WO2021168836A1 - 异常检测方法和设备 - Google Patents

异常检测方法和设备 Download PDF

Info

Publication number
WO2021168836A1
WO2021168836A1 PCT/CN2020/077286 CN2020077286W WO2021168836A1 WO 2021168836 A1 WO2021168836 A1 WO 2021168836A1 CN 2020077286 W CN2020077286 W CN 2020077286W WO 2021168836 A1 WO2021168836 A1 WO 2021168836A1
Authority
WO
WIPO (PCT)
Prior art keywords
matrix
vector
vectors
battery pack
abnormality detection
Prior art date
Application number
PCT/CN2020/077286
Other languages
English (en)
French (fr)
Inventor
程康
王甲佳
朱泽敏
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202080004134.4A priority Critical patent/CN112513883A/zh
Priority to PCT/CN2020/077286 priority patent/WO2021168836A1/zh
Publication of WO2021168836A1 publication Critical patent/WO2021168836A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
    • H01M10/4285—Testing apparatus
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Definitions

  • This application relates to the field of battery detection, and in particular to an abnormality detection method and equipment.
  • the Gaussian distribution law and the 3 ⁇ confidence criterion method are usually used to analyze the battery data and judge whether the battery is abnormal according to the analysis result.
  • this method strongly relies on the assumption that the battery data changes conform to the Gaussian distribution.
  • this assumption is usually not satisfied, resulting in a higher error rate for detecting battery abnormalities using this method.
  • the embodiments of the present application provide an abnormality detection method and device, which can improve the accuracy of battery abnormality detection.
  • an abnormality detection method and corresponding device are provided.
  • the first device obtains the first similarity matrix and the first covariance matrix, and determines the first feature matrix according to the first similarity matrix and the first covariance matrix, and then determines the first feature matrix according to the first feature matrix.
  • the abnormal state of each battery pack in the L battery packs of the second device, where the first similarity matrix is the similarity matrix corresponding to the first group state data of the L battery packs of the second device, and the first covariance matrix is The covariance matrix corresponding to the first group of state data of the L battery packs, and L is a positive integer.
  • the similarity matrix can represent the local characteristics of the data
  • the covariance matrix can represent the global characteristics of the data
  • the feature matrix obtained from the similarity matrix and the covariance matrix can not only Representing the global characteristics of the data can also represent the local characteristics of the data, thereby making full use of the spatial information of the data for anomaly analysis and improving the accuracy of battery anomaly detection; on the other hand, the first device performs the first device through remote services.
  • the abnormal detection of the battery of the second device can avoid the detection on the second device, thereby avoiding the problem that the abnormal detection cannot be realized due to the hardware limitation of the second device.
  • the first device obtaining the first similarity matrix includes: the first device obtains L first vectors, performs cluster analysis on the L first vectors, and determines the first similarity matrix according to the results of the cluster analysis.
  • a similarity matrix where the first vector includes N state data in the first group of state data, the L first vectors correspond to the L battery packs one-to-one, and N is a positive integer.
  • determining the similarity matrix based on cluster analysis can make the state data in the first vectors of different classes have a more obvious degree of discrimination, which is conducive to better identifying different dynamic vectors in subsequent analysis. , Thereby improving the accuracy of data analysis; on the other hand, since the number of status data of each battery pack in the L battery packs is N, and the value of N can be changed according to the actual situation, the batteries can be used flexibly
  • the historical data is used for abnormal detection, which improves the flexibility of detection.
  • the N state data are data after normalization processing. Based on this scheme, the dimensional difference of each state data can be eliminated, and the accuracy of data analysis can be improved.
  • the first similarity matrix is The value of the element in row i and column j is determined by the distance function between the i-th first vector and the j-th first vector, and i and j are positive integers less than or equal to L.
  • the distance function between the i-th first vector and the j-th first vector satisfies the following first formula:
  • S i,j is an element in the i-th row and j-th column of the first similarity matrix
  • x i is the i-th first vector
  • x j is the j-th first vector
  • ⁇ is a preset value
  • the above-mentioned first similarity matrix and the first covariance matrix satisfy the following second formula:
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the first feature matrix, including: the first device performs principal component analysis on the first feature matrix to obtain a projection matrix, and The abnormal state of each battery pack in the L battery packs is determined according to the projection matrix.
  • the first device performs principal component analysis on the first feature matrix to obtain the projection matrix, including: the first device obtains a transpose matrix of the first feature matrix, and transposes the first feature matrix
  • the matrix performs singular value decomposition to obtain N singular values and the left singular vector corresponding to each singular value of the N singular values; the first device according to the left singular vector corresponding to the first K singular values among the N singular values, Determine the projection matrix, K is a positive integer less than or equal to N.
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the projection matrix, including: the first device determines L according to the projection matrix and the L first vectors. Second vectors, the L second vectors correspond to the L first vectors one-to-one; the first device determines according to the T 2 statistic of each second vector in the L second vectors The abnormal state of each of the L battery packs.
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the T 2 statistic of each second vector in the L second vectors, including: The T 2 statistic of the p-th second vector in the second vector is greater than or equal to the first threshold.
  • the first device determines that the M states of the p-th battery pack in the L battery packs are abnormal, and updates the p-th battery pack.
  • the number of abnormal states of a battery pack, p is a positive integer from 1 to L, and M represents the number of state types of N state data included in the first vector corresponding to the p-th battery pack.
  • the abnormality detection method further includes: the first device determines the abnormality level of the p-th battery pack according to the total number of abnormal states of the p-th battery pack and a preset rule.
  • the first group of state data includes: discharge voltage data, discharge current data, temperature data, or state-of-charge data.
  • an abnormality detection device for implementing the above-mentioned various methods.
  • the abnormality detection device may be the first device in the foregoing first aspect, or a device including the foregoing first device, or a device included in the foregoing first device.
  • the abnormality detection device includes a module, unit, or means corresponding to the foregoing method, and the module, unit, or means can be realized by hardware, software, or by hardware executing corresponding software.
  • the hardware or software includes one or more modules or units corresponding to the above-mentioned functions.
  • an anomaly detection device including: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the anomaly detection device can execute the anomaly detection device described in any of the above aspects. method.
  • the abnormality detection device may be the first device in the foregoing first aspect, or a device including the foregoing first device, or a device included in the foregoing first device.
  • an abnormality detection device including: a processor; the processor is configured to couple with a memory, and after reading an instruction in the memory, execute the method according to any one of the foregoing aspects according to the instruction.
  • the abnormality detection device may be the first device in the foregoing first aspect, or a device including the foregoing first device, or a device included in the foregoing first device.
  • an abnormality detection device including: a processor and an interface circuit, the interface circuit may be a code/data read-write interface circuit, and the interface circuit is used to receive computer-executed instructions (computer-executed instructions are stored in a memory) , May be directly read from the memory, or may be transmitted through other devices) and transmitted to the processor; the processor is used to run the computer-executable instructions to execute the method described in any of the foregoing aspects.
  • the abnormality detection device may be the first device in the foregoing first aspect, or a device including the foregoing first device, or a device included in the foregoing first device.
  • a computer-readable storage medium stores computer instructions.
  • the anomaly detection device can execute any of the foregoing The method described.
  • a computer program product containing instructions which when running on a processor, enables the abnormality detection device to execute the method described in any of the foregoing aspects.
  • an abnormality detection device for example, the abnormality detection device may be a chip or a chip system
  • the abnormality detection device includes a processor for implementing the functions involved in any of the foregoing aspects.
  • the anomaly detection device further includes a memory for storing necessary program instructions and data.
  • the anomaly detection device is a chip system, it may be composed of a chip, or may include a chip and other discrete devices.
  • FIG. 1 is a schematic diagram of the architecture of an anomaly detection system provided by an embodiment of the application
  • FIG. 2 is a flowchart of an abnormality detection method provided by an embodiment of the application
  • FIG. 3 is a flowchart of another abnormality detection method provided by an embodiment of the application.
  • FIG. 4 is a structural block diagram of an abnormality detection device provided by an embodiment of this application.
  • FIG. 5 is a structural block diagram of a detected device provided by an embodiment of this application.
  • FIG. 6 is a structural block diagram of another abnormality detection device provided by an embodiment of the application.
  • FIG. 7 is a structural block diagram of yet another anomaly detection device provided by an embodiment of the application.
  • At least one item (a) refers to any combination of these items, including any combination of a single item (a) or a plurality of items (a).
  • at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple .
  • words such as “first” and “second” are used to distinguish the same or similar items with substantially the same function and effect. Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and order of execution, and words such as “first” and “second” do not limit the difference.
  • an abnormality detection system 10 provided by an embodiment of this application.
  • the abnormality detection system 10 includes a first device, and the first device is used as an abnormality detection device.
  • the abnormality detection system 10 may further include a second device and a terminal device, where the second device is used as a detected device.
  • an application program (APP) for controlling the power battery of the detected device is installed in the terminal device.
  • an abnormality detection method includes the following steps:
  • the first device obtains a first similarity matrix and a first covariance matrix.
  • the first similarity matrix is the similarity matrix corresponding to the first set of state data of the L battery packs of the second device
  • the first covariance matrix is the covariance matrix corresponding to the first set of state data of the L battery packs
  • L is a positive integer
  • the first device may first obtain the first group of state data of the L battery packs, and then obtain the similarity matrix and the covariance matrix corresponding to the first group of state data of the L battery packs, that is, the first similarity matrix And the first covariance matrix.
  • the method for the first device to obtain the first group of state data of the L battery packs will be described below.
  • the second device may periodically collect state data of its L battery packs, and send the collected state data to the first device.
  • the first device receives the status data from the second device, analyzes and cleans the data, and stores the status data of each battery pack according to the identification of the first device according to the category of the battery pack status data.
  • the state of the battery pack may include one or more of the following four states: discharge voltage state, discharge current state, temperature state, and state of charge; correspondingly, the state data of the battery pack may include the following one Or multiple items: discharge voltage data of the battery pack, discharge current data of the battery pack, temperature data of the battery pack, or state of charge data of the battery pack.
  • the discharge voltage data of the L battery packs of the second device stored by the first device may be as shown in Table 1.
  • the interval between any two adjacent moments may be the same, and the interval duration may be the period during which the second device collects and reports the discharge voltage data.
  • the first set of state data of the L battery packs can be obtained from the stored state data of the L battery packs.
  • the first group status data of the L battery packs includes N status data of each battery pack in the L battery packs, and N is a positive integer, that is, the first group status of the L battery packs
  • the data includes N*L data.
  • the categories of different status data in the N status data of a battery pack can be the same or different, that is, the N status data can include one or more of the following types of status data: discharge voltage data, discharge current data, For temperature data or state-of-charge data, in the following embodiments of the present application, the first group of state data of the L battery packs includes one type of state data (for example, discharge voltage data) as an example for description.
  • the first set of state data of the L battery packs including N discharge voltage data of each battery pack as an example
  • the first set of state data of the L battery packs may include the above-mentioned table 1 All discharge voltage data.
  • the first device after the first device obtains the first group of status data of the L battery packs, it can perform normalization processing on the first group of status data to eliminate the dimensional difference of each status data and improve the accuracy of data analysis. . Therefore, finally the first group of state data of the L battery packs may be the original state data on the second device, or may be the data after the first device normalizes the original state data.
  • acquiring the first similarity matrix by the first device may include: the first device acquiring L first vectors, the first vectors may be column vectors, and the first vectors include the first group states of the L battery packs.
  • the L first vectors correspond to the L battery packs one-to-one. That is, one first vector corresponds to one battery pack, and the N status data included in the first vector corresponding to the battery pack are the status data of the battery pack.
  • the N discharge voltage data in the column where the battery pack 1 is located in Table 1 constitute the corresponding battery pack 1
  • N discharge voltage data of the column type where the battery pack 2 is located constitute the first vector corresponding to the battery pack 2, and so on.
  • the first device performs cluster analysis on the L first vectors, and determines the first similarity matrix according to the result of the cluster analysis. Among them, the first device performs cluster analysis on the L first vectors to reduce the L first vectors to M categories, where M is a positive integer, and each category in the M categories includes one or more first vectors. vector.
  • the state data of the battery packs corresponding to one or more first vectors belonging to the same category has similar change characteristics in a macroscopic view, such as increasing or decreasing at the same time within a certain range, which can indicate that the dynamic behavior of the multiple battery packs is generally Unanimous. Therefore, the determination of the similarity matrix based on cluster analysis can make the state data in the first vector of different classes have a more obvious degree of discrimination, which is conducive to better identification of different dynamic vectors in subsequent analysis, thereby improving data analysis Accuracy.
  • the first vector includes the N state data in the first group of state data, which may include:
  • the first vector includes data obtained by normalizing the N status data in the first group of status data.
  • the first device determines the first similarity matrix according to the result of the aforementioned clustering analysis
  • the result of the clustering analysis indicates the i-th first vector and the L-th first vector among the L first vectors
  • the value of the element in the i-th row and j-th column of the first similarity matrix is determined by the distance function between the i-th first vector and the j-th first vector.
  • i and j are positive integers less than or equal to L
  • the distance function is a function used to define the distance between elements in the metric space, and can be understood as a special function that satisfies specific properties in the metric space.
  • the distance function between the i-th first vector and the j-th first vector satisfies the following first formula:
  • S i,j are elements in the i-th row and j-th column of the first similarity matrix
  • x i is the i-th first vector
  • x j is the j-th first vector
  • ⁇ is the preset value
  • the value in the first similarity matrix is 0.
  • the first device may calculate the first covariance matrix according to the first group of state data of the L battery packs, and the embodiment of the present application does not specifically limit the calculation method of the first covariance matrix.
  • the first device can execute the abnormality detection method provided in the embodiment of the present application in a variety of situations, for example:
  • the first device may periodically execute the abnormality detection method provided in the embodiment of the present application, that is, the first device periodically performs abnormality detection on the state of the L battery packs of the second device.
  • the second device may send a request message to the first device.
  • the request message is used to request the first device to detect whether the battery of the second device is abnormal.
  • the request message may include The device ID of the second device.
  • the first device performs abnormal detection on the status of the L battery packs of the second device.
  • the terminal device may send a request message to the first device, and the request message may be triggered by the user to send the terminal device.
  • the request message is used to request the first device to detect whether the battery of the second device is abnormal.
  • the request message may include the device identification and/or user identification of the second device, where the user identification exists with the second device The association relationship, that is, the second device can be determined through the user identification.
  • the first device after receiving the request message, the first device performs abnormal detection on the status of the L battery packs of the second device.
  • the first device determines a first feature matrix according to the first similarity matrix and the first covariance matrix.
  • the first device may determine the first feature matrix according to the first similarity matrix and the first covariance matrix by using the following formula 2:
  • C is the first covariance matrix
  • S is the first similarity matrix
  • X is the matrix composed of L first vectors
  • the columns of X correspond to the L first vectors one-to-one, that is, a first
  • the vector is a column of X
  • X is a matrix of N rows and L columns
  • X T is the transposed matrix of X, ⁇ (0,1).
  • the first device determines the first feature matrix
  • it can determine the abnormal state of each battery pack in the L battery packs of the second device according to the first feature matrix. Specifically, it can include the following steps S203-S204:
  • the first device performs principal component analysis (PCA) on the first feature matrix to obtain a projection matrix.
  • PCA principal component analysis
  • the first device performs principal component analysis on the first feature matrix to obtain the projection matrix, which may include: the first device obtains the transposed matrix of the first feature matrix, and performs singular value decomposition on the transposed matrix of the first feature matrix , Get N singular values and the left singular vector corresponding to each singular value of the N singular values; the first device determines the projection matrix according to the left singular vector corresponding to the first K singular values in the N singular values, K Is a positive integer less than or equal to N.
  • the proportion of the first K singular values in the total singular values among the N singular values is ⁇ .
  • ⁇ is a predefined value or a value configured by the administrator to the first device.
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the projection matrix.
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the projection matrix, which may include: the first device determines the second vector according to the projection matrix and the L first vectors, where the L The second vector corresponds to the L first vectors one-to-one; the first device determines the abnormal state of each battery pack in the L battery packs according to the T 2 statistic of each second vector in the L second vectors.
  • determining the second vector by the first device according to the projection matrix and the L first vectors may include: the first device obtains the transposed matrix of the projection matrix, and projects the L first vectors to the projection matrix. Transpose the matrix to get L second vectors.
  • projecting the L first vectors to the transposed matrix of the projection matrix can be understood as performing matrix multiplication operations on the transposed matrix of the projection matrix and the L first vectors, for example, the second vector,
  • the transposed matrix of the first vector and the projection matrix can satisfy the following third formula:
  • y i is the i- th second vector among the L second vectors
  • U is the projection matrix
  • U T is the transpose matrix of the projection matrix
  • x i is the i- th first vector among the L first vectors .
  • the first device may calculate the T 2 statistic of each second vector in the L second vectors.
  • the T 2 statistic of the i-th second vector can be obtained according to the following formula 4:
  • T i 2 is the T 2 statistic of the i-th second vector in the L second vectors
  • y i is the i-th second vector
  • matrix Y is a matrix composed of L second vectors
  • the columns of Y correspond to the L second vectors one-to-one, that is, one second vector is used as a column of Y.
  • the first device determines the abnormal state of each battery pack in the L battery packs according to the T 2 statistic of each second vector in the L second vectors, which may include:
  • the first device determines the p-th battery pack corresponding to the p-th second vector in the L battery packs
  • the number of abnormal states of the p-th battery pack is updated and the number of abnormal states of the p-th battery pack is updated
  • p is a positive integer from 1 to L
  • M represents the state category of the N status data included in the first vector corresponding to the p-th battery pack Number, M is a positive integer less than or equal to 4.
  • N state data included in the first vector corresponding to the p-th battery pack are all the discharge voltage data of the p-th battery pack, then M is equal to 1; or, if the p-th battery pack corresponds to the p-th battery pack.
  • the N state data included in a vector are the discharge voltage data and discharge current data of the p-th battery pack, and M is equal to 2.
  • the above-mentioned first threshold satisfies the following formula 6:
  • T is the first threshold
  • F represents the F distribution
  • FL (NL)
  • ⁇ represents the value of the ⁇ quantile that obeys the F distribution with the degrees of freedom L and NL.
  • the first device may execute the above steps S201-S204 multiple times to determine whether each state of each battery pack in the L battery packs is abnormal, and finally determine the abnormal state of each battery pack total.
  • the first device executes the above steps S201-S204, the N status data included in the first vector corresponding to the p-th battery pack are all one type of status data, then the first device can execute four The above steps S201-S204, for example, the first execution can determine whether the discharge voltage state of the p-th battery pack is abnormal. If it is abnormal, the number of abnormal states of the p-th battery pack is updated, for example, its value is increased by 1.
  • the second execution can determine whether the discharge current state of the p-th battery pack is abnormal, and so on, and finally determine the total number of abnormal states, assuming that the first device determines the discharge of the p-th battery pack If the voltage state, the discharge current state, and the temperature are abnormal, and the state of charge is normal, the total number of abnormal states of the p-th battery pack is 3.
  • the similarity matrix can represent the local characteristics of the data
  • the covariance matrix can represent the global characteristics of the data
  • the feature matrix obtained from the similarity matrix and the covariance matrix can not only Representing the global characteristics of the data can also represent the local characteristics of the data, thereby making full use of the spatial information of the data for anomaly analysis and improving the accuracy of battery anomaly detection; on the other hand, the first device performs the first device through remote services.
  • the abnormal detection of the battery of the second device can avoid the detection on the second device, thereby avoiding the problem that the abnormal detection cannot be realized due to the hardware limitation of the second device.
  • the abnormality detection method may further include the following step S205:
  • S205 The first device sends first indication information.
  • the first indication information is used to indicate the total number of abnormal states and/or the category of abnormal states of each battery pack in the L battery packs.
  • the first device determines the total number of abnormal states of each battery pack, it can report to the second device, the terminal device, the service center of the manufacturer of the second device, and other application servers (such as navigation One or more of the system servers) send the above-mentioned first indication information.
  • the second device the terminal device, the service center of the manufacturer of the second device, and other application servers (such as navigation One or more of the system servers) send the above-mentioned first indication information.
  • the above-mentioned one or more devices can perform related processing according to the first indication information, thereby reducing the occurrence of accidents caused by abnormal batteries. The probability.
  • the related processing performed by the second device and/or the terminal device according to the first indication information may include, for example, issuing an alarm signal to warn the user that the battery of the second device is abnormal, so that the user can deal with it in time.
  • the abnormality detection method may further include the following steps S206-S207:
  • the first device determines the abnormality level of each battery pack in the L battery packs.
  • the first device may determine the abnormality level of each battery pack according to a preset rule and the total number of abnormal states of each battery pack.
  • the preset rule may be: if the total number of abnormal states of the p-th battery pack is 0, then its abnormality level is no abnormal; if the total number of abnormal states of the p-th battery pack is less than or Equal to the first value, the abnormality level is minor; if the total number of abnormal states of the p-th battery pack is greater than the first value and less than or equal to the second value, the abnormality level is normal; if the p-th battery pack is abnormal If the total number of states is greater than the second value, the abnormality level is normal.
  • the first value and the second value may be determined by the first device according to the total number of states of the battery pack. For example, if the total number of states of the battery pack is 4, the first value may be 1, and the second value may be 3.
  • the preset rule may also be a mathematical model pre-trained by the first device, and the first device inputs the total number of abnormal states of each battery pack into the mathematical model to obtain each battery pack The anomaly level.
  • S207 The first device sends second indication information.
  • the second indication information is used to indicate the abnormality level of each battery pack in the L battery packs.
  • the first device determines the abnormality level of each battery pack, it can report to the second device, terminal device, the manufacturer’s service center of the second device, and other application servers used to assist the second device in driving (such as a navigation system server).
  • One or more of) sends the above-mentioned second indication information.
  • the above-mentioned one or more devices can perform related processing according to the abnormal level of the battery pack, thereby reducing the occurrence of accidents caused by battery abnormalities. The probability.
  • FIG. 2 or FIG. 3 describes the abnormality detection method provided in the embodiment of the present application from the perspective of the overall abnormality detection device. The following will provide the embodiment of the present application from the perspective of the internal implementation of the abnormality detection device. The anomaly detection method will be explained.
  • FIG. 4 a structural block diagram of an abnormality detection device provided in this embodiment of the present application.
  • the structural block diagram may be understood as a division of the abnormality detection device from the perspective of logical functions.
  • the anomaly detection equipment can be divided into three layers in terms of logic function.
  • the lower layer is used to implement data collection, storage, and processing functions, and can include data collection modules, data storage modules, and data processing modules;
  • the middle layer provides data analysis for the upper layer Services related to basic algorithms can include data analysis modules and algorithm service modules;
  • the upper layer provides battery anomaly detection applications to implement battery anomaly detection functions, and can include anomaly detection modules and information interaction modules.
  • each module can communicate with each other (not shown in Figure 4).
  • a structural block diagram of a detected device provided in this embodiment of the present application, the structural block diagram may be understood as a division of the detected device from the perspective of logical functions.
  • the detected device can be logically divided into a data collection module, which is used to collect the status data of the battery pack of the detected device; a data reporting module, which is used to report the status of the battery pack collected by the data collection module to the anomaly detection device Data; service request module, used to request the abnormal detection device to perform abnormal detection on the state of the battery pack of the detected device; display module, used to display information.
  • each module can communicate with each other (not shown in Figure 5).
  • FIG. 4 or FIG. 5 is schematic, and is only a logical function division, and there may be other division methods in actual implementation.
  • the anomaly detection method includes:
  • the anomaly detection module of the first device invokes the algorithm service module to obtain the first similarity matrix and the first covariance matrix.
  • the data collection module of the second device may periodically collect the status data of the L battery packs of the second device, and send it to the data collection module of the first device through the data reporting module of the second device. After the data collection module of the first device receives the status data, it is sent to the data processing module of the first device to analyze and clean the data, and then the data storage module of the first device according to the identification of the first device according to the status of the battery pack The category of data stores the status data of each battery pack.
  • the anomaly detection module can first call the data analysis module and the data storage module to obtain the first group of status data of the L battery packs; after obtaining the first group of status data, the anomaly detection module can call the algorithm service module to obtain the first similarity matrix And the first covariance matrix.
  • the method for obtaining the first similarity matrix and the first covariance matrix can refer to the related description in the above step S201, which will not be repeated here.
  • the anomaly detection module of the first device can execute the anomaly detection method provided in the embodiment of the present application in a variety of situations, for example:
  • the abnormality detection module of the first device may periodically execute the abnormality detection method provided in the embodiment of the present application.
  • the service request module of the second device may send a request message to the information exchange module of the first device, so that the abnormality detection module of the first device can check the status of the L battery packs of the second device.
  • the description of the request message can refer to the related description in the above step S201, which will not be repeated here.
  • the terminal device may send a request message to the information exchange module of the first device, so that the abnormality detection module of the first device performs abnormality detection on the state of the L battery packs of the second device.
  • the request message For the description of the request message, reference may be made to the related description in step S201, which is not repeated here.
  • the anomaly detection module of the first device invokes the algorithm service module to determine the first feature matrix according to the first similarity matrix and the first covariance matrix.
  • step S202 For the method for determining the first feature matrix, reference may be made to the related description in step S202 above, which will not be repeated here.
  • the anomaly detection module of the first device invokes the algorithm service module to perform principal component analysis on the first feature matrix to obtain the projection matrix.
  • step S203 For the method of performing principal component analysis on the first feature matrix to obtain the projection matrix, reference may be made to the related description in step S203 above, which will not be repeated here.
  • the abnormality detection module of the first device invokes the algorithm service module to determine the abnormal state of each battery pack in the L battery packs.
  • step S204 For related description, please refer to the above step S204, which will not be repeated here.
  • the abnormality detection method may further include the following step S305:
  • S305 The information interaction module of the first device sends first indication information.
  • the second device may display the content of the first indication information through its display module, so that This allows the user to perform related processing according to the content of the first instruction information, reducing the probability of accidents.
  • the abnormality detection method may further include the following steps S306-S307:
  • the abnormality detection module of the first device determines the abnormality level of each battery pack in the L battery packs.
  • S307 The information exchange module of the first device sends second indication information.
  • steps S306-S307 can refer to the above-mentioned steps S206-S207, which will not be repeated here.
  • the first device can perform some or all of the steps in the embodiments of the present application. These steps or operations are only examples, and the embodiments of the present application may also perform other operations or variations of various operations. . In addition, each step may be executed in a different order presented in the embodiments of the present application, and it may not be necessary to perform all the operations in the embodiments of the present application.
  • the methods and/or steps implemented by the first device can also be implemented by components (such as chips or circuits) that can be used in the first device, and the methods and/or steps implemented by the second device can also be implemented by the second device.
  • a step can also be implemented by a component (such as a chip or a circuit) that can be used in the second device.
  • an embodiment of the present application also provides an abnormality detection device, which is used to implement the above-mentioned various methods, that is, the abnormality detection device is the execution subject of the abnormality detection method shown in FIG. 2 or FIG. 3.
  • the abnormality detection device may be the first device in the foregoing method embodiment, or a device including the foregoing first device, or a component that can be used for the first device. It can be understood that, in order to realize the above-mentioned functions, the abnormality detection device includes hardware structures and/or software modules corresponding to each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.
  • FIG. 6 shows a structural block diagram of an abnormality detection device 60 provided in an embodiment of this application.
  • the anomaly detection device 60 includes one or more processors 601, a communication bus 602, and at least one communication interface (in FIG. 6 it is only an example that includes a communication interface 604 and a processor 601 as an example).
  • a memory 603 may also be included.
  • the processor 601 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more programs for controlling the execution of the program of this application. integrated circuit.
  • CPU central processing unit
  • ASIC application-specific integrated circuit
  • the communication bus 602 may be a peripheral component interconnect standard (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • PCI peripheral component interconnect standard
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 6, but it does not mean that there is only one bus or one type of bus.
  • the communication bus 602 is used to connect different components in the constant detection device 60 so that different components can communicate.
  • the communication interface 604 is used to communicate with other devices or communication networks.
  • the communication network may be, for example, a radio access network (RAN), a wireless local area network (WLAN), or the like.
  • the communication interface 604 may be a device such as a transceiver or a transceiver.
  • the communication interface 604 may also be a transceiver circuit located in the processor 601 to implement signal input and signal output of the processor.
  • the memory 603 may be a device having a storage function. For example, it can be read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM), or other types that can store information and instructions Dynamic storage devices can also be electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage, optical disc storage ( Including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store desired program codes in the form of instructions or data structures and can be stored by a computer Any other media taken, but not limited to this.
  • the memory may exist independently, and is connected to the processor through the communication line 602. The memory can also be integrated with the processor.
  • the memory 603 is used to store computer-executable instructions for executing the solution of the present application, and the processor 601 controls the execution.
  • the processor 601 is configured to execute computer-executable instructions stored in the memory 603, so as to implement the abnormality detection method provided in the embodiment of the present application.
  • the processor 601 may also perform processing-related functions in the abnormality detection method provided in the following embodiments of the present application, and the communication interface 604 is responsible for communicating with other devices or communication networks.
  • the application embodiment does not specifically limit this.
  • the computer-executable instructions in the embodiments of the present application may also be referred to as application program codes, which are not specifically limited in the embodiments of the present application.
  • the processor 601 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 6.
  • the abnormality detection device 60 may include multiple processors, such as the processor 601 and the processor 608 in FIG. 6. Each of these processors can be a single-CPU (single-CPU) processor or a multi-core (multi-CPU) processor.
  • the processor here may refer to one or more devices, circuits, and/or processing cores for processing data (for example, computer program instructions).
  • the abnormality detection device 60 may further include an output device 605 and an input device 606.
  • the output device 605 communicates with the processor 601 and can display information in a variety of ways.
  • the output device 605 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector (projector) Wait.
  • the input device 606 communicates with the processor 601 and can receive user input in a variety of ways.
  • the input device 606 may be a mouse, a keyboard, a touch screen device, a sensor device, or the like.
  • the actions of the first device in steps S201 to S205 or steps S201 to S207 can be called by the processor 601 in the abnormality detection device shown in FIG. 6 to call the application code stored in the memory 603 to instruct the abnormality detection device to execute
  • the actions of the first device in the above steps S301 to S305 or steps S301 to S307 can be executed by the processor 601 in the anomaly detection device shown in FIG. 6 calling the application code stored in the memory 603 to instruct the anomaly detection device to execute, This embodiment does not impose any limitation on this.
  • an embodiment of the present application further provides an abnormality detection device (for example, the abnormality detection device may be a chip or a chip system), the abnormality detection device includes a processor, and is configured to implement the method in any of the foregoing method embodiments. .
  • the anomaly detection device further includes a memory.
  • the memory is used to store necessary program instructions and data, and the processor can call the program code stored in the memory to instruct the abnormality detection device to execute the method in any of the foregoing method embodiments.
  • the memory may not be in the abnormality detection device.
  • the anomaly detection device further includes an interface circuit, the interface circuit is a code/data read-write interface circuit, and the interface circuit is used to receive computer-executed instructions (computer-executed instructions are stored in a memory, and may be directly Read from the memory, or possibly through other devices) and transfer to the processor.
  • the abnormality detection device is a chip system, it may be composed of a chip, or may include a chip and other discrete devices, which is not specifically limited in the embodiment of the present application.
  • the aforementioned anomaly detection device may be a roadside unit (RSU) in a vehicle to everything (V2X) system; or it may be a cloud network device; or it may also be an application server; or It may be a chip installed in the above-mentioned RSU or cloud network device or application server.
  • RSU roadside unit
  • V2X vehicle to everything
  • the embodiment of the present application does not limit the specific form of the abnormality detection device.
  • the detected device in the embodiment of the present application may be a mobility tool driven by a power battery (such as an electric car, an electric bicycle, etc.), or a vehicle-mounted terminal installed in the mobility tool, or a vehicle-mounted terminal Inside the chip.
  • a power battery such as an electric car, an electric bicycle, etc.
  • a vehicle-mounted terminal installed in the mobility tool, or a vehicle-mounted terminal Inside the chip.
  • the terminal device in the embodiment of the present application may be a device used to implement a wireless communication function, such as a terminal or a chip that can be used in a terminal.
  • the aforementioned vehicle-mounted terminal or terminal may be a user equipment (UE) and access device in a fifth-generation (5th generation, 5G) network or a public land mobile network (PLMN) that will evolve in the future.
  • the access terminal can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), with wireless communication Functional handheld devices, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices or wearable devices, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, industrial control (industrial) Wireless terminal in control), wireless terminal in self-driving (self-driving), etc.
  • the vehicle-mounted terminal or terminal can be mobile or fixed.
  • the embodiments of the present application can also divide the anomaly detection device into functional modules according to the above method embodiments.
  • each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • the obtaining module 702 is configured to obtain a first similarity matrix and a first covariance matrix.
  • the first similarity matrix is the similarity matrix corresponding to the first group of state data of the L battery packs of the second device.
  • the variance matrix is the covariance matrix corresponding to the first group of state data of the L battery packs, and L is a positive integer;
  • the processing module 701 is configured to determine the first characteristic matrix according to the first similarity matrix and the first covariance matrix;
  • the module 701 is also used to determine the abnormal state of each battery pack in the L battery packs according to the first characteristic matrix.
  • the obtaining module 702 is configured to obtain a first similarity matrix, including: the obtaining module 702 is configured to obtain L first vectors, the first vectors include N state data in the first group of state data, and L The first vector has a one-to-one correspondence with the L battery packs, and N is a positive integer; the obtaining module 702 is also used to perform a cluster analysis on the L first vectors, and determine the first similarity matrix according to the result of the cluster analysis.
  • the processing module 701 is further configured to determine the abnormal state of each battery pack in the L battery packs according to the first feature matrix, including: the processing module 701 is further configured to perform principal component analysis on the first feature matrix Obtain the projection matrix, and determine the abnormal state of each battery pack in the L battery packs according to the projection matrix.
  • the processing module 701 is further configured to perform principal component analysis on the first feature matrix to obtain the projection matrix, including: the processing module 701 is also configured to obtain the transposed matrix of the first feature matrix, and compare the The transposed matrix performs singular value decomposition to obtain N singular values and the left singular vector corresponding to each singular value in the N singular values; the processing module 701 is also used to calculate the first K singular values corresponding to the N singular values Left singular vector, determine the projection matrix, K is a positive integer less than or equal to N.
  • the processing module 701 is further configured to determine the abnormal state of each battery pack in the L battery packs according to the projection matrix, including: the processing module 701 is further configured to determine L battery packs according to the projection matrix and the L first vectors The second vector, the L second vectors are in one-to-one correspondence with the L first vectors; the processing module 701 is further configured to determine the number of L battery packs according to the T 2 statistic of each second vector in the L second vectors The abnormal state of each battery pack.
  • the processing module 701 is further configured to determine the abnormal state of each battery pack in the L battery packs according to the T 2 statistic of each second vector in the L second vectors, including: The T 2 statistic of the p-th second vector in the vector is greater than or equal to the first threshold, and the processing module 701 is also used to determine that the M states of the p-th battery pack in the L battery packs are abnormal, and update the p-th battery pack.
  • the number of abnormal states of a battery pack, p is a positive integer from 1 to L
  • M represents the number of state types of N state data included in the first vector corresponding to the p-th battery pack.
  • the processing module 701 is further configured to determine the abnormality level of the p-th battery pack according to the total number of abnormal states of the p-th battery pack and a preset rule.
  • the first device 70 is presented in the form of dividing various functional modules in an integrated manner.
  • the "module” here can refer to a specific ASIC, circuit, processor and memory that executes one or more software or firmware programs, integrated logic circuit, and/or other devices that can provide the above-mentioned functions.
  • the first device 70 may take the form of the abnormality detection device 60 shown in FIG. 6.
  • the processor 601 in the abnormality detection device 60 shown in FIG. 6 may invoke the computer execution instructions stored in the memory 603 to make the first device 70 execute the abnormality detection method in the foregoing method embodiment.
  • the function/implementation process of the processing module 701 and the acquisition module 702 in FIG. 7 may be implemented by the processor 601 in the abnormality detection device 60 shown in FIG. 6 calling a computer execution instruction stored in the memory 603.
  • the first device 70 provided in this embodiment can execute the above-mentioned abnormality detection method, the technical effects that can be obtained can refer to the above-mentioned method embodiment, and will not be repeated here.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or includes one or more data storage devices such as servers, data centers, etc. that can be integrated with the medium.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).
  • the computer may include the aforementioned device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Chemical & Material Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • General Chemical & Material Sciences (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

本申请实施例提供异常检测方法和设备，可以提高电池异常检测的准确性。该方法包括：第一设备获取第一相似度矩阵和第一协方差矩阵，并根据该第一相似度矩阵和第一协方差矩阵确定第一特征矩阵，之后，根据该第一特征矩阵确定第二设备的L个电池组中每个电池组的异常状态，其中，第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，第一协方差矩阵为该L个电池组的第一组状态数据对应的协方差矩阵，L为正整数。

Description

异常检测方法和设备 技术领域
本申请涉及电池检测领域，尤其涉及一种异常检测方法和设备。
背景技术
近年来，随着电动汽车的大规模普及应用，由于电池异常导致的汽车自燃事故时有发生，因此，如何在事故发生之前检测到电池的异常以使各方采取相应的处理措施，是避免汽车自燃事故发生的重要手段。
目前，通常运用高斯分布的规律以及3σ置信准则方法对电池数据进行分析，并根据分析结果判断电池是否异常。但是，该方法强烈依赖于电池数据变化符合高斯分布的假设，然而实际中这种假设通常不能满足，从而导致使用该方法检测电池异常的错误率较高。
因此，如何提高电池异常检测的准确性，是目前亟待解决的问题。
发明内容
本申请实施例提供一种异常检测方法和设备，可以提高电池异常检测的准确性。
为达到上述目的，本申请的实施例采用如下技术方案：
第一方面，提供了一种异常检测方法及相应的装置。该方案中，第一设备获取第一相似度矩阵和第一协方差矩阵，并根据该第一相似度矩阵和第一协方差矩阵确定第一特征矩阵，之后，根据该第一特征矩阵确定第二设备的L个电池组中每个电池组的异常状态，其中，第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，第一协方差矩阵为该L个电池组的第一组状态数据对应的协方差矩阵，L为正整数。
基于该方案，一方面，由于相似度矩阵可以表示数据的局部特性，协方差矩阵可以表示数据的全局特性，因此，本申请实施例中，根据相似度矩阵和协方差矩阵得到的特征矩阵不仅可以表示数据的全局特性还可以表示数据的局部特性，从而充分利用了数据的空间信息进行异常分析，提高了电池异常检测的准确性；另一方面，通过远程服务的方式即由第一设备进行第二设备电池的异常检测，可以避免在第二设备上进行检测，从而避免了由于第二设备的硬件限制而无法实现异常检测的问题。
在一种可能的设计中，第一设备获取第一相似度矩阵，包括：第一设备获取L个第一向量，对L个第一向量做聚类分析，并根据聚类分析的结果确定第一相似度矩阵，其中，第一向量包括第一组状态数据中的N个状态数据，L个第一向量与L个电池组一一对应，N为正整数。
基于该方案，一方面，基于聚类分析确定相似度矩阵可以使得不同类的第一向量中的状态数据具有更明显的区分度，有利于在后续的分析中能够更好地辨识不同动态的向量，进而提高数据分析的准确度；另一方面，由于L个电池组中每个电池组的状态数据的个数为N，而N的取值可以根据实际情况进行改变，因此可以灵活地利用电池的历史数据进行异常检测，提高检测的灵活性。
在一种可能的设计中，该N个状态数据为进行归一化处理后的数据。基于该方案，可以消除各个状态数据的量纲差别，提升数据分析的准确度。
在一种可能的设计中，当上述聚类分析的结果指示该L个第一向量中的第i个第一向量和第j个第一向量属于同一类时，该第一相似度矩阵中第i行第j列元素的值由该第i个第一向量和该第j个第一向量的距离函数决定，i、j为小于或等于L的正整数。
在一种可能的设计中，上述第i个第一向量和第j个第一向量的距离函数，满足如下第一公式：
Figure PCTCN2020077286-appb-000001
其中，S i，j为第一相似度矩阵中第i行第j列的元素，x i为该第i个第一向量，x j为该第j个第一向量，σ为预设值。
在一种可能的设计中，当上述聚类分析的结果指示该L个第一向量中的第i个第一向量和第j个第一向量不属于同一类时，第一相似度矩阵中第i行第j列元素的值为0。
在一种可能的设计中，上述第一相似度矩阵和第一协方差矩阵，满足如下第二公式：
Figure PCTCN2020077286-appb-000002
其中，
Figure PCTCN2020077286-appb-000003
为该第一特征矩阵，C为该第一协方差矩阵，S为该第一相似度矩阵，X为该L个第一向量组成的矩阵，X T为X的转置矩阵，λ∈(0，1)。
在一种可能的设计中，第一设备根据第一特征矩阵，确定L个电池组中每个电池组的异常状态，包括：第一设备对第一特征矩阵进行主成分分析得到投影矩阵，并根据该投影矩阵确定该L个电池组中每个电池组的异常状态。
在一种可能的设计中，第一设备对第一特征矩阵进行主成分分析得到投影矩阵，包括：第一设备获取该第一特征矩阵的转置矩阵，并对该第一特征矩阵的转置矩阵进行奇异值分解，得到N个奇异值和该N个奇异值中每个奇异值对应的左奇异向量；第一设备根据该N个奇异值中的前K个奇异值对应的左奇异向量，确定该投影矩阵，K为小于或等于N的正整数。
在一种可能的设计中，第一设备根据投影矩阵确定上述L个电池组中每个电池组的异常状态，包括：第一设备根据所述投影矩阵和所述L个第一向量，确定L个第二向量，所述L个第二向量与所述L个第一向量一一对应；所述第一设备根据所述L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态。
在一种可能的设计中，第一设备根据L个第二向量中每个第二向量的T 2统计量，确定该L个电池组中每个电池组的异常状态，包括：若该L个第二向量中的第p个第二向量的T 2统计量大于或等于第一阈值，第一设备确定该L个电池组中的第p个电池组的M个状态异常，并更新该第p个电池组的异常状态的个数，p为1至L的正整数，M表示该第p个电池组对应的第一向量包括的N个状态数据的状态类别数。
在一种可能的设计中，该异常检测方法还包括：第一设备根据该第p个电池组的异常状态的总数与预设规则，确定该第p个电池组的异常等级。
在一种可能的设计中，第一组状态数据包括：放电电压数据、放电电流数据、温度数据、或者荷电状态数据。
第二方面，提供了一种异常检测设备用于实现上述各种方法。该异常检测设备可以为 上述第一方面中的第一设备，或者包含上述第一设备的装置，或者上述第一设备中包含的装置。所述异常检测设备包括实现上述方法相应的模块、单元、或手段(means)，该模块、单元、或means可以通过硬件实现，软件实现，或者通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块或单元。
第三方面，提供了一种异常检测设备，包括：处理器和存储器；该存储器用于存储计算机指令，当该处理器执行该指令时，以使该异常检测设备执行上述任一方面所述的方法。该异常检测设备可以为上述第一方面中的第一设备，或者包含上述第一设备的装置，或者上述第一设备中包含的装置。
第四方面，提供了一种异常检测设备，包括：处理器；所述处理器用于与存储器耦合，并读取存储器中的指令之后，根据所述指令执行如上述任一方面所述的方法。该异常检测设备可以为上述第一方面中的第一设备，或者包含上述第一设备的装置，或者上述第一设备中包含的装置。
第五方面，提供了一种异常检测设备，包括：处理器和接口电路，该接口电路可以为代码/数据读写接口电路，该接口电路用于接收计算机执行指令(计算机执行指令存储在存储器中，可能直接从存储器读取，或可能经过其他器件)并传输至该处理器；该处理器用于运行所述计算机执行指令以执行上述任一方面所述的方法。该异常检测设备可以为上述第一方面中的第一设备，或者包含上述第一设备的装置，或者上述第一设备中包含的装置。
第六方面，提供了一种计算机可读存储介质，该计算机可读存储介质中存储有计算机指令，当该计算机指令在处理器上运行时，使得所述异常检测设备可以执行上述任一方面所述的方法。
第七方面，提供了一种包含指令的计算机程序产品，当其在处理器上运行时，使得所述异常检测设备可以执行上述任一方面所述的方法。
第八方面，提供了一种异常检测设备(例如，该异常检测设备可以是芯片或芯片系统)，该异常检测设备包括处理器，用于实现上述任一方面所涉及的功能。在一种可能的设计中，该异常检测设备还包括存储器，该存储器，用于保存必要的程序指令和数据。该异常检测设备是芯片系统时，可以由芯片构成，也可以包含芯片和其他分立器件。
其中，第二方面至第八方面中任一种设计方式所带来的技术效果可参见上述第一方面中不同设计方式所带来的技术效果，此处不再赘述。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种异常检测系统的架构示意图；
图2为本申请实施例提供的一种异常检测方法的流程图；
图3为本申请实施例提供的另一种异常检测方法的流程图；
图4为本申请实施例提供的一种异常检测设备的结构框图；
图5为本申请实施例提供的一种被检测设备的结构框图；
图6为本申请实施例提供的另一种异常检测设备的结构框图；
图7为本申请实施例提供的又一种异常检测设备的结构框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。其中，在本申请的描述中，除非另有说明，“/”表示前后关联的对象是一种“或”的关系，例如，A/B可以表示A或B；本申请中的“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况，其中A,B可以是单数或者复数。并且，在本申请的描述中，除非另有说明，“多个”是指两个或多于两个。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b，或c中的至少一项(个)，可以表示：a，b，c，a-b，a-c，b-c，或a-b-c，其中a，b，c可以是单个，也可以是多个。另外，为了便于清楚描述本申请实施例的技术方案，在本申请的实施例中，采用了“第一”、“第二”等字样对功能和作用基本相同的相同项或相似项进行区分。本领域技术人员可以理解“第一”、“第二”等字样并不对数量和执行次序进行限定，并且“第一”、“第二”等字样也并不限定一定不同。
如图1所示，为本申请实施例提供的一种异常检测系统10。该异常检测系统10包括第一设备，所述第一设备用于作为异常检测设备。可选的，该异常检测系统10还可以包括第二设备和终端设备，其中所述第二设备用于作为被检测设备。可选的，该终端设备中安装有用于控制被检测设备的动力电池的应用程序(application program，APP)。
下面将结合图1，对本申请实施例提供的异常检测方法进行展开说明。
需要说明的是，本申请下述实施例中各个网元之间的消息名字或消息中各参数的名字等只是一个示例，具体实现中也可以是其他的名字，本申请实施例对此不作具体限定。
如图2所示，为本申请实施例提供的一种异常检测方法，该异常检测方法包括如下步骤：
S201、第一设备获取第一相似度矩阵和第一协方差矩阵。
其中，第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，第一协方差矩阵为该L个电池组的第一组状态数据对应的协方差矩阵，L为正整数。
可选的，第一设备可以先获取L个电池组的第一组状态数据，再获取该L个电池组的第一组状态数据对应的相似度矩阵和协方差矩阵，即第一相似度矩阵和第一协方差矩阵。下面对第一设备获取L个电池组的第一组状态数据的方法进行说明。
可选的，第二设备可以周期性地采集其L个电池组的状态数据，并将采集的状态数据发送给第一设备。相应的，第一设备接收到来自第二设备的状态数据，对数据进行解析清洗等处理后，根据第一设备的标识按照电池组状态数据的类别分类存储每个电池组的状态数据。
可选的，电池组的状态可以包括以下四种状态中的一种或多种：放电电压状态、放电电流状态、温度状态、荷电状态；相应的，电池组的状态数据可以包括以下一项或多项：电池组的放电电压数据、电池组的放电电流数据、电池组的温度数据、或者电池组的荷电 状态(state of charge)数据。
示例性地，以电池组的状态数据为放电电压数据为例，第一设备存储的第二设备的L个电池组的放电电压数据可以如表1所示。
表1
Figure PCTCN2020077286-appb-000004
其中，任意两个相邻时刻的间隔可以相同，间隔时长可以为第二设备采集并上报放电电压数据的周期。
可选的，由于第一设备存储有第二设备的L个电池组的状态数据，因此可以从其存储的L个电池组的状态数据中，获取L个电池组的第一组状态数据。其中，该L个电池组的第一组状态数据中包括该L个电池组中每个电池组的N个状态数据，N为正整数，也就是说，该L个电池组的第一组状态数据中包括N*L个数据。一个电池组的该N个状态数据中不同的状态数据的类别可以相同也可以不同，即该N个状态数据中可以包括以下一种或多种类别的状态数据：放电电压数据、放电电流数据、温度数据、或者荷电状态数据，本申请下述实施例中以该L个电池组的第一组状态数据包括一种类别的状态数据(例如放电电压数据)为例进行说明。
示例性地，以该L个电池组的第一组状态数据中包括每个电池组的N个放电电压数据为例，则该L个电池组的第一组状态数据可以包括上述表1中的全部放电电压数据。
可选的，第一设备获取到该L个电池组的第一组状态数据后，可以对该第一组状态数据进行归一化处理，消除各个状态数据的量纲差别提升数据分析的准确度。由此最终该L个电池组的第一组状态数据可以为第二设备上的原始状态数据，也可以是第一设备对该原始状态数据进行归一化处理后的数据。
基于该方案，由于L个电池组中每个电池组的状态数据的个数为N，而N的取值可以根据实际情况进行改变，因此可以灵活地利用电池的历史数据进行异常检测，提高检测的灵活性。
可选的，第一设备获取第一相似度矩阵，可以包括：第一设备获取L个第一向量，第一向量可以为列向量，该第一向量包括上述L个电池组的第一组状态数据中的N个状态数据，该L个第一向量与该L个电池组一一对应。即，一个第一向量对应一个电池组，该电池组对应的第一向量中包括的N个状态数据为该电池组的状态数据。示例性地，以L个电池组的第一组状态数据包括上述表1中的全部放电电压数据为例，则表1中电池组1所在的列中的N个放电电压数据构成电池组1对应的第一向量，同样，电池组2所在的列种的N个放电电压数据构成电池组2对应的第一向量，依次类推。
之后，第一设备对该L个第一向量做聚类分析，并根据聚类分析的结果确定第一相似度矩阵。其中，第一设备对该L个第一向量做聚类分析是为了将该L个第一向量归结为M类，M为正整数，该M类中的每一类包括一个或多个第一向量。
其中，属于同一类的一个或多个第一向量对应的电池组的状态数据在宏观上具有相似 的变化特征，比如在一定范围内同时增加或减少，可以表示该多个电池组的动态行为大体一致。从而，基于聚类分析确定相似度矩阵可以使得不同类的第一向量中的状态数据具有更明显的区分度，有利于在后续的分析中能够更好地辨识不同动态的向量，进而提高数据分析的准确度。
可以理解的是，当L个电池组的第一组状态数据为对原始状态数据进行归一化处理后的数据时，第一向量包括第一组状态数据中的N个状态数据，可以包括：第一向量包括对第一组状态数据中的N个状态数据进行归一化处理后的数据。
第一设备根据上述聚类分析的结果确定第一相似度矩阵时，一种可能的实现方式中，当聚类分析的结果指示L个第一向量中的第i个第一向量和L个第一向量中的第j个第一向量属于同一类时，该第一相似度矩阵中第i行第j列元素的值由第i个第一向量和第j个第一向量的距离函数决定，其中，i、j为小于或等于L的正整数，距离函数是度量空间中的用于定义元素之间距离的函数，可以理解为度量空间中满足特定性质的特殊函数。
可选的，上述第i个第一向量和第j个第一向量的距离函数，满足如下第一公式：
Figure PCTCN2020077286-appb-000005
其中，S i，j为第一相似度矩阵中第i行第j列的元素，x i为第i个第一向量，x j为第j个第一向量，σ为预设值。
另一种可能的实现方式中，当聚类分析的结果指示该L个第一向量中的第i个第一向量和第j个第一向量不属于同一类时，第一相似度矩阵中的i行第j列元素的值为0。
可选的，第一设备可以根据L个电池组的第一组状态数据计算第一协方差矩阵，本申请实施例对第一协方差矩阵的计算方法不做具体限定。
可以理解的是，第一设备可以在多种情况下执行本申请实施例提供的异常检测方法，示例性地：
在一种可能的实现方式中，第一设备可以周期性地执行本申请实施例提供的异常检测方法，即第一设备周期性地对第二设备的L个电池组的状态进行异常检测。
在另一种可能的实现方式中，第二设备可以向第一设备发送请求消息，该请求消息用于请求第一设备检测第二设备的电池是否异常，可选的，该请求消息中可以包括第二设备的设备标识。相应的，第一设备接收到该请求消息后，对第二设备的L个电池组的状态进行异常检测。
在又一种可能的实现方式中，终端设备可以向第一设备发送请求消息，该请求消息可以是用户触发终端设备发送的。该请求消息用于请求第一设备检测第二设备的电池是否异常，可选的，该请求消息中可以包括第二设备的设备标识和/或用户标识，其中，该用户标识与第二设备存在关联关系，即通过用户标识可以确定第二设备。相应的，第一设备接收到该请求消息后，对第二设备的L个电池组的状态进行异常检测。
S202、第一设备根据第一相似度矩阵和第一协方差矩阵，确定第一特征矩阵。
可选的，第一设备可以通过如下公式二，根据第一相似度矩阵和第一协方差矩阵，确定第一特征矩阵：
Figure PCTCN2020077286-appb-000006
其中，
Figure PCTCN2020077286-appb-000007
为第一特征矩阵，C为第一协方差矩阵，S为第一相似度矩阵，X为L个第 一向量组成的矩阵，X的列与L个第一向量一一对应，即一个第一向量作为X的一列，X为N行L列的矩阵，X T为X的转置矩阵，λ∈(0，1)。
其中，第一设备确定第一特征矩阵后，可以根据第一特征矩阵，确定第二设备的L个电池组中每个电池组的异常状态，具体地，其可以包括如下步骤S203-S204：
S203、第一设备对第一特征矩阵进行主成分分析(principal components analysis，PCA)得到投影矩阵。
可选的，第一设备对第一特征矩阵进行主成分分析得到投影矩阵，可以包括：第一设备获取第一特征矩阵的转置矩阵，并对第一特征矩阵的转置矩阵进行奇异值分解，得到N个奇异值和该N个奇异值中每个奇异值对应的左奇异向量；第一设备根据该N个奇异值中的前K个奇异值对应的左奇异向量，确定投影矩阵，K为小于或等于N的正整数。
其中，该N个奇异值中的前K个奇异值占总体奇异值的比重为δ。可选的，δ为预定义的值或者为管理员向第一设备配置的值。
S204、第一设备根据投影矩阵确定L个电池组中每个电池组的异常状态。
可选的，第一设备根据投影矩阵确定L个电池组中每个电池组的异常状态，可以包括：第一设备根据投影矩阵和L个第一向量，确定第二向量，其中，该L个第二向量与该L个第一向量一一对应；第一设备根据L个第二向量中每个第二向量的T 2统计量，确定L个电池组中每个电池组的异常状态。
可选的，第一设备根据投影矩阵和L个第一向量，确定第二向量可以包括：第一设备获取该投影矩阵的转置矩阵，并将L个第一向量分别投影到该投影矩阵的转置矩阵，得到L个第二向量。
可选的，将L个第一向量分别投影到该投影矩阵的转置矩阵可以理解为，对该投影矩阵的转置矩阵与L个第一向量分别进行矩阵乘法运算，例如，第二向量、第一向量、投影矩阵的转置矩阵可以满足如下第三公式：
y i＝U Tx i
其中，y i为L个第二向量中的第i个第二向量，U为投影矩阵，U T为投影矩阵的转置矩阵，x i为L个第一向量中的第i个第一向量。
可选的，第一设备确定L个第二向量后，可以分别计算L个第二向量中每个第二向量的T 2统计量。其中，第i个第二向量的T 2统计量可以根据如下公式四得到：
Figure PCTCN2020077286-appb-000008
其中，T i 2为L个第二向量中的第i个第二向量的T 2统计量，y i为第i个第二向量，
Figure PCTCN2020077286-appb-000009
为第i个第二向量的转置，
Figure PCTCN2020077286-appb-000010
由N和矩阵Y决定，矩阵Y为L个第二向量构成矩阵，Y的列与L个第二向量一一对应，即一个第二向量作为Y的一列。可选的，
Figure PCTCN2020077286-appb-000011
满足如下公式五：
Figure PCTCN2020077286-appb-000012
可选的，第一设备根据L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态，可以包括：
若L个第二向量中的第p个第二向量的T 2统计量大于或等于第一阈值，第一设备确 定L个电池组中与该第p个第二向量对应的第p个电池组的M个状态异常，并更新第p个电池组的异常状态的个数，p为1至L的正整数，M表示第p个电池组对应的第一向量包括的N个状态数据的状态类别数，M为小于等于4的正整数。示例性地，若第p个电池组对应的第一向量包括的N个状态数据均为该第p个电池组的放电电压数据，则M等于1；或者，若第p个电池组对应的第一向量包括的N个状态数据为该第p个电池组的放电电压数据和放电电流数据，则M等于2。
可选的，上述第一阈值满足如下公式六:
Figure PCTCN2020077286-appb-000013
其中，T为第一阈值，F表示F分布，F L,(N-L),α表示服从自由度为L和N-L的F分布的α分位点的值。
可选的，在一轮检测中，第一设备可以多次执行上述步骤S201-S204，确定L个电池组中每个电池组的每个状态是否异常，最终确定出每个电池组的异常状态的总数。示例性地，以第一设备每次执行上述步骤S201-S204时，第p个电池组对应的第一向量包括的N个状态数据均为一类状态数据为例，则第一设备可以执行四次上述步骤S201-S204，例如，第一次执行可以确定第p个电池组的放电电压状态是否异常，若异常，则更新第p个电池组的异常状态的个数，例如将其值加1，若正常，则不更新；第二次执行可以确定第p个电池组的放电电流状态是否异常，依此类推，最终确定其异常状态的总数，假设第一设备确定第p个电池组的放电电压状态、放电电流状态、以及温度异常，荷电状态正常，则第p个电池组的异常状态的总数为3。
基于该方案，一方面，由于相似度矩阵可以表示数据的局部特性，协方差矩阵可以表示数据的全局特性，因此，本申请实施例中，根据相似度矩阵和协方差矩阵得到的特征矩阵不仅可以表示数据的全局特性还可以表示数据的局部特性，从而充分利用了数据的空间信息进行异常分析，提高了电池异常检测的准确性；另一方面，通过远程服务的方式即由第一设备进行第二设备电池的异常检测，可以避免在第二设备上进行检测，从而避免了由于第二设备的硬件限制而无法实现异常检测的问题。
可选的，在本申请实施例的一种实施场景下，如图3所示，该异常检测方法还可以包括如下步骤S205:
S205、第一设备发送第一指示信息。
其中，第一指示信息用于指示L个电池组中每个电池组的异常状态的总数和/或异常状态的类别。
可选的，第一设备确定每个电池组的异常状态的总数后，可以向第二设备、终端设备、第二设备的厂家服务中心、用于辅助第二设备行驶的其他应用服务器(例如导航系统服务器)中的一个或多个发送上述第一指示信息。
基于该方案，由于第一设备向上述与一个或多个设备发送第一指示信息，因此可以使得上述一个或多个设备根据该第一指示信息进行相关处理，进而降低由于电池异常导致的事故发生的概率。
示例性地，第二设备和/或终端设备根据第一指示信息进行的相关处理，例如可以包 括:发出告警信号，警示用户第二设备的电池出现异常，以便用户及时处理。
可选的，在本申请实施例的另一种实施场景下，如图3所示，该异常检测方法还可以包括如下步骤S206-S207：
S206、第一设备确定L个电池组中每个电池组的异常等级。
可选的，第一设备可以根据预设规则与每个电池组的异常状态的总数，确定每个电池组的异常等级。
一种可能的实现方式中，该预设规则可以为：若第p个电池组的异常状态的总数为0，则其异常等级为无异常；若第p个电池组的异常状态的总数小于或等于第一数值，则其异常等级为轻微；若第p个电池组的异常状态的总数大于第一数值且小于或等于第二数值，则其异常等级为普通；若第p个电池组的异常状态的总数大于第二数值，则其异常等级为普通。
可选的，上述第一数值和第二数值可以是第一设备根据电池组的状态总数确定的，例如，若电池组的状态总数为4，则第一数值可以为1，第二数值可以为3。
另一种可能的实现方式中，该预设规则还可以是第一设备预先训练好的数学模型，第一设备将每个电池组的异常状态的总数输入该数学模型即可获得每个电池组的异常等级。
S207、第一设备发送第二指示信息。
其中，该第二指示信息用于指示L个电池组中每个电池组的异常等级。
可选的，第一设备确定每个电池组的异常等级后，可以向第二设备、终端设备、第二设备的厂家服务中心、用于辅助第二设备行驶的其他应用服务器(例如导航系统服务器)中的一个或多个发送上述第二指示信息。
基于该方案，由于第一设备向上述与一个或多个设备发送第二指示信息，因此可以使得上述一个或多个设备根据电池组的异常等级进行相关处理，进而降低由于电池异常导致的事故发生的概率。
可以理解的是，图2或图3所示的方法从异常检测设备整体的角度对本申请实施例提供的异常检测方法进行了说明，下面将从异常检测设备内部实现的角度，对本申请实施例提供的异常检测方法进行说明。
首先，对本申请实施例提供的异常检测设备和被检测设备的结构框图进行说明。
可选的，如图4所示，为本申请实施例提供的一种异常检测设备的结构框图，该结构框图可以理解为是对异常检测设备从逻辑功能的角度进行的划分。
其中，异常检测设备从逻辑功能上可以分为三层，下层用于实现数据收集、存储、以及处理等功能，可以包括数据收集模块、数据存储模块和数据处理模块；中间层为上层提供数据分析和基础算法相关服务，可以包括数据分析模块和算法服务模块；上层提供电池异常检测应用，用于实现电池异常检测的功能，可以包括异常检测模块和信息交互模块。其中，各个模块之间可以相互通信(图4中未示出)。
可选的，如图5所示，为本申请实施例提供的一种被检测设备的结构框图，该结构框图可以理解为是对被检测设备从逻辑功能的角度进行的划分。
其中，被检测设备从逻辑功上可以划分为数据采集模块，用于采集该被检测设备的电池组的状态数据；数据上报模块，用于向异常检测设备上报数据采集模块采集的电池组的状态数据；服务请求模块，用于请求异常检测设备对该被检测设备的电池组的状态进行异 常检测；显示模块，用于显示信息。其中，各个模块之间可以相互通信(图5中未示出)。
需要说明的是，图4或图5中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
下面，以图4所示的异常检测设备为第一设备，图5所示的被检测设备为第二设备为例，从异常检测设备内部实现的角度，对本申请实施例提供的异常检测方法进行说明，该异常检测方法包括：
S301、第一设备的异常检测模块调用算法服务模块获取第一相似度矩阵和第一协方差矩阵。
可选的，第二设备的数据采集模块可以周期性地采集第二设备的L个电池组的状态数据，并通过第二设备的数据上报模块将其发送给第一设备的数据收集模块。第一设备的数据收集模块接收到该状态数据后，交由第一设备的数据处理模块对数据进行解析清洗等处理后，由第一设备的数据存储模块根据第一设备的标识按照电池组状态数据的类别分类存储每个电池组的状态数据。
之后，异常检测模块可以先调用数据分析模块和数据存储模块获取L个电池组的第一组状态数据；获取第一组状态数据后，异常检测模块可以调用算法服务模块，获取第一相似度矩阵和第一协方差矩阵。其中，第一相似度矩阵和第一协方差矩阵的获取方法可参考上述步骤S201中的相关描述，在此不再赘述。
可以理解的是，第一设备的异常检测模块可以在多种情况下执行本申请实施例提供的异常检测方法，示例性地：
在一种可能的实现方式中，第一设备的异常检测模块可以周期性地执行本申请实施例提供的异常检测方法。
在另一种可能的实现方式中，第二设备的服务请求模块可以向第一设备的信息交互模块发送请求消息，以使第一设备的异常检测模块对第二设备的L个电池组的状态进行异常检测，该请求消息的说明可参考上述步骤S201中的相关描述，在此不再赘述。
在又一种可能的实现方式中，终端设备可以向第一设备的信息交互模块发送请求消息，以使第一设备的异常检测模块对第二设备的L个电池组的状态进行异常检测，该请求消息的说明可参考上述步骤S201中的相关描述，在此不再赘述。
S302、第一设备的异常检测模块调用算法服务模块根据第一相似度矩阵和第一协方差矩阵，确定第一特征矩阵。
其中，第一特征矩阵的确定方法可参考上述步骤S202中的相关描述，在此不再赘述。
S303、第一设备的异常检测模块调用算法服务模块对第一特征矩阵进行主成分分析得到投影矩阵。
其中，对第一特征矩阵进行主成分分析得到投影矩阵的方法可参考上述步骤S203中的相关描述，在此不再赘述。
S304、第一设备的异常检测模块调用算法服务模块确定L个电池组中每个电池组的异常状态。
其中，相关描述可参考上述步骤S204，在此不再赘述。
可选的，在本申请实施例的一种实施场景下，该异常检测方法还可以包括如下步骤S305:
S305、第一设备的信息交互模块发送第一指示信息。
其中，第一指示信息的相关描述可参考上述步骤S205中的相关描述，在此不再赘述。
可选的，若第一设备的信息交互模块向第二设备发送第一指示信息，则第二设备接收到该第一指示信息后，可以通过其显示模块显示第一指示信息的内容，从而可以使得用户根据第一指示信息的内容进行相关处理，降低事故发生的概率。
可选的，在本申请实施例的另一种实施场景下，该异常检测方法还可以包括如下步骤S306-S307：
S306、第一设备的异常检测模块确定L个电池组中每个电池组的异常等级。
S307、第一设备的信息交互模块发送第二指示信息。
其中，步骤S306-S307的相关描述可参考上述步骤S206-S207，在此不再赘述。
可选的，若第一设备的信息交互模块向第二设备发送第二指示信息，则第二设备接收到该第二指示信息后，同样可以通过其显示模块显示第二指示信息的内容，从而可以使得用户根据第二指示信息的内容进行相关处理，降低事故发生的概率。
可以理解的是，本申请实施例中，第一设备可以执行本申请实施例中的部分或全部步骤，这些步骤或操作仅是示例，本申请实施例还可以执行其它操作或者各种操作的变形。此外，各个步骤可以按照本申请实施例呈现的不同的顺序来执行，并且有可能并非要执行本申请实施例中的全部操作。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
可以理解的是，以上各个实施例中，由第一设备实现的方法和/或步骤，也可以由可用于第一设备的部件(例如芯片或者电路)实现，由第二设备实现的方法和/或步骤，也可以由可用于第二设备的部件(例如芯片或者电路)实现。
上述主要对本申请实施例提供的异常检测方法进行了介绍。相应的，本申请实施例还提供了异常检测设备，该异常检测设备用于实现上述各种方法，即该异常检测设备是上述图2或图3所示的异常检测方法的执行主体。该异常检测设备可以为上述方法实施例中的第一设备，或者包含上述第一设备的装置，或者为可用于第一设备的部件。可以理解的是，该异常检测设备为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
可选的，图6所示为本申请实施例提供的异常检测设备60的结构框图。该异常检测设备60包括一个或多个处理器601，通信总线602，以及至少一个通信接口(图6中仅是示例性的以包括通信接口604，以及一个处理器601为例进行说明)，可选的还可以包括存储器603。
处理器601可以是一个通用中央处理器(central processing unit，CPU)，微处理器，特定应用集成电路(application-specific integrated circuit，ASIC)，或一个或多个用于控制 本申请方案程序执行的集成电路。
通信总线602可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。该通信总线602用于连接常检测设备60中的不同组件，使得不同组件可以通信。
通信接口604用于与其他设备或通信网络通信，通信网络例如可以为无线接入网(radio access network，RAN)，无线局域网(wireless local area networks，WLAN)等。可选的，所述通信接口604可以是收发器、收发机一类的装置。可选的，所述通信接口604也可以是位于处理器601内的收发电路，用以实现处理器的信号输入和信号输出。
存储器603可以是具有存储功能的装置。例如可以是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、只读光盘(compact disc read-only memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。存储器可以是独立存在，通过通信线路602与处理器相连接。存储器也可以和处理器集成在一起。
其中，存储器603用于存储执行本申请方案的计算机执行指令，并由处理器601来控制执行。处理器601用于执行存储器603中存储的计算机执行指令，从而实现本申请实施例中提供的异常检测方法。
或者，可选的，本申请实施例中，也可以是处理器601执行本申请下述实施例提供的异常检测方法中的处理相关的功能，通信接口604负责与其他设备或通信网络通信，本申请实施例对此不作具体限定。
可选的，本申请实施例中的计算机执行指令也可以称之为应用程序代码，本申请实施例对此不作具体限定。
在具体实现中，作为一种实施例，处理器601可以包括一个或多个CPU，例如图6中的CPU0和CPU1。
在具体实现中，作为一种实施例，异常检测设备60可以包括多个处理器，例如图6中的处理器601和处理器608。这些处理器中的每一个可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
在具体实现中，作为一种实施例，异常检测设备60还可以包括输出设备605和输入设备606。输出设备605和处理器601通信，可以以多种方式来显示信息。例如，输出设备605可以是液晶显示器(liquid crystal display，LCD)，发光二级管(light emitting diode，LED)显示设备，阴极射线管(cathode ray tube，CRT)显示设备，或投影仪(projector)等。输入设备606和处理器601通信，可以以多种方式接收用户的输入。例如，输入设备606可以是鼠标、键盘、触摸屏设备或传感设备等。
其中，上述步骤S201至S205或步骤S201至S207中的第一设备的动作可以由图6所示的异常检测设备中的处理器601调用存储器603中存储的应用程序代码以指令该异常检测设备执行；上述步骤S301至S305或步骤S301至S307中的第一设备的动作可以由图6所示的异常检测设备中的处理器601调用存储器603中存储的应用程序代码以指令该异常检测设备执行，本实施例对此不作任何限制。
可选的，本申请实施例还提供一种异常检测设备(例如，该异常检测设备可以是芯片或芯片系统)，该异常检测设备包括处理器，用于实现上述任一方法实施例中的方法。在一种可能的设计中，该异常检测设备还包括存储器。该存储器，用于保存必要的程序指令和数据，处理器可以调用存储器中存储的程序代码以指令该异常检测设备执行上述任一方法实施例中的方法。当然，存储器也可以不在该异常检测设备中。在另一种可能的设计中，该异常检测设备还包括接口电路，该接口电路为代码/数据读写接口电路，该接口电路用于接收计算机执行指令(计算机执行指令存储在存储器中，可能直接从存储器读取，或可能经过其他器件)并传输至该处理器。该异常检测设备是芯片系统时，可以由芯片构成，也可以包含芯片和其他分立器件，本申请实施例对此不作具体限定。
可选的，上述异常检测设备可以是车联网(vehicle to everything，V2X)系统中的路侧单元(road side unit，RSU)；或者也可以是云端网络设备；或者还可以是应用服务器；或者还可以是安装在上述RSU或云端网络设备或应用服务器中的芯片，本申请实施例对异常检测设备的具体形式不做限定。
此外，可选的，本申请实施例中的被检测设备可以是基于动力电池驱动的代步工具(如电动汽车、电动自行车等)，也可以是安装在该代步工具中的车载终端，或者车载终端内的芯片。
可选的，本申请实施例中的终端设备，可以是是用于实现无线通信功能的设备，例如终端或者可用于终端中的芯片等。
可选的，上述车载终端或终端可以是第五代(5th generation，5G)网络或者未来演进的公共陆地移动网络(public land mobile network，PLMN)中的用户设备(user equipment，UE)、接入终端、终端单元、终端站、移动站、移动台、远方站、远程终端、移动设备、无线通信设备、终端代理或终端装置等。接入终端可以是蜂窝电话、无绳电话、会话启动协议(session initiation protocol，SIP)电话、无线本地环路(wireless local loop，WLL)站、个人数字处理(personal digital assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备或可穿戴设备，虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端、无人驾驶(self driving)中的无线终端等。车载终端或终端可以是移动的，也可以是固定的。
本申请实施例还可以根据上述方法实施例中对异常检测设备进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
比如，以异常检测设备为上述方法实施例中的第一设备为例。图7示出了一种第一设 备70的结构框图。该第一设备70包括处理模块701和获取模块702。
其中，获取模块702，用于获取第一相似度矩阵和第一协方差矩阵，第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，第一协方差矩阵为L个电池组的第一组状态数据对应的协方差矩阵，L为正整数；处理模块701，用于根据第一相似度矩阵和第一协方差矩阵，确定第一特征矩阵；处理模块701，还用于根据第一特征矩阵确定L个电池组中每个电池组的异常状态。
可选的，获取模块702，用于获取第一相似度矩阵，包括：获取模块702，用于获取L个第一向量，第一向量包括第一组状态数据中的N个状态数据，L个第一向量与L个电池组一一对应，N为正整数；获取模块702，还用于对L个第一向量做聚类分析，并根据聚类分析的结果确定第一相似度矩阵。
可选的，处理模块701，还用于根据第一特征矩阵，确定L个电池组中每个电池组的异常状态，包括：处理模块701，还用于对该第一特征矩阵进行主成分分析得到投影矩阵，并根据投影矩阵确定L个电池组中每个电池组的异常状态。
可选的，处理模块701，还用于对第一特征矩阵进行主成分分析得到投影矩阵，包括：处理模块701，还用于获取第一特征矩阵的转置矩阵，并对第一特征矩阵的转置矩阵进行奇异值分解，得到N个奇异值和N个奇异值中每个奇异值对应的左奇异向量；处理模块701，还用于根据N个奇异值中的前K个奇异值对应的左奇异向量，确定投影矩阵，K为小于或等于N的正整数。
可选的，处理模块701，还用于根据投影矩阵确定L个电池组中每个电池组的异常状态，包括：处理模块701，还用于根据投影矩阵和L个第一向量，确定L个第二向量，L个第二向量与L个第一向量一一对应；处理模块701，还用于根据L个第二向量中每个第二向量的T 2统计量，确定L个电池组中每个电池组的异常状态。
可选的，处理模块701，还用于根据L个第二向量中每个第二向量的T 2统计量，确定L个电池组中每个电池组的异常状态，包括：若L个第二向量中的第p个第二向量的T 2统计量大于或等于第一阈值，处理模块701，还用于确定L个电池组中的第p个电池组的M个状态异常，并更新第p个电池组的异常状态的个数，p为1至L的正整数，M表示第p个电池组对应的第一向量包括的N个状态数据的状态类别数。
可选的，处理模块701，还用于根据第p个电池组的异常状态的总数与预设规则，确定第p个电池组的异常等级。
其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
在本实施例中，该第一设备70以采用集成的方式划分各个功能模块的形式来呈现。这里的“模块”可以指特定ASIC，电路，执行一个或多个软件或固件程序的处理器和存储器，集成逻辑电路，和/或其他可以提供上述功能的器件。在一个简单的实施例中，本领域的技术人员可以想到该第一设备70可以采用图6所示的异常检测设备60的形式。
比如，图6所示的异常检测设备60中的处理器601可以通过调用存储器603中存储的计算机执行指令，使得第一设备70执行上述方法实施例中的异常检测方法。
具体的，图7中的处理模块701和获取模块702的功能/实现过程可以通过图6所示的异常检测设备60中的处理器601调用存储器603中存储的计算机执行指令来实现。
由于本实施例提供的第一设备70可执行上述的异常检测方法，因此其所能获得的技术效果可参考上述方法实施例，在此不再赘述。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件程序实现时，可以全部或部分地以计算机程序产品的形式来实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或者数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可以用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)，光介质(例如，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。本申请实施例中,计算机可以包括前面所述的装置。
尽管在此结合各实施例对本申请进行了描述，然而，在实施所要求保护的本申请过程中，本领域技术人员通过查看所述附图、公开内容、以及所附权利要求书，可理解并实现所述公开实施例的其他变化。在权利要求中，“包括”(comprising)一词不排除其他组成部分或步骤，“一”或“一个”不排除多个的情况。单个处理器或其他单元可以实现权利要求中列举的若干项功能。相互不同的从属权利要求中记载了某些措施，但这并不表示这些措施不能组合起来产生良好的效果。
尽管结合具体特征及其实施例对本申请进行了描述，显而易见的，在不脱离本申请的精神和范围的情况下，可对其进行各种修改和组合。相应地，本说明书和附图仅仅是所附权利要求所界定的本申请的示例性说明，且视为已覆盖本申请范围内的任意和所有修改、变化、组合或等同物。显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (31)

  1. 一种异常检测方法，其特征在于，所述方法包括：
    第一设备获取第一相似度矩阵和第一协方差矩阵，所述第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，所述第一协方差矩阵为所述L个电池组的所述第一组状态数据对应的协方差矩阵，L为正整数；
    所述第一设备根据所述第一相似度矩阵和所述第一协方差矩阵，确定第一特征矩阵；
    所述第一设备根据所述第一特征矩阵，确定所述L个电池组中每个电池组的异常状态。
  2. 根据权利要求1所述的方法，其特征在于，所述第一设备获取第一相似度矩阵，包括：
    所述第一设备获取L个第一向量，所述第一向量包括所述第一组状态数据中的N个状态数据，所述L个第一向量与所述L个电池组一一对应，N为正整数；
    所述第一设备对所述L个第一向量做聚类分析，并根据所述聚类分析的结果确定所述第一相似度矩阵。
  3. 根据权利要求2所述的方法，其特征在于，所述N个状态数据为进行归一化处理后的数据。
  4. 根据权利要求2或3所述的方法，其特征在于，当所述聚类分析的结果指示所述L个第一向量中的第i个第一向量和第j个第一向量属于同一类时，所述第一相似度矩阵中第i行第j列元素的值由所述第i个第一向量和所述第j个第一向量的距离函数决定，i、j为小于或等于L的正整数。
  5. 根据权利要求4所述的方法，其特征在于，所述第i个第一向量和所述第j个第一向量的距离函数，满足如下第一公式：
    Figure PCTCN2020077286-appb-100001
    其中，S i，j为所述第一相似度矩阵中第i行第j列的元素，x i为所述第i个第一向量，x j为所述第j个第一向量，σ为预设值。
  6. 根据权利要求2或3所述的方法，其特征在于，当所述聚类分析的结果指示所述L个第一向量中的第i个第一向量和第j个第一向量不属于同一类时，所述第一相似度矩阵中第i行第j列元素的值为0。
  7. 根据权利要求2-6任一项所述的方法，其特征在于，所述第一相似度矩阵和所述第一协方差矩阵，满足如下第二公式：
    Figure PCTCN2020077286-appb-100002
    其中，
    Figure PCTCN2020077286-appb-100003
    为所述第一特征矩阵，C为所述第一协方差矩阵，S为所述第一相似度矩阵，X为所述L个第一向量组成的矩阵，X T为X的转置矩阵，λ∈(0，1)。
  8. 根据权利要求2-7任一项所述的方法，其特征在于，所述第一设备根据所述第一特征矩阵，确定所述L个电池组中每个电池组的异常状态包括：
    所述第一设备对所述第一特征矩阵进行主成分分析得到投影矩阵，并根据所述投影矩阵确定所述L个电池组中每个电池组的异常状态。
  9. 根据权利要求8所述的方法，其特征在于，所述第一设备对所述第一特征矩阵进行主成分分析得到投影矩阵，包括：
    所述第一设备获取所述第一特征矩阵的转置矩阵，并对所述第一特征矩阵的转置矩阵进行奇异值分解，得到N个奇异值和所述N个奇异值中每个奇异值对应的左奇异向量；
    所述第一设备根据所述N个奇异值中的前K个奇异值对应的左奇异向量，确定所述投影矩阵，K为小于或等于N的正整数。
  10. 根据权利要求8或9所述的方法，其特征在于，所述第一设备根据所述投影矩阵确定所述L个电池组中每个电池组的异常状态，包括：
    所述第一设备根据所述投影矩阵和所述L个第一向量，确定L个第二向量，所述L个第二向量与所述L个第一向量一一对应；
    所述第一设备根据所述L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态。
  11. 根据权利要求10所述的方法，其特征在于，所述第一设备根据所述L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态，包括：
    若所述L个第二向量中的第p个第二向量的T 2统计量大于或等于第一阈值，所述第一设备确定所述L个电池组中的第p个电池组的M个状态异常，并更新所述第p个电池组的异常状态的个数，p为1至L的正整数，M表示所述第p个电池组对应的第一向量包括的N个状态数据的状态类别数。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    所述第一设备根据所述第p个电池组的异常状态的总数与预设规则，确定所述第p个电池组的异常等级。
  13. 根据权利要求1-12任一项所述的方法，其特征在于，所述第一组状态数据包括：放电电压数据、放电电流数据、温度数据、或者荷电状态数据。
  14. 一种异常检测设备，其特征在于，所述异常检测设备包括：获取模块和处理模块；
    所述获取模块，用于获取第一相似度矩阵和第一协方差矩阵，所述第一相似度矩阵为第二设备的L个电池组的第一组状态数据对应的相似度矩阵，所述第一协方差矩阵为所述L个电池组的所述第一组状态数据对应的协方差矩阵，L为正整数；
    所述处理模块，用于根据所述第一相似度矩阵和所述第一协方差矩阵，确定第一特征矩阵；
    所述处理模块，还用于根据所述第一特征矩阵，确定所述L个电池组中每个电池组的异常状态。
  15. 根据权利要求14所述的异常检测设备，其特征在于，所述获取模块，用于获取第一相似度矩阵，包括：
    所述获取模块，用于获取L个第一向量，所述第一向量包括所述第一组状态数据中的N个状态数据，所述L个第一向量与所述L个电池组一一对应，N为正整数；
    所述获取模块，还用于对所述L个第一向量做聚类分析，并根据所述聚类分析的结果确定所述第一相似度矩阵。
  16. 根据权利要求15所述的异常检测设备，其特征在于，所述N个状态数据为进行归一化处理后的数据。
  17. 根据权利要求15或16所述的异常检测设备，其特征在于，当所述聚类分析的结果指示所述L个第一向量中的第i个第一向量和第j个第一向量属于同一类时，所述第一相似度矩阵中第i行第j列元素的值由所述第i个第一向量和所述第j个第一向量的距离函数决定，i、j为小于或等于L的正整数。
  18. 根据权利要求17所述的异常检测设备，其特征在于，所述第i个第一向量和所述第j个第一向量的距离函数，满足如下第一公式：
    Figure PCTCN2020077286-appb-100004
    其中，S i，j为所述第一相似度矩阵中第i行第j列的元素，x i为所述第i个第一向量，x j为所述第j个第一向量，σ为预设值。
  19. 根据权利要求15或16所述的异常检测设备，其特征在于，当所述聚类分析的结果指示所述L个第一向量中的第i个第一向量和第j个第一向量不属于同一类时，所述第一相似度矩阵中第i行第j列元素的值为0。
  20. 根据权利要求15-19任一项所述的异常检测设备，其特征在于，所述第一相似度矩阵和所述第一协方差矩阵，满足如下第二公式：
    Figure PCTCN2020077286-appb-100005
    其中，
    Figure PCTCN2020077286-appb-100006
    为所述第一特征矩阵，C为所述第一协方差矩阵，S为所述第一相似度矩阵，X为所述L个第一向量组成的矩阵，X T为X的转置矩阵，λ∈(0，1)。
  21. 根据权利要求15-20任一项所述的异常检测设备，其特征在于，所述处理模块，还用于根据所述第一特征矩阵，确定所述L个电池组中每个电池组的异常状态，包括：
    所述处理模块，还用于对所述第一特征矩阵进行主成分分析得到投影矩阵，并根据所述投影矩阵确定所述L个电池组中每个电池组的异常状态。
  22. 根据权利要求21所述的异常检测设备，其特征在于，所述处理模块，还用于对所述第一特征矩阵进行主成分分析得到投影矩阵，包括：
    所述处理模块，还用于获取所述第一特征矩阵的转置矩阵，并对所述第一特征矩阵的转置矩阵进行奇异值分解，得到N个奇异值和所述N个奇异值中每个奇异值对应的左奇异向量；
    所述处理模块，还用于根据所述N个奇异值中的前K个奇异值对应的左奇异向量，确定所述投影矩阵，K为小于或等于N的正整数。
  23. 根据权利要求21或22所述的异常检测设备，其特征在于，所述处理模块，用于根据所述投影矩阵确定所述L个电池组中每个电池组的异常状态，包括：
    所述处理模块，用于根据所述投影矩阵和所述L个第一向量，确定L个第二向量，所述L个第二向量与所述L个第一向量一一对应；
    所述处理模块，还用于根据所述L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态。
  24. 根据权利要求23所述的异常检测设备，其特征在于，所述处理模块，还用于根据所述L个第二向量中每个第二向量的T 2统计量，确定所述L个电池组中每个电池组的异常状态，包括：
    若所述L个第二向量中的第p个第二向量的T 2统计量大于或等于第一阈值，所述处 理模块，还用于确定所述L个电池组中的第p个电池组的M个状态异常，并更新所述第p个电池组的异常状态的个数，p为1至L的正整数，M表示所述第p个电池组对应的第一向量包括的N个状态数据的状态类别数。
  25. 根据权利要求24所述的异常检测设备，其特征在于，所述处理模块，还用于根据所述第p个电池组的异常状态的总数与预设规则，确定所述第p个电池组的异常等级。
  26. 根据权利要求14-25任一项所述的异常检测设备，其特征在于，所述第一组状态数据包括：放电电压数据、放电电流数据、温度数据、或者荷电状态数据。
  27. 一种异常检测设备，其特征在于，所述异常检测设备包括：处理器；
    所述处理器用于读取存储器中的计算机执行指令，并执行所述计算机执行指令，以使所述异常检测设备执行如权利要求1-13中任一项所述的方法。
  28. 一种异常检测设备，其特征在于，所述异常检测设备包括：处理器和存储器；
    所述存储器用于存储计算机执行指令，当所述处理器执行所述计算机执行指令时，以使所述异常检测设备执行如权利要求1-13中任一项所述的方法。
  29. 一种异常检测设备，其特征在于，所述异常检测设备包括：处理器和接口电路；
    所述接口电路，用于接收计算机执行指令并传输至所述处理器；
    所述处理器用于执行所述计算机执行指令，以使所述异常检测设备执行如权利要求1-13中任一项所述的方法。
  30. 一种计算机可读存储介质，其特征在于，包括计算机指令，当所述计算机指令在处理器上运行时，以使所述异常检测设备执行如权利要求1-13中任一项所述的方法。
  31. 一种计算机程序产品，其特征在于，当所述计算机程序产品在处理器上运行时，以使所述异常检测设备执行如权利要求1-13中任一项所述的方法。
PCT/CN2020/077286 2020-02-28 2020-02-28 异常检测方法和设备 WO2021168836A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080004134.4A CN112513883A (zh) 2020-02-28 2020-02-28 异常检测方法和设备
PCT/CN2020/077286 WO2021168836A1 (zh) 2020-02-28 2020-02-28 异常检测方法和设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/077286 WO2021168836A1 (zh) 2020-02-28 2020-02-28 异常检测方法和设备

Publications (1)

Publication Number Publication Date
WO2021168836A1 true WO2021168836A1 (zh) 2021-09-02

Family

ID=74952840

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/077286 WO2021168836A1 (zh) 2020-02-28 2020-02-28 异常检测方法和设备

Country Status (2)

Country Link
CN (1) CN112513883A (zh)
WO (1) WO2021168836A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115275396A (zh) * 2022-08-15 2022-11-01 珠海冠宇电源有限公司 电池保护技术和电池包

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113777517B (zh) * 2021-09-13 2023-10-17 傲普(上海)新能源有限公司 储能电站短板电芯筛选方法
CN114509690A (zh) * 2022-04-19 2022-05-17 杭州宇谷科技有限公司 一种基于pca分解的锂电芯充放电异常检测方法及系统
CN116404186B (zh) * 2023-06-08 2023-09-19 西安黄河电子技术有限公司 一种功率型锂锰电池生产系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105277891A (zh) * 2014-07-18 2016-01-27 三星电子株式会社 用于估计电池的状态的方法和设备
CN105789676A (zh) * 2016-03-25 2016-07-20 杭州电子科技大学 一种基于消息传播的动力电池配组方法
EP3045925A1 (en) * 2015-01-14 2016-07-20 Corvus Energy Ltd. Method and system for iteratively determining state of charge of a battery cell

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3029296B1 (fr) * 2014-11-28 2016-12-30 Renault Sa Procede automatique d'estimation de l'etat de charge d'une cellule d'une batterie
CN108173670B (zh) * 2016-12-07 2020-06-02 华为技术有限公司 检测网络的方法和装置
CN107679553A (zh) * 2017-09-14 2018-02-09 深圳大学 基于密度峰值的聚类方法及装置
CN109471035B (zh) * 2018-10-17 2020-11-06 山东斯博科特电气技术有限公司 基于随机矩阵特征谱分析的燃料电池系统状态评估方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105277891A (zh) * 2014-07-18 2016-01-27 三星电子株式会社 用于估计电池的状态的方法和设备
EP3045925A1 (en) * 2015-01-14 2016-07-20 Corvus Energy Ltd. Method and system for iteratively determining state of charge of a battery cell
CN105789676A (zh) * 2016-03-25 2016-07-20 杭州电子科技大学 一种基于消息传播的动力电池配组方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHONG GUOBIN, SHEN JIANI , XU KAIQI , WANG QIANKUN , HE YIJUN , SU WEI , MA ZIFENG: "Dynamic Time Warping and Multidimensional Scaling Approach based Abnormal Battery Visual Recognition for Series-Connected Lithium-Ion Batteries Pack", ENERGY STORAGE SCIENCE AND TECHNOLOGY, CN, vol. 8, no. 1, 1 January 2019 (2019-01-01), CN, pages 180 - 190, XP055841067, ISSN: 2095-4239, DOI: 10.12028/j.issn.2095-4239.2018.0193 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115275396A (zh) * 2022-08-15 2022-11-01 珠海冠宇电源有限公司 电池保护技术和电池包

Also Published As

Publication number Publication date
CN112513883A (zh) 2021-03-16

Similar Documents

Publication Publication Date Title
WO2021168836A1 (zh) 异常检测方法和设备
US9275353B2 (en) Event-processing operators
WO2021184727A1 (zh) 数据异常检测方法、装置、电子设备及存储介质
WO2021068513A1 (zh) 异常对象识别方法、装置、介质及电子设备
US10778707B1 (en) Outlier detection for streaming data using locality sensitive hashing
WO2021212670A1 (zh) 新发传染病发病风险预测方法、装置、终端设备及介质
CN110837582B (zh) 数据关联方法、装置、电子设备和计算机可读存储介质
CN110909222B (zh) 基于聚类的用户画像建立方法、装置、介质及电子设备
CN110245714B (zh) 图像识别方法、装置及电子设备
CN111782900B (zh) 异常业务检测方法、装置、电子设备及存储介质
CN114637650B (zh) 一种基于Kubernetes集群的弹性伸缩方法
WO2021238563A1 (zh) 基于配置算法的企业运行数据分析方法、装置、电子设备及介质
US20230017653A1 (en) Method for recommending similar incident, and related device
CN111768096A (zh) 基于算法模型的评级方法、装置、电子设备及存储介质
CN112949278A (zh) 数据核对方法、装置、电子设备及可读存储介质
CN114172819B (zh) Nfv网元的需求资源预测方法、系统、电子设备和存储介质
US10979848B1 (en) Method for identifying a device using attributes and location signatures from the device
CN116955413A (zh) 基于线上分析处理的数据查询方法、装置、介质及设备
WO2022160443A1 (zh) 谱系挖掘方法、装置、电子设备及计算机可读存储介质
CN113946493A (zh) 一种监控阈值确定及监控报警方法、装置、设备和介质
CN111652741A (zh) 用户偏好分析方法、装置及可读存储介质
CN113568773B (zh) 一种异常服务分类方法、装置、设备及存储介质
TWM653235U (zh) 影像辨識績效的模糊判斷系統
CN112328960B (zh) 数据运算的优化方法、装置、电子设备及存储介质
CN113657429B (zh) 面向数字孪生城市物联网的数据融合方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20921836

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20921836

Country of ref document: EP

Kind code of ref document: A1