Storage battery operation state defect identification method and device

Abstract

The invention provides a storage battery operation state defect identification method and device. The method comprises the following steps: firstly, collecting measurable variables in the charge-discharge operation process of the storage battery, carrying out normalization preprocessing on the measurable variables, and converting the variables into data in a matrix form through a sliding window technology; then, building convolutional self-encoding CAE to extract deep features of measurable variables of the battery, and designing a loss function to optimize CAE training performance; on the basis, performing clustering analysis on the deep features by using a structural similarity evaluation index, and dividing a clustering result into a defect-free cluster and a defect cluster in combination with a deep feature permutation entropy; and finally, establishing a quantitative evaluation index to calculate the defect probability of the battery, and further establishing a long short-term memory (LSTM) neural network to realize the defect prediction of the running state of the battery. The storage battery operation state defect can be efficiently and accurately identified, the defect occurrence probability is quantified, and support is provided for battery health management.

Description

Technical Field

[0001] The present invention relates to the technical field of battery status detection, and in particular to a method and device for identifying battery operating status defects. Background Art

[0002] As an important component of energy storage, batteries are widely used in power systems, communication base stations and other fields. However, as the battery is used for a long time, performance degradation and capacity reduction may occur, which seriously affects its service life and safety. Traditional battery detection methods usually rely on manual detection and threshold judgment. This method has great limitations in practical applications and is difficult to accurately reflect the complex operating status of the battery. Therefore, it is particularly important to develop a real-time, intelligent sliding window-based battery operating status defect identification method.

[0003] In recent years, deep learning technology has made significant progress in data processing and pattern recognition, especially models such as autoencoders and recurrent neural networks have been rapidly promoted in the fields of deep feature learning and time series analysis. However, for the operating characteristics of batteries, traditional deep learning technology still has shortcomings in defect identification efficiency and accuracy. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method for identifying battery operating status defects, which specifically includes the following steps:

[0005] Step S101, real-time acquisition of measurable variable data of the battery within a certain period of time;

[0006] Step S103, converting the measurable variable data into a first time series data set in a matrix form based on a sliding window method;

[0007] Step S105, inputting the time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set;

[0008] Step S107: dividing the first deep feature set into a non-defective cluster and a defective cluster based on the similarity between the features;

[0009] Step S109: evaluating the probability of defects occurring in the first deep feature set within the sliding window based on the quantitative evaluation index model;

[0010] Step S1011: input the first deep feature set into a first long short-term memory neural network (LSTM) model, and output the defect probability of each sliding window.

[0011] The measurable variable data include voltage, current, temperature and internal resistance.

[0012] Wherein, the step S103 further includes calculating sample entropy for the data segments in each sliding window to select the optimal window size, which specifically includes:

[0013] Step S1031, initializing a series of window sizes W and step sizes S;

[0014] Step S1033: For each combination of W and S, calculate and record the sample entropy SampEn=ln A m (r)-ln A m+1 (r), where A m (r) and A m+1 (r) all represent the matching probability of the phase space vector formed by the data in the window, m represents the dimension of the vector taken from the first time series data set, and r is the tolerance threshold;

[0015] Step S1035 , draw a two-dimensional surface graph of sample entropy versus W and S, set a second threshold T, and find the minimum window whose sample entropy of all windows is greater than the threshold.

[0016] Among them, A m (r) and A m+1 (r) represents the probability that the phase space vector satisfies the similarity condition when the embedding dimension of the data sequence is m and m+1. The embedding dimension m means that the data points in the time series are combined as an m-dimensional vector, that is, the analysis is performed at m consecutive time points. Usually a small positive number, such as 2 or 3, is selected to capture the short-term dynamic characteristics of the data.

[0017] The tolerance threshold r is used to judge the similarity between vectors. It is usually used as part of data standard production to control the matching requirements between data. That is, if the Euclidean distance between two m-dimensional vectors is less than r, they are considered to match.

[0018] Probability A m (r) represents the probability that all possible m-dimensional vector pairs in the sequence meet the similarity requirement. Specifically, it is the number of m-dimensional vector pairs that meet the similarity requirement divided by the number of all possible vector pairs.

[0019] Probability A m+1 (r) represents the proportion of vector pairs that still meet the similarity requirements when the embedding dimension increases to m+1.

[0020] The calculation steps of sample entropy include:

[0021] Construct the phase space vector, take out the m-dimensional vector from the time series, and form an m-dimensional phase space vector set.

[0022] Calculate the number of matches. For each vector, calculate the distance between it and other vectors. If the distance is less than the tolerance threshold r, it is considered a match. Count the total number of matches to obtain A. m (r).

[0023] Increase the embedding dimension, add one dimension to each vector to form an m+1 dimensional vector set, and repeat the above steps to obtain A m+1 (r).

[0024] Take the logarithmic difference and take the natural logarithm of the ratio of the two probabilities to get the sample entropy.

[0025] The convolutional autoencoder CAE model in step S105 adopts the following loss function: L CAE =αL M (x,x rec )+βL S (x,x rec ),in x represents the input data, x rec Represents the reconstruction data, x ij and x rec,ij They represent the values ​​at the (i, j) position in the input data and the reconstructed data respectively, α and β represent weight coefficients, and O and P represent the number of rows and columns of the matrix.

[0026] Wherein, step S107 includes: performing cluster analysis on the first deep feature based on the first structural similarity index model to form two independent clusters, wherein the first structural similarity index model is specifically defined as:

[0027]

[0028] In the formula, and represents any two eigenvectors, represents the feature dimension, The value range is [0, 1].

[0029] The clustering analysis of the first deep feature set is performed based on the first structural similarity index model to form two independent clusters, which specifically includes the following steps:

[0030] S1071, randomly select two features in the first deep feature set as the initial centroids of two clusters;

[0031] S1073, calculating the structural similarity indexes of all other deep features and the two centroids, and reallocating all features in the first deep feature layer to two clusters accordingly;

[0032] S1075, calculating the mean of each dimension of the features in the two clusters to update the centroids of the two clusters;

[0033] S1077. Repeat steps S1071 to S1075 until the centroids of the two clusters no longer change or the specified number of updates is reached.

[0034] Among them, the clusters with permutation entropy less than the set threshold are defect-free clusters, and the clusters with permutation entropy greater than the set threshold are defective clusters.

[0035] Among them, based on the distribution of centroids and samples within clusters, a first quantitative evaluation index model is established.

[0036] The quantitative evaluation index model is expressed by the following formula: in represents the defect probability of the t-th deep feature, ξθ(t) represents the position value of the deep feature θ; represents the value of the position of the defect-free cluster center θ; Indicates the value of the defect cluster center θ position.

[0037] The value range is 0 to 1, where 0 indicates no defect, 1 indicates a defect, and 0.5 is the dividing value between the no-defect state and the defect state.

[0038] Wherein, step S1011 includes, according to the output of LSTM, if the defect probability exceeds a second set threshold, determining that a defect exists; otherwise, the battery state is considered to be normal.

[0039] The present invention also provides a battery operating state defect recognition device, which adopts the above-mentioned battery operating state defect recognition method based on sliding window, and the device comprises:

[0040] A data acquisition module, which is used to collect measurable variable data of the battery within a certain period of time in real time;

[0041] A data conversion module, which is used to convert the measurable variable data into a first time series data set in a matrix form based on a sliding window method;

[0042] A feature extraction module, which is used to input the first time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set;

[0043] A feature division module, which is used to divide the first deep feature set into a non-defective cluster and a defective cluster based on similarities between features;

[0044] A defect assessment module, which is used to assess the probability of defects occurring in the first deep feature set within the sliding window based on a quantitative evaluation index model;

[0045] A probability output module is used to input the first deep feature set into a first long short-term memory neural network (LSTM) model and output the defect probability of each sliding window.

[0046] Expected effects of implementing the present invention

[0047] The method proposed in the present invention can efficiently extract deep features from battery charging and discharging data, and quantify the probability of battery operating state defects based on these features, thus achieving high-precision battery defect identification. Compared with traditional defect detection methods, the method of the present invention has the following advantages:

[0048] 1. Improved accuracy: By extracting deep features through convolutional autoencoder (CAE) and combining it with the powerful time series modeling capability of long short-term memory neural network (LSTM), the working status of the battery can be analyzed more comprehensively and deeply, significantly improving the accuracy of defect identification;

[0049] 2. Enhanced adaptability: The present invention innovatively adopts a clustering method based on structural similarity evaluation indicators and permutation entropy analysis to effectively distinguish between defect-free and defective battery states, and establishes a defect evaluation system to enhance the system's adaptability to different types of batteries and operating environments;

[0050] 3. Wide range of applications: This method is not only applicable to various types of batteries, but also can maintain good performance in a variety of operating scenarios, especially in the power supply, communication security and other industries, showing broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 The present invention is a flow chart of a method for identifying defects in a battery operating state.

[0052] Figure 2 The present invention is a flow chart of preprocessing data of measurable variables of a storage battery.

[0053] Figure 3 It is a schematic diagram of the convolutional autoencoder structure of the present invention.

[0054] Figure 4 It is a flow chart of cluster analysis based on structural similarity index of the present invention.

[0055] Figure 5 It is a schematic diagram of the long short-term memory network structure of the present invention.

[0056] Figure 6 It is a schematic diagram of a battery operating status defect identification device of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings.

[0058] Embodiment 1

[0059] like Figure 1 A method for identifying battery operating status defects provided by the present invention specifically comprises the following steps:

[0060] Step S101, real-time acquisition of measurable variable data of the battery within a certain time period; wherein the certain time period is a time period when the battery is in a charging and discharging operation state;

[0061] Step S103, converting the measurable variable data into a first time series data set in a matrix form based on a sliding window method;

[0062] Step S105, inputting the time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set;

[0063] Step S107: dividing the first deep feature set into a non-defective cluster and a defective cluster based on the similarity between the features;

[0064] Step S109: evaluating the probability of defects occurring in the first deep feature set within the sliding window based on the quantitative evaluation index model;

[0065] Step S1011: input the first deep feature set into a first long short-term memory neural network (LSTM) model, and output the defect probability of each sliding window.

[0066] The acquired data includes multiple measurable variables such as voltage, current, temperature and internal resistance.

[0067] During the charging and discharging process of the battery, multiple measurable variables (such as voltage, current, temperature and internal resistance) are collected in real time. These data are recorded continuously within a certain time range. These variables change in a time series and usually form a multidimensional data set.

[0068] This data can be considered as time series data, which is usually collected at specific time intervals. For example, data is recorded once per second. This forms a multidimensional dataset containing multiple time points over time.

[0069] For analysis and feature extraction, a sliding window technique is used. Specifically:

[0070] A fixed window size is set (e.g., 10 seconds) and a data segment is extracted in each time period.

[0071] The window is moved to cover subsequent time periods, possibly overlapping (e.g., the window slides by 5 seconds), thus generating multiple window segments.

[0072] Each window segment will contain the data of all measurable variables within that time period, forming a multi-dimensional feature vector.

[0073] Each window segment generates a feature vector after deep feature extraction (e.g., using a convolutional autoencoder). These feature vectors represent the state of the battery during that time period.

[0074] When these window segments are input into the convolutional autoencoder (CAE), CAE extracts features through multiple convolutional layers and pooling layers. Ultimately, CAE outputs a deep feature representation of each window segment.

[0075] These deep features are usually a combination of multiple features to form a new feature vector. For example, if the feature vector output by each window segment after CAE processing has 10 dimensions, then each window of the new data will correspond to a 10-dimensional feature vector.

[0076] Based on the deep feature vectors extracted from all window segments, a clustering algorithm can be applied to analyze these features.

[0077] By clustering, similar feature vectors in the feature space can be grouped to form multiple feature clusters. Each cluster represents a class of similar states (such as normal or defective states).

[0078] After clustering, each cluster will contain feature vectors of multiple windows, which together describe a specific state.

[0079] Centroid positioning: After clustering, the centroid of each feature cluster is calculated. The centroid is the average value of the feature vectors of all samples in the cluster and represents the main features of the cluster.

[0080] The feature vector formed by the collected data after deep feature extraction can be compared with the centroid of each cluster.

[0081] Based on the distance between the centroid and the feature vector, combined with the pre-established quantitative evaluation index model, the probability of defects in new samples can be evaluated. For example, samples that are farther away from the centroid may be more likely to be judged as defects.

[0082] Embodiment 2

[0083] The present invention provides a method for identifying battery operating status defects based on a sliding window, which specifically includes the following steps:

[0084] Step S101, real-time acquisition of measurable variable data of the battery within a certain period of time;

[0085] Step S103, converting the measurable variable data into a first time series data set in a matrix form based on a sliding window method;

[0086] Step S105, inputting the time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set;

[0087] Step S107: dividing the first deep feature set into a non-defective cluster and a defective cluster based on the similarity between the features;

[0088] Step S109: evaluating the probability of defects occurring in the first deep feature set within the sliding window based on the quantitative evaluation index model;

[0089] Step S1011: input the first deep feature set into a first long short-term memory neural network (LSTM) model, and output the defect probability of each sliding window.

[0090] The measurable variable data include voltage, current, temperature and internal resistance.

[0091] Among them, Figure 2 The example is a flow chart of preprocessing data of measurable variables of a battery according to the present invention. The step S103 also includes calculating sample entropy for data segments in each sliding window to select an optimal window size, which specifically includes:

[0092] Step S1031, initializing a series of window sizes W and step sizes S;

[0093] Step S1033: For each combination of W and S, calculate and record the sample entropy SampEn=ln A m (r)-ln A m+1 (r), where Am(r) and A m+1 (r) all represent the matching probability of the phase space vector formed by the data in the window, m represents the dimension of the vector taken from the first time series data set, and r is the tolerance threshold;

[0094] Step S1035 , draw a two-dimensional surface graph of sample entropy versus W and S, set a second threshold T, and find the minimum window whose sample entropy of all windows is greater than the threshold.

[0095] The convolutional autoencoder CAE model in step S105 adopts the following loss function: L CAE =αL M (x,x rec )+βL S (x,x rec ),in x represents the input data, x rec Represents the reconstruction data, x ij and x rec,ijThey represent the values ​​at position (i, j) in the input data and the reconstructed data respectively, and α and β represent weight coefficients.

[0096] like Figure 3 As shown, it is the structure of the convolutional autoencoder CAE, and the step S105 specifically includes:

[0097] Step S1051, using the matrix data formed by the sliding window as input data x, whose dimension is O×P;

[0098] Step S1053, the input data x is sent to the convolution encoder e1 for processing, which specifically includes: firstly, feature extraction is performed by Q1 convolution filters C1 with a window size of c×c and a step size of q, and then feature activation is performed by the ReLU activation function [y(λ)=max(0,λ), λ represents the input neuron], and feature dimension reduction is performed by the maximum pooling layer P1 with a window size of o×o and a step size of l, and finally the deep feature h1 with a dimension of a1×b1×c1 is output;

[0099] Step S1055, the deep feature h1 is processed by the convolution encoders e2, e3, and e4 in sequence. The data processing process is similar to step S3.2, thereby outputting the deep feature h4 with the dimension of a4×b4×c4;

[0100] Step S1057, the deep feature h4 is sent to the convolution decoder d1 for processing. First, the feature dimension is increased by the upsampling layer U1 (g×g) with a g×g window size, and then processed by the convolution filter C5 (Q5@c×c+q) and the ReLU activation function to obtain the deep feature h5;

[0101] Step S1059, the deep feature h5 is processed by the convolution decoders d2, d3, and d4 in turn. The data processing process is similar to step 3.4, except that the activation function of the convolution decoder d4 is different, that is, the Sigmoid function [y(λ)=1 / 1+exp(-λ), λ represents the input neuron, and the final output dimension is O×P reconstructed data xrec.

[0102] Wherein, step S107 includes: performing cluster analysis on the first deep feature based on the first structural similarity index model to form two independent clusters, wherein the first structural similarity index model is specifically defined as:

[0103]

[0104] In the formula, and represents any two eigenvectors, represents the feature dimension, The value range is [0, 1].

[0105] Among them, Figure 4 As shown, cluster analysis is performed on the first deep feature set based on the first structural similarity index model to form two independent clusters, which specifically includes the following steps:

[0106] S1071, randomly select two features in the first deep feature set as the initial centroids of two clusters;

[0107] S1073, calculating the structural similarity indexes of all other deep features and the two centroids, and reallocating all features in the first deep feature layer to two clusters accordingly;

[0108] S1075, calculating the mean of each dimension of the features in the two clusters to update the centroids of the two clusters;

[0109] S1077. Repeat steps S1071 to S1075 until the centroids of the two clusters no longer change or the specified number of updates is reached.

[0110] Among them, the clusters with permutation entropy less than the set threshold are defect-free clusters, and the clusters with permutation entropy greater than the set threshold are defective clusters.

[0111] The specific steps of obtaining the permutation entropy are as follows:

[0112] For the deep features {h t}, construct the phase space vector sequence H t =[h t ,h t+τ , ..., h t+(m-1)τ ], where H t represents the phase space vector at time t, τ represents the delay time, and m represents the embedding dimension;

[0113] For each phase space vector H t , determine its sequential pattern τ t , that is, H t The order of the elements in ;

[0114] Count the frequency or probability P(π) of all possible sequential patterns π, and calculate the permutation entropy PermEn=-∑ π P(π)log P(π).

[0115] Among them, based on the distribution of centroids and samples within clusters, a first quantitative evaluation index model is established.

[0116] The quantitative evaluation index model is expressed by the following formula: in represents the defect probability of the t-th deep feature, ξ θ (t) represents the position value of deep feature θ; represents the value of the position of the defect-free cluster center θ; Indicates the value of the defect cluster center θ position.

[0117] The value range is 0 to 1, where 0 indicates no defect, 1 indicates a defect, and 0.5 is the dividing value between the no-defect state and the defect state.

[0118] In step S109, the goal is to evaluate the state of the new sample in the feature space by calculating the centroid and establishing quantitative evaluation indicators, focusing mainly on the relationship between the current sample and the known clusters. Based on the results of cluster analysis, the centroids of the defect-free cluster and the defective cluster are calculated. These centroids represent the center point of each cluster and reflect the average characteristics of the samples within the cluster.

[0119] The calculation of the centroid provides a reference point for subsequent defect probability assessment.

[0120] Based on the centroid and the feature vector of the new sample, a quantitative evaluation index is established. This index is used to evaluate the probability of defects in the new sample within the sliding window.

[0121] Calculate the distance between the new sample and the centroid: The distance between the feature vector of the new sample and the centroid can reflect its similarity to the normal state or defect state. The closer the distance, the higher the similarity between the sample and the cluster.

[0122] Distribution density of samples in the cluster: By analyzing the distribution of samples within the cluster, the status of new samples can be further evaluated.

[0123] Among them, step S1011 includes judging that there is a defect according to the output of LSTM if the defect probability exceeds the second set threshold; otherwise, the battery state is considered to be normal. The prediction of defect probability through LSTM model focuses on the dynamic characteristics of time series data and can use historical information to improve the accuracy of prediction.

[0124] like Figure 5 The figure shows the LSTM structure of the long short-term memory network, which is composed of an input gate i, a forget gate f, and an output gate o. The specific calculation process is as follows:

[0125]

[0126]

[0127]

[0128]

[0129]

[0130] r t =o t ⊙tanhc t (10)

[0131] In the formula, represents the deep features at time t, r t represents the time series characteristics at time t, r t-1 represents the time series characteristics at time t-1, i t 、f t and t Respectively represent the activation vectors of the input gate, forget gate, and output gate, σ represents the Sigmoid function, Tanh represents the hyperbolic sine function, represents the candidate storage state, c t represents the internal state; U and W both represent weight matrices, b represents the bias, and ⊙ represents the dot product of the matrices.

[0132] LSTM is a network that can capture long-term and short-term dependencies in time series data. It is designed so that it can remember previously input information and use it to make more accurate predictions.

[0133] LSTM outputs the probability of defect for each window based on the input sliding window features and the patterns learned during training. This means that for each time window, LSTM will evaluate whether the battery is likely to be defective within that window and give a probability value.

[0134] LSTM predicts the defect probability of each window based on the input feature vector and its time dependency. The key is that LSTM not only considers the characteristics of the current window, but also captures the dynamic changes of historical windows in the time series, thereby improving the accuracy of defect identification.

[0135] Embodiment 3

[0136] like Figure 6 As shown, the present invention provides a battery operating state defect recognition device, which adopts the above-mentioned battery operating state defect recognition method based on sliding window, and the device may include:

[0137] A data acquisition module, which is used to collect measurable variable data of the battery within a certain period of time in real time;

[0138] A data conversion module, which is used to convert the measurable variable data into a first time series data set in a matrix form based on a sliding window method;

[0139] A feature extraction module, which is used to input the first time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set;

[0140] A feature division module, which is used to divide the first deep feature set into a non-defective cluster and a defective cluster based on similarities between features;

[0141] A defect assessment module, which is used to assess the probability of defects occurring in the first deep feature set within the sliding window based on a quantitative evaluation index model;

[0142] A probability output module is used to input the first deep feature set into a first long short-term memory neural network (LSTM) model and output the defect probability of each sliding window.

Claims

1. A method for identifying battery operating status defects, characterized in that: It includes the following steps: Step S101, real-time acquisition of measurable variable data of the battery within a certain period of time; Step S103, converting the measurable variable data into a first time series data set in a matrix form based on a sliding window method; Step S105: input the first time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set; Step S107: dividing the first deep feature set into a non-defective cluster and a defective cluster based on the similarity between the features; Step S109: evaluating the probability of defects occurring in the first deep feature set within the sliding window based on the quantitative evaluation index model; Step S1011: input the first deep feature set into a first long short-term memory neural network (LSTM) model, and output the defect probability of each sliding window.

2. The method according to claim 1, characterized in that: The step S103 further includes calculating sample entropy for the data segments in each sliding window to select the optimal window size, which specifically includes: Step S1031, initializing a series of window sizes W and step sizes S; Step S1033: For each combination of W and S, calculate and record the sample entropy SampEn=lnA m (r)-ln A m+1 (r), where A m (r) and A m+1 (r) all represent the matching probability of the phase space vector formed by the data in the window, m represents the dimension of the vector taken from the first time series data set, and r is the tolerance threshold; Step S1035 , draw a two-dimensional surface graph of sample entropy versus W and S, set a second threshold T, and find the minimum window whose sample entropy of all windows is greater than the threshold.

3. The method according to claim 1, characterized in that: The convolutional autoencoder CAE model in step S105 adopts the following loss function: L CAE =αL M (x,x rec )+βL S (x,x rec ),in x represents the input data, x rec Represents the reconstruction data, x ij and x rec,ij They represent the values ​​at the (i, j) position in the input data and the reconstructed data respectively, α and β represent weight coefficients, and O and P represent the number of rows and columns of the matrix.

4. The method according to claim 1, characterized in that: Step S107 includes: performing cluster analysis on the first deep feature based on a first structural similarity index model to form two independent clusters, wherein the first structural similarity index model is specifically defined as: In the formula, and represents any two eigenvectors, represents the feature dimension, The value range is [0,1].

5. The method according to claim 4, characterized in that: The cluster analysis of the first deep feature set is performed based on the first structural similarity index model to form two independent clusters, which specifically includes the following steps: S1071, randomly select two features in the first deep feature set as the initial centroids of two clusters; S1073, calculating the structural similarity indexes of all other deep features and the two centroids, and reallocating all features in the first deep feature layer to two clusters accordingly; S1075, calculating the mean of each dimension of the features in the two clusters to update the centroids of the two clusters; S1077. Repeat steps S1071 to S1075 until the centroids of the two clusters no longer change or the specified number of updates is reached.

6. The method according to claim 5, characterized in that The clusters whose permutation entropy is less than the set threshold are defect-free clusters, and the clusters whose permutation entropy is greater than the set threshold are defective clusters.

7. The method according to claim 5, characterized in that: The first quantitative evaluation index model is established based on the distribution of centroids and samples within the cluster.

8. The method according to claim 7, characterized in that: The quantitative evaluation index model is expressed by the following formula: in represents the defect probability of the t-th deep feature, ξ θ (t) represents the position value of deep feature θ; represents the value of the position of the defect-free cluster center θ; Indicates the value of the defect cluster center θ position. The value range is 0 to 1, where 0 indicates no defect, 1 indicates a defect, and 0.5 is the dividing value between the no-defect state and the defect state.

9. The method according to claim 1, characterized in that: Wherein step S1011 includes, according to the output of LSTM, if the defect probability exceeds a second set threshold, determining that a defect exists; otherwise, the battery state is considered to be normal.

10. A battery operating status defect identification device, characterized in that: The method for identifying battery operating status defects according to any one of claims 1 to 9 is adopted, and the device comprises: A data acquisition module, which is used to collect measurable variable data of the battery within a certain period of time in real time; A data conversion module, which is used to convert the measurable variable data into a first time series data set in a matrix form based on a sliding window method; A feature extraction module, which is used to input the first time series data set into a first convolutional autoencoder CAE model to extract a first deep feature set; A feature division module, which is used to divide the first deep feature set into a non-defective cluster and a defective cluster based on similarities between features; A defect assessment module, which is used to assess the probability of defects occurring in the first deep feature set within the sliding window based on a quantitative evaluation index model; A probability output module is used to input the first deep feature set into a first long short-term memory neural network (LSTM) model and output the defect probability of each sliding window.

Images