An Adaptive Safety Early Warning Method for Lithium-ion Batteries Based on Actual Operating Data

Abstract

The present invention relates to an adaptive safety early warning method for lithium-ion batteries based on actual operation data, and belongs to the field of battery diagnosis technology. The method selects the difference between the maximum and minimum voltage values ​​and the maximum temperature as fusion feature inputs, and uses data enhancement technology to establish an enhancement matrix; selects an appropriate kernel function, maps the enhancement matrix to a high-dimensional feature space, and then calculates the enhanced kernel Mahalanobis distance; calculates the adaptive threshold according to the Chebyshev inequality, and locates the early warning time; determines the multi-level early warning value based on the median outlier value of the sliding window, and locates the abnormal single cell. The method can be applied to lithium-ion battery packs in actual operation, taking thermal runaway vehicle data as the research object, obtaining relevant parameters through normal battery data before thermal runaway occurs, and then calculating the early warning index of the vehicle at any time, and realizing timely early warning of thermal runaway by calculating multi-level adaptive thresholds.

Description

Technical Field

[0001] The invention belongs to the technical field of battery diagnosis and relates to a lithium-ion battery adaptive safety early warning method based on actual operation data. Background Art

[0002] As an important new energy storage carrier, lithium-ion batteries are an important breakthrough in addressing global climate change, breaking through resource and environmental constraints and other prominent issues. With the advancement of technology, global shipments of lithium-ion batteries have continued to rise in recent years, and the scale of the industry has continued to expand. With the widespread application of lithium-ion batteries, the safety issues that come with it are becoming increasingly prominent. News such as fires and explosions in new energy vehicles and energy storage power stations are emerging in an endless stream, which not only seriously damages people’s lives and property safety, but also affects the healthy development of the entire lithium-ion battery industry. Therefore, the development of a lithium-ion battery safety warning method has great practical value for the entire industry.

[0003] The methods of lithium-ion battery safety warning can be mainly divided into model-based methods and data-driven methods. The model-based methods need to establish accurate lithium-ion battery electrical models, thermal models or fractional-order models, etc., with high precision requirements, complex modeling process, high modeling difficulty, and the diagnostic effect is affected by the accuracy and robustness of the model; data-driven methods are artificial intelligence algorithms developed using massive battery data, including signal processing methods, which use various signal processing techniques to extract thermal runaway characteristics of data collected by BMS in the time domain or frequency domain, such as deviation, variance, frequency, entropy, correlation coefficient, etc.; they also include methods using machine learning and reinforcement learning, but such methods require large amounts of data for training in advance, and such methods are not explainable.

[0004] Based on this, the present invention uses the multi-dimensional signal of the battery pack as the fusion input, uses data enhancement and kernel function to characterize the early warning index; obtains the adaptive threshold in real time based on the Chebyshev inequality to locate the early warning time; determines the multi-level early warning value based on the median outlier value of the sliding window, and locates the abnormal single cell. The online adaptive safety early warning of the actual running lithium-ion battery is realized. Summary of the invention

[0005] In view of this, an object of the present invention is to provide a lithium-ion battery adaptive safety early warning method based on actual operation data.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A lithium-ion battery adaptive safety early warning method based on actual operation data, the method comprising the following steps:

[0008] S1: Data acquisition: obtain the battery pack data of thermal runaway accidents and perform preprocessing, extract the voltage and temperature information of normal and abnormal segments and standardize them;

[0009] S2: Feature enhancement: The difference between the maximum and minimum voltage values ​​and the maximum temperature value are used as fusion features to expand the feature dimension and establish an enhancement matrix;

[0010] S3: Calculation of parameters and early warning indicators: Calculate the parameters under normal conditions based on the enhanced kernel Mahalanobis distance, and substitute the parameters into the enhanced kernel Mahalanobis distance of the abnormal fragment as the early warning indicator;

[0011] S4: Calculate the adaptive threshold: While calculating the warning indicator, set the warning indicator sliding window, and calculate the adaptive threshold synchronously according to the indicator based on the Chebyshev inequality;

[0012] S5: Fault time detection: If the warning indicator exceeds the adaptive threshold, a warning is issued, the fault time is determined according to the warning time, and the continuous warning time and duration are counted;

[0013] S6: Faulty cell detection: Based on the median outlier value of the sliding window, the cell voltage outlier value is calculated, and the abnormal cell is located according to the degree of outlier;

[0014] S7: Hierarchical warning: A multi-level warning strategy is developed based on the continuous warning time and the degree of outlier of the faulty unit.

[0015] Further, the S1 specifically includes the following steps:

[0016] S11: Select the accident vehicle as the research object, obtain the normal state data of the vehicle and the data before the accident, and extract the temperature, voltage, time and alarm time data in the data;

[0017] S12: Data preprocessing including deduplication, leakage compensation, interpolation smoothing and elimination of abnormal points;

[0018] S13: Standardize the voltage and temperature.

[0019] Further, the S2 specifically includes the following steps:

[0020] S21: Calculate the difference between the maximum and minimum voltage at the same time, then calculate the maximum temperature, use the voltage maximum difference and the temperature maximum as fusion features, and establish a feature matrix:

[0021] X=[X1,X2,…,X m ,...,X D ]∈R N×D

[0022] X m=[x 1,m ,x 2,m ,...,x k,m ,...,x N,m ]

[0023] Where D represents the variable dimension, N represents the length of the sampling point, and x k,m represents the m-th dimension feature vector of the k-th sampling point;

[0024] S22: Introduce process variable samples, determine the maximum time lag L of process variable samples, L is a non-negative integer, and the enhanced vector at each sampling time contains the information of the current and previous L sampling points to describe the dynamic information of the process;

[0025] S23: Calculate the enhancement matrix Z with a time lag of L.

[0026] Further, the S3 specifically includes the following steps:

[0027] S31: Through nonlinear transformation φ k =F(z k ), the enhancement matrix is ​​mapped to a high-dimensional feature space, whose dimension is represented by h, and the mapping matrix is ​​represented as Φ = [φ1, φ2, ..., φ k ,...,φ N-L ]∈R h×(N-L) , indicating the mapping feature φ at the kth sampling point k The enhanced kernel Mahalanobis distance to the "center" of the feature space:

[0028]

[0029]

[0030]

[0031]

[0032]

[0033] in represents the centered eigenvector, Σ φ represents the covariance of the mapping vector in the feature space, represents a centered matrix that satisfies H is a symmetric idempotent matrix:

[0034]

[0035] Among them I N-L ∈R (N-L)×(N-L) is the identity matrix of (NL)×(NL), e N-Lis a unit vector of (NL)×1;

[0036] S32: Select an appropriate kernel function to calculate the dot product of the mapping vector, and express the kernel matrix K and the centered kernel matrix

[0037] S33: Using singular value decomposition (SVD) method to Perform full rank decomposition and calculate The Moore-Penrose pseudo-inverse matrix

[0038] S34: Solve the final calculation formula of the enhanced kernel Mahalanobis distance:

[0039]

[0040] make according to You can get:

[0041]

[0042] Let γ = 1 / (NL)HKe N-L , then the enhanced kernel Mahalanobis distance in the feature space can be calculated as follows:

[0043]

[0044] in

[0045] Substitute the normal state enhancement matrix and calculate the parameters γ and Υ;

[0046] S35: Substitute the parameters γ and Υ and the enhancement matrix of the abnormal data to be detected into the calculation formula of the enhanced kernel Mahalanobis distance to solve the early warning indicator D.

[0047] Further, the S4 specifically includes the following steps:

[0048] S41: Determine the number of sliding windows w and the mean value μ of the warning indicator at time i of the abnormal data to be tested i and mean square error σ i ;

[0049]

[0050]

[0051] S42: According to Chebyshev's inequality, for any probability distribution, for any real number k>0, there are no more than The distribution value of may differ from the mean value by more than k standard deviations. Since the larger the enhanced kernel Mahalanobis distance is, the more likely it is that an anomaly exists, the upper limit of Chebyshev’s inequality is used as the adaptive threshold of the algorithm, the k value is set, and the adaptive threshold is calculated in real time:

[0052] J i =μ i +kσ i .

[0053] Further, the S5 specifically includes the following steps:

[0054] S51: Compare the warning index of the abnormal data to be tested with the adaptive threshold. If the warning index exceeds the threshold at a certain moment, an abnormality occurs, and the warning moment is located. In actual application, when the warning continues for a certain period of time, the power supply is disconnected and corresponding rescue measures are taken;

[0055] S52: Record the start time and duration of continuous warning;

[0056] Further, the S6 specifically includes the following steps:

[0057] S61: Calculate the outlier value of each monomer voltage to locate the abnormal monomer; propose an outlier value calculation method based on the median:

[0058]

[0059] where u ti is the standardized voltage value of the ith cell at time t, u median is the median of all normalized monomer voltages under a specified window length w;

[0060] S62: setting an outlier threshold. According to the proposed outlier definition, the outlier value range is [0,1]. The closer the outlier value is to 0, the more normal the monomer state is. According to Chebyshev inequality, the maximum outlier value recorded at the same time is used to calculate the adaptive threshold in the form of a sliding window, and the multi-level warning threshold is set by adjusting different k values.

[0061] S63: Determine the outlier status of each monomer according to the threshold, locate the abnormal monomer, and determine the severity of the monomer abnormality according to the situation that the monomer exceeds the multi-level threshold.

[0062] The beneficial effects of the present invention are:

[0063] 1. The present invention adopts the actual lithium-ion battery as the research object, and is not limited to the type and application scenario of the lithium-ion battery, which has better practical significance;

[0064] 2. The present invention adopts fusion feature input, combined with data enhancement technology, taking into account the mutual correlation of multiple features and the autocorrelation of single features, and can predict the occurrence of thermal runaway more timely;

[0065] 3. The present invention fully considers the nonlinear changes in the charging and discharging process of lithium-ion batteries and introduces kernel functions to better describe early warning indicators;

[0066] 4. The present invention can provide early warning for lithium-ion batteries in real-time operation, and can adaptively generate thresholds according to the battery's own state and aging degree, thereby reducing missed warnings and false alarms;

[0067] 5. The present invention can determine the severity of the current abnormality of the lithium-ion battery according to the adaptive multi-level warning value, so that maintenance personnel can take corresponding measures;

[0068] 6. The present invention can not only give an early warning before the lithium-ion battery completely thermally runs away, but also accurately locate abnormal cells.

[0069] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0071] Figure 1 It is the technical roadmap of the present invention;

[0072] Figure 2 The preprocessed data set includes the cell voltage value and probe temperature;

[0073] Figure 3 It is the fusion feature after data enhancement;

[0074] Figure 4 It is the early warning indicator and adaptive threshold;

[0075] Figure 5 is the maximum value of the outlier monomer;

[0076] Figure 6 It is an implementation flow chart of the present invention. DETAILED DESCRIPTION

[0077] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways 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 only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0078] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0079] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0080] See also Figure 1 to Figure 6 The present invention provides a lithium-ion battery adaptive safety early warning method based on actual operation data, which can effectively perform adaptive safety early warning on abnormal lithium-ion battery packs to improve the safety of the battery system. The method can be divided into the following steps:

[0081] S1: Data acquisition: Obtain the battery pack data of thermal runaway accidents and perform preprocessing, extract the voltage, temperature and other information of normal and abnormal segments and standardize them;

[0082] S2: Feature enhancement: The difference between the maximum and minimum voltage values ​​and the maximum temperature value are used as fusion features to expand the feature dimension and establish an enhancement matrix;

[0083] S3: Calculation of parameters and early warning indicators: Calculate the parameters under normal conditions based on the enhanced kernel Mahalanobis distance, and substitute the parameters into the enhanced kernel Mahalanobis distance of the abnormal fragment as the early warning indicator;

[0084] S4: Calculate the adaptive threshold: While calculating the warning indicator, set the warning indicator sliding window, and calculate the adaptive threshold synchronously according to the indicator based on the Chebyshev inequality;

[0085] S5: Fault time detection: If the warning indicator exceeds the adaptive threshold, a warning is issued, the fault time is determined according to the warning time, and the continuous warning time and duration are counted;

[0086] S6: Faulty cell detection: Based on the median outlier value of the sliding window, the cell voltage outlier value is calculated, and the abnormal cell is located according to the degree of outlier;

[0087] S7: Hierarchical warning: A multi-level warning strategy is developed based on the continuous warning time and the degree of outlier of the faulty unit.

[0088] Furthermore, the step S1 specifically includes the following steps:

[0089] S11: Select the accident vehicle as the research object, obtain the normal state data of the vehicle and the data before the accident, and extract the temperature, voltage, time, alarm time and other data from the data;

[0090] S12: Data preprocessing such as deduplication, leakage compensation, interpolation smoothing and abnormal point removal;

[0091] S13: Standardize the voltage and temperature. Taking voltage as an example, the standardization process is as follows:

[0092] V t =(v t1 ,v t2 ,v t3 ,...,v ti ,...v tn ) (1)

[0093]

[0094]

[0095] U t =(u t1 ,u t2 ,u3,...,u tn ) (4)

[0096] Where n is the number of battery cells in the battery pack, v ti and u ti Represent the voltage and characteristics of the ith battery cell at the tth sampling moment, U t is the feature vector at the tth sampling time.

[0097] Further, the step S2 specifically includes the following steps:

[0098] S21: Calculate the difference between the maximum and minimum voltage at the same time, then calculate the maximum temperature, use the voltage maximum difference and the temperature maximum as fusion features, and establish a feature matrix:

[0099] X=[X1,X2,...,X m ,...,X D ]∈R N×D (5)

[0100] X m =[x 1,m ,x 2,m ,...,x k,m ,...,x N,m ] (6)

[0101] Where D represents the variable dimension, N represents the length of the sampling point, and x k,m Represents the m-th dimension feature vector of the k-th sampling point.

[0102] S22: Introduce process variable samples, determine the maximum time lag L of process variable samples, L is a non-negative integer, and the enhanced vector at each sampling time contains the information of the current and previous L sampling points to describe the dynamic information of the process;

[0103] S23: Calculate x at the kth sampling point k The enhancement vector is:

[0104]

[0105] where x k Represents the feature vector at the kth sampling point.

[0106] S24: Calculate the enhancement matrix Z:

[0107] Z=[z1,z2,...,z k ,...,z N-L ] T ∈R (N-L)×(L+1)D ,k>L (8)

[0108] Further, the step S3 specifically includes the following steps:

[0109] S31: Through nonlinear transformation φ k =F(z k ), the enhancement matrix is ​​mapped to a high-dimensional feature space, whose dimension is represented by h, and the mapping matrix is ​​represented as Φ = [φ1, φ2, ..., φ k ,...,φ N-L ]∈R h×(N-L), indicating the mapping feature φ at the kth sampling point k The enhanced kernel Mahalanobis distance to the "center" of the feature space:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] in represents the centered eigenvector, Σ φ represents the covariance of the mapping vector in the feature space, represents a centered matrix that satisfies H is a symmetric idempotent matrix:

[0116]

[0117] Among them I N-L ∈R (N-L)×(N-L) is the identity matrix of (NL)×(NL), e N-L is a unit vector of (NL)×1. S32: Select a polynomial kernel function to calculate the dot product of the mapping vector:

[0118]

[0119] Where α>0, serving as a tuning parameter, and β is the degree of the polynomial, which is usually not more than 3 to avoid overfitting.

[0120] Represents the kernel matrix K, the centered kernel matrix

[0121] K=Φ T Φ∈R (N-L)×(N-L) (16)

[0122]

[0123] S33: Using singular value decomposition (SVD) method to Perform full rank decomposition and calculate The Moore-Penrose pseudo-inverse matrix

[0124]

[0125]

[0126] where U∈R h×h , V∈R (N-L)×(N-L) , both are orthogonal matrices, S∈R h×(N-L) Is The singular values ​​of .

[0127] Solve the final calculation formula of the enhanced kernel Mahalanobis distance:

[0128]

[0129] make according to You can get:

[0130]

[0131] Let γ = 1 / (NL)HKe N-L , then the enhanced kernel Mahalanobis distance in the feature space can be calculated as follows:

[0132]

[0133] in

[0134] Substitute the normal state enhancement matrix and calculate the parameters γ and Υ;

[0135] S35: Substitute the parameters γ and Υ and the enhancement matrix of the abnormal data to be tested into the calculation formula of the enhanced kernel Mahalanobis distance to solve the early warning indicator D;

[0136] Further, the step S4 specifically includes the following steps:

[0137] S41: Determine the number of sliding windows w and the mean value μ of the warning indicator at time i of the abnormal data to be tested i and mean square error σ i ;

[0138]

[0139]

[0140] S42: According to Chebyshev's inequality, for any probability distribution, for any real number k>0, there are no more than The distribution value of may differ from the mean value by more than k standard deviations. Since the larger the enhanced kernel Mahalanobis distance is, the more likely it is that an anomaly exists, the upper limit of Chebyshev’s inequality is used as the adaptive threshold of the algorithm, the k value is set, and the adaptive threshold is calculated in real time:

[0141] J i =μ i+kσ i (25)

[0142] Further, the step S5 specifically includes the following steps:

[0143] S51: Compare the warning index of the abnormal data to be tested with the adaptive threshold. If the warning index exceeds the threshold at a certain moment, an abnormality occurs, and the warning moment is located. In actual applications, when the warning continues for a certain period of time, the power supply should be disconnected and corresponding measures should be taken.

[0144] S52: Record the start time and duration of continuous warning;

[0145] Further, the step S6 specifically includes the following steps:

[0146] S61: Calculate the outlier value of each cell voltage to locate the abnormal cell. A method for calculating outliers based on the median is proposed:

[0147]

[0148] where u ti is the standardized voltage value of the ith cell at time t, u median is the median of all normalized cell voltages over a specified window length w.

[0149] S62: Set the outlier threshold. According to the proposed outlier definition, the outlier value range is [0,1]. The closer the outlier is to 0, the more normal the monomer state is. According to the Chebyshev inequality, the maximum outlier recorded at the same time is used to calculate the adaptive threshold in the form of a sliding window, and the multi-level warning threshold is set by adjusting different k values.

[0150] S63: Determine the outlier status of each monomer according to the threshold, locate the abnormal monomer, and determine the severity of the monomer abnormality according to the situation that the monomer exceeds the multi-level threshold.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A lithium-ion battery adaptive safety early warning method based on actual operation data, characterized in that: The method comprises the following steps: S1: Data acquisition: obtain the battery pack data of thermal runaway accidents and perform preprocessing, extract the voltage and temperature information of normal and abnormal segments and standardize them; S2: Feature enhancement: The difference between the maximum and minimum voltage values ​​and the maximum temperature value are used as fusion features to expand the feature dimension and establish an enhancement matrix; The S2 specifically includes the following steps: S21: Calculate the difference between the maximum and minimum voltage at the same time, then calculate the maximum temperature, use the voltage maximum difference and the temperature maximum as fusion features, and establish a feature matrix: X=[X1,X2,…,X m ,…,X D ]∈R N×D X m =[x 1,m ,x 2,m ,...,x k,m ,...,x N,m ] Where D represents the variable dimension, N represents the length of the sampling point, and x k,m Represents the m-th dimension feature vector of the k-th sampling point; S22: introducing process variable samples, determining the maximum time lag L of process variable samples, where L is a non-negative integer, and the enhanced vector at each sampling moment contains information of the current and previous L sampling points to describe the dynamic information of the process; S23: Calculate the enhancement matrix Z with a time lag of L; S3: Calculation of parameters and early warning indicators: Calculate the parameters under normal conditions based on the enhanced kernel Mahalanobis distance, and substitute the parameters into the enhanced kernel Mahalanobis distance of the abnormal fragment as the early warning indicator; The S3 specifically includes the following steps: S31: Through nonlinear transformation φ k =F(z k ), the enhancement matrix is ​​mapped to a high-dimensional feature space, whose dimension is represented by h, and the mapping matrix is ​​represented as Φ = [φ1, φ2, ..., φ k ,…,φ N-L ]∈R h×(N-L) , indicating the mapping feature φ at the kth sampling point k The enhanced kernel Mahalanobis distance to the "center" of the feature space: in represents the centered eigenvector, Σ φ represents the covariance of the mapping vector in the feature space, represents a centered matrix that satisfies H is a symmetric idempotent matrix: Among them I N-L ∈R (N-L)×(N-L) is the identity matrix of (NL)×(NL), e N-L is a unit vector of (NL)×1; S32: Select an appropriate kernel function to calculate the dot product of the mapping vector, and express the kernel matrix K and the centered kernel matrix K: S33: Use the singular value decomposition (SVD) method to perform full rank decomposition on Φ and calculate The Moore-Penrose pseudo-inverse matrix S34: Solve the final calculation formula of the enhanced kernel Mahalanobis distance: make according to You can get: Let γ = 1 / (NL)HKe N-L , then the enhanced kernel Mahalanobis distance in the feature space can be calculated as follows: in Substitute the normal state enhancement matrix and calculate the parameters γ and Υ; S35: Substitute the parameters γ and Υ and the enhancement matrix of the abnormal data to be tested into the calculation formula of the enhanced kernel Mahalanobis distance to solve the early warning indicator D; S4: Calculate the adaptive threshold: While calculating the warning indicator, set the warning indicator sliding window, and calculate the adaptive threshold synchronously according to the indicator based on the Chebyshev inequality; S5: Fault time detection: If the warning indicator exceeds the adaptive threshold, a warning is issued, the fault time is determined according to the warning time, and the continuous warning time and duration are counted; S6: Faulty cell detection: Based on the median outlier value of the sliding window, the cell voltage outlier value is calculated, and the abnormal cell is located according to the degree of outlier; S7: Hierarchical warning: A multi-level warning strategy is developed based on the continuous warning time and the degree of outlier of the faulty unit.

2. The lithium-ion battery adaptive safety early warning method based on actual operation data according to claim 1, characterized in that: The S1 specifically includes the following steps: S11: Select the accident vehicle as the research object, obtain the normal state data of the vehicle and the data before the accident, and extract the temperature, voltage, time and alarm time data in the data; S12: Data preprocessing including deduplication, leakage compensation, interpolation smoothing and elimination of abnormal points; S13: Standardize the voltage and temperature.

3. The lithium-ion battery adaptive safety early warning method based on actual operation data according to claim 1, characterized in that: The S4 specifically comprises the following steps: S41: Determine the number of sliding windows w and the mean value μ of the warning indicator at time i of the abnormal data to be tested i and mean square error σ i ; S42: According to Chebyshev's inequality, for any probability distribution, for any real number k>0, there are no more than The distribution value of may differ from the mean value by more than k standard deviations. Since the larger the enhanced kernel Mahalanobis distance is, the more likely it is that an anomaly exists, the upper limit of Chebyshev’s inequality is used as the adaptive threshold of the algorithm, the k value is set, and the adaptive threshold is calculated in real time: J i =μ i +kσ i 。 4. The lithium-ion battery adaptive safety early warning method based on actual operation data according to claim 3 is characterized in that: The S5 specifically includes the following steps: S51: Compare the warning index of the abnormal data to be tested with the adaptive threshold. If the warning index exceeds the threshold at a certain moment, an abnormality occurs, and the warning moment is located. In actual application, when the warning continues for a certain period of time, the power supply is disconnected and corresponding rescue measures are taken; S52: Record the start time and duration of the continuous warning.

5. The lithium-ion battery adaptive safety early warning method based on actual operation data according to claim 4, characterized in that: The S6 specifically comprises the following steps: S61: Calculate the outlier value of each monomer voltage to locate the abnormal monomer; propose an outlier value calculation method based on the median: where u ti is the standardized voltage value of the ith cell at time t, u median is the median of all normalized monomer voltages under a specified window length w; S62: setting an outlier threshold. According to the proposed outlier definition, the outlier value range is [0,1]. The closer the outlier value is to 0, the more normal the monomer state is. According to Chebyshev inequality, the maximum outlier value recorded at the same time is used to calculate the adaptive threshold in the form of a sliding window, and the multi-level warning threshold is set by adjusting different k values. S63: Determine the outlier status of each monomer according to the threshold, locate the abnormal monomer, and determine the severity of the monomer abnormality according to the situation that the monomer exceeds the multi-level threshold.

Images