, it is specifically used for: The optimized battery health status assessment report is subjected to structured analysis to obtain the analysis results of the health problems of the lithium battery; Extract the risk level and risk impact range from the lifespan risk warning information to obtain the risk characteristic information of the lithium battery; Based on the health problem analysis results and risk characteristic information, the corresponding battery protection strategies in the preset battery protection control strategy library are selected to obtain the candidate protection strategy set for the lithium battery. The suitability of the candidate protection strategy set is verified by adaptation simulation to obtain the suitability score of the candidate protection strategy set; The battery protection strategy with the highest compatibility score is adopted as the autonomous protection strategy for the lithium battery.

[0088] The specific process of performing structured analysis on the optimized battery health status assessment report to obtain the analysis results of the lithium battery health problems is as follows: The optimized battery health status assessment report is a document formed after supplementing and correcting the initial health status assessment report. The report contains structured modules such as health status description, deterioration trend information, and lifespan risk warning. The content related to lithium battery health abnormalities in these modules is extracted one by one, and the abnormal parameter types and deviations from the health status are identified. The result of integrating and sorting this information is the analysis result of the lithium battery health problems.

[0089] The specific process of extracting the risk level and risk impact range from the lifespan risk warning information to obtain the risk characteristic information of the lithium battery is as follows: the lifespan risk warning information is the prompt content marked in the optimized battery health status assessment report. The corresponding risk severity category is determined from this content, which is the risk level. At the same time, the area and degree of impact of the risk on the lifespan, performance, etc. of the lithium battery are determined, which is the risk impact range. The set formed by integrating the extracted risk level and risk impact range is the risk characteristic information of the lithium battery.

[0090] Based on the health problem analysis results and risk characteristic information, the specific process of selecting the corresponding battery protection strategies from the preset battery protection control strategy library to obtain the candidate protection strategy set for the lithium battery is as follows: The preset battery protection control strategy library is a set of strategies pre-constructed according to different lithium battery health problems and risk characteristics. The abnormal type in the health problem analysis results, the level and impact range in the risk characteristic information are matched one by one with the applicable conditions corresponding to each strategy in the strategy library. All strategies whose applicable conditions completely correspond to the current information are selected. The set formed by integrating these strategies is the candidate protection strategy set for the lithium battery.

[0091] The specific process of performing adaptability simulation verification on the candidate protection strategy set to obtain the adaptability score of the candidate protection strategy set is as follows: simulate the current operating environment and health status of the lithium battery, apply each strategy in the candidate protection strategy set to the simulated scenario, observe the improvement of lithium battery health problems and the degree of reduction of risk characteristic information after the implementation of each strategy, and assign a corresponding score to each strategy based on these actual performances. This score is the adaptability score of each strategy in the candidate protection strategy set.

[0092] The specific process of using the battery protection strategy with the highest adaptability score as the autonomous protection strategy of the lithium battery involves comparing the adaptability scores of all strategies in the candidate protection strategy set, determining the strategy with the highest score, and identifying this strategy as the protection strategy applicable to the current state of the lithium battery, which is the autonomous protection strategy of the lithium battery.

[0093] The beneficial effects include: structured analysis of optimized battery health assessment reports to identify health anomalies and deviations, obtaining accurate health problem results; extraction of the level and scope of lifespan risk to form risk characteristic information; screening of a pre-set strategy library to obtain a set of suitable candidate protection strategies; conducting adaptability simulation verification of candidate strategies to objectively evaluate their effectiveness and obtain an adaptability score; selecting the strategy with the highest adaptability as the autonomous protection strategy to obtain the optimal solution and effectively maintain the health of lithium batteries.

[0094] Reference Figure 2 The diagram shown is a flowchart illustrating a lithium battery life monitoring and health status autonomous protection method according to an embodiment of the present invention. In this embodiment, the lithium battery life monitoring and health status autonomous protection method includes: S1. Collect the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery. S2. Based on a preset time window, and combined with the changing trend characteristics of the parameters in the multi-dimensional electrical parameter dataset, the consistency of the parameter trends in adjacent time windows is compared to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset, thereby obtaining the time-series associated parameter set of the lithium battery. S3. Based on the electrical parameter characteristics of the lithium battery in a healthy state, perform matching and correlation analysis on the key feature parameters in the time-series correlation parameter set to obtain the initial health status assessment report of the lithium battery. S4. Verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the degree of deviation of the health status of the lithium battery. S5. Based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, the deterioration risk of the health status of the lithium battery in subsequent operating cycles is deduced, and the optimized battery health status assessment report and life risk warning information of the lithium battery are obtained. S6. Based on the optimized battery health status assessment report and the life risk warning information, select the corresponding autonomous protection strategy from the preset battery protection control strategy library.

[0095] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0096] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A lithium battery life monitoring and health status autonomous protection system, characterized in that, The system includes a data acquisition module, a trend consistency analysis module, a health assessment report generation module, a health deviation verification module, a deterioration risk prediction module, and a self-protection strategy generation module, wherein: The data acquisition module is used to collect the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery, and obtain a multi-dimensional electrical parameter dataset of the lithium battery. The trend consistency analysis module is used to compare the parameter trends of adjacent time windows based on a preset time window and the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, so as to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery. The health assessment report generation module is used to perform matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state, so as to obtain an initial health status assessment report of the lithium battery. The health deviation verification module is used to verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery during the same period, so as to obtain the health status deviation of the lithium battery. The degradation risk simulation module is used to perform degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, and to obtain the optimized battery health status assessment report and life risk warning information of the lithium battery. The autonomous protection strategy generation module is used to select the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the life risk warning information.

2. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, When the data acquisition module collects the battery terminal voltage, charging and discharging current, and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery, it is specifically used for: The real-time electrical signals of the lithium battery are collected through the electrical signal transmission link during the operation of the lithium battery; The real-time electrical signal is subjected to multi-level anti-interference filtering and purification to obtain the pure electrical signal of the lithium battery; Based on the parameter characteristics of the pure electrical signal, the signal amplitude of the pure electrical signal is accurately captured; Based on the signal amplitude, wavelet transform is performed on the pure electrical signal to obtain characteristic signals of the battery terminal voltage, charging and discharging current and internal resistance change rate in the lithium battery; Based on the electrical parameter storage specifications of the lithium battery, the feature signals are standardized and calibrated to obtain a multi-dimensional electrical parameter dataset of the lithium battery.

3. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, The trend consistency analysis module, when performing a consistency comparison of parameter trends in adjacent time windows based on a preset time window and in conjunction with the changing trend characteristics of parameters in the multi-dimensional electrical parameter dataset, in order to eliminate random abnormal fluctuation data in the multi-dimensional electrical parameter dataset and obtain the time-series associated parameter set of the lithium battery, is specifically used for: Based on the temporal distribution characteristics of the multidimensional electrical parameter dataset, the multidimensional electrical parameter dataset is adaptively divided into temporal windows to obtain continuous temporal windows in the multidimensional electrical parameter dataset and parameter subsets corresponding to the temporal windows. By using the least squares method, the parameter subset is trend-fitted to obtain the trend curve and trend feature vector of the parameter subset; Based on the trend feature vectors of adjacent time series windows, the trend curve is quantified to obtain the trend consistency coefficient of the adjacent time series windows. The formula for calculating the trend consistency coefficient is as follows: ； In the formula, This represents the trend consistency coefficient. This represents the dimension of the trend feature vector. The first element in the trend feature vector represents the... Preset weights for each feature, This represents the first trend feature vector in the previous time series window. One portion, This represents the first trend eigenvector in the next time series window. One component; Identify adjacent time-series windows where the trend consistency coefficient exceeds a preset consistency threshold, and mark the adjacent time-series windows as abnormal time-series windows of the lithium battery; Based on the parameter subset corresponding to the abnormal time series window, random abnormal fluctuation data in the multi-dimensional electrical parameter dataset are removed to obtain the time series correlation parameter set of the lithium battery.

4. The lithium battery life monitoring and health status autonomous protection system as described in claim 3, characterized in that, When the trend consistency analysis module executes the parameter subset corresponding to the abnormal time series window to remove random abnormal fluctuation data from the multi-dimensional electrical parameter dataset and obtain the time series correlation parameter set of the lithium battery, it is specifically used for: Extract the parameter change magnitude of the parameter subset in the abnormal time series window; The abnormal causes of the parameter changes are determined to distinguish the abnormal types of the parameter subset; Based on the aforementioned anomaly type, the parameter subset marked as random fluctuation is precisely filtered out to obtain the preliminary filtered parameter subset set of the lithium battery. The time-series continuity of the parameter subset after initial screening is verified to obtain the time-series associated parameter set of the lithium battery.

5. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, When the health assessment report generation module performs matching and correlation analysis on key feature parameters in the time-series correlation parameter set based on the electrical parameter characteristics of the lithium battery in a healthy state to obtain an initial health state assessment report for the lithium battery, it is specifically used for: The time-series correlation parameter set is mapped to the standard electrical parameter feature library of the lithium battery to obtain the sensitivity of the electrical parameters in the time-series correlation parameter set to the health status of the lithium battery. The sensitivity is prioritized, and electrical parameters with a sensitivity higher than a preset sensitivity threshold are retained to obtain the key feature parameters of the time-series correlation parameter set; The key feature parameters are matched and compared with the corresponding feature ranges in the standard electrical parameter feature library in a dimension-by-dimensional manner to obtain the multi-dimensional matching results of the key feature parameters. Based on the failure mechanism of the lithium battery and the sensitivity, the influence weight of the key characteristic parameters is determined; Based on the aforementioned influence weights, the multi-dimensional matching results are weighted and comprehensively evaluated to obtain a preliminary health assessment result for the lithium battery. According to the preset report format specifications, the preliminary health assessment results are standardized and integrated to obtain the initial health status assessment report of the lithium battery.

6. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, When the health deviation verification module performs a consistency verification between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the health status deviation of the lithium battery, it is specifically used for: The initial health status assessment report is decomposed into dimensions to obtain the multi-dimensional assessment results of the initial health status assessment report; Based on the historical health status database of the lithium battery, retrieve the historical health status assessment data corresponding to the current monitoring cycle of the lithium battery, and align the parameter dimensions and statistical caliber of the multi-dimensional assessment results with those of the historical health status assessment data. Calculate the evaluation difference value for the aligned parameter dimensions, wherein the calculation formula for the evaluation difference value is as follows: ； In the formula, Indicates the first Evaluation difference values ​​for each parameter dimension, This indicates the current monitoring cycle number of the lithium battery. Evaluation values ​​for each parameter dimension, This indicates the first [item] in the historical health status assessment data. Evaluation values ​​for each parameter dimension; Based on the influence weights of the aforementioned parameter dimensions, the evaluation difference values ​​are weighted and fused to obtain the comprehensive deviation coefficient of the lithium battery. The comprehensive deviation coefficient is mapped to a preset deviation level range to determine the degree of deviation of the health status of the lithium battery.

7. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, When the degradation risk simulation module performs degradation risk simulation on the health status of the lithium battery in subsequent operating cycles based on the degree of deviation from the health status and the trend change rate of the time-series correlation parameter set, and obtains an optimized battery health status assessment report and lifespan risk warning information for the lithium battery, it is specifically used for: A time-series change rate analysis is performed on the key feature parameters in the time-series correlation parameter set to obtain a set of trend change rates of the key feature parameters; Based on the set of the degree of deviation from the health status and the rate of change of the trend, the risk coefficient of the deterioration of the health status of the lithium battery is calculated. Based on the aforementioned deterioration risk coefficient and combined with the risk level classification rules for lithium batteries, the deterioration tendency type of the lithium battery is determined to obtain the deterioration tendency type of the lithium battery. Based on the type of deterioration tendency, a risk situation simulation is performed on the health status of the lithium battery to obtain the deterioration trend of the health status of the lithium battery. Based on the deterioration trend of the health status, the initial health status assessment report is supplemented and corrected to obtain the optimized battery health status assessment report of the lithium battery. Based on the risk level corresponding to the deterioration risk coefficient, the corresponding lifespan risk warning information in the optimized battery health status assessment report is marked.

8. The lithium battery life monitoring and health status autonomous protection system as described in claim 7, characterized in that, The formula for calculating the risk coefficient of deterioration is as follows: ； In the formula, This represents the risk coefficient of deterioration. This represents the comprehensive deviation coefficient corresponding to the degree of deviation from the stated health status. This represents the preset trend influence coefficient. This indicates the number of the key feature parameters. Indicates the first The deterioration of key feature parameters affects the weights. Indicates the first The rate of change of the trend of key characteristic parameters.

9. The lithium battery life monitoring and health status autonomous protection system as described in claim 1, characterized in that, When the autonomous protection strategy generation module performs the task of selecting the corresponding autonomous protection strategy from the preset battery protection control strategy library based on the optimized battery health status assessment report and the lifespan risk warning information, it is specifically used for: The optimized battery health status assessment report is subjected to structured analysis to obtain the analysis results of the health problems of the lithium battery; Extract the risk level and risk impact range from the lifespan risk warning information to obtain the risk characteristic information of the lithium battery; Based on the health problem analysis results and risk characteristic information, the corresponding battery protection strategies in the preset battery protection control strategy library are selected to obtain the candidate protection strategy set for the lithium battery. The suitability of the candidate protection strategy set is verified by adaptation simulation to obtain the suitability score of the candidate protection strategy set; The battery protection strategy with the highest compatibility score is adopted as the autonomous protection strategy for the lithium battery.

10. A method for monitoring the lifespan and autonomously protecting the health status of a lithium battery, characterized in that, The method is used in the lithium battery life monitoring and health status autonomous protection system according to claim 1. S1. Collect the battery terminal voltage, charging and discharging current and internal resistance change rate during the operation of the lithium battery to obtain a multi-dimensional electrical parameter dataset of the lithium battery. S2. Based on a preset time window, and combined with the changing trend characteristics of the parameters in the multi-dimensional electrical parameter dataset, the consistency of the parameter trends in adjacent time windows is compared to remove random abnormal fluctuation data in the multi-dimensional electrical parameter dataset, thereby obtaining the time-series associated parameter set of the lithium battery. S3. Based on the electrical parameter characteristics of the lithium battery in a healthy state, perform matching and correlation analysis on the key feature parameters in the time-series correlation parameter set to obtain the initial health status assessment report of the lithium battery. S4. Verify the consistency between the initial health status assessment result and the historical health status assessment data of the lithium battery to obtain the degree of deviation of the health status of the lithium battery. S5. Based on the degree of deviation of the health status and the trend change rate of the time-series correlation parameter set, the deterioration risk of the health status of the lithium battery in subsequent operating cycles is deduced, and the optimized battery health status assessment report and life risk warning information of the lithium battery are obtained. S6. Based on the optimized battery health status assessment report and the life risk warning information, select the corresponding autonomous protection strategy from the preset battery protection control strategy library.

Images