A fault warning method for automotive lithium batteries based on multivariate prediction and anomaly detection

Abstract

The present invention discloses a vehicle lithium battery fault warning method based on multivariate prediction and anomaly detection, comprising: collecting operating data of the vehicle battery system through a big data platform; performing data cleaning on the collected data and forming a data set; dividing the data set into a training set and a test set; constructing a prediction model through the training set; inputting the test set into the prediction model, and obtaining a prediction result with the highest cell voltage and the highest probe temperature as the prediction label value; and outputting a warning result. The present invention performs high-precision synchronous forward prediction of the battery voltage and temperature. Experimental results show that compared with the existing battery management system (BMS) warning method, the present invention can achieve voltage over-limit warning 4.5 minutes in advance, achieve abnormal voltage rise and fall warning before undervoltage 83.5 minutes in advance, achieve temperature alarm 24.6 minutes in advance, and achieve temperature warning 35.1 minutes before the fault occurs, providing drivers with sufficient reaction time and significantly enhancing the safety performance of the vehicle.

Description

Technical Field

[0001] The present invention relates to the field of battery management technology fault diagnosis, and in particular to a vehicle lithium battery fault early warning method based on multivariate prediction and anomaly detection. Background Art

[0002] Accurate battery fault diagnosis and early warning before dangerous failures occur are crucial for ensuring the safe, stable, and reliable operation of electric vehicle power battery systems. They also provide theoretical, methodological, and technical support for the precise operation and maintenance of battery systems. Currently, power battery fault diagnosis and warning methods fall into three main categories: statistical analysis-based methods, battery model-based methods, and data-driven methods. Statistical analysis-based methods directly analyze the data collected by different sensors using various statistical methods, such as entropy, Gaussian distribution, correlation coefficient, and maximum likelihood, and ultimately implement fault diagnosis by setting appropriate thresholds. Battery model-based methods focus on establishing an accurate battery model and generating fault warnings by comparing the residuals between the model's predicted values ​​and the actual values. In contrast, data-driven methods utilize machine learning and statistical analysis techniques to analyze historical and real-time battery data to detect and predict potential faults.

[0003] However, statistical analysis methods typically rely on simple thresholds or specific statistical indicators, but are often unable to effectively detect faults in the early stages of complex, nonlinear, and multivariate lithium-ion battery fault diagnosis. Battery model-based approaches have the disadvantage of relying on highly accurate battery models and providing limited early warning capabilities for faults. Data-driven approaches overcome the difficulties of building complex battery models, especially electrochemical models, and utilize large amounts of vehicle operating data for analysis, offering significant advantages in dealing with nonlinear systems. Despite extensive research on data-driven approaches, most focus on using historical data for fault diagnosis, while data prediction often only achieves real-time or single-step prediction (i.e., predicting data at a future point in time). This biases research towards diagnosis after a fault has occurred, while fault warning can only achieve real-time or short-term advance warning. Furthermore, most studies consider only the impact of a single output on the fault, limiting the warning effect to a single dimension. For example, diagnosing or warning only voltage or temperature faults fails to fully consider the progressive relationship between voltage and temperature faults, resulting in a single and limited warning effect. The vehicle battery management system (BMS) itself often issues an alarm only when each level of fault (generally divided into three levels) occurs or with a relatively delayed delay. Due to the problem of reduced accuracy in multivariate long-term predictions, research on long-term early warning of multiple faults in lithium-ion batteries is still relatively scarce at this stage, or it is impossible to achieve high-precision long-term early warning of multiple faults. Establishing a method that conforms to actual application scenarios and developing a technology that can achieve accurate long-term early warning of multiple faults in lithium-ion batteries are of great significance for ensuring personal safety and promoting the development of electric vehicles. Summary of the Invention

[0004] In order to solve the above-mentioned problems of single fault warning for the two important parameters of voltage and temperature, decreased accuracy in multiple fault warning, and inability to provide long-term warning, the present invention provides a vehicle lithium battery fault warning method based on multivariate prediction and anomaly detection.

[0005] To implement the above technical solution, the details are as follows:

[0006] S1. Collect the operating data of the vehicle battery system through the big data platform;

[0007] The vehicle battery system includes: a battery system of a normal vehicle and a vehicle that has had a fault alarm;

[0008] The fault types include: voltage fault and temperature fault;

[0009] The voltage fault includes: battery cell overvoltage, undervoltage, and rapid voltage change;

[0010] The temperature faults include: temperature rising too fast, temperature exceeding the set threshold;

[0011] The operating data collected from the vehicle battery system includes: vehicle ID, sampling time, total battery pack voltage (TV), maximum cell voltage (HCV), minimum cell voltage (LCV), SOC, total current (C), maximum probe temperature (HT), and minimum probe temperature (LT);

[0012] S2, clean the collected data and generate a data set;

[0013] Due to the complex operating conditions, the collected data needs to be cleaned as necessary;

[0014] Data cleaning methods include:

[0015] (1) Linear interpolation is used to fill in the missing data of less than three frames, and the missing fragments of more than three frames are eliminated; that is, the sampling frequency is once every ten seconds, which is six data per minute. If 1-3 data are missing in this fragment, linear interpolation is used to fill the missing data of this fragment. If more than 3 data are missing, this fragment is directly deleted;

[0016] (2) Compare the total voltage, total current, maximum and minimum voltage of each cell, and maximum and minimum temperature of the probe with the data collected within the normal range; the normal range of SOC is [200V, 500V], [-1000A, 1000A], [2V, 5V], [-40℃, 210℃], and [0, 100]. Data outside the range is considered abnormal sensor data and should be discarded;

[0017] (3) Use wavelet transform to reduce noise of all data;

[0018] The dataset is generated as follows: the cell maximum voltage (HCV) and probe maximum temperature (HT) are randomly assigned to the last two columns. The order of the first five columns, including the battery pack total voltage (TV), total current (C), SOC, cell minimum voltage (LCV), and probe minimum temperature (LT), is not fixed, forming a matrix X with a dimension of [N,7]. The dataset is partitioned by vehicle ID, and the vehicle ID itself is not included in the dataset.

[0019] The expression is as follows:

[0020]

[0021] The maximum voltage of the battery cell is selected as the predicted tag value Y1, and the maximum temperature of the probe is selected as the predicted tag value Y2; the expression is as follows:

[0022]

[0023] Where N represents the total length of the matrix composed of all data, which is equal to the sum of the number of rows in the training set and test set matrices;

[0024] S3, divide the data set into training set and test set;

[0025] Specifically, the normal vehicle data is used as the training set to obtain the training matrix X tr , the faulty vehicle is used as the test set to obtain the test matrix X te , the training set and test set keep the same data form;

[0026] That is, the data matrix consisting of normal vehicles No. 1 and No. 2 is used as the training set, and the data matrix consisting of faulty vehicle No. 3 is used as the test set;

[0027] The expression is as follows:

[0028]

[0029]

[0030] Where n represents the total number of rows in the training set matrix;

[0031] S4. Build a prediction model using the training set. The steps are as follows:

[0032] S4.1. Input the training set into the TCN model and perform causal convolution to extract input features. The output formula of causal convolution is:

[0033]

[0034] Where, represents the output sequence at time step t and output channel c out The value on c in is the number of input channels, which is equal to the number of input features and has a value of 7; c out is the number of output channels, which is equal to the number of convolution kernels. Its value is 256, which means that the extracted features are converted into 256-dimensional data. z is the size of the convolution kernel. Its value is 3. In time convolution, this value determines how many time steps the convolution kernel covers. i represents the position of the convolution kernel in the time dimension. Is the weight of the convolution kernel, indicating that in the output channel c out , input channel c in , the weight parameter at the convolution kernel position i, the initial value is a random value with a mean of 0 and a standard deviation of 0.01 that conforms to the normal distribution. These weights determine how the convolution kernel performs weighted summation on the input features to generate the output; is the input data at time step ti and input channel c inHere ti represents the input value of a lag relative to the current time step t; Represents the bias term of each output channel. The initial value is 0 and there is no fixed value. The bias term will be continuously adjusted during the training process. The bias term is used to add an additional linear offset to the weighted sum result of the convolution to increase the flexibility of the model.

[0035] S4.2. Use the output after extracting the input features as the input of LSTM to obtain the hidden state of the current time step t;

[0036] Specifically, the output after extracting the input features is used as the input of LSTM. After the features enter the LSTM, they will go through the input gate, forget gate, candidate cell state, cell state update, output gate, and hidden state update calculations in sequence. The LSTM model further captures long-term dependencies and finally outputs the predicted value through the fully connected layer. The expression is as follows:

[0037]

[0038] Where i t represents the activation value of the input gate, which is used to control the amount of new information added to the cell state; σ represents the sigmoid activation function, whose output value is between 0 and 1, which is used to control the proportion of input information added; W i represents the weight matrix of the input gate; z t-1 Represents the hidden state of the previous time step, the value is 128; represents the output sequence at time step t and output channel c out The value on is used as the input of the LSTM model; Indicates concatenating the hidden state of the previous time step and the features extracted by TCN at the current time step; b i represents the bias term of the input gate; f t is the activation value of the forget gate; W f is the weight matrix of the forget gate; b f is the bias term of the forget gate; is the candidate cell state; tanh represents the hyperbolic tangent activation function; W c is the weight matrix used to generate candidate cell states; b c is the bias term of the candidate cell state; c t is the cell state at the current time step; f t ⊙c t-1 is the ratio of the previous cell state f t , indicating the selectively forgotten part; is the candidate state update under the input gate state; ⊙ represents element-wise multiplication; o t is the activation value of the output gate; W ois the weight matrix of the output gate; b o is the bias term of the output gate; z t is the hidden state of LSTM at the current time step t; tanh(c t ) indicates a nonlinear change in the cell state;

[0039] S4.3. LSTM calculates the hidden state of the current time step t and passes it to the fully connected layer, which maps the hidden state to the target prediction space to obtain the predicted value. The expression is as follows:

[0040]

[0041] Where, is the predicted result of voltage or temperature at time step t; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t; b y It is the bias term of the fully connected layer. Since the prediction is binary data (voltage and temperature), the dimension of the bias term is 2, which means that the hidden state is mapped to two output targets.

[0042] S4.4. After the training set is input into the model, all weight matrices and bias items in S4.1-S4.3 will be initialized and assigned values. In the forward propagation, the model will use the currently initialized parameter values ​​to calculate the above formula on the input until the final prediction result is output. The prediction value obtained by forward propagation The error between the true label and the training set is calculated through the loss function, and then back propagation is performed to calculate the gradient of the loss function with respect to each parameter. Back propagation will pass back the influence of the loss function on each parameter. The weight and bias parameters obtained in the above steps are then updated by the Adam optimizer to reduce the loss function. The present invention uses the mean square error (MSE) as the training set loss function, and the expression is as follows:

[0043]

[0044] Where n represents the length of the training set data, here n is 907578, Y t represents the true value of voltage or temperature at time step t, is the predicted voltage or temperature value at time t;

[0045] S5. Input the test set into the prediction model and obtain the prediction result by taking the highest cell voltage and the highest probe temperature as the prediction label values;

[0046] Specifically, after the test set is input into the prediction model, the model will repeat the formula obtained by inputting the training set into the model to perform calculations and call the obtained training parameters. The steps for obtaining the prediction result using the highest cell voltage and the highest probe temperature as the prediction label values ​​are as follows:

[0047] S5.1. Input the test set into the TCN model and perform causal convolution to extract input features. The expression for extracting features is as follows:

[0048]

[0049] Where, Represents the input sequence X t-τ+1:t Output value after feature extraction; X t-τ+1:t represents the test set input sequence of the past τ time steps; τ is the time window size, which is 126;

[0050] S5.2. The features extracted from TCN are passed as input to LSTM to obtain the hidden state z of the time step t ; The expression is as follows:

[0051]

[0052] Where z t-τ+1:t Represents the hidden state sequence obtained after accepting feature input;

[0053] S5.3. Generate the predicted value for the next Δ time steps by inputting the hidden state into the fully connected layer; the expression is as follows:

[0054]

[0055] Where, Indicates the maximum voltage of the monomer and the maximum temperature of the probe in the next Δ time steps, where the value of Δ is 24; [HCV t+1:t+Δ ,HT t+1:t+Δ ] is the prediction vector of voltage and temperature in the next Δ time steps; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t. Here, only the hidden state obtained at the last time step t is used; b y It is the bias term of the fully connected layer. The bias term is continuously adjusted during the training process. The bias term is used to add an additional linear offset to the weighted sum of the convolution results to increase the flexibility of the model.

[0056] Specifically, when the test set enters the TCN-LSTM model, the data is divided into M samples, each sample contains a sliding window of length 126 and a label output of prediction length 24. As sample data 1 enters the model, the trained model parameters are called to obtain the highest single voltage label data. After that, sample data 2 enters the model and repeats the above process to obtain label data And so on, for the last sample Get label data M is the number of samples, which is Nn-126-24+1=29766. The specific prediction process is as follows:

[0057]

[0058]

[0059] Similarly, the predicted data of the probe's maximum temperature can be obtained according to the above method. like The prediction process is:

[0060]

[0061] Where, X te represents the test set matrix; Indicates the first sample of the test set entering the TCN-LSTM model, and so on Indicates the Mth sample of the test set entering the model, which is also the last sample; n represents the data length of the training set, which is equal to the number of matrix rows; N represents the total length of the training set and test set data; Y1 (1) Represents the highest single-cell voltage prediction data vector obtained by the first sample, and so on Y1 (M) represents the highest cell voltage prediction data vector obtained from the Mth sample;

[0062] In order to better quantify the difference between the predicted value and the true value obtained from the test set, the root mean square error (RMSE) is used as the evaluation indicator for the prediction performance of the model test set. The calculation formula of RMSE is as follows:

[0063]

[0064] Where Nn represents the length of the test set data, Y t Indicates the true value of voltage or temperature, is the predicted voltage or temperature value at time step t;

[0065] S6. Output warning results;

[0066] Specifically, when the predicted voltage or temperature value exceeds the set upper and lower limits, an overvoltage, undervoltage or temperature abnormality alarm is triggered; when the predicted value does not exceed the set upper and lower limits, but the LOF outlier factor value obtained by the local anomaly detection algorithm (LOF) exceeds 1, a voltage abnormal rise and fall alarm or a temperature abnormal rise and fall alarm is triggered;

[0067] Here are the steps:

[0068] S6.1. Standardize the prediction results;

[0069] Specifically, after obtaining the predicted values ​​of voltage and temperature data, the input data needs to be normalized to ensure that the data is compared on the same scale; the normalization formula is:

[0070]

[0071] Where, is the predicted voltage or temperature value obtained at time t; μ j is the mean value of voltage or temperature characteristic j; σ j is the standard deviation of voltage or temperature characteristic j; z j is the normalized voltage or temperature value;

[0072] S6.2. Combine the standardized voltage data or temperature data into data sets D and U, respectively, and calculate the local outlier factor of each point in data sets D and U to obtain the warning result; the details are as follows:

[0073] S6.2.1. Define the Euclidean distance. Take any data point p in the set and any point o in D or U except p, and define the Euclidean distance between point p and point o as d. (p,o) , for any two points p=(p1,p2,...,p m ) and o=(o1,o2,...,o m )The Euclidean distance formula in m-dimensional space is:

[0074]

[0075] S6.2.2. Define the kth distance; that is, the distance between point p and its k nearest points is defined as d 1～k (p), d 1～k The maximum value in (p) is defined as d k (p), d k (p) is defined as the kth distance to point p;

[0076] d k (p) must satisfy the following two conditions: (1) In addition to point p, there are at least k points o' in D or U such that d k (p,o′)≤dk (p,o); (2) In D or U, there are at most k-1 points o' other than point k such that d(p,o') < d(p,o); here the value of k is 25, which means calculating the distance to the 25 adjacent points;

[0077] S6.2.3. Define the kth distance neighborhood N k (p); that is, the kth distance range N of point p k (p) The set of all points whose distance to point p is less than or equal to the kth distance to point p; the expression for the kth distance range is:

[0078] N k (p)={o′|d(p,o′)≤d k (p)}

[0079] Where d(p,o′) is the Euclidean distance between point p and point o′, d k (p) the kth distance of point p;

[0080] S6.2.4. Calculate the kth reachable distance d k,reach (p,o); the calculation formula for the kth reachable distance is:

[0081] d k,reach (p,o)=max{d(p,o),d k (o)}

[0082] Where d(p,o) is the Euclidean distance between point p and point o; d k (o) is the kth distance of point o; max means taking the maximum value of the two;

[0083] S6.2.5. Calculate the kth local reachability density lrd of point p k (p); the local reachable density calculation formula is:

[0084]

[0085] Where, |N k (p)| is the area N of point p k (p) the number of points; d k,reach (p,o) is the kth reachable distance from point p to point o;

[0086] S6.2.6. Calculate the kth local outlier factor LOF of point p k (p); the calculation formula of the kth local outlier factor is as follows:

[0087]

[0088] Where, lrd k(o) The kth local reachable density of point o; lrd k (p) is the kth local reachable density of point p; |N k (p)| is the area N of point p k (p) the number of points;

[0089] S6.2.7, based on the calculated local outlier factor value, separate the points into outliers and normal points, set the threshold of the local outlier factor to 1, when the calculated LOF k If (p) is greater than 1, it is considered an outlier;

[0090] The rules for outputting warning results are as follows: when the predicted value of the cell's maximum voltage is greater than the upper cutoff voltage, an overvoltage alarm is triggered; when it is less than the lower cutoff voltage, an undervoltage alarm is triggered; when the predicted value is within the normal range but the LOF outlier factor is greater than 1, a voltage abnormal fluctuation warning is triggered; when the predicted value of the cell's maximum temperature is greater than the upper temperature limit, a temperature abnormality warning is triggered; when the temperature value is within the normal range but the LOF outlier factor is greater than 1, a temperature abnormal fluctuation warning is triggered;

[0091] The upper cut-off voltage is 4.25V and the lower cut-off voltage is 3.4V;

[0092] The upper temperature limit is 55°C.

[0093] Beneficial effects of the present invention

[0094] This paper proposes a fault warning method for automotive lithium batteries based on multivariate prediction and anomaly detection. Experimental results show that, based on accurate prediction, it achieves precise multi-step (24 steps, or 4 minutes in advance) prediction of future data for voltage and temperature faults, thereby expanding the warning range from voltage faults to temperature faults, which have a greater impact on safety, providing drivers with more time for emergency response. Experimental results show that compared with existing battery management system (BMS) warning methods, this method can warn of voltage overlimits 4.5 minutes in advance, provide an early warning of abnormal voltage rise and fall before undervoltage 83.5 minutes in advance, warn of temperature anomalies 24.6 minutes in advance, and provide a temperature warning 35.1 minutes before a fault occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0096] Figure 1 is a flow chart of the method of the present invention;

[0097] Figure 2 It is a schematic diagram of the method of the present invention;

[0098] Figure 3 : This is a model structure diagram of the present invention, wherein part (a) is a structural principle diagram of the temporal convolutional network (TCN); part (b) is a residual convolution block diagram of the TCN model; and part (c) is a structural diagram of the long short-term memory neural network (LSTM);

[0099] Figure 4 The predicted results of the maximum probe temperature obtained by the present invention and the comparison results with the true value, wherein part (a) represents the true value of the temperature; part (b) represents the predicted value of the temperature; part (c) represents the error between the true value and the predicted value;

[0100] Figure 5 The predicted results of the maximum voltage of a single cell obtained by implementing the present invention and the comparison results with the actual value, wherein part (a) represents the actual value of the voltage, part (b) represents the predicted value of the voltage, and part (c) represents the error between the actual value and the predicted value;

[0101] Figure 6 is the overvoltage warning result obtained by implementing the present invention;

[0102] Figure 7 This is the undervoltage warning result obtained by implementing the present invention;

[0103] Figure 8 It is the temperature early warning result obtained by implementing the present invention. DETAILED DESCRIPTION

[0104] The present invention is further described in detail below with reference to specific embodiments.

[0105] like Figure 1 、 Figure 2 As shown, a vehicle lithium battery fault warning method based on multivariate prediction and anomaly detection includes the following steps:

[0106] S1. Collect the operating data of the vehicle battery system through the big data platform;

[0107] The vehicle battery system includes: a battery system of a normal vehicle and a vehicle that has had a fault alarm;

[0108] The fault types include: voltage fault and temperature fault;

[0109] The voltage fault includes: battery cell overvoltage, undervoltage, and rapid voltage change;

[0110] The temperature faults include: temperature rising too fast, temperature exceeding the set threshold;

[0111] Specifically, based on the big data platform, vehicle operation data is collected and the actual operation data of the power battery is extracted; the collected vehicles include: normal vehicles and vehicles with fault alarms; fault types include: voltage fault and temperature fault; voltage fault includes: battery cell overvoltage, undervoltage, and rapid voltage change; temperature fault includes: rapid temperature rise and temperature exceeding the set threshold (-20℃~55℃);

[0112] The operating data collected from the vehicle battery system includes: vehicle ID, sampling time, total battery pack voltage (TV), maximum cell voltage (HCV), minimum cell voltage (LCV), SOC, total current (C), maximum probe temperature (HT), and minimum probe temperature (LT);

[0113] In this embodiment, the real data of the battery systems of three electric vehicles for half a year are obtained through the big data detection platform; the data collection process strictly follows the "Electric Vehicle Remote Service and Management Technical Specifications" protocol, including two normally operating vehicles (car 1 and car 2) and one vehicle (car 3) that has had a fault alarm; car 1 operates in a high temperature environment in summer, car 2 operates in a low temperature environment in winter, and car 3 has a BMS fault alarm. The fault types include voltage fault (single cell overvoltage, undervoltage, and too fast voltage change rate) and temperature fault (too fast temperature rise, temperature exceeding the set threshold). The data sampling frequency of the three vehicles is once every 10 seconds, the battery's charge cut-off voltage (upper cut-off voltage) is 4.25V, the discharge cut-off voltage (lower cut-off voltage) is 3.4V, and the temperature upper and lower limits range from -20°C to 55°C;

[0114] S2, clean the collected data and generate a data set;

[0115] Due to the complex operating conditions, the collected data needs to be cleaned as necessary;

[0116] Data cleaning methods include:

[0117] (1) Linear interpolation is used to fill in the missing data of less than three frames, and the missing fragments of more than three frames are eliminated; that is, the sampling frequency is once every ten seconds, which is six data per minute. If 1-3 data are missing in this fragment, linear interpolation is used to fill the missing data of this fragment. If more than 3 data are missing, this fragment is directly deleted;

[0118] (2) Compare the total voltage, total current, maximum and minimum voltage of each cell, and maximum and minimum temperature of the probe with the data collected within the normal range; the normal range of SOC is [200V, 500V], [-1000A, 1000A], [2V, 5V], [-40℃, 210℃], and [0, 100]. Data outside the range is considered abnormal sensor data and should be discarded;

[0119] (3) Use wavelet transform to reduce noise of all data;

[0120] The dataset is generated as follows: the cell maximum voltage (HCV) and probe maximum temperature (HT) are randomly assigned to the last two columns. The order of the first five columns, including the battery pack total voltage (TV), total current (C), SOC, cell minimum voltage (LCV), and probe minimum temperature (LT), is not fixed, forming a matrix X with a dimension of [N,7]. The dataset is partitioned by vehicle ID, and the vehicle ID itself is not included in the dataset.

[0121] The expression is as follows:

[0122]

[0123] The maximum voltage of the battery cell is selected as the predicted tag value Y1, and the maximum temperature of the probe is selected as the predicted tag value Y2; the expression is as follows:

[0124]

[0125] Where N represents the total length of the matrix composed of all data, which is equal to the sum of the number of rows in the training set and test set matrices; in this embodiment, N is 937433;

[0126] Some of the recorded data of the constructed dataset are shown in Table 1:

[0127] Table 1 Part of the data for constructing the dataset

[0128]

[0129]

[0130] S3, divide the data set into training set and test set;

[0131] Specifically, the normal vehicle data is used as the training set to obtain the training matrix X tr , the faulty vehicle is used as the test set to obtain the test matrix X te , the training set and test set keep the same data form;

[0132] That is, the data matrix consisting of normal vehicles No. 1 and No. 2 is used as the training set, and the data matrix consisting of faulty vehicle No. 3 is used as the test set;

[0133] The expression is as follows:

[0134]

[0135] Where n represents the total number of rows in the training set matrix; in this embodiment, n is 907578;

[0136] S4. Build a prediction model using the training set. The steps are as follows:

[0137] S4.1. Input the training set into the TCN model and perform causal convolution to extract input features. The output formula of causal convolution is:

[0138]

[0139] Where, represents the output sequence at time step t and output channel c out The value on c in is the number of input channels, which is equal to the number of input features and has a value of 7; c out is the number of output channels, which is equal to the number of convolution kernels. Its value is 256, which means that the extracted features are converted into 256-dimensional data. z is the size of the convolution kernel. Its value is 3. In time convolution, this value determines how many time steps the convolution kernel covers. i represents the position of the convolution kernel in the time dimension. Is the weight of the convolution kernel, indicating the output channel c out , input channel c in , the weight parameter at the convolution kernel position i, the initial value is a random value with a mean of 0 and a standard deviation of 0.01 that conforms to the normal distribution. These weights determine how the convolution kernel performs weighted summation on the input features to generate the output; is the input data at time step ti and input channel c in Here ti represents the input value of a lag relative to the current time step t; Represents the bias term of each output channel. The initial value is 0 and there is no fixed value. The bias term will be continuously adjusted during the training process. The bias term is used to add an additional linear offset to the weighted sum result of the convolution to increase the flexibility of the model.

[0140] S4.2. Use the output after extracting the input features as the input of LSTM to obtain the hidden state of the current time step t;

[0141] Specifically, the output after extracting the input features is used as the input of LSTM. After the features enter the LSTM, they will go through the input gate, forget gate, candidate cell state, cell state update, output gate, and hidden state update calculations in sequence. The LSTM model further captures long-term dependencies and finally outputs the predicted value through the fully connected layer. The expression is as follows:

[0142]

[0143] Where i trepresents the activation value of the input gate, which is used to control the amount of new information added to the cell state; σ represents the sigmoid activation function, whose output value is between 0 and 1, which is used to control the proportion of input information added; W i represents the weight matrix of the input gate; z t-1 Represents the hidden state of the previous time step, the value is 128; represents the output sequence at time step t and output channel c out The value on is used as the input of the LSTM model; Indicates concatenating the hidden state of the previous time step and the features extracted by TCN at the current time step; b i represents the bias term of the input gate; f t is the activation value of the forget gate; W f is the weight matrix of the forget gate; b f is the bias term of the forget gate; is the candidate cell state; tanh represents the hyperbolic tangent activation function; W c is the weight matrix used to generate candidate cell states; b c is the bias term of the candidate cell state; c t is the cell state at the current time step; f t ⊙c t-1 is the ratio of the previous cell state f t , indicating the selectively forgotten part; is the candidate state update under the input gate state; ⊙ represents element-wise multiplication; o t is the activation value of the output gate; W o is the weight matrix of the output gate; b o is the bias term of the output gate; z t is the hidden state of LSTM at the current time step t; tanh(c t ) indicates a nonlinear change in the cell state;

[0144] S4.3. LSTM calculates the hidden state of the current time step t and passes it to the fully connected layer, which maps the hidden state to the target prediction space to obtain the predicted value. The expression is as follows:

[0145]

[0146] Where, is the predicted result of voltage or temperature at time step t; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t; b y It is the bias term of the fully connected layer. Since the prediction is binary data (voltage and temperature), the dimension of the bias term is 2, which means that the hidden state is mapped to two output targets.

[0147] S4.4. After the training set is input into the model, all weight matrices and bias items in S4.1-S4.3 will be initialized and assigned values. In the forward propagation, the model will use the currently initialized parameter values ​​to calculate the above formula on the input until the final prediction result is output. The prediction value obtained by forward propagation The error between the true label and the training set is calculated through the loss function, and then back propagation is performed to calculate the gradient of the loss function with respect to each parameter. Back propagation will pass back the influence of the loss function on each parameter. The weight and bias parameters obtained in the above steps are then updated by the Adam optimizer to reduce the loss function. The present invention uses the mean square error (MSE) as the training set loss function, and the expression is as follows:

[0148]

[0149] Where n represents the length of the training set data, here n is 907578, Y t represents the true value of voltage or temperature at time step t, is the predicted voltage or temperature value at time t;

[0150] The main function of the time convolution network TCN in the constructed TCN-LSTM hybrid neural network voltage and temperature prediction model is to capture the local time dependency of the input sequence. This is achieved through multi-layer time residual convolution blocks. Each convolution block includes two convolution layers, ReLU activation function and Dropout layer. The size of the convolution kernel is 3, the number of convolution kernels is 256, and the window moving step is 1. In TCN, the output of each layer is used as the input of the next layer, and the features in the time series are extracted layer by layer. Finally, the output shape is converted into a shape and dimension suitable for the input of the LSTM model through a fully connected layer mapping, and the length and shortness are proportional to the input size. The Long-Term Memory (LSTM) neural network is designed to handle long-term dependencies in time series data. The LSTM model consists of an input layer, a hidden layer with 128 hidden units, a linear layer, and an output layer. The data after TCN convolution is input to the input layer and hidden layer of the LSTM, and the final output is obtained through the ReLU activation function and the fully connected layer. The model's hyperparameters include the number of hidden layers, the number of batches, the number of training iterations, the sliding time window step size, the prediction step size, and the learning rate. The corresponding parameters are set to 128, 16, 50, 126, 24, and 0.001 respectively.

[0151] The training model uses the constructed training set. The parameters saved during model training include: the convolution kernel weights and bias terms of the TCN model, and the weights of the input gate, forget gate, candidate memory unit, output gate, and the bias terms of the input gate, forget gate, candidate memory unit, and output gate of the LSTM model.

[0152] Further, such as Figure 3 As shown in Figure 1, part a shows the structural principle diagram of the temporal convolutional network (TCN). When the dilation rate is 1, the model performs causal convolution without skipping time steps, and when it is greater than 1, dilated convolution is performed; part b is the residual convolution block diagram of the TCN model; part c is the structural diagram of the long short-term memory neural network (LSTM);

[0153] In this embodiment, the training set used by the model is only the data of two electric vehicles running for half a year. During the model training process, the amount of training set data and the data operation range can be increased so that the model can fully learn the data characteristics of vehicles in different environments and driving behavior habits. The above steps can be repeated for different models to train multiple models.

[0154] Furthermore, the normal vehicle data used to train the model should include as much vehicle data as possible and data from a wider range of vehicles. This will enable the model to learn the impact of different driving habits, different operating conditions, and external environments on battery data changes, allowing the model to obtain more parameters and achieve higher prediction accuracy.

[0155] Furthermore, the training model adopts a “train-test” approach, and model parameters can be updated at any time or regularly by adding training vehicles or improving data quality;

[0156] Furthermore, in order to achieve higher training accuracy, different vehicle data of different models can be collected for different vehicle models to conduct common feature training of vehicles;

[0157] S5. Input the test set into the prediction model and obtain the prediction result by taking the highest cell voltage and the highest probe temperature as the prediction label values;

[0158] Specifically, after the test set is input into the prediction model, the model will repeat the formula obtained by inputting the training set into the model to perform calculations and call the obtained training parameters. The steps for obtaining the prediction result using the highest cell voltage and the highest probe temperature as the prediction label values ​​are as follows:

[0159] S5.1. Input the test set into the TCN model and perform causal convolution to extract input features. The expression for extracting features is as follows:

[0160]

[0161] Where, Represents the input sequence X t-τ+1:t Output value after feature extraction; X t-τ+1:t represents the test set input sequence of the past τ time steps; τ is the time window size, which is 126;

[0162] S5.2. The features extracted from TCN are passed as input to LSTM to obtain the hidden state z of the time step t ; The expression is as follows:

[0163]

[0164] Where z t-τ+1:t Represents the hidden state sequence obtained after accepting feature input;

[0165] S5.3. Generate the predicted value for the next Δ time steps by inputting the hidden state into the fully connected layer; the expression is as follows:

[0166]

[0167] Where, Indicates the maximum voltage of the monomer and the maximum temperature of the probe in the next Δ time steps, where the value of Δ is 24; [HCV t+1:t+Δ ,HT t+1:t+Δ ] is the prediction vector of voltage and temperature in the next Δ time steps; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t. Here, only the hidden state obtained at the last time step t is used; b y It is the bias term of the fully connected layer. The bias term is continuously adjusted during the training process. The bias term is used to add an additional linear offset to the weighted sum of the convolution results to increase the flexibility of the model.

[0168] Specifically, when the test set enters the TCN-LSTM model, the data is divided into M samples, each sample contains a sliding window of length 126 and a label output of prediction length 24. As sample data 1 enters the model, the trained model parameters are called to obtain the highest single voltage label data. After that, sample data 2 enters the model and repeats the above process to obtain label data And so on, for the last sample Get label data M is the number of samples, which is Nn-126-24+1=29766. The specific prediction process is as follows:

[0169]

[0170] Similarly, the predicted data of the probe's maximum temperature can be obtained according to the above method. like The prediction process is:

[0171]

[0172] Where, X te represents the test set matrix; Indicates the first sample of the test set entering the TCN-LSTM model, and so on Indicates the Mth sample of the test set entering the model, which is also the last sample; n represents the data length of the training set, which is equal to the number of matrix rows; N represents the total length of the training set and test set data; Y1 (1) Represents the highest single-cell voltage prediction data vector obtained by the first sample, and so on Y1 (M) represents the highest cell voltage prediction data vector obtained from the Mth sample;

[0173] In order to better quantify the difference between the predicted value and the true value obtained from the test set, the root mean square error (RMSE) is used as the evaluation indicator for the prediction performance of the model test set. The calculation formula of RMSE is as follows:

[0174]

[0175] Where Nn represents the length of the test set data, Y t Indicates the true value of voltage or temperature, is the predicted voltage or temperature value at time step t;

[0176] The results of the test set temperature prediction are as follows Figure 4 As shown, part a shows the true value of temperature, part b is the predicted value of temperature, and part c is the error between the true value and the predicted value (error = true value - predicted value). The RMSE of temperature prediction is 0.4616℃;

[0177] The voltage prediction results are as follows: Figure 5 As shown in Figure 1, part a shows the true value of the voltage, part b shows the predicted value of the voltage, and part c shows the error between the true value and the predicted value. The RMSE of the voltage prediction is 0.0117 V, which proves that the prediction method proposed in this invention still has high accuracy when maintaining a 24-step forward prediction.

[0178] S6. Output warning results;

[0179] Specifically, when the predicted voltage or temperature value exceeds the set upper and lower limits, an overvoltage, undervoltage or temperature abnormality alarm is triggered; when the predicted value does not exceed the set upper and lower limits, but the LOF outlier factor value obtained by the local anomaly detection algorithm (LOF) exceeds 1, a voltage abnormal rise and fall alarm or a temperature abnormal rise and fall alarm is triggered;

[0180] The details are as follows:

[0181] S6.1. Standardize the prediction results;

[0182] Specifically, after obtaining the predicted values ​​of voltage and temperature data, the input data needs to be normalized to ensure that the data is compared on the same scale; the normalization formula is:

[0183]

[0184] Where, is the predicted voltage or temperature value obtained at time t; μ j is the mean value of voltage or temperature characteristic j; σ j is the standard deviation of voltage or temperature characteristic j; z j is the normalized voltage or temperature value;

[0185] S6.2. Combine the standardized voltage data or temperature data into data sets D and U, respectively, and calculate the local outlier factor of each point in data sets D and U to obtain the warning result; the details are as follows:

[0186] S6.2.1. Define the Euclidean distance. Take any data point p in the set and any point o in D or U except p, and define the Euclidean distance between point p and point o as d. (p,o) , for any two points p=(p1,p2,...,p m ) and o=(o1,o2,...,o m )The Euclidean distance formula in m-dimensional space is:

[0187]

[0188] S6.2.2. Define the kth distance; that is, define the distance between point p and its k nearest points as d 1～k (p), d 1～k The maximum value in (p) is defined as d k (p), d k (p) is defined as the kth distance to point p; d k (p) must satisfy the following two conditions: (1) In addition to point p, there are at least k points o' in D or U such that d k (p,o′)≤d k (p,o); (2) In D or U, there are at most k-1 points o' other than point k such that d(p,o') < d(p,o); here the value of k is 25, which means calculating the distance to the 25 adjacent points;

[0189] S6.2.3. Define the kth distance neighborhood N k (p); that is, the kth distance field N of point p k (p) The set of all points whose distance to point p is less than or equal to the kth distance to point p; the expression representing the kth distance range is:

[0190] N k (p)={o′|d(p,o′)≤d k (p)}

[0191] Where d(p,o′) is the Euclidean distance between point p and point o′, d k (p) the kth distance of point p;

[0192] S6.2.4. Calculate the kth reachable distance d k,reach (p,o); the calculation formula for the kth reachable distance is:

[0193] d k,reach (p,o)=max{d(p,o),d k (o)}

[0194] Where d(p,o) is the Euclidean distance between point p and point o; d k (o) is the kth distance of point o; max means taking the maximum value of the two;

[0195] S6.2.5. Calculate the kth local reachability density lrd of point p k (p); the local reachable density calculation formula is:

[0196]

[0197] Where, |N k (p)| is the area N of point p k (p) the number of points; d k,reach (p,o) is the kth reachable distance from point p to point o;

[0198] S6.2.6. Calculate the kth local outlier factor LOF of point p k (p); the calculation formula of the kth local outlier factor is as follows:

[0199]

[0200] Where, lrd k (o) The kth local reachability density of point o; lrd k (p) is the kth local reachable density of point p; |N k (p)| is the area N of point p k (p) the number of points;

[0201] S6.2.7, based on the calculated local outlier factor value, separate the points into outliers and normal points, set the threshold of the local outlier factor to 1, when the calculated LOF k If (p) is greater than 1, it is considered an outlier;

[0202] The voltage fault warning result obtained in this embodiment is as follows: Figure 6 and Figure 7 As shown, from Figure 6 As can be seen from the figure, the terminal data of the voltage prediction value (frames 29400 to 29915) is 4.26V at frame 29444, which has exceeded the upper limit cut-off voltage of the battery, 4.25V. According to the output rule of the warning result in step 6, the overvoltage warning is triggered at this time, and the BMS alarm point of the vehicle appears at frame 29447, which proves that compared with the original BMS detection method of the vehicle, the warning method proposed in the present invention realizes the overvoltage warning 4.5 minutes earlier [(29447-29444+24)×10÷60]; Figure 7 It can be seen that the voltage prediction value at frame 257 is 3.6 V. Although it is not lower than the lower limit cut-off voltage, the calculated LOF outlier factor value is 1.35, which exceeds the set threshold and triggers the voltage abnormality alarm. The BMS triggers the undervoltage alarm at frame 734, proving that this method realizes the abnormal trend warning of voltage before undervoltage 83.5 minutes in advance [(734-257-24)×10÷60].

[0203] The temperature fault warning result obtained in this embodiment is as follows: Figure 8 As shown in the figure, a temperature anomaly was first detected at frame 29728 and the anomaly point was marked. At this time, the LOF calculated value of the point was 752.34, which exceeded the set LOF anomaly detection threshold, while the temperature prediction value was 26.7°C, which did not exceed the upper temperature limit. Afterwards, the battery temperature rose significantly and rapidly. However, compared with the voltage data at this time, it can be seen that the actual voltage value was within the normal range, while the predicted voltage value only showed an abnormal upward trend but the value was still within the normal range. Therefore, focusing only on voltage data has limitations for fault warning.

[0204] From the first detection of an abnormal temperature value (frame 29,728) to the data termination point of frame 29,915, the TCN-LSTM-based multi-step prediction model and the LOF local anomaly detection algorithm achieved a temperature warning duration of 35.1 minutes [(29,915-29,728+24)×10÷60]. This was 24.6 minutes [(29,852-29,728+24)×10÷60] earlier than the BMS warning, providing drivers with ample time for emergency response.

Claims

1. A vehicle lithium battery fault warning method based on multivariate prediction and anomaly detection, characterized by: The following steps are involved: S1. Collect the operating data of the vehicle battery system through the big data platform; The vehicle battery system includes: a battery system of a normal vehicle and a vehicle that has had a fault alarm; Fault types include: voltage fault and temperature fault; The voltage fault includes: battery cell overvoltage, undervoltage, and rapid voltage change; The temperature faults include: temperature rising too fast, temperature exceeding the set threshold; The operating data of the battery system includes: vehicle ID, sampling time, total voltage of the battery pack, maximum voltage of a single cell, minimum voltage of a single cell, SOC, total current, maximum temperature of the probe, and minimum temperature of the probe; S2, clean the collected data and generate a data set; The data cleaning of the collected data includes: (1) Linear interpolation is used to fill in the missing data of missing frames less than three frames, and the missing fragments of more than three frames are eliminated; (2) Compare the total voltage, total current, maximum and minimum voltage of each cell, and maximum and minimum temperature of the probe with the data collected within the normal range; the normal range of SOC is [200V, 500V], [-1000A, 1000A], [2V, 5V], [-40℃, 210℃], and [0, 100]. Data outside the range is considered abnormal sensor data and should be discarded; (3) Use wavelet transform to reduce noise of all data; The data set is generated by forming a matrix with a dimension of [N, 7] by combining the total voltage of the battery pack, the maximum voltage of a single cell, the minimum voltage of a single cell, the SOC, the total current, the maximum temperature of the probe, and the minimum temperature of the probe; wherein the maximum voltage of the single cell and the maximum temperature of the probe are the last two columns; S3, divide the data set into training set and test set; S4, build a prediction model through the training set; S5. Input the test set into the prediction model and obtain the prediction result by taking the highest cell voltage and the highest probe temperature as the prediction label values; S6. Output the warning result.

2. The method for early warning of automotive lithium battery failure based on multivariate prediction and anomaly detection according to claim 1, characterized in that: The data set is divided in such a way that the normal vehicle data is used as the training set to obtain a training matrix, and the faulty vehicle data is used as the test set to obtain a test matrix.

3. The method for early warning of automotive lithium battery failure based on multivariate prediction and anomaly detection according to claim 1, characterized in that: The steps of constructing a prediction model through a training set are as follows: S4.

1. Input the training set into the TCN model and perform causal convolution to extract input features. The output formula of causal convolution is: Where, represents the output sequence at time step t and output channel c out The value on c in is the number of input channels, which is equal to the number of input features; c out is the number of output channels, which is equal to the number of convolution kernels; z is the size of the convolution kernel; i represents the position of the convolution kernel in the time dimension; Is the weight of the convolution kernel, indicating that in the output channel c out , input channel c in , the weight parameter at the convolution kernel position i; is the input data at time step td·i and input channel c in The value on d represents the expansion rate. When d is 1, causal convolution is performed, and when it is not 1, dilated convolution is performed. Represents the bias term of each output channel; S4.

2. The output after extracting the input features is used as the input of LSTM. After the features enter the LSTM, they will go through the input gate, forget gate, candidate cell state, cell state update, output gate, and hidden state update calculations in sequence. The LSTM model further captures long-term dependencies and finally outputs the predicted value through the fully connected layer. The calculation formula of LSTM is as follows: Where i t Represents the activation value of the input gate; σ represents the sigmoid activation function; W i represents the weight matrix of the input gate; z t-1 represents the hidden state of the previous time step; represents the output sequence at time step t and output channel c out The value on is used as the input of the LSTM model; Indicates concatenating the hidden state of the previous time step and the features extracted by TCN at the current time step; b i represents the bias term of the input gate; f t is the activation value of the forget gate; W f is the weight matrix of the forget gate; b f is the bias term of the forget gate; is the candidate cell state; tanh represents the hyperbolic tangent activation function; W c is the weight matrix used to generate candidate cell states; b c is the bias term of the candidate cell state; c t is the cell state at the current time step; f t ⊙c t-1 is the ratio of the previous cell state f t , indicating the selectively forgotten part; is the candidate state update under the input gate state; ⊙ represents element-wise multiplication; o t is the activation value of the output gate; W o is the weight matrix of the output gate; b o is the bias term of the output gate; z t is the hidden state of LSTM at the current time step t; tanh(c t ) indicates a nonlinear change in the cell state; S4.3, LSTM calculates the hidden state z of the current time step t t It is then passed to the fully connected layer, which maps the hidden state to the target prediction space to obtain the predicted value. The expression is as follows: Where, is the predicted result of voltage or temperature at time step t; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t; b y is the bias term of the fully connected layer; S4.

4. After the training set is input into the model, all weight matrices and bias items in the previous steps will be initialized and assigned values. In the forward propagation, the model will use the currently initialized parameter values ​​to calculate the input formula until the final prediction result is output. The prediction value obtained by forward propagation The error between the true label and the training set is calculated through the loss function, and then backpropagation is performed to calculate the gradient of the loss function with respect to each parameter. Backpropagation will pass back the influence of the loss function on each parameter. The weight and bias parameters obtained in the above steps are then updated through the Adam optimizer to reduce the loss function. The mean square error (MSE) is used as the training set loss function, and the expression is as follows: In the formula, n represents the length of the training set data, Y t represents the true value of voltage or temperature at time step t, is the predicted voltage or temperature value at time t.

4. The method for early warning of automotive lithium battery failure based on multivariate prediction and anomaly detection according to claim 1, characterized in that: The steps of inputting the test set into the prediction model and obtaining the prediction result using the highest cell voltage and the highest probe temperature as the prediction label values ​​are as follows: S5.

1. Input the test set into the TCN model and perform causal convolution to extract input features. The expression for extracting features is as follows: Where, Represents the input sequence X t-τ+1:t Output value after feature extraction; X t-τ+1:t represents the test set input sequence for the past τ time steps; τ is the time window size; S5.

2. The features extracted from TCN are passed as input to LSTM to obtain the hidden state z of the time step t ; The expression is as follows: Where z t-τ+1:t Represents the hidden state sequence obtained after accepting feature input; S5.

3. Generate the predicted value for the next Δ time steps by inputting the hidden state into the fully connected layer; the expression is as follows: Where, Indicates the maximum voltage of the monomer and the maximum temperature of the probe in the next Δ time steps; [HCV t+1:t+Δ ,HT t+1:t+Δ ] is the prediction vector of voltage and temperature in the next Δ time steps; W y is the weight matrix of the fully connected layer; z t is the hidden state of LSTM at the current time step t. Here, only the hidden state obtained at the last time step t is used; b y is the bias term of the fully connected layer.

5. The method for early warning of automotive lithium battery failure based on multivariate prediction and anomaly detection according to claim 1, characterized in that: The steps of outputting the warning result are as follows: S6.

1. Standardize the prediction results; S6.

2. Combine the standardized voltage data or temperature data into data sets D and U, respectively, and calculate the local outlier factor of each point in data sets D and U to obtain the warning result; the details are as follows: S6.2.

1. Define the Euclidean distance: Take any data point p in the set and any point o in D or U except p, and define the Euclidean distance between point p and point o as d (p，o) ; S6.2.

2. Define the kth distance: define the distance between point p and its k nearest points as d 1～k (p), d 1～k The maximum value in (p) is defined as d k (p), d k (p) is defined as the kth distance of point p; the value of k is 25, which means calculating the distances to the 25 nearest points; d k (p) must satisfy the following two conditions: (1) In addition to point p, there are at least k points o' in D or U such that d k (p,o′)≤d k (p,o); (2) In D or U, except the k-th point, there are at most k-1 points o' such that d(p,o')<d(p,o); S6.2.

3. Define the kth distance neighborhood N k (p); the kth distance range N of point p k (p) The set of all points whose distance to point p is less than or equal to the kth distance to point p; the expression representing the kth distance range is: N k (p)={o′|d(p,o′)≤d k (p)} Where d(p,o′) is the Euclidean distance between point p and point o′, d k (p) the kth distance of point p; S6.2.

4. Calculate the kth reachable distance d k,reach (p,o); the calculation formula for the kth reachable distance is: d k,reach (p,o)=max{d(p,o),d k (o)} Where d(p,o) is the Euclidean distance between point p and point o; d k (o) is the kth distance of point o; max means taking the maximum value of the two; S6.2.

5. Calculate the kth local reachability density lrd of point p k (p); the local reachable density calculation formula is: Where, |N k (p)| is the area N of point p k (p) the number of points; d k,reach (p,o) is the kth reachable distance from point p to point o; S6.2.

6. Calculate the kth local outlier factor LOF of point p k (p); the calculation formula of the kth local outlier factor is as follows: Where, lrd k (o) The kth local reachable density of point o; lrd k (p) is the kth local reachable density of point p; |N k (p)| is the area N of point p k (p) the number of points; S6.2.7, based on the calculated local outlier factor value, separate the points into outliers and normal points, set the threshold of the local outlier factor to 1, when the calculated LOF k If (p) is greater than 1, it is considered an outlier; The rule for outputting the warning result is that when the predicted maximum voltage of a cell is greater than the upper cut-off voltage, an overvoltage alarm is triggered; and when it is less than the lower cut-off voltage, an undervoltage alarm is triggered. When the predicted value is within the normal range but the outlier factor value is greater than 1, an abnormal voltage fluctuation warning is triggered; When the probe's maximum temperature prediction value is greater than the upper temperature limit, a temperature anomaly warning is triggered; When the temperature value is within the normal range but the LOF outlier factor value is greater than 1, a temperature abnormal fluctuation warning is triggered; The upper cut-off voltage is 4.25V, and the lower cut-off voltage is 3.4V; The upper temperature limit is 55°C.

Images