CN111929591A

CN111929591A - Fault battery detection method, device, equipment and computer storage medium

Info

Publication number: CN111929591A
Application number: CN202010849105.XA
Authority: CN
Inventors: 黄亮
Original assignee: Rainbow Wireless Beijing New Technology Co ltd
Current assignee: Rainbow Wireless Beijing New Technology Co ltd
Priority date: 2020-08-21
Filing date: 2020-08-21
Publication date: 2020-11-13

Abstract

The application discloses a method, a device and equipment for detecting a fault battery and a computer storage medium, and relates to the field of computers. The application can be applied to the field of electric vehicles. The specific implementation scheme is as follows: obtaining voltage data of each single body of the battery within a set time after a fault occurs; performing principal component analysis on voltage data of each single body of the battery within a set time length when a fault occurs, and obtaining principal component data of each single body of the battery within the set time length; performing cluster analysis on the principal component data of each monomer of the battery meeting the conditions within the set time length to obtain the classification of each monomer according to the principal component data; and determining whether each monomer is a fault monomer or not according to the category.

Description

Fault battery detection method, device, equipment and computer storage medium

Technical Field

The present application relates to the field of electronic technology, and more particularly, to the field of electric vehicles.

Background

With the national emphasis on new energy vehicles, electric vehicles are beginning to enter thousands of households. The battery is a vital component of the electric vehicle, which directly affects the performance of the whole electric vehicle in all aspects, but at the same time, the battery is also the most prone to failure.

The power battery pack needs dozens or hundreds of battery cells to be connected in series to form a group to provide enough power to meet the requirement of a vehicle. The battery system is often out of order on the performance of one or a few of the battery cells, but because the number of the cells is large, it is difficult to find out that the cells in the battery pack are out of order. The good and bad consistency of the power battery pack directly affects the service life, the driving mileage, the safety of the whole vehicle and the like of the electric vehicle, and therefore, the detection method of the battery fault single body needs to be improved so as to find out the fault single body in time when the battery single body series connection pack breaks down.

Disclosure of Invention

In order to solve at least one problem in the prior art, embodiments of the present application provide a method, an apparatus, a device, and a computer storage medium for detecting a faulty battery.

In a first aspect, an embodiment of the present application provides a method for detecting a faulty battery, including:

obtaining voltage data of each single body of the battery within a set time after a fault occurs;

performing principal component analysis on voltage data of each single body of the battery within a set time length when a fault occurs, and obtaining principal component data of each single body of the battery within the set time length;

performing cluster analysis on the main component data of each monomer of the battery within the set time length to obtain the classification of each monomer according to the main component data;

and determining whether each monomer is a fault monomer or not according to the category.

In a second aspect, an embodiment of the present application provides a faulty battery detection apparatus, including:

the voltage data module is used for obtaining voltage data of each single body of the battery within a set time length after a fault occurs;

the main component analysis module is used for carrying out main component analysis on voltage data of each single body of the battery within a set time length when a fault occurs to obtain main component data of each single body of the battery within the set time length;

the cluster analysis module is used for carrying out cluster analysis on the principal component data of each monomer of the battery within the set time length to obtain the classification of each monomer according to the principal component data;

and the fault judging module is used for determining whether each monomer is a fault monomer according to the category.

One embodiment in the above application has the following advantages or benefits: the method comprises the steps of obtaining voltage data of battery monomers in set time after a battery fault happens, clustering the voltage data after principal component analysis is carried out on the voltage data, and then determining the type of the battery monomers with faults according to the number of the battery monomers in each type, so that the fault battery monomers in the battery can be rapidly identified, and the use safety of the battery is ensured.

Other effects of the above-described alternative will be described below with reference to specific embodiments.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

FIG. 1 is a schematic diagram of a battery fault detection method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a battery fault detection method according to another embodiment of the present application;

fig. 3A is a schematic diagram of a battery cell cluster according to another embodiment of the present application;

fig. 3B is a schematic diagram of the number of categories of a battery cell cluster according to another embodiment of the present application;

FIG. 4 is a schematic diagram of a battery failure detection apparatus according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a battery failure detection apparatus according to another embodiment of the present application;

FIG. 6 is a schematic diagram of a battery failure detection apparatus according to another embodiment of the present application;

fig. 7 is a block diagram of an electronic device for implementing the battery failure detection method according to the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The embodiment of the present application first provides a method for detecting a faulty battery, as shown in fig. 1, including:

step S11: obtaining voltage data of each single body of the battery within a set time after a fault occurs;

step S12: performing principal component analysis on voltage data of each single body of the battery within a set time length when a fault occurs, and obtaining principal component data of each single body of the battery within the set time length;

step S13: performing cluster analysis on the main component data of each monomer of the battery within the set time length to obtain the classification of each monomer according to the main component data;

step S14: and determining whether each monomer is a fault monomer or not according to the category.

In a specific embodiment, the fault reminding information of the battery can be acquired through the battery management system, and after the fault reminding information of the battery is received, the voltage data of each cell in the battery within a set time length after the time point of receiving the fault reminding information is acquired. The voltage data may be obtained by voltmeter measurements of the individual cells connected in parallel to the battery. The voltage data may be sorted in time sequence after obtaining the voltage data of each elevator in the battery to form a voltage data determinant, and then the determinant is converted to obtain a voltage data matrix, the rows of which correspond to cells in the battery and the columns correspond to times of day.

In a specific embodiment, the voltage data of each cell in the set time length after the fault occurs comprises voltage data detected at a plurality of time points in the set time length after the fault occurs, and the time intervals of the plurality of time points are equal.

In a specific embodiment, the principal component data of each cell of the battery in the set time period may be voltage data detected by each cell at multiple time points, which are arranged into a matrix with time as columns and cells as rows, and then the matrix is converted into a matrix with a smaller number of columns by using a principal component analysis method. Principal Component Analysis (PCA) is a statistical method that transforms a set of variables that may have a correlation into a set of linearly uncorrelated variables by orthogonal transformation, the set of transformed variables being the Principal components. The complexity of the matrix can be reduced by principal component analysis methods. In another embodiment, the voltage data detected at a plurality of time points by each cell may be arranged into a matrix with time as rows and cells as columns, and then the matrix may be converted into a matrix with a smaller number of rows by using a principal component analysis method.

In a specific embodiment, the main component data of each cell of the battery within the set time period is subjected to cluster analysis, so as to approximately divide the voltage of each cell of the battery into one class. Any clustering method can be adopted to cluster the voltage data of the single batteries.

In a specific embodiment, according to the relative size of the number of the battery cells in each divided category, whether the battery cell of the category has a fault or not can be determined. Because the number of the battery cells with faults is generally a small number under the fault condition, if the number of the battery cells in a certain category is obviously less than that of the battery cells in other categories, it can be determined that the battery cells in the category have faults. For example, 100 battery cells exist in the battery cell group, and after clustering, the main component data of 1 battery cell belongs to the first category, and the main component data of 99 battery cells belongs to the second category, then it can be determined that 1 battery cell of the first category is a faulty battery cell.

The fault single body determined in the embodiment of the application is a possible fault single body, and whether the corresponding single body is in fault can be further determined through other modes such as manual operation and the like.

In the embodiment of the application, through taking place the back to the trouble, the free voltage data of battery is collected, then carry out principal component analysis to the free voltage data of battery, and according to principal component analysis result, cluster the free voltage data of battery, thereby finally find out the battery monomer that breaks down according to the classification of dividing, thereby this application embodiment can find out the battery monomer that breaks down rapidly after the battery breaks down, help handling and maintaining rapidly the battery trouble, guarantee vehicle safety of traveling.

In one embodiment, the performing principal component analysis on the voltage data of each cell of the battery within a set time period when a fault occurs to obtain the principal component data of each cell of the battery within the set time period includes:

obtaining a voltage data matrix according to voltage data of each single body of the battery within a set time length when a fault occurs, wherein rows of the voltage data matrix correspond to the single bodies of the battery, and columns of the voltage data matrix correspond to time;

standardizing the voltage data matrix to obtain a standardized voltage data matrix;

calculating a correlation coefficient matrix of the voltage data matrix according to the standardized voltage data matrix;

determining the variance contribution rate of each column of the voltage data to each column of the voltage data according to the correlation coefficient matrix;

selecting the first N columns with the largest variance contribution rate as main component data of each single body of the battery in the set time length; n is a positive integer.

In a specific embodiment, the determination method of N may be the number of principal components whose cumulative variance contribution rate reaches 85%.

In a specific embodiment, the voltage data matrix may be:

the normalization process for the voltage data matrix may use the following equation:

wherein i, j are the number of rows and columns respectively,

in the embodiment of the present application, the first N columns with the largest variance contribution rates may be selected as the principal component data of each cell of the battery in the set time period, where the first N columns with the largest cumulative variance contribution rates reach the set value. For example, the dimensionality reduction is performed by a principal component analysis method, and the first two principal components with the cumulative variance contribution rate of more than 85% are selected. Specifically, if the variance contribution rates of the first 4 principal components are 0.6054, 0.2614, 0.0813 and 0.0621, respectively, the cumulative contribution rates of the first two principal components exceed 85%, which satisfies the principal component dimension reduction standard, and the first two columns can be selected as principal component data.

In a specific embodiment, the principal component analysis can capture the core contradiction of data, can find the most important factors influencing the process from multivariate complications, reveals the essence of things and simplifies complex problems. If the main aspects of things are embodied on just a few main variables, only the variables need to be separated for detailed analysis. But in general, such key variables cannot be directly found. The main aspects of the things can be represented by linear combination of original variables, and the principal component analysis is realized by projecting high-dimensional data to a lower-dimensional space, compressing the expression of redundant data and reflecting an original data matrix by using an observation matrix of the lower-dimensional space without losing correlation information.

In one embodiment, the performing cluster analysis on the principal component data of each cell of the battery in the set time length to obtain the category of each cell according to the principal component data includes:

a clustering algorithm may be employed to classify the principal component data.

In a particular embodiment, the clustering algorithm may be a K-Means algorithm.

In a specific embodiment, the principle of classifying the principal component data by using the K-Means algorithm may be that, first, N samples are determined to be classified into N classes by an initial value, the value of N may be determined manually, then, several clustering center points are randomly selected in a sample space to make the sample points near the clustering center most dense, then, the distance from each remaining sample to the clustering center is calculated and assigned to the nearest cluster, then, the average value of each cluster is recalculated, and the whole process is continuously repeated. If the two adjacent adjustments have no significant change, it indicates that the cluster formed by the data cluster has converged. The algorithm has the advantage that the accuracy of the classification of each sample is verified in each iteration. If the accuracy is not correct, the clustering samples are readjusted, after all the samples are adjusted, the clustering center is modified, the next iteration operation is carried out, and the operation is repeated until the set termination condition is met, wherein the termination condition can be any one of the following conditions: no samples are reassigned to different clusters, no change in cluster centers occurs and the sum of squared errors is locally minimal.

In a specific embodiment, the main component data can be classified by a clustering tool, and then whether the classification classified by the clustering tool meets the real condition of the main component data or not is evaluated according to the classification result of the clustering tool. For example, the main component data is classified by using a clustering tool, and the classification into 2 classes is artificially determined, but in the 2 nd class, 2 data are greatly different from other data in the second class, and then it can be determined that the main component data should be classified into 4 classes.

Specifically, the optimal number of the clustered categories can be found through an index of "goodness of clustering" (goodness of clustering is equal to the sum of squares and/or total squares between groups), and the greater the goodness of clustering is, the smaller the inter-group difference is, the greater the inter-group difference is after clustering is, i.e., the better the clustering effect is. And finally determining the optimal clustering category number to which the main component data is divided. The optimal number of clustering classes is the number of classes when the "goodness of clustering" increases to a certain value and does not increase significantly any more.

In a specific example, assuming that specific data of the voltage data matrix is data in the first voltage data matrix, as shown in fig. 2, classifying the principal component data by using a K-Means algorithm specifically includes:

step S21: randomly calculating K data in the first voltage data matrix to serve as initial clustering centers, wherein the K data correspond to K categories;

step S22: calculating the distance between each voltage data except all the clustering centers and the clustering centers;

step S23: selecting the data with the minimum distance as the data in the category corresponding to each clustering center;

step S24: recalculating new cluster centers for each category: specifically, the distance from each voltage data in each category to the initial clustering center can be calculated according to the initial clustering center of each category, then the mean value of the distances from the voltage data in the category to the initial clustering center is calculated, and a new clustering center is determined according to the mean value;

step S25: returning to step S22 until the data in each category is no longer changed, based on the new cluster center.

In one embodiment, the determining whether each cell is a faulty cell according to the category includes:

determining the number of the single batteries corresponding to each category;

and when the proportion of the number of the divided battery monomers corresponding to the first category in the total number of the battery monomers is smaller than a set threshold value, judging that the battery monomers corresponding to the first category are fault monomers.

The proportion of the number of the divided single batteries corresponding to the first category in the total number of the single batteries is smaller than a set threshold value, and the proportion of the number of the divided single batteries corresponding to the first category in the total number of the single batteries can also be determined according to whether the number of the single batteries corresponding to the first category is far smaller than the number of the single batteries corresponding to other categories.

In a specific embodiment, for example, the battery cells are divided into 3 categories, the total number of the battery cells is 100, the number of the battery cells in the first category is 97, the number of the battery cells in the second category is 1, and the number of the battery cells in the third category is 2, then it can be determined that the number of the battery cells in the second category and the third category is significantly far less than that in the first category, and therefore, it can be determined that the battery cells in the second category and the third category are faulty cells. The judgment result can be verified in other modes such as manual work and the like, and the accuracy of the judgment result is determined.

In a specific embodiment, when the proportion of the number of the divided battery cells corresponding to the first category in the total number of the battery cells is smaller than a set threshold and the number of the divided battery cells corresponding to the first category does not exceed an empirically determined limit value, it is determined that the battery cell corresponding to the first category is a faulty battery cell. In a specific embodiment, for example, if the number of the divided battery cells corresponding to the first category is far smaller than that of the divided battery cells of the other categories and does not exceed 5 battery cells determined according to experience, it is determined that the battery cell corresponding to the first category is a faulty battery cell.

In one particular example, the faulty battery detection method still includes the steps shown in fig. 1.

In executing step S11, voltage data of each cell of the battery for a set period of time after the occurrence of the failure is obtained. The voltage data may include voltage data of 300-400 battery cells, and the time point of acquiring the voltage data may be 30-40 time points.

Specifically, the voltage data includes voltage data of 337 battery cells, the voltage data at the time point of acquiring the voltage data may be 33 time points, and form a first voltage data matrix, in this example, voltage data of 10 time points and the first 20 voltage cells in the actual data are intercepted, and the intercepted voltage data may be:

in step S12, the 337 voltage units, the 33 time point voltage data, and the first voltage data matrix may be converted into principal component data by a principal component analysis method. The main component data of the first 20 voltage cells are intercepted as follows, wherein each row corresponds to one battery cell,

in step S13, the total number of cells is 337, numbered 1-337, and the cells are classified into categories. The images output by the clustering tool are shown in fig. 3A, and when the number of the clustering categories is calculated from 1 to 20, the corresponding cluster goodness is respectively calculated, and as a result, as shown in fig. 3B, when the number of the categories is increased from 0 to 4, the cluster goodness is remarkably increased, and when the number of the categories exceeds 4, the change is not large, so that the optimal number of the categories is determined to be 4. As shown in fig. 3A, the total number of cells in the first category is 335, and the total number of cells in the second category is 1, numbered 334. The total number of cells in the third category is 1, numbered 14. The total number of cells in the fourth category is 1, numbered 330.

When step S14 is executed, since the total number of the battery cells in the second category, the third category, and the fourth category is significantly less than that in the first category, it may be determined that the battery cells in the second category, the third category, and the fourth category are faulty cells.

In a specific embodiment, the process of determining the faulty cells according to the number of the battery cells corresponding to each category can be realized through machine learning.

The embodiment of the application adopts the real-time data of the fault collected in the set time period after the fault moment, can perform real-time diagnosis, overcomes the defect that a fault monomer cannot be identified by a traditional BMS method through a machine learning method, has the advantages of intuitive and concise conclusion, and greatly improves the diagnosis range, depth and efficiency.

An embodiment of the present application further provides a device for detecting a faulty battery, as shown in fig. 4, including:

a voltage data module 41, configured to obtain voltage data of each cell of the battery within a set time after a fault occurs;

the principal component analysis module 42 is configured to perform principal component analysis on voltage data of each cell of the battery within a set time period when a fault occurs, and obtain principal component data of each cell of the battery within the set time period;

a cluster analysis module 43, configured to perform cluster analysis on the principal component data of each cell of the battery within the set time duration to obtain a category of each cell divided according to the principal component data;

and a fault determination module 44, configured to determine whether each single cell is a faulty single cell according to the category.

In one embodiment, as shown in FIG. 5, the principal component analysis module 42 includes:

a voltage data matrix unit 51, configured to obtain a voltage data matrix according to voltage data of each cell of the battery within a set time period when a fault occurs, where rows of the voltage data matrix correspond to the cells, and columns of the voltage data matrix correspond to time;

a normalizing unit 52, configured to perform normalization processing on the voltage data matrix to obtain a normalized voltage data matrix;

a correlation coefficient matrix unit 53, configured to calculate a correlation coefficient matrix of the voltage data matrix according to the normalized voltage data matrix;

a variance contribution rate unit 54, configured to determine, according to the correlation coefficient matrix, a variance contribution rate of each column of the voltage data to each column of the voltage data;

a principal component data unit 55, configured to select the top N rows with the largest variance contribution rates as principal component data of each cell of the battery in the set time length; n is a positive integer.

In one embodiment, the cluster analysis module is further configured to:

and classifying the main component data by adopting a clustering algorithm.

In one embodiment, as shown in fig. 6, the fault determination module 44 includes:

a cell number unit 61 for determining the number of the battery cells corresponding to each category;

and the faulty single cell unit 62 is configured to determine that the battery cell corresponding to the first category is a faulty single cell when the proportion of the number of the divided battery cells corresponding to the first category in the total number of the battery cells is smaller than a set threshold.

The functions of each module in each apparatus in the embodiment of the present application may refer to corresponding descriptions in the above method, and are not described herein again.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

As shown in fig. 7, it is a block diagram of an electronic device according to the battery failure detection method of the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display Graphical information for a Graphical User Interface (GUI) on an external input/output device, such as a display device coupled to the Interface. In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 7, one processor 701 is taken as an example.

The memory 702 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the battery failure detection methods provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the battery failure detection method provided by the present application.

The memory 702, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the battery fault detection method in the embodiment of the present application (for example, the voltage data module 41, the principal component analysis module 42, the cluster analysis module 43, and the fault determination module 44 shown in fig. 4). The processor 701 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 702, that is, implements the battery failure detection method in the above-described method embodiment.

The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the electronic device of the battery failure detection method, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 702 may optionally include memory located remotely from the processor 701, which may be connected to the electronic devices via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.

The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 704 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The Display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) Display, and a plasma Display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, Integrated circuitry, Application Specific Integrated Circuits (ASICs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (Cathode Ray Tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical scheme of this application embodiment, in this application embodiment, through after the trouble takes place, the free voltage data of battery is collected, then carry out the principal component analysis to the free voltage data of battery, and according to the principal component analysis result, carry out the clustering to the free voltage data of battery, thereby finally find out the battery monomer that breaks down according to the classification of dividing, thereby this application embodiment can find out the battery monomer that breaks down rapidly after the battery breaks down, help handling and maintaining rapidly the battery trouble, guarantee vehicle safety of traveling.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A faulty battery detection method, comprising:

2. The method according to claim 1, wherein the performing principal component analysis on the voltage data of each cell of the battery within a set time period when a fault occurs to obtain the principal component data of each cell of the battery within the set time period comprises:

and selecting the first N columns with the largest variance contribution rate as the main component data of each single cell of the battery in the set time length, wherein N is a positive integer.

3. The method according to claim 1, wherein the performing cluster analysis on the principal component data of each cell of the battery in the set time length to obtain the classification of each cell according to the principal component data comprises:

and classifying the main component data by adopting a clustering algorithm.

4. The method of claim 1, wherein said determining whether said respective cell is a faulty cell according to said category comprises:

determining the number of the single batteries corresponding to each category;

5. A faulty battery detection device comprising:

6. The apparatus of claim 5, wherein the principal component analysis module comprises:

the voltage data matrix unit is used for obtaining a voltage data matrix according to voltage data of each single cell of the battery within a set time length when a fault occurs, wherein the row of the voltage data matrix corresponds to the single cell of the battery, and the column corresponds to the moment;

the standardization unit is used for standardizing the voltage data matrix to obtain a standardized voltage data matrix;

a correlation coefficient matrix unit for calculating a correlation coefficient matrix of the voltage data matrix according to the normalized voltage data matrix;

the variance contribution rate unit is used for determining the variance contribution rate of the voltage data of each column to the voltage data of each column according to the correlation coefficient matrix;

the main component data unit is used for selecting the first N columns with the largest variance contribution rate as the main component data of each single cell of the battery in the set time length; n is a positive integer.

7. The apparatus of claim 5, wherein the cluster analysis module is further configured to:

and classifying the main component data by adopting a clustering algorithm.

8. The apparatus of claim 5, wherein the fault determination module comprises:

the single body number unit is used for determining the number of the single batteries corresponding to each category;

and the fault single unit is used for judging that the battery single body corresponding to the first class is a fault single body when the proportion of the number of the divided battery single bodies corresponding to the first class in the total number of the battery single bodies is smaller than a set threshold value.

9. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-4.