New Energy Vehicle Battery Fault Identification and Early Warning Method Based on Hybrid Deep Learning

Abstract

The present invention discloses a new energy vehicle battery fault identification and early warning method based on hybrid deep learning. The method first defines the fault type and judgment criteria, and generates labels for training data. Then, a hybrid deep learning model including a convolutional layer model and a bidirectional gated recurrent unit layer is constructed to extract the spatial features of the battery data and the long-term dependencies in the time series, respectively, and encode the battery status information. Next, the extracted features are input into the fault identification module to fine-tune the model parameters, optimize the cross-entropy loss function of the model, and minimize the error between the model prediction and the actual fault, so as to reduce the calculation time and improve the training efficiency. Finally, based on the trained hybrid deep learning model, the fault probability of the battery data is detected, and the model is used to predict the target feature data in the future period to generate fault early warning information. This method can improve the accuracy of battery fault identification and the reliability of early warning.

Description

Technical Field

[0001] The present invention belongs to the field of deep learning technology and relates to a method for identifying and warning battery faults of new energy vehicles, and specifically to a method for identifying and warning battery faults of new energy vehicles based on hybrid deep learning. Background Art

[0002] As a core component of new energy vehicles, the health of batteries directly impacts the vehicle's operating efficiency and safety. Currently, models and methods used for battery fault identification and early warning primarily include fault classification models based on traditional statistical models, fault classification models based on traditional learning methods such as support vector machines, fault time series identification models based on deep learning, and fault feature extraction and analysis models based on signal processing. However, traditional statistical models lack the ability to identify complex nonlinear fault patterns and are unable to process large-scale dynamic data. Traditional learning methods such as support vector machines are inefficient in high-dimensional feature spaces and rely on manual feature engineering. Time series models based on single deep learning networks, such as RNNs and LSTMs, suffer from limited ability to capture long-sequence information and issues such as vanishing or exploding gradients. Signal processing-based analysis methods are limited by feature extraction accuracy and cannot meet the requirements for high-precision fault identification. Furthermore, existing fault identification models generally lack versatility, their applicability is often limited to specific fault modes, making them difficult to generalize to fault scenarios across different vehicle or battery types, and they lack adaptability to complex environments.

[0003] In summary, existing battery fault identification and early warning methods not only rely on large amounts of historical fault data but are also susceptible to noise during model training, resulting in insufficient fault identification accuracy and early warning reliability. Furthermore, they lack versatility and are difficult to adapt to complex fault scenarios. To improve the accuracy of new energy vehicle battery fault identification and enhance the ability to warn of potential battery failures, a more advanced and adaptable hybrid deep learning model and early warning strategy is urgently needed to address the complex characteristics of multiple battery failures and provide a more versatile and explainable fault identification and early warning method. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention proposes a new energy vehicle battery fault identification and early warning method based on hybrid deep learning. The hybrid deep learning model is constructed using convolutional layers (CNN) and bidirectional gated recurrent units (BiGRU) layers to extract the spatial features of battery data and the long-term dependencies in the time series, encode the battery status information, and improve the accuracy of battery fault identification and the reliability of early warning.

[0005] The new energy vehicle battery fault identification and early warning method based on hybrid deep learning includes the following steps:

[0006] Step 1: Preprocessing and labeling battery fault feature data

[0007] First, acquire the characteristic data collected from the power battery during the operation of new energy vehicles, including charging status, vehicle speed, accumulated mileage, battery voltage, battery current, SOC, insulation resistance, temperature, maximum voltage, minimum voltage, maximum temperature, and minimum temperature. Set the valid value range for each characteristic data, and based on the fault identification method and generation mechanism, select the appropriate feature data type from the collected characteristic data, perform preprocessing, and then integrate and generate labels for fault identification:

[0008] s1.1. Outlier removal and missing value processing: Clean the acquired data, remove outliers that exceed the normal range of the features, use the mean or interpolation method to fill in missing values to ensure data integrity, and finally delete duplicate sample rows.

[0009] s1.2, feature data smoothing: After completing the outlier removal and missing value filling, the collected feature data X = [x1, x2, ..., x n ]∈R c×n Use Savitzky-Golay filter to smooth the data. Generate the i-th feature and smooth the data at time t t=1, 2, ..., n, i=1, 2, ..., c, c is the total number of sampled battery feature types, and n is the number of sampling time points, that is, the number of samples.

[0010] s1.3、Standardization and normalization of feature data: After the smoothing process is completed, the smoothed data set Standardization and normalization operations are performed so that all eigenvalues related to new energy vehicle battery failure fall within the same numerical range [0,1], with a mean of 0 and a variance of 1.

[0011]

[0012] Where μ i and σ i are the mean and standard deviation of the i-th feature, X i，min and X i，max is the minimum and maximum value of the i-th feature, Represents the data after the standardization of the i-th feature, Represents the dataset after normalization of the i-th feature. Standardization and normalization make the values of each feature in the same dimension, which is conducive to improving the convergence speed and stability of the model.

[0013] s1.4, Battery Failure Marking: During its operating cycle, the power battery of a new energy vehicle is in a relatively complex and changeable environment, and is easily subject to challenges from various situations. There are many factors that affect the safety of power battery charging, and the resulting new energy vehicle battery failures also present diverse characteristics. After completing data preprocessing, through an in-depth analysis of the factors affecting the safety of new energy vehicle charging, the collected feature data is classified and the target feature set of the fault is extracted. j = 1, 2, ..., m, where m represents the number of fault types and each type of fault is labeled accordingly:

[0014] ① Abnormal self-discharge: The battery energy does not enter the external circuit through discharge, but is lost in other ways, causing one or more battery cells to be in an obvious outlier state and posing a safety hazard. The self-discharge rate is calculated by the voltage changes at adjacent sampling points:

[0015]

[0016] Where V t and V t-1 They are the voltage values at the current moment and the previous moment respectively. When the self-discharge rate SDR>3%, it is marked as an abnormal state.

[0017] ② Sudden internal short circuit: This occurs when a battery cell suddenly enters a thermal runaway state due to abnormal conduction between the positive and negative electrodes. This is manifested by a sharp rise in cell temperature or an abnormal increase in voltage. Sudden internal short circuits are categorized as those caused by high temperature or high voltage. A sudden internal short circuit is indicated when the battery temperature exceeds 38°C, the voltage is greater than 4.1V, or the voltage is less than 2.5V.

[0018] ③Insulation failure: The insulation resistance of the battery system is lower than the limit due to vehicle wading, battery leakage, insulation layer aging or other reasons. The insulation ratio IRR is an important basis for judging insulation failure:

[0019]

[0020] Where IR is the insulation resistance, U SUM Expressed as total voltage. When IRR ≤ 100Ω / V when the battery is in a charging state, or IRR ≤ 500Ω / V in other states, it is marked as an insulation failure.

[0021] According to the above-mentioned fault judgment indicators, the fault data is marked to form label data Y={y t，j |y t，j ∈{0, 1}}∈R n×m , where m represents the number of fault types, y t，jIndicates whether the j-th type of fault occurs at time point t, 1 indicates the presence of this type of fault, 0 indicates the absence of this type of fault, j=1, 2, ..., m.

[0022] Step 2: Extract key features of battery failure

[0023] After labeling the fault type in step 1, we conduct an in-depth analysis of the relevant operating conditions during the operation of the new energy vehicle to extract key features that can help accurately diagnose battery faults. To quantify the impact of each feature on different fault types, we use the Pearson correlation coefficient to perform correlation analysis, quantify the linear relationship between the feature and the fault type label, and select the key feature variables that are most indicative of fault identification:

[0024]

[0025] Where, Represents the feature data vector after smoothing of the i-th feature, y j is the fault label vector of the jth type of fault; and They are and y j The mean of The value range is [-1,1], The closer the absolute value is to 1, the more characteristic and faulty j The stronger the correlation between them.

[0026] Sort the Pearson correlation coefficients of each feature and the fault label by absolute value, and select the feature variables whose absolute value of the correlation coefficient is higher than the preset threshold as the key feature variables highly correlated with the fault label to form the key feature identification matrix Z, Z = {z ij |z ij ∈{0, 1}}∈R c×m , matrix element z ij Indicates whether feature i is the key feature of fault j. 1 indicates that feature i is the key feature of fault j, and 0 indicates that it is not the key feature.

[0027] Step 3: Battery Fault Type Identification Model

[0028] Construct a hybrid deep learning model that combines a convolutional neural network (CNN) layer with a bidirectional gated recurrent unit (BiGRU) layer. In order to improve the accuracy of recognition, the fault recognition tasks of different categories are decomposed into multiple binary classification subtasks. For the subtask Type corresponding to the jth type of fault, j Separately detect whether a specific type of fault occurs, the model input matrix

[0029] The convolutional neural network layer includes a convolution layer, an activation function and a pooling layer. j Perform feature extraction to capture local patterns and spatial relationships between features; each element in the output matrix C generated by the convolution operation is processed by the ReLU activation function to obtain the matrix C' after nonlinear transformation, which can effectively suppress negative features and make the model focus on positive features, helping the model learn complex patterns and avoid the problem of gradient disappearance. C' contains multiple channels, each channel represents a different feature map extracted by the convolution kernel, which captures the patterns and features of the input data in the local space; on each channel of the feature map C', the maximum pooling operation is used to reduce the dimension of the feature map, extract the maximum value of the channel, and use the maximum value of each channel max(c1), max(c2), ..., max(c q ) are combined into a maximum value vector max(c), where q represents the number of channels generated by the convolution operation, that is, the number of convolution kernels.

[0030] The bidirectional gated recurrent unit layer is used to further process the feature data output by the convolutional neural network layer, and uses bidirectional information flow to capture the front-to-back dependencies of sequence data, thereby improving the model's ability to understand and extract time-dependent features. The BiGRU structure processes data in two directions, forward GRU and backward GRU, providing a comprehensive feature representation for each time step, and then performs a forward hidden state on each time step. and the backward hidden state Merge to form the final hidden state representation h t :

[0031]

[0032] The output of BiGRU passes through the fully connected layer, and the hidden states of all time steps captured by BiGRU are summarized to form a high-level feature vector set h = {h1, h2, ..., h n} is mapped to the target fault label vector y j =[y 1，j ,y 2，j ,...,y n，j ], and use the Sigmoid activation function to convert the output into a fault probability value of [0, 1], and then use the fault threshold τ to get the fault label

[0033] y j =W f h+b f

[0034]

[0035] Where Wf and b f is the weight matrix and bias of the fully connected layer; define the fault threshold τ, if It is determined that there is a fault j at time point t, otherwise it is determined to be in a normal state.

[0036] Binary cross entropy loss is used as the loss function for model training to handle the fault characteristics of each fault label appearing independently or together:

[0037]

[0038] Where y t，j represents the fault label of the j-th fault at the t-th time point, The fault label at the tth time point for the jth type of fault identified by the model.

[0039] Step 4: Battery Failure Warning Strategy

[0040] s4.1, Fault warning setting

[0041] Define fault thresholds, use hybrid deep learning models to predict relevant fault parameters, detect whether fault characteristics exceed safety thresholds, and issue early warnings:

[0042] Define a basic threshold e threshold，j , when the prediction value P of the j-th type of fault output by the hybrid deep learning model at time point t t，j Exceeding the basic threshold e threshold，j To reduce false alarms and sporadic risks, a minimum number of warning points k is set. This requires that a fault warning is only triggered when at least k data points in a continuous time window show a fault risk.

[0043] s4.2. Predicting future fault characteristic values

[0044] The goal of the early warning strategy is to predict the temperature conditions of the battery probes in the future in advance so that preventive measures can be taken before the battery temperature becomes abnormal.

[0045] The target characteristic data Q of the j-th type fault collected t，j Input the trained hybrid deep learning model to get the first prediction result P t+1，j , P t+1，j Add to Q t，j At the end of the update sequence, we get Q t+1，j , input the trained hybrid deep learning model again to make the next prediction. Repeat the above steps until the prediction is T steps The predicted value for future time steps T steps =N×60 / tgap , t gap Indicates the sampling interval, and N indicates the prediction duration.

[0046] s 4.3. Detecting Fault Characteristics in the Future Time Period

[0047] The feature sequence of the predicted future time step For the predicted value of the j-th type of fault at each prediction time point t, an indicator function δ is defined t，j , record whether it exceeds the basic threshold e threshold :

[0048]

[0049] Where, δ i，j =1 indicates that the jth fault at the tth prediction time point exceeds the threshold and needs to be recorded as an abnormal fault state, and 0 indicates a normal state.

[0050] s4.4. Generate fault warning information

[0051] For each prediction time point t, according to the indicator function δ t，j Construct abnormal fault set S t , including all abnormal faults that occurred at the corresponding time point:

[0052] S t ={j|δ t，j =1}

[0053] If there is an abnormal fault set An early warning is issued and corresponding warning information Info is generated, including the fault type, fault occurrence time and fault threshold.

[0054] The present invention has the following gain effects:

[0055] The present invention proposes a new energy vehicle battery fault identification and early warning method based on a hybrid deep learning model composed of a convolutional neural network (CNN) layer and a bidirectional gated recurrent unit (BiGRU) layer, which effectively improves the accuracy, real-time and adaptability of multi-category battery fault identification. First, the battery data that meets the fault classification requirements is preprocessed, and the key indicators are further marked with custom feature coding using the valid value range of key feature variables such as voltage and temperature to achieve effective distinction between normal and abnormal states. Through fault labeling and Pearson correlation coefficient screening, the fault identification input features are optimized to ensure that the model has versatility and adaptability in multiple types of faults. The hybrid deep learning model of this method uses the CNN layer to extract the spatial features of the battery data, and uses the BiGRU layer to capture the long-term dependencies in the time series, thereby enhancing the understanding and recognition capabilities of multi-category battery fault modes; in addition, the CNN-BiGRU recognition model of the present invention decomposes each type of fault detection task into two-class subtasks, and combines the attention mechanism to improve the accurate capture capability of fault information. At the same time, the threshold setting and recursive prediction method based on fault characteristics can achieve early warning and issue alarms for potential abnormal fault conditions before the fault occurs, which helps to improve the safety of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is the flow chart for fault data feature analysis.

[0057] Figure 2 Schematic diagram of the structure of the hybrid deep learning model (CNN-BiGRU) constructed for the embodiment.

[0058] Figure 3 This is a flowchart for selecting model hyperparameters in an embodiment.

[0059] Figure 4 The figure is a flow chart of the battery failure early warning method based on the hybrid deep learning model. DETAILED DESCRIPTION

[0060] The present invention will be further explained below with reference to the accompanying drawings;

[0061] The new energy vehicle battery fault identification and early warning method based on hybrid deep learning includes the following steps:

[0062] Step 1: Preprocessing and labeling battery fault feature data

[0063] like Figure 1As shown, the battery monitoring data is read from the acquired new energy vehicle driving monitoring data file, including the battery charging status, vehicle speed, cumulative mileage, battery voltage, battery current, SOC, insulation resistance, temperature, maximum voltage, minimum voltage, maximum temperature, and minimum temperature at different time points; it is converted into a matrix form X∈R that can be used for analysis c ×n , c represents the fault feature dimension, n is the number of sampling time points, that is, the number of samples, and data preprocessing is performed on the data X. The threshold conditions corresponding to the three fault types of self-discharge abnormality, sudden internal short circuit abnormality and insulation failure are defined. The preprocessed sample data is traversed and the fault label Y = {y t，j |y t，j ∈{0, 1}}∈R n×m , m represents the number of fault types, and the elements y in the matrix t，j Describes the label value of the j-th type of fault at time point t, 1 indicates the presence of this type of fault, and 0 indicates the absence of this type of fault.

[0064] Step 2: Extract key features of battery failure

[0065] The Pearson correlation coefficient is used for correlation analysis. According to the results of the correlation analysis, the absolute value of the correlation with the fault label is selected. p，q |More than r threshold The key feature set F key :

[0066] F key ={f1, f2, ..., f m}

[0067]

[0068] F key ={f1, f2, ..., f m} is the key feature sampling data set, where m represents the number of fault types, is the sampling data after preprocessing and smoothing of the i-th type feature data, r i，j is the correlation coefficient between the i-th type feature and the j-th type fault. Finally, the key feature set of different fault type labels is shown in Table 1:

[0069] Table 1 Key feature sets of different fault type labels

[0070]

[0071]

[0072] Step 3: Battery Fault Type Identification Model

[0073] like Figure 2 As shown in the figure, a hybrid deep learning model combining convolutional neural network (CNN) layer and bidirectional gated recurrent unit (BiGRU) layer is constructed to decompose the fault identification task of different categories into multiple binary classification subtasks; each subtask Type j Detect whether the jth type fault occurs separately and set F key f in j Input parameter training Type j The model of the subtask. Figure 3 As shown in FIG, in order to ensure the best performance of the model, a grid search method is used to select the hyperparameters of the model, including the number of filters in the convolutional layer and the number of neural units in the bidirectional gated recurrent unit layer.

[0074] The number of filters in a convolutional layer reflects the richness of feature patterns that the model can learn during the convolution process. A smaller number of filters may not be sufficient to fully capture the complex features of the data, while an excessive number of filters may introduce unnecessary computational burden and increase the risk of overfitting. This example selects three representative values of 32, 64, and 128 and compares their performance in different situations to find the optimal balance.

[0075] The number of neural units in the bidirectional gated recurrent unit layer is a key parameter in determining a model's ability to process time series data. A sufficient number of units ensures the model has sufficient memory capacity to capture long-term dependencies in the sequence, but too many units also increase model complexity, potentially leading to unstable training and overfitting. We set three different unit number options (50, 100, and 150) and compared the model performance under these options to determine the best bidirectional gated recurrent unit layer configuration for the task at hand.

[0076] We use a grid search method to systematically test the performance of different hyperparameter combinations, using accuracy as the criterion for evaluating the quality of the parameters. By traversing all possible combinations and evaluating the accuracy of each combination, we can fully understand the impact of each hyperparameter on model performance and determine the optimal hyperparameter combination. The specific steps are as follows:

[0077] s3.1. Construct a hyperparameter combination space, including the number of filters Filter size and the number of GRU units GRU units:

[0078] Filter size∈{32,64,128},GRU units∈{50,100,150}

[0079] s3.2. Model training is performed for each hyperparameter combination. To prevent overfitting of the model, a regularization term is introduced during the training process:

[0080]

[0081] Where λ is the regularization strength, w g is the model weight under the g-th hyperparameter combination, and S represents the total number of all trainable weight parameters in the model. Therefore, the size of S is directly related to the structure and complexity of the model. By adjusting the value of λ, L reg This is applied to the original loss function to balance the model's fit and generalization capabilities. The accuracy of different combinations is then evaluated, and the hyperparameter combination with the highest accuracy is selected as the final configuration. Comparison revealed that when the number of filters is set to 64 and the number of GRU units is set to 100, the model's accuracy reaches 0.9948, so this combination is used as the final configuration.

[0082] In addition, batch size also affects training efficiency and model convergence speed. Smaller batch sizes can improve the generalization ability of training, but increase computation time. In this example, the best batch size was selected from 16, 32, and 64 as the final setting.

[0083] Step 4: Battery Failure Warning Strategy

[0084] like Figure 4 As shown in Table 2, first set the basic threshold for each type of fault:

[0085] Table 2 Basic threshold settings for various types of faults

[0086]

[0087] Where SDR represents the self-discharge rate of the battery, T u represents the temperature of the u-th temperature probe, U o represents the voltage of the oth cell in the battery, IRR represents the insulation ratio of the battery, k1 is the total number of probes for battery pack temperature measurement, and k2 is the number of battery cells.

[0088] Using the hybrid deep learning model trained in step 3, recursively predict the fault data in the next N minutes to generate the future T steps The predicted sequence of type j fault at time step.

[0089] In the predicted future fault sequence, construct the indicator function δ t，j To mark whether abnormal data occurs, and according to δ t，j Construct abnormal fault set S t , when there is S t When it is not an empty set, a warning message is generated.

Claims

1. A hybrid deep learning-based new energy vehicle battery fault identification and early warning method collects Class C feature data of power batteries during the operation of new energy vehicles and performs preprocessing. The characteristics are: The following steps are involved: Step 1: Battery Fault Feature Marking Define the fault type of new energy vehicle battery, set the valid value range and fault threshold of each type of characteristic data, and generate the fault label data Y={y t，j |y t，j ∈{0, 1}}∈R n×m , where m represents the number of fault types, n is the number of sampling time points, i.e. the number of samples; y t，j Indicates whether the jth type of fault occurs at time point t, 1 indicates the presence of this type of fault, and 0 indicates the absence of this type of fault, t = 1, 2, ..., n, j = 1, 2, ..., m; Step 2: Extract key features of battery failure Calculate the feature data vector of the i-th category feature after preprocessing The fault label vector y of the j-th fault j Pearson correlation coefficient between Select the absolute value of the correlation coefficient Feature variables above the preset threshold As the key feature variables that are highly correlated with the j-th type fault label, the key feature identification matrix Z = {z ij |z ij ∈{0, 1}}∈R c×m , z ij =1 indicates that the i-th type feature is the key feature of the j-th type fault, and 0 indicates that it is not a key feature; Step 3: Battery Fault Type Identification Model Construct a hybrid deep learning model that combines a convolutional neural network layer with a bidirectional gated recurrent unit layer, and input the matrix composed of the key feature variables of the jth type of fault into the hybrid deep learning model. Predict target fault label vector y j =[y 1，j ,y 2，j ,...,y n，j ], and use the Sigmoid activation function to convert the output into a fault probability value of [0, 1], and then use the fault threshold τ to get the fault label Binary cross entropy loss is used as the loss function for model training to handle the fault characteristics of each fault label appearing independently or together; Step 4: Battery Failure Warning Strategy s4.1, Fault warning setting Define a basic threshold e threshold，j , when the prediction value P of the j-th type of fault output by the hybrid deep learning model at time point t t，j Exceeding the basic threshold e threshold，j When , it is considered to have a failure risk; then a minimum warning point number k is set, requiring that when there are at least k data points with failure risk in the continuous time window, the failure warning is triggered; s4.

2. Predicting future fault characteristic values The target characteristic data Q of the j-th type fault collected t，j Input the trained hybrid deep learning model to get the first prediction result P t+1，j , P t+1，j Add to Q t，j At the end of the update sequence, we get Q t+1，j , input the trained hybrid deep learning model again to make the next prediction; repeat the above steps until the prediction is T steps The predicted value for future time steps T steps =N×60 / t gap , t gap Indicates the sampling interval, N indicates the prediction duration; s4.

3. Detecting fault characteristics in the future time period The feature sequence of the predicted future time step For the predicted value of the j-th type of fault at each prediction time point t, an indicator function δ is defined t，j , record whether it exceeds the basic threshold e threshold : Where, δ t，j =1 indicates that the jth fault at the tth prediction time point exceeds the threshold and needs to be recorded as an abnormal fault state, and 0 indicates a normal state; s4.

4. Generate fault warning information For each prediction time point t, according to the indicator function δ t，j Construct abnormal fault set S t , including all abnormal faults that occurred at the corresponding time point: S t ={j|δ t，j =1} If there is an abnormal fault set An early warning is issued and corresponding warning information Info is generated, including the fault type, fault occurrence time and fault threshold.

2. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 1, characterized in that: Obtain the charging status, vehicle speed, accumulated mileage, battery voltage, battery current, SOC, insulation resistance, temperature, maximum voltage, minimum voltage, maximum temperature, and minimum temperature of the power battery during the operation of new energy vehicles.

3. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 1, characterized in that: The specific steps of the pretreatment are: s1.

1. Clean the acquired data, remove outliers that are outside the normal range of the features, fill missing values using the mean or interpolation method to ensure data integrity, and finally delete duplicate sample rows; s1.2, after the outliers are removed and the missing values are processed, the feature data X=[x1,x2,...,x n ]∈R c×n Use Savitzky-Golay filter to smooth the data; generate the i-th feature smoothing data at time t c is the total number of sampled battery feature types; s1.3, smooth the data set Standardization and normalization operations are performed so that all eigenvalues related to new energy vehicle battery failure fall within the same numerical range [0,1], with a mean of 0 and a variance of 1.

4. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 1, characterized in that: The failure types of new energy vehicle batteries are defined as including abnormal self-discharge, sudden internal short circuit caused by high voltage, sudden internal short circuit caused by high temperature and insulation failure.

5. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 4, characterized in that: When the self-discharge rate SDR>3%, it is marked as an abnormal self-discharge state; When the battery temperature exceeds 38°C or the voltage is less than 2.5V, it is marked as a sudden internal short circuit abnormal state caused by high temperature; When the voltage is greater than 4.1V, it is marked as a sudden internal short circuit abnormal state caused by high voltage; When the insulation ratio IRR is less than or equal to 100Ω / V when the battery is in a charging state, or when the insulation ratio IRR is less than or equal to 500Ω / V in other states, it is marked as an insulation failure state.

6. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 1, characterized in that: The convolutional neural network layer includes a convolution layer, an activation function and a pooling layer. j Perform feature extraction to capture local patterns and spatial relationships between features; each element in the output matrix C generated by the convolution operation is processed by the ReLU activation function to obtain the matrix C' after nonlinear transformation; C' contains multiple channels, each channel represents a different feature map extracted by the convolution kernel, and these channels capture the patterns and features of the input data in the local space; on each channel of the feature map C', use the maximum pooling operation to reduce the dimension of the feature map, extract the maximum value of the channel, and use the maximum value of each channel max(c1), max(c2), ..., max(c q ) are combined into a maximum value vector max(c), where q represents the number of channels generated by the convolution operation, that is, the number of convolution kernels; The bidirectional gated recurrent unit layer is used to further process the feature data output by the convolutional neural network layer, and uses bidirectional information flow to capture the front-end and back-end dependencies of the sequence data, thereby improving the model's ability to understand and extract time-dependent features; the BiGRU structure processes the data in two directions, forward GRU and backward GRU, providing a comprehensive feature representation for each time step, and then performs a forward hidden state on each time step. and the backward hidden state Merge to form the final hidden state representation h t : The output of BiGRU passes through the fully connected layer, and the hidden states of all time steps captured by BiGRU are summarized to form a high-level feature vector set h = {h1, h2, ..., h n } is mapped to the target fault label vector y j =[y 1，j ,y 2，j ,...,y n，j ], use the Sigmoid activation function to convert the output into a fault probability value of [0, 1], and then use the fault threshold τ to get the fault label 7. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 1, characterized in that: Set the number of filters in the convolutional layer to 32, 64, or 128, the number of neural units in the bidirectional gated recurrent unit layer to 50, 100, or 150, and the batch size to 16, 32, or 64. Use a grid search method to test the accuracy of the hybrid model under different hyperparameter combinations, and select the hyperparameter combination with the highest hybrid model accuracy as the final model hyperparameter.

8. The hybrid deep learning-based new energy vehicle battery fault identification and early warning method according to claim 7, characterized in that: Set the number of filters to 64 and the number of GRU units to 100.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 8.

Images