A lithium battery health status assessment method and system

Abstract

The present invention discloses a lithium battery health status assessment method and system, which specifically relates to the technical field of battery health status assessment. The method constructs a structured data set by performing time series alignment and structured preprocessing on multi-source operating data of a target lithium battery in multiple historical working cycles; constructs a spatiotemporal feature residual map based on residual mapping analysis and extracts spatial heterogeneity indicators; generates a regional degradation feature map in combination with the spatial heterogeneity indicators; identifies heterogeneous aging patterns and generates classification results through high-dimensional feature embedding and evolutionary path clustering; evaluates the health status level of the target lithium battery based on the regional degradation feature map and the heterogeneous aging pattern classification results; determines whether the battery has a local potential thermal runaway risk based on the assessment results, and generates corresponding risk warning signals and safety disposal suggestions, which can accurately identify the nonlinear impact of lithium battery aging heterogeneity and effectively improve the health status assessment accuracy and safety risk warning capabilities.

Description

Technical Field

[0001] The present invention relates to the technical field of battery health status assessment, and more specifically, to a lithium battery health status assessment method and system. Background Art

[0002] Traditional lithium battery health assessment techniques generally establish global degradation models based on the overall voltage-current curve, capacity retention, or a single impedance characteristic, assuming that the internal aging process of the battery is uniform and the indicator evolution is monotonous. However, the aging rate, aging pattern, and aging degree experienced by different regions within the battery during cycling are inconsistent and uneven. Existing methods infer health status only from macroscopic average signals and fail to identify the masking effect of localized prior degradation on the overall performance of the lithium battery, resulting in amplified errors in remaining life prediction.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a lithium battery health status assessment method and system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for evaluating the health status of a lithium battery comprises the following steps:

[0007] S1: Collect multi-source operating data of the target lithium battery in multiple historical working cycles, perform time series alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set;

[0008] S2: Perform residual mapping analysis on structured data sets, construct spatiotemporal feature residual maps, and extract spatial heterogeneity indicators;

[0009] S3: Identify degradation trends in different regions within the battery based on spatial heterogeneity indicators and generate regional degradation feature maps;

[0010] S4: Perform high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators to identify the evolution paths of heterogeneous aging patterns and generate heterogeneous aging pattern classification results;

[0011] S5: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, the health status of the target lithium battery is evaluated and the health status level of the target lithium battery is output;

[0012] S6: Based on the health status level of the target lithium battery, determine whether the target lithium battery has a local potential thermal runaway risk, and output a warning signal and safety disposal recommendations.

[0013] In a preferred embodiment, S1 is specifically:

[0014] Collect multi-source operating data of the target lithium battery in multiple historical working cycles;

[0015] Synchronize multi-source operation data according to timestamps, unify the time dimension using preset time series alignment rules, and obtain a multivariate data set;

[0016] Perform format standardization and missing value filling on multivariate data sets to construct structured data sets.

[0017] In a preferred embodiment, S2 is specifically:

[0018] The residual mapping analysis method is used to calculate the difference between each variable in the structured data set and the preset benchmark model;

[0019] According to the preset time series window length, the difference data is divided into multiple continuous time windows, and the feature residual matrix is ​​constructed for each continuous time window;

[0020] Perform two-dimensional spatial interpolation processing on each feature residual matrix to construct a spatiotemporal feature residual map;

[0021] Extracting spatial heterogeneity indicators from spatiotemporal feature residual maps.

[0022] In a preferred embodiment, S3 is specifically:

[0023] Based on the spatial heterogeneity index, the internal space of the target lithium battery is divided into multiple independent analysis areas;

[0024] According to the spatial heterogeneity index in each analysis area, the degradation trend curve of each analysis area over time is fitted, and the degradation trend characteristic parameters of each analysis area are extracted;

[0025] According to the degradation trend characteristic parameters, a regional degradation characteristic map is generated.

[0026] In a preferred embodiment, S4 is specifically:

[0027] The kernel function is used to map the spatial heterogeneity index to a high-dimensional feature space to form a multi-dimensional feature vector;

[0028] Applying spectral clustering algorithm to the multidimensional feature vectors to classify multiple heterogeneous aging pattern categories;

[0029] The evolution paths of the heterogeneous aging pattern categories in the time dimension are sorted to generate the heterogeneous aging pattern classification results.

[0030] In a preferred embodiment, S5 is specifically:

[0031] Input the regional degradation feature mapping and heterogeneous aging pattern classification results into the health status assessment model to calculate the health status index of the target lithium battery;

[0032] According to the preset health status classification standard, the health status index is graded and the health status grade of the target lithium battery is output.

[0033] In a preferred embodiment, S6 is specifically:

[0034] Combine the regional degradation feature map with the target lithium battery health status level to determine the comprehensive health index of each analysis area;

[0035] For each analysis area's comprehensive health index, determine whether the analysis area has potential thermal runaway risk according to the preset risk threshold;

[0036] For analysis areas determined to have potential thermal runaway risks, corresponding local risk warning signals and safety disposal recommendations are output.

[0037] In another aspect, the present invention provides a lithium battery health status assessment system, comprising:

[0038] Data acquisition unit: collects multi-source operating data of the target lithium battery in multiple historical working cycles, performs time sequence alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set;

[0039] Residual analysis unit: performs residual mapping analysis on structured data sets, constructs spatiotemporal feature residual maps, and extracts spatial heterogeneity indicators;

[0040] Trend modeling unit: Identifies degradation trends in different regions within the battery based on spatial heterogeneity indicators and generates regional degradation feature maps;

[0041] Cluster identification unit: performs high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators, identifies the evolution path of heterogeneous aging patterns, and generates heterogeneous aging pattern classification results;

[0042] Health assessment unit: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, it evaluates the health status of the target lithium battery and outputs the health status level of the target lithium battery;

[0043] Risk warning unit: Based on the health status level of the target lithium battery, it determines whether the target lithium battery has a local potential thermal runaway risk, and outputs a warning signal and safety disposal recommendations.

[0044] The technical effects and advantages of the lithium battery health status assessment method and system of the present invention are as follows:

[0045] By performing time-series synchronization and structured preprocessing on multi-source operating data, data integrity and consistency are achieved; based on residual mapping, a spatiotemporal feature residual map is constructed to accurately reveal the regional heterogeneity within the battery; spatial heterogeneity indicators are combined to identify the degradation trends of each region and accurately characterize the local degradation characteristics; high-dimensional feature embedding and evolution path clustering are used to identify the temporal evolution characteristics of heterogeneous aging patterns; with regional feature mapping and heterogeneous aging pattern classification results as input, the health status level is output through the health status assessment model; based on the health level, the local thermal runaway risk is accurately determined and early warning signals and safety disposal recommendations are issued, realizing refined prevention and control of local failure risks and significantly enhancing the operational safety and reliability of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a schematic diagram of a lithium battery health status assessment method according to the present invention;

[0047] Figure 2 This is a structural diagram of a lithium battery health status assessment system of the present invention. DETAILED DESCRIPTION

[0048] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] Example 1

[0050] Figure 1 The present invention provides a method for evaluating the health status of a lithium battery, which includes the following steps:

[0051] S1: Collect multi-source operating data of the target lithium battery in multiple historical working cycles, perform time series alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set;

[0052] S2: Perform residual mapping analysis on structured data sets, construct spatiotemporal feature residual maps, and extract spatial heterogeneity indicators;

[0053] S3: Identify degradation trends in different regions within the battery based on spatial heterogeneity indicators and generate regional degradation feature maps;

[0054] S4: Perform high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators to identify the evolution paths of heterogeneous aging patterns and generate heterogeneous aging pattern classification results;

[0055] S5: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, the health status of the target lithium battery is evaluated and the health status level of the target lithium battery is output;

[0056] S6: Based on the health status level of the target lithium battery, determine whether the target lithium battery has a local potential thermal runaway risk, and output a warning signal and safety disposal recommendations.

[0057] S1: Collect multi-source operating data of the target lithium battery in multiple historical working cycles, perform time alignment and structured preprocessing on the multi-source data based on preset synchronization rules, and obtain a structured data set, including:

[0058] Collect multi-source operating data of the target lithium battery in multiple historical working cycles;

[0059] Specifically, a continuous operating cycle of the lithium battery is set in the battery test platform. Each working cycle includes a complete charging stage, a constant voltage holding stage, a static stage, and a discharge stage. Through a multi-channel data acquisition device, the following operating data are continuously collected in each working cycle: voltage data is collected through a high-precision voltage sensor connected to the positive and negative terminals of the battery; current data is collected in real time through a Hall current sensor connected in series in the main circuit of the battery; electrochemical impedance spectrum data is obtained by applying an AC excitation signal and measuring the response signal at multiple set frequency points through an electrochemical impedance analyzer connected to the battery terminals; battery surface temperature data is collected through thermocouple sensors arranged at different positions on the surface of the battery casing to ensure that the temperature information of different spatial positions of the target lithium battery is fully covered.

[0060] During the acquisition process, the sampling frequency is set to ensure that the sampling rates of voltage data, current data, and battery surface temperature data are consistent. The sampling frequency of electrochemical impedance spectroscopy data is determined according to the actual operating conditions of the target lithium battery.

[0061] Synchronize multi-source operation data according to timestamps, unify the time dimension using preset time series alignment rules, and obtain a multivariate data set;

[0062] Specifically, when collecting multi-source operating data, the corresponding precise timestamp information is recorded and calibrated using a unified time server to ensure the accuracy and consistency of the timestamps recorded by each sensor. Pre-set timing alignment rules are then used to uniformly align the voltage data, current data, electrochemical impedance spectroscopy data, and battery surface temperature data in the time dimension. This involves interpolating or truncating missing or misplaced data in multiple data sequences. For example, when the timestamp of the current data does not match the timestamp of the voltage data, linear interpolation is used to obtain a current data point between two adjacent current data points that is consistent with the corresponding time of the voltage data. This ensures that all multi-source operating data correspond to each other in the same time dimension, forming a multivariate data set at a unified time scale.

[0063] Standardize the format and fill in missing values ​​of multivariate data sets to construct structured data sets;

[0064] Specifically, the data format of the multivariate data set is standardized, that is, the voltage data, current data, electrochemical impedance spectroscopy data and battery surface temperature data are converted into a unified data format structure, for example, they are all converted into floating-point data format, and the accuracy requirements of each data are unified, such as voltage accuracy to millivolt level, current accuracy to milliampere level, and temperature accuracy to two decimal places in Celsius, to achieve unified data analysis accuracy.

[0065] The missing data points in the multivariate data set are filled by using the moving window averaging method of the same variable data in adjacent time windows: the arithmetic average of multiple known data points before and after the missing position is taken to obtain the estimated value of the missing data, and the missing data is filled in to the corresponding position to ensure that the entire multivariate data set is continuous and complete, and there are no vacant data points.

[0066] After completing the above standardization and missing value imputation processes, a structured dataset containing voltage series, current series, electrochemical impedance spectroscopy series, and battery surface temperature series was constructed. The specific form of the structured dataset is a two-dimensional data table with multiple rows and columns, where each row represents a unified sampling time and each column represents a different type of data variable.

[0067] S2: Perform residual mapping analysis on structured datasets, construct spatiotemporal feature residual maps, and extract spatial heterogeneity indicators, including:

[0068] The residual mapping analysis method is used to calculate the difference between each variable in the structured data set and the preset benchmark model;

[0069] Specifically, the method for constructing the preset benchmark model is to use the operating data of the target lithium battery in its initial health state as the benchmark state data, and perform point-by-point difference calculations on the voltage series, current series, electrochemical impedance spectrum series, and battery surface temperature series collected by the target lithium battery in different historical working cycles with the corresponding variable series in the benchmark state data. After subtracting the data at the corresponding position of each variable, the difference data series of the corresponding variable is obtained to represent the degree of change of each variable in the current state of the target lithium battery relative to the initial health state. The difference calculation process is as follows: take the data value of a variable in the structured data set at a specific moment, subtract the data value of the corresponding variable of the benchmark model at the same moment, and calculate the residual value of the variable at the specific moment. Repeat this calculation until the data of all moments in the structured data set are processed, and finally obtain a complete difference data set.

[0070] According to the preset time series window length, the difference data is divided into multiple continuous time windows, and the feature residual matrix is ​​constructed for each continuous time window;

[0071] Specifically, the difference data of the historical working cycle is divided into multiple non-overlapping continuous time windows of consistent length in chronological order. Each continuous time window contains the difference data of multiple consecutive sampling moments to ensure that the amount of data covered by each time window is consistent and the time span is the same. The length of the continuous time window is determined based on ensuring that the difference data in each time window can fully characterize the changes in the electrochemical characteristics of the target lithium battery in the corresponding time window. The specific window length is determined based on the actual operating characteristics of the target lithium battery and the data sampling frequency. For example, each continuous time window can cover the data of a complete charge and discharge process, ensuring the integrity and representativeness of the difference data within the time window.

[0072] The characteristic residual matrix is ​​constructed by taking each sampling moment in each continuous time window as the row coordinate of the matrix and each variable in the structured data set as the column coordinate of the matrix. The value of each matrix element is the difference calculated between the variable at the sampling moment and the preset benchmark model, thereby obtaining a characteristic residual matrix that can characterize the time-varying trends of multiple variables in each continuous time window.

[0073] Perform two-dimensional spatial interpolation processing on each feature residual matrix to construct a spatiotemporal feature residual map;

[0074] Specifically, the interpolation method uses the Kriging interpolation method. The Kriging interpolation method can fully consider the covariance relationship between spatial positions to estimate the difference. Specifically, a coordinate grid system is set for the internal space of the lithium battery, and the coordinates of each grid node of the coordinate grid system represent a specific spatial position inside the lithium battery; for each element in the characteristic residual matrix, the estimated difference of the position to be interpolated is calculated through spatial correlation using the difference data at multiple known measurement spatial positions closest to the grid node. The specific calculation process is: weights are applied to multiple known difference data closest to the grid node and weighted sums are obtained. The calculated weights are determined according to the covariance function between the spatial positions; finally, complete and continuous interpolation data are obtained at the spatial grid node position inside the battery, thereby completing the two-dimensional spatial interpolation processing of each characteristic residual matrix, and obtaining a complete spatiotemporal characteristic residual map that can reflect the change law of spatial position and time dimension.

[0075] Extracting spatial heterogeneity indicators from the spatiotemporal feature residual maps;

[0076] Specifically, for each grid node position in the spatiotemporal feature residual map, the observation period in the time dimension is set as a time series interval of fixed length. Within this observation period, a time series of grid node interpolation data is extracted. The corresponding variance value is calculated for this time series as an indicator of the temporal variation of the grid node. The variance calculation formula used is: the sum of the squared differences between the interpolated value at each moment in the time series and its mean value is divided by the length of the series to obtain the spatial heterogeneity index.

[0077] S3: Identify degradation trends in different regions within the battery based on spatial heterogeneity indicators and generate regional degradation feature maps, including:

[0078] Based on the spatial heterogeneity index, the internal space of the target lithium battery is divided into multiple independent analysis areas;

[0079] Specifically, the regional division method is as follows: based on the numerical distribution of spatial heterogeneity indicators at different locations inside the battery, a density cluster analysis method is used to cluster and divide the spatial locations inside the battery. The density cluster analysis method is to classify and aggregate spatial locations based on the spatial density of spatial heterogeneity indicators and the similarity of spatial distances; the key parameters for setting the density cluster analysis method include the spatial distance threshold and the minimum density threshold, where the setting of the spatial distance threshold is determined based on the internal structural dimensions of the battery, and the minimum density threshold is determined based on the local point density distribution of spatial heterogeneity indicators at the grid locations inside the battery, by analyzing the distribution characteristics of the number of samples in the neighborhood of each grid node; through the above cluster division method, the internal space of the target lithium battery is divided into multiple independent and spatially clearly distributed analysis areas, each analysis area contains several spatial grid nodes, and the spatial locations between the analysis areas do not overlap, providing a spatial division basis for regional degradation trend analysis.

[0080] According to the spatial heterogeneity index in each analysis area, the degradation trend curve of each analysis area over time is fitted, and the degradation trend characteristic parameters of each analysis area are extracted;

[0081] Specifically, the spatial heterogeneity indicators of all spatial grid nodes in each analysis area are used as sample points, time is used as the independent variable, and the spatial heterogeneity indicators are used as the dependent variable. A nonlinear trend fitting model is selected to fit the degradation trend curve. The nonlinear trend fitting model is specifically an exponential decay fitting model. The exponential decay fitting model realizes parameter estimation through the least squares method. The fitting process is: with the goal of minimizing the sum of squares of the errors between the measured values ​​of the spatial heterogeneity indicators in the region and the predicted values ​​of the exponential decay fitting model, the exponential decay fitting model parameters are calculated so that the output results of the exponential decay fitting model are as close as possible to the actual measured data. Finally, the degradation trend curve in each analysis area is obtained.

[0082] Degradation trend characteristic parameters include a trend decay rate parameter and a decay amplitude parameter. The trend decay rate parameter is obtained by calculating the derivative of the regional degradation trend curve. Specifically, it is the slope value of the fitted trend curve at different times. The degradation rate is quantified by calculating the average of the slope values. The decay amplitude parameter is calculated by calculating the numerical difference between the initial and final values ​​of the fitted trend curve to quantify the overall degree of degradation in each region over the entire observation period. Through the above method, the degradation trend curve within each analysis area can be quantified into characteristic parameters such as trend decay rate and decay amplitude, enabling quantitative comparison of the analysis areas.

[0083] Generate regional degradation characteristic map based on degradation trend characteristic parameters;

[0084] Specifically, the regional degradation characteristic map is constructed by establishing a mapping coordinate system in two-dimensional space, using the trend decay rate parameter and decay amplitude parameter as the two-dimensional coordinate axes. The trend decay rate parameter and decay amplitude parameter of each analysis region are used as coordinate points in the mapping coordinate system. The regional degradation characteristic map is a mapping coordinate system composed of the degradation trend characteristic parameters (trend decay rate parameter and trend decay amplitude parameter) of multiple analysis regions. The regional degradation characteristic map reveals the differences in the spatial degradation degree between the analysis regions, providing an accurate spatial basis for regional heterogeneity analysis and regional location of thermal runaway risks in lithium battery health assessment.

[0085] S4: Perform high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators to identify the evolution paths of heterogeneous aging patterns and generate heterogeneous aging pattern classification results, including:

[0086] The kernel function is used to map the spatial heterogeneity index to a high-dimensional feature space to form a multi-dimensional feature vector;

[0087] Specifically, the distance measurement method between each data point in the kernel function is defined as Euclidean distance, that is, the distance between any two spatial heterogeneity indicator data points is obtained by calculating the square root of the sum of the squares of the numerical differences of the corresponding dimensions of the two spatial heterogeneity indicator data points; according to the calculation rules of the selected kernel function, the Euclidean distance between any two spatial heterogeneity indicator data points is subjected to an exponential decay transformation, that is, the square of the Euclidean distance value is taken as the opposite, and then the kernel function output value is obtained by performing an exponential function operation; after the above kernel mapping calculation, the spatial heterogeneity indicator at each spatial position is converted into a feature vector in a high-dimensional space, and a multi-dimensional feature vector set is obtained.

[0088] Applying spectral clustering algorithm to the multidimensional feature vectors to classify multiple heterogeneous aging pattern categories;

[0089] Specifically, all multidimensional eigenvectors in the high-dimensional feature space are paired, and a feature similarity matrix is ​​constructed by calculating the cosine similarity between each pair of eigenvectors. The similarity matrix is ​​used to construct the Laplace matrix required for the spectral clustering algorithm, specifically, the similarity matrix is ​​converted into a Laplace matrix obtained by the difference between the degree matrix and the similarity matrix. The Laplace matrix is ​​subjected to eigendecomposition to obtain an eigenvector matrix. According to the distribution of each eigenvector element of the eigenvector matrix, a clustering method is used to cluster the spatial heterogeneity index to obtain multiple heterogeneous aging pattern categories. The clustering method adopts the classic K-means clustering method, and the number of clusters is determined according to the clustering effect evaluation index, which is the silhouette coefficient of the clustering result. The number of clusters that makes the silhouette coefficient reach the optimal value is selected as the basis for determining the number of categories. Heterogeneous aging patterns refer to local aging trends that differ from the general patterns of lithium batteries as a whole during the aging process due to various factors such as differences in internal structure, uneven chemical composition, and inconsistent temperature fields. For example, there may be significant differences in aging rates (capacity decay or internal resistance growth in a local area is significantly faster than in other areas) or differences in aging severity (some areas exhibit early degradation characteristics, while other areas do not degrade significantly). Heterogeneous aging pattern categories refer to heterogeneous aging patterns with common aging characteristic trends. For example, Category 1 (rapid capacity decay): dominated by rapid capacity decay, manifested by a high trend decay rate; Category 2 (temperature-sensitive): the aging rate varies significantly with local temperature, manifesting as temperature-dependent aging.

[0090] The evolution path of each heterogeneous aging pattern category in the time dimension is sorted to generate the heterogeneous aging pattern classification results;

[0091] Specifically, for each heterogeneous aging pattern category, the average occurrence time of all multidimensional feature vectors in the heterogeneous aging pattern category in the time dimension, that is, the category average time position, is calculated respectively. The category average time position calculation is realized by taking the arithmetic mean of the timestamp data corresponding to all multidimensional feature vectors in the category; each category is sorted in order according to the calculated category average time position, and the sorting method is ascending order of the category average time position value from small to large, thereby reflecting the evolutionary order of different heterogeneous aging pattern categories appearing in the battery operation cycle; through the above sorting, a clear and clear classification result of the heterogeneous aging pattern evolution path is obtained, which provides data input for the overall health status level assessment of lithium batteries.

[0092] S5: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, the health status of the target lithium battery is evaluated and the health status level of the target lithium battery is output, including:

[0093] Input the regional degradation feature mapping and heterogeneous aging pattern classification results into the health status assessment model to calculate the health status index of the target lithium battery;

[0094] Specifically, the health status assessment model is a multi-parameter fusion assessment model. The specific implementation method of the multi-parameter fusion assessment model is to use the degradation trend characteristic parameters of each analysis area in the regional degradation characteristic map, including the trend attenuation rate parameter and the attenuation amplitude parameter, and the heterogeneous aging pattern category characteristics corresponding to the analysis area as input at the same time. The specific calculation method of the multi-parameter fusion assessment model is to linearly combine the trend attenuation rate parameter and the attenuation amplitude parameter of each analysis area to obtain the preliminary degradation index of the region; perform nonlinear fusion calculation on the preliminary degradation index of the region and the heterogeneous aging pattern category characteristics. The nonlinear fusion calculation method adopts a feedforward neural network, which is configured as a three-layer network structure, including an input layer, a hidden layer and an output layer; the number of neurons in the input layer corresponds to the dimension of the input parameter, and the number of neurons in the hidden layer corresponds to the dimension of the input parameter. The quantity is determined through repeated experiments, and the optimization is carried out with the goal of minimizing the output error of the multi-parameter fusion evaluation model; the single output value of the output layer neuron is the health status index of the target lithium battery; the training process of the feedforward neural network adopts the supervised learning method, and the supervised learning method is the back propagation algorithm; the implementation of the back propagation algorithm is to use the historically known actual battery aging data as training data, and to minimize the sum of the squares of the errors between the actual data and the output results of the multi-parameter fusion evaluation model as the optimization goal, and repeatedly adjust the network weight parameters until the error converges; after the training is completed through the above process, the regional degradation feature map and the heterogeneous aging pattern classification results are input into the trained feedforward neural network to calculate the health status index of the target lithium battery.

[0095] According to the preset health status classification standard, the health status index is graded and the health status level of the target lithium battery is output;

[0096] Specifically, the health status classification standard uses a numerical interval classification method: a first threshold and a second threshold are preset; the health status index is compared with the preset first and second thresholds. When the health status index is less than the first threshold, the health status of the target lithium battery is judged to be severely degraded; when the health status index is greater than or equal to the first threshold and less than the second threshold, the health status of the target lithium battery is judged to be slightly degraded; when the health status index is greater than or equal to the second threshold, the health status of the target lithium battery is judged to be in good health.

[0097] S6: Based on the health status of the target lithium battery, determine whether the target lithium battery has a local potential thermal runaway risk and output a warning signal and safety disposal suggestions, including:

[0098] Combine the regional degradation feature map with the target lithium battery health status level to determine the comprehensive health index of each analysis area;

[0099] Specifically, the trend attenuation rate parameters and trend attenuation amplitude parameters of the above regional degradation characteristic mapping are correlated and fused with the overall health status level of the lithium battery, and the additive fusion method is adopted: the trend attenuation rate parameters, the trend attenuation amplitude parameters and the overall health status level of the lithium battery are respectively assigned different fusion weights, and the fusion weights are determined by statistical regression analysis of historical lithium battery measured data. Specifically, the fusion weights are determined with the goal of optimizing the statistical regression analysis results of historical data, so that the fusion effect of the regional characteristic parameters and the overall health status level is optimal; the fused value is the comprehensive health index corresponding to each analysis area, thereby reflecting the correlation between the regional characteristics and the overall lithium battery status level.

[0100] For each analysis area's comprehensive health index, determine whether the analysis area has potential thermal runaway risk according to the preset risk threshold;

[0101] Specifically, a risk threshold is pre-set by statistically analyzing the historical operating data of lithium batteries to determine the critical value that can effectively distinguish between safe areas and risk areas. This is the critical point of the comprehensive health index risk obtained through historical data analysis; the judgment process is to compare the comprehensive health index of each analysis area with the risk threshold one by one. If the comprehensive health index value of the analysis area is less than the preset risk threshold, it is judged that the analysis area has a potential thermal runaway risk; if the comprehensive health index of the analysis area is greater than or equal to the risk threshold, it is judged that the analysis area does not have a potential thermal runaway risk.

[0102] For analysis areas identified as having potential thermal runaway risks, the system outputs corresponding local risk warning signals and safety disposal recommendations;

[0103] Specifically, a local risk warning signal is generated for the analysis area determined to have potential thermal runaway risk. The specific warning signal is a comprehensive warning prompt information containing clear spatial location information and real-time monitoring suggestions; the spatial location information specifically includes the position coordinates of the risk area in the internal coordinate system of the lithium battery; the real-time monitoring suggestions are continuous monitoring methods given for the risk area, including, for example, increasing the monitoring frequency, increasing the sensor layout density, etc., to ensure the safety monitoring of the risk area.

[0104] Generate safety disposal recommendations to ensure the safe operation of lithium batteries. The safety disposal recommendations specifically include: implementing safety disposal plans such as load adjustment, power limitation, local temperature control enhancement, and charge and discharge rate adjustment for risk areas; for example, for analysis areas with potential thermal runaway risks, give recommendations to reduce the charge and discharge rate and increase the cooling capacity, so that the disposal plan can achieve the best risk reduction effect on the analysis area.

[0105] Example 2

[0106] The difference between Example 2 of the present invention and Example 1 is that this example introduces a lithium battery health status assessment system.

[0107] Figure 2 A schematic diagram of a lithium battery health status assessment system according to the present invention is provided. The lithium battery health status assessment system comprises:

[0108] Data acquisition unit: collects multi-source operating data of the target lithium battery in multiple historical working cycles, performs time sequence alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set;

[0109] Residual analysis unit: performs residual mapping analysis on structured data sets, constructs spatiotemporal feature residual maps, and extracts spatial heterogeneity indicators;

[0110] Trend modeling unit: Identifies degradation trends in different regions within the battery based on spatial heterogeneity indicators and generates regional degradation feature maps;

[0111] Cluster identification unit: performs high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators, identifies the evolution path of heterogeneous aging patterns, and generates heterogeneous aging pattern classification results;

[0112] Health assessment unit: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, it evaluates the health status of the target lithium battery and outputs the health status level of the target lithium battery;

[0113] Risk warning unit: Based on the health status level of the target lithium battery, it determines whether the target lithium battery has a local potential thermal runaway risk, and outputs a warning signal and safety disposal recommendations.

[0114] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0115] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0116] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0117] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0119] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0120] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0121] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0122] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0123] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating the health status of a lithium battery, characterized in that: The steps include: S1: Collect multi-source operating data of the target lithium battery in multiple historical working cycles, perform time series alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set; S2: Perform residual mapping analysis on structured data sets, construct spatiotemporal feature residual maps, and extract spatial heterogeneity indicators; S3: Identify degradation trends in different regions within the battery based on spatial heterogeneity indicators and generate regional degradation feature maps; S4: Perform high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators to identify the evolution paths of heterogeneous aging patterns and generate heterogeneous aging pattern classification results; S5: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, the health status of the target lithium battery is evaluated and the health status level of the target lithium battery is output; S6: Based on the health status level of the target lithium battery, determine whether the target lithium battery has a local potential thermal runaway risk, and output a warning signal and safety disposal recommendations.

2. A lithium battery health status assessment method according to claim 1, characterized in that: S1, specifically: Collect multi-source operating data of the target lithium battery in multiple historical working cycles; Synchronize multi-source operation data according to timestamps, unify the time dimension using preset time series alignment rules, and obtain a multivariate data set; Perform format standardization and missing value filling on multivariate data sets to construct structured data sets.

3. A lithium battery health status assessment method according to claim 2, characterized in that: S2, specifically: The residual mapping analysis method is used to calculate the difference between each variable in the structured data set and the preset benchmark model; According to the preset time series window length, the difference data is divided into multiple continuous time windows, and the feature residual matrix is ​​constructed for each continuous time window; Perform two-dimensional spatial interpolation processing on each feature residual matrix to construct a spatiotemporal feature residual map; Extracting spatial heterogeneity indicators from spatiotemporal feature residual maps.

4. A lithium battery health status assessment method according to claim 3, characterized in that: S3, specifically: Based on the spatial heterogeneity index, the internal space of the target lithium battery is divided into multiple independent analysis areas; According to the spatial heterogeneity index in each analysis area, the degradation trend curve of each analysis area over time is fitted, and the degradation trend characteristic parameters of each analysis area are extracted; According to the degradation trend characteristic parameters, a regional degradation characteristic map is generated.

5. A lithium battery health status assessment method according to claim 4, characterized in that: S4, specifically: The kernel function is used to map the spatial heterogeneity index to a high-dimensional feature space to form a multi-dimensional feature vector; Applying spectral clustering algorithm to the multidimensional feature vectors to classify multiple heterogeneous aging pattern categories; The evolution paths of the heterogeneous aging pattern categories in the time dimension are sorted to generate the heterogeneous aging pattern classification results.

6. A lithium battery health status assessment method according to claim 5, characterized in that: S5, specifically: Input the regional degradation feature mapping and heterogeneous aging pattern classification results into the health status assessment model to calculate the health status index of the target lithium battery; According to the preset health status classification standard, the health status index is graded and the health status grade of the target lithium battery is output.

7. A lithium battery health status assessment method according to claim 6, characterized in that: S6, specifically: Combine the regional degradation feature map with the target lithium battery health status level to determine the comprehensive health index of each analysis area; For each analysis area's comprehensive health index, determine whether the analysis area has potential thermal runaway risk according to the preset risk threshold; For analysis areas determined to have potential thermal runaway risks, corresponding local risk warning signals and safety disposal recommendations are output.

8. A lithium battery health status assessment system, used to implement a lithium battery health status assessment method according to any one of claims 1 to 7, characterized in that: include: Data acquisition unit: collects multi-source operating data of the target lithium battery in multiple historical working cycles, performs time sequence alignment and structured preprocessing on the multi-source data based on preset synchronization rules to obtain a structured data set; Residual analysis unit: performs residual mapping analysis on structured data sets, constructs spatiotemporal feature residual maps, and extracts spatial heterogeneity indicators; Trend modeling unit: Identifies degradation trends in different regions within the battery based on spatial heterogeneity indicators and generates regional degradation feature maps; Cluster identification unit: performs high-dimensional feature embedding and evolution path clustering on spatial heterogeneity indicators, identifies the evolution path of heterogeneous aging patterns, and generates heterogeneous aging pattern classification results; Health assessment unit: Based on the regional degradation feature mapping and heterogeneous aging pattern classification results, it evaluates the health status of the target lithium battery and outputs the health status level of the target lithium battery; Risk warning unit: Based on the health status level of the target lithium battery, it determines whether the target lithium battery has a local potential thermal runaway risk, and outputs a warning signal and safety disposal recommendations.

Images