A battery fault identification method for real vehicle working conditions

Abstract

The application relates to a battery fault identification method for real vehicle working conditions and belongs to the technical field of batteries. The method comprises the following steps: S1: collecting battery operation data of an electric vehicle, containing operation data of each monomer in a battery pack, and establishing a battery operation database; S2: according to the collected battery data, a correlation coefficient method is used to screen out features with high correlation with the monomer voltage; S3: an accurate voltage estimation model is established; S4: real-time power battery operation data of the electric vehicle is input into the trained model in S3, and based on the residual error of real-time voltage and model estimated voltage, it is judged whether a fault occurs; S5: when a fault is detected, a sliding window is designed to extract sensitive features of the fault, and a fault feature two-dimensional graph is constructed; S6: an unsupervised clustering algorithm is used to identify whether the detected fault is a battery fault or a sensor reading abnormality. The application can greatly reduce the risk of false positives and false negatives.

Description

Technical Field

[0001] This invention belongs to the field of battery technology and relates to a battery fault identification method for real vehicle operating conditions. Background Technology

[0002] With the rapid development of new energy vehicles, the safety and reliability of battery systems have become increasingly important issues. During long-term use, battery systems are prone to failures such as self-discharge and internal short circuits due to material defects, extreme operating conditions, and improper operation. If these failures are not detected and addressed in a timely manner, they will seriously affect the operational safety of the vehicle and may even lead to safety accidents.

[0003] Currently, battery management systems (BMS) are typically equipped with voltage sensors to monitor the voltage of individual battery cells and identify potential faults by comparing the differences between cell voltages. However, in practical applications, this voltage difference-based fault detection method has the following limitations:

[0004] Complex operating conditions: During actual operation, electric vehicles are affected by various factors, such as driving habits, road conditions, and ambient temperature, resulting in complex and variable battery operating conditions. This makes fault detection methods based on voltage differences difficult to adapt to different operating conditions, easily leading to false alarms or missed alarms.

[0005] Abnormal sensor readings: Sensor readings in the battery management system may be affected by noise interference or their own malfunctions, leading to abnormal voltage data. Fault detection methods based on voltage differences cannot distinguish voltage differences caused by abnormal sensor readings, easily misinterpreting abnormal sensor readings as battery faults, resulting in false alarms.

[0006] Therefore, developing a battery fault identification method that can adapt to real vehicle operating conditions and effectively distinguish between battery faults and abnormal sensor readings is of great significance for ensuring the safe operation of new energy vehicles. Summary of the Invention

[0007] In view of this, the purpose of the present invention is to provide a battery fault identification method for real vehicle operating conditions.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A battery fault identification method for real-world vehicle operating conditions includes the following steps:

[0010] S1: Collect battery operation data of electric vehicles, including battery pack parameters and the individual voltage of all battery cells and the temperature of nearby temperature probes, and establish a battery operation database;

[0011] S2: Based on the battery operation database, use correlation analysis to screen out features that are highly correlated with the cell voltage;

[0012] S3: Based on the features selected in S2, establish an accurate voltage estimation model;

[0013] S4: Input the real-time power battery operation data of the electric vehicle into the voltage estimation model trained in S3, and determine whether a fault has occurred based on the residual between the real-time voltage and the model estimated voltage.

[0014] S5: When a fault is detected in S4, a sliding window is designed to extract the sensitive features of the fault and construct a two-dimensional fault feature map.

[0015] S6: Based on the two-dimensional fault feature map constructed in S5, an unsupervised clustering algorithm is used to identify whether the detected fault is a battery fault or an abnormal sensor reading.

[0016] Furthermore, in step S2, correlation analysis is performed using the Pearson correlation coefficient or the grayscale correlation coefficient to screen out features whose correlation coefficient with the unit voltage is greater than a preset value.

[0017] Furthermore, in S3, a nonlinear regression algorithm is selected as the voltage estimation model, including long short-term memory neural network, convolutional neural network, Gaussian process regression or related vector machine regression.

[0018] Furthermore, in S4, the preset fault threshold is 0.1V, 0.15V, or 0.2V.

[0019] Furthermore, in S5, the extracted fault-sensitive features include the voltage change rate and the average voltage difference.

[0020] Furthermore, in step S6, fault identification is performed using a density-based clustering algorithm with noise, a Gaussian mixture algorithm, a K-means algorithm, or an unsupervised clustering algorithm of fuzzy clustering.

[0021] Furthermore, in S1, the collected battery operating data also includes the battery pack's SOC, internal resistance, SOH, or discharge rate.

[0022] Furthermore, in S3, a linear regression algorithm using support vector machine regression or ridge regression is used as the voltage estimation model.

[0023] Furthermore, in S5, the constructed two-dimensional fault feature map includes features in two dimensions: voltage change rate and average voltage difference.

[0024] Furthermore, in step S6, the faults are classified into two categories based on the clustering results: battery faults and abnormal sensor readings.

[0025] The beneficial effects of this invention are as follows:

[0026] (1) By establishing an accurate voltage estimation model and comparing it with the real-time voltage, it is possible to effectively identify abnormalities in the voltage of individual battery cells and reduce the occurrence of missed and false alarms.

[0027] (2) By collecting and analyzing data such as battery pack parameters and individual cell voltages, the established features can adapt to different driving habits, road conditions and ambient temperatures, thereby improving the robustness of fault detection.

[0028] (3) By extracting fault-sensitive features and performing cluster analysis, it is possible to effectively distinguish between battery faults and abnormal sensor readings, thus avoiding false alarms caused by abnormal sensor readings.

[0029] (4) By timely detection of battery faults, the further development of the fault can be avoided, thereby improving the safety of the battery system and ensuring the safe operation of the vehicle.

[0030] (5) By timely detection and handling of battery faults, damage to the battery caused by the fault can be avoided, thereby extending the battery's service life.

[0031] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0032] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0033] Figure 1 This is a flowchart of the entire invention;

[0034] Figure 2 These are the cell voltage curves of normal and faulty cells in the embodiments of the present invention;

[0035] Figure 3 These are the safety risk assessment results for normal and faulty cells in the embodiments of the present invention;

[0036] Figure 4 For fault identification based on different algorithm parameters. Detailed Implementation

[0037] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0038] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0039] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0040] Please see Figure 1 A battery fault identification method for real-world vehicle operating conditions can be divided into the following steps:

[0041] S1: Collect battery operation data of electric vehicles, including the operation data of each cell in the battery pack, and establish a battery operation database;

[0042] S2: Based on the collected battery data, the correlation coefficient method is used to screen out features that are highly correlated with the cell voltage;

[0043] S3: Based on the features extracted in S2, establish an accurate voltage estimation model;

[0044] S4: Input the real-time power battery operation data of the electric vehicle into the model trained in S3, and determine whether a fault has occurred based on the residual between the real-time voltage and the model estimated voltage.

[0045] S5: When a fault is detected in S4, a sliding window is designed to extract the sensitive features of the fault and construct a two-dimensional fault feature map.

[0046] S6: Based on the two-dimensional fault feature map constructed in S5, an unsupervised clustering algorithm is used to identify whether the detected fault is a battery fault or an abnormal sensor reading.

[0047] As an optional embodiment, the above S1 specifically includes S11-S13:

[0048] S11: Collect battery pack operating data of electric vehicles, including battery pack parameters such as time, current, voltage, temperature, and insulation resistance;

[0049] S12: Collect battery operation data of electric vehicles, including the individual cell voltage of all battery cells, and the temperature of each temperature probe placed near the cell.

[0050] S13: Establish a power battery database based on the collected battery data.

[0051] As an optional embodiment, the above-mentioned S2 specifically includes S21-S22:

[0052] S21: Initially select data that are theoretically related to the unit voltage as features;

[0053] S22: Use the correlation coefficient method to screen out features that are highly correlated with the voltage of individual cells.

[0054] As an optional embodiment, the data in S21 that are theoretically related to the cell voltage include total current, battery pack voltage, average cell voltage, SOC, battery pack temperature, internal resistance, SOH, discharge rate, etc.

[0055] As an optional embodiment, the correlation coefficient method in S22 can use the Pearson correlation coefficient, the formula of which is as follows:

[0056]

[0057] As an optional embodiment, in S22, the feature with a high correlation to the single-cell voltage can be selected as the feature with a Pearson correlation coefficient greater than 0.9.

[0058] As an optional embodiment, the above-mentioned S3 specifically includes S31-S32:

[0059] S31: Select a nonlinear regression algorithm as the target machine learning algorithm;

[0060] S32: Based on the characteristics of the selected fault-free phase and the individual unit voltage data, establish an accurate voltage estimation model.

[0061] As an optional embodiment, the nonlinear regression algorithm in S31 can employ a long short-term memory neural network. The construction process of the long short-term memory neural network is as follows:

[0062] Long Short-Term Memory (LSTM) neural networks are a variant of recurrent neural networks (RNNs) that avoid the vanishing and exploding gradient problems common in RNNs during training. Furthermore, LSTM neural networks can retain historical learning information, enabling more accurate future predictions. The basic structure of a neuron in an LSTM neural network can be represented as follows:

[0063] i t =σ(W Xt X t +W hi h t-1 +b i )

[0064] f t =σ(W Xf X t +W hf h t-1 +b f )

[0065] o t =σ(W Xo X t +W ho h t-1 +b o )

[0066]

[0067] Where i, f, o, and c represent the input gate, forget gate, output gate, and memory unit, respectively; the subscript t represents the time step; h is the hidden state; and W and b are the weights and biases of different neurons. The element-wise multiplication operator is represented; σ and tanh are activation functions. In this work, the input X consists of SOC, battery pack voltage, and average cell voltage.

[0068] Typically, fully connected layers are concatenated to long short-term memory layers before being used to output predictions. A fully connected layer can be represented as:

[0069]

[0070] Where y and h represent the output and input, respectively; w and b represent the weight and variance of the i-th neuron in the previous layer, respectively; and N represents the number of neurons in the previous layer used for information transmission.

[0071] As an optional embodiment, the above S4 specifically includes S41-S42:

[0072] S41: Based on the trained voltage estimation model, input real-time battery operating data and output the real-time estimated voltage;

[0073] S42: Calculate the residual between the real-time voltage and the estimated voltage, design a threshold based on the voltage residual, and determine whether a fault has occurred.

[0074] As an optional embodiment, the fault threshold in S42 can be set to 0.15V.

[0075] As an optional embodiment, the above S5 specifically includes S51-S52:

[0076] S51: Extract the fault-sensitive features of the detected faulty part, including voltage change rate, average voltage difference, etc.

[0077] S52: Construct a two-dimensional diagram of fault characteristics.

[0078] As an optional embodiment, the calculation formula for the fault-sensitive characteristics in S51 is as follows:

[0079] By performing statistical analysis on the voltage of the faulty section, and based on the designed data sliding window dw, the average absolute values ​​of the voltage change rate aavcr and the voltage difference aavd were extracted as voltage sensitivity features. Their calculation formulas are as follows:

[0080]

[0081] Where v represents the voltage of a single battery cell; the subscript t indicates the moment when the fault was detected; and si represents the sampling period of the battery management system. It is the voltage estimated by the Long Short-Term Memory neural network.

[0082] As an optional embodiment, the above-mentioned S6 specifically includes S61-S62:

[0083] S61: Select an unsupervised clustering algorithm as the target machine learning algorithm for fault identification;

[0084] S62: Cluster the two-dimensional fault feature map to identify whether the detected fault is a battery fault or an abnormal sensor reading.

[0085] As an optional embodiment, one of the unsupervised clustering algorithms in S61 may be a density-based clustering algorithm with noise (DBSCAN).

[0086] DBSCAN is a density-based clustering algorithm. Its performance is closely related to two parameters: the minimum density reachable points (MinPts) and the cluster radius (ε). It also has the advantage of not requiring pre-specifying the number of clusters. The DBSCAN clustering process is as follows:

[0087] 1) Given the radius of the domain: ε and the minimum number of points within the radius that become the core object: MinPts.

[0088] 2) Starting from any point p, mark it as "visited" and check if it is a core point (i.e., p has at least MinPts objects in its ε neighborhood). If it is not a core point, mark it as a noise point. Otherwise, create a new cluster C for p and add all objects in p's ε neighborhood to the candidate set N.

[0089] 3) Iteratively add objects from N that do not belong to other clusters to C. During this process, for an object p′ marked as "unvisited" in N, mark it as "visited" and check its ε-neighborhood. If p′ is also a core object, then all objects in p′'s ε-neighborhood are added to N. Continue adding objects to C until C cannot be expanded, i.e., until N is empty. At this point, cluster C is completely generated.

[0090] 4) Randomly select the next unvisited object from the remaining objects and repeat the process in 3) until all objects have been visited.

[0091] The above method can effectively identify battery faults and avoid false alarms and misreports caused by abnormal sensor readings.

[0092] To illustrate the effectiveness of this invention, this embodiment provides battery pack operating data from two electric vehicles, such as... Figure 2 As shown. Among them, cells 2 and 49 of vehicle 1 experienced self-discharge and internal short-circuit faults, respectively. The individual cell voltages of cells 87, 90, and 100-108 (11 cells in total) showed abnormalities due to sensor reading issues, such as... Figure 2 As shown in the upper part; the cell voltages of cells 83-89 in vehicle 2 are abnormal due to sensor reading issues, as shown below. Figure 2 As shown in the lower half. Testing revealed that all fault detection methods detected individual battery cells with abnormal voltage data, but failed to distinguish between battery malfunctions and abnormal sensor readings. Figure 3 Two-dimensional feature maps extracted based on different time windows; Figure 4The results show that the F1 score for fault identification based on different algorithm parameters is greater than 0.96. When identifying voltage anomalies, clusters of voltage anomalies concentrated around the battery fault center are considered battery faults. Conversely, clusters classified as "other" are considered to indicate abnormal sensor readings. Therefore, this invention demonstrates that it can accurately and effectively identify battery faults and abnormal sensor readings, and is universally applicable to different vehicles, significantly reducing the risk of false alarms and false negatives.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A battery fault identification method for real vehicle working conditions, characterized in that: Includes the following steps: S1: Collect battery operation data of electric vehicles, including battery pack parameters and the individual voltage of all battery cells and the temperature of nearby temperature probes, and establish a battery operation database; S2: Based on the battery operation database, use correlation analysis to screen out features that are highly correlated with the cell voltage; S3: Based on the features selected in S2, establish an accurate voltage estimation model; S4: Input the real-time power battery operation data of the electric vehicle into the voltage estimation model trained in S3, and determine whether a fault has occurred based on the residual between the real-time voltage and the model estimated voltage. S5: When a fault is detected in S4, a sliding window is designed to extract the sensitive features of the fault and construct a two-dimensional fault feature map. The extracted fault-sensitive features include the rate of voltage change and the average voltage difference; The constructed two-dimensional fault feature map includes features in two dimensions: voltage change rate and average voltage difference. S6: Based on the two-dimensional fault feature map constructed in S5, an unsupervised clustering algorithm is used to identify whether the detected fault is a battery fault or an abnormal sensor reading. Based on the clustering results, the faults were divided into two categories: battery faults and abnormal sensor readings.

2. The battery fault identification method for real vehicle working conditions according to claim 1, characterized in that: In step S2, correlation analysis is performed using the Pearson correlation coefficient or the grayscale correlation coefficient to screen out features whose correlation coefficient with the unit voltage is greater than a preset value.

3. The method according to claim 1, wherein: In step S3, a nonlinear regression algorithm is selected as the voltage estimation model, including long short-term memory neural network, convolutional neural network, Gaussian process regression or related vector machine regression.

4. The battery fault identification method for real vehicle working conditions according to claim 1, characterized in that: In S4, the preset fault threshold is 0.1V, 0.15V, or 0.2V.

5. The battery fault identification method for real-vehicle operating conditions according to claim 1, characterized in that: In step S6, fault identification is performed using density-based clustering algorithms with noise, Gaussian mixture algorithms, K-means algorithms, or unsupervised clustering algorithms with fuzzy clustering.

6. The method according to claim 1, wherein: In S1, the collected battery operating data also includes the battery pack's SOC, internal resistance, SOH, or discharge rate.

7. The method according to claim 1, wherein the method is a method for identifying battery faults in real vehicle conditions. In S3, a linear regression algorithm using support vector machine regression or ridge regression is used as the voltage estimation model.

Images