Battery pack anomaly detection method, computer readable storage medium and electronic device

Abstract

The application discloses a battery pack abnormality detection method, a computer readable storage medium and an electronic device, and relates to the technical field of battery pack abnormality detection. The battery pack abnormality detection method comprises the following steps: obtaining K measurement distances adjacent to the operation parameters of each battery pack at the same time through a K nearest neighbor algorithm according to the operation parameters of each battery pack; averaging the K measurement distances corresponding to each battery pack to obtain an average distance corresponding to the operation parameters of each battery pack; sequentially performing normalization processing on the average distance corresponding to the operation parameters of each battery pack; and obtaining a detection result of each battery pack according to the normalization processing result. The battery pack abnormality detection method can detect the operation state of the battery pack in real time, so that abnormal conditions can be found in time, and the overall operation condition of the battery pack can be more accurately reflected, thereby improving the detection accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery, in particular to a battery pack abnormality detection method, a computer readable storage medium and an electronic device. BACKGROUND

[0002] Lithium ion battery has high energy density, long service life, low self-discharge rate and other advantages, and is an important energy storage device. At the same time, lithium ion battery may have safety accidents such as thermal runaway during use. Therefore, for energy storage companies, it is necessary to monitor the running state of all batteries so as to find abnormal battery pack in time. In the energy storage system, the accident such as thermal runaway of battery is often an overall safety problem caused by single or several abnormal battery packs, which is represented as the outlying of battery parameters of single or several battery packs in data. At present, in the related technology, the research is mainly carried out on single battery parameter, which causes that the schemes for monitoring different battery operation parameters are often quite different. The use of different monitoring schemes for different battery operation parameters will bring great operation and maintenance difficulties, which is not conducive to the cost reduction and efficiency improvement of enterprises. At the same time, the monitoring scheme for battery operation parameters in the related technology has the problems of poor accuracy and high algorithm complexity. SUMMARY

[0003] The present application is proposed in order to solve at least one of the above problems. According to a first aspect of the present application, a battery pack abnormality detection method is provided, the battery pack includes at least two battery packs, and the method includes: obtaining K metric distances adjacent to the running parameters of each battery pack by K nearest neighbor algorithm according to the running parameters of each battery pack at the same time; obtaining average distances corresponding to the running parameters of each battery pack by averaging the K metric distances corresponding to each battery pack; sequentially performing normalization processing on the average distances corresponding to the running parameters of each battery pack; and obtaining detection results of each battery pack according to the normalization processing results.

[0004] In an embodiment of the present application, the obtaining detection results of each battery pack according to the normalization processing results includes: obtaining outlying probabilities of each battery pack according to the normalization processing results; and obtaining detection results of each battery pack by sliding window according to the outlying probabilities of each battery pack.

[0005] In an embodiment of the present application, the detection result of each battery pack is obtained according to the target outlier probability value, including: when at least one of the following occurs, the detection result of the battery pack is that there is an anomaly:

[0006] In an embodiment of the present application, the operating parameters include voltage, current, battery temperature, battery capacity, battery energy, and battery SOH.

[0007] In an embodiment of the present application, the detection result of each battery pack is obtained according to the target outlier probability value, including: when at least one of the following occurs, the detection result of the battery pack is that there is an anomaly:

[0008] The target outlier probability value corresponding to the voltage of the battery pack is greater than or equal to a preset voltage threshold, the target outlier probability value corresponding to the current is greater than or equal to a preset current threshold, and the target outlier probability value corresponding to the battery temperature is greater than or equal to a preset battery temperature threshold, the target outlier probability value corresponding to the battery capacity of the battery pack is greater than or equal to a preset battery capacity threshold, the target outlier probability value corresponding to the battery energy of the battery pack is greater than or equal to a preset battery energy threshold, and the target outlier probability value corresponding to the battery SOH of the battery pack is greater than or equal to a preset battery SOH threshold.

[0009] In an embodiment of the present application, the detection result of each battery pack is obtained according to the target outlier probability value, including: if the target outlier probability value corresponding to the voltage of the battery pack is less than a preset voltage threshold, the target outlier probability value corresponding to the current of the battery pack is less than a preset current threshold, the target outlier probability value corresponding to the battery temperature of the battery pack is less than a preset battery temperature threshold, the target outlier probability value corresponding to the battery capacity of the battery pack is less than a preset battery capacity threshold, the target outlier probability value corresponding to the battery energy of the battery pack is less than a preset battery energy threshold, and the target outlier probability value corresponding to the battery SOH of the battery pack is less than a preset battery SOH threshold, the detection result of the battery pack is that there is no anomaly.

[0010] In an embodiment of the present application, the average distance corresponding to the operating parameters of the battery pack is normalized by the following formula:

[0011]

[0012] wherein P i,tD(i, t) represents the outlier probability of the i th battery pack in the battery pack at time t, and D(i, K) represents the average distance of the i th battery pack in the battery pack.

[0013] In an embodiment of the present application, the K nearest neighbor algorithm is used to obtain K metric distances adjacent to the operating parameters of each battery pack according to the operating parameters of each battery pack, including: calculating the metric distances between each operating parameter; searching the metric distances between each operating parameter by the K nearest neighbor algorithm to obtain K metric distances adjacent to the operating parameters of each battery pack.

[0014] In an embodiment of the present application, the searching of the metric distances between each operating parameter by the K nearest neighbor algorithm includes: constructing a KD tree data structure according to the metric distances between each operating parameter; searching in the KD tree data structure by the K nearest neighbor algorithm.

[0015] In an embodiment of the present application, the metric distance is Manhattan distance.

[0016] According to a second aspect of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. When the computer program is executed by a processor, the battery pack anomaly detection method described above is implemented.

[0017] According to a third aspect of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, any of the battery pack anomaly detection methods described above is implemented.

[0018] According to a fourth aspect of the present application, a computer program product is provided, which includes a computer program or instructions. When the computer program or instructions are executed, any of the battery pack anomaly detection methods described above is implemented.

[0019] According to the battery pack anomaly detection method, the computer readable storage medium and the electronic device provided by the embodiments of the present application, the battery pack anomaly detection method of the present application can detect the running state of the battery pack in real time, so as to discover abnormal conditions in time. At the same time, by calculating K metric distances adjacent to each battery pack and averaging these distances, the overall running state of the battery pack can be more accurately reflected, the detection accuracy is improved, and the complexity of battery pack anomaly detection is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings described below only show some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0021] Figure 1 The flowchart of the battery pack abnormality detection method provided by an embodiment of the present application is shown in the figure.

[0022] Figure 2 The structural diagram of the electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0023] In order to make the objects, technical solutions and advantages of the present application more obvious, the following will describe the example embodiments according to the present application in detail with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described here. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the protection scope of the present application.

[0024] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, some technical features known in the art are not described in order to avoid obscuring the present application.

[0025] It should be understood that the present application can be implemented in different forms, and should not be interpreted as being limited to the embodiments presented here. On the contrary, these embodiments are provided to make the disclosure complete and complete, and to fully convey the scope of the present application to those skilled in the art.

[0026] In order to thoroughly understand the present application, detailed structures will be presented in the following description in order to explain the technical solutions presented by the present application. The alternative embodiments of the present application are described in detail as follows, however, in addition to these detailed descriptions, the present application can also have other implementation manners.

[0027] The following will describe some embodiments of the present application in detail with reference to the drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] The first aspect of the present application provides a battery pack abnormality detection method, as shown in the figure, the battery pack abnormality detection method comprises: Figure 1 The battery pack abnormality detection method comprises:

[0029] S1, according to the operation parameters of each battery pack at the same time, the K nearest neighbor algorithm is used to obtain K metric distances adjacent to the operation parameters of each battery pack.

[0030] As an example, the operation parameters of the battery pack can include at least one of voltage, current, battery temperature, battery capacity, battery energy, and battery SOH (State of Health). The real-time voltage, current, and battery temperature of the battery pack can be obtained by voltage sensors, current sensors, and temperature sensors, respectively. The battery capacity of the battery pack can be obtained in real time by a BMS (Battery Management System). The battery energy of the battery pack can be estimated by a current sensor. The battery SOH of the battery pack can be determined by internal resistance measurement.

[0031] It should be noted that the K nearest neighbor algorithm is a supervised learning algorithm for classification and regression. The operation parameters of each battery pack can be used as a feature vector. The metric distances between the battery packs are calculated according to the feature vectors, and K metric distances adjacent to the operation parameters of each battery pack are selected.

[0032] S2, the K metric distances corresponding to each battery pack are averaged to obtain the average distance corresponding to the operation parameters of each battery pack.

[0033] Taking the voltage as an example, the voltages of three battery packs closest to the voltage of the target battery pack at a certain time can be selected, and the average distance of the voltage of the target battery pack can be obtained by averaging.

[0034] It should be noted that the above calculation steps can be completed by the K nearest neighbor algorithm in the python machine learning library sklearn.

[0035] S3, the average distances corresponding to the operation parameters of each battery pack are normalized in sequence.

[0036] S4, according to the normalization result, the detection result of each battery pack is obtained.

[0037] The battery pack abnormality detection method of the embodiment can detect the running state of the battery pack in real time, so as to timely discover abnormal conditions and improve the efficiency and robustness of monitoring safety problems such as thermal runaway of the battery pack. At the same time, by calculating the K metric distances adjacent to each battery pack and averaging these distances, the overall operation of the battery pack can be more accurately reflected, and the detection accuracy is improved.

[0038] In some embodiments, according to the normalization result, the detection result of each battery pack is obtained, including:

[0039] S41, obtaining the outlier probability of each battery pack according to the normalization processing result. As an example, the outlier probability of the battery pack can be obtained by dividing the average distance of the operation parameter of the battery pack at the current time by the sum of the average distances of the operation parameters of all battery packs at the current time.

[0040] It should be noted that the normalization processing means summing the average distances of each battery pack at the same time, and correcting the sum to obtain a correction value; and then dividing the average distance corresponding to the operation parameter of each battery pack by the correction value to obtain the outlier probability of each battery pack.

[0041] Specifically, the average distance corresponding to the operation parameter of the battery pack can be normalized by the following formula:

[0042]

[0043] wherein P i,t represents the outlier probability of the i-th battery pack in the battery pack at t, and D(i, K) represents the average distance of the i-th battery pack in the battery pack.

[0044] It should be noted that by calculating the outlier probability of the battery pack, the influence of special singular values on the detection result of the battery pack can be avoided.

[0045] Since the operation parameters of the battery pack can include voltage, current, battery temperature, battery capacity, battery energy and battery SOH, etc., by normalizing the average distance corresponding to the operation parameter, different types of operation parameters of the battery pack can be applied to the battery pack anomaly detection method of the present application. Therefore, various operation parameters can be monitored by a unified algorithm, which will effectively improve the monitoring efficiency of the battery operation state, thereby realizing the cost reduction and efficiency improvement of enterprises.

[0046] S42, obtaining the detection result of each battery pack by a sliding window according to the outlier probability of each battery pack.

[0047] As an example, a probability threshold can be set to determine whether each battery pack has an anomaly. If the outlier probability of the battery pack exceeds the preset probability threshold, it can be determined that the battery pack has an anomaly. Specifically, a plurality of different probability thresholds can be set, respectively corresponding to different anomaly levels, such as warning, attention or emergency, to facilitate the staff to understand the abnormal situation of the battery pack.

[0048] The battery pack abnormality detection method of the embodiment can detect the running state of the battery pack in real time, so as to timely find abnormal conditions and improve the efficiency and robustness of monitoring the safety problems such as thermal runaway of the battery pack. Meanwhile, by calculating the K metric distances of each battery pack and its adjacent battery pack and averaging these distances, the overall running condition of the battery pack can be more accurately reflected, and the detection accuracy is improved.

[0049] Generally, the out-of-control state is a continuous condition, and the out-of-control of a single time running parameter is generally not judged as the out-of-control of the running parameter of the battery pack, and the out-of-control of multiple time running parameters in time series is generally judged as the out-of-control of the running parameter of the battery pack.

[0050] In some embodiments, according to the out-of-control probability of each battery pack, the detection result of each battery pack is obtained through a sliding window, including:

[0051] S421, the obtained out-of-control probability is placed in the data queue corresponding to each battery pack, wherein the data queue is composed of the historical out-of-control probability of the battery pack.

[0052] As an example, when a new out-of-control probability of the battery pack corresponding to the current time is generated, the newly generated out-of-control probability can be placed at the right end of the data queue. When no new out-of-control probability of the battery pack corresponding to the current time is generated, no data update is performed on the data queue.

[0053] S422, a sliding window is set, wherein the size of the sliding window is n, and n is greater than or equal to 1.

[0054] Specifically, after the sliding window is selected, it needs to be initialized so that the values in the sliding window are all 0.

[0055] It should be noted that the size of the sliding window determines the immediacy degree of the algorithm in judging the out-of-control parameter of the battery pack. The smaller the size of the sliding window is set, the more rapid the algorithm reacts, and at the same time, the anti-interference ability will decrease, and the sensitivity to singular values will increase. When the size of the sliding window is equal to 1, it is equivalent to directly setting the threshold method, which is very sensitive to singular values.

[0056] As an example, the size of the sliding window can be set to different sizes according to different running parameters to cope with different types of running parameters.

[0057] S423, the latest n out-of-control probabilities in the data queue are updated to the sliding window, the out-of-control probabilities in the sliding window are obtained and summed to obtain a target out-of-control probability value.

[0058] It should be noted that the sliding window records the out-of-control probability values of the battery pack at the current time and n-1 times before the current time.

[0059] Taking the size of the sliding window as 10 and the running parameter as voltage as an example, 10 voltage outlier probabilities are included in the sliding window corresponding to each battery pack. If the voltage outlier probability of the No. 2 battery pack is updated at the current time, the earliest data in the sliding window corresponding to the No. 2 battery pack needs to be removed, and the voltage outlier probability at the current time is placed in the sliding window. Then, the sum of the outlier probabilities in the sliding window corresponding to the No. 2 battery pack is obtained, and the voltage target outlier probability value of the No. 2 battery pack is obtained.

[0060] S424, a detection result of each battery pack is obtained according to the target outlier probability value.

[0061] As an example, if the target outlier probability value is greater than the probability sum threshold value, the running parameter in the battery pack corresponding to the target outlier probability value is out of range, indicating that the battery pack is abnormal.

[0062] In this embodiment, by using the sliding window, the anti-interference ability of a single singular value in the running parameter can be improved. Avoiding the singular value of a single running parameter can avoid misjudgment of the running state of the battery pack.

[0063] In some embodiments, the running parameters include voltage, current, battery temperature, battery capacity, battery energy, and battery SOH.

[0064] Specifically, the detection result of each battery pack is obtained according to the target outlier probability value, including:

[0065] When at least one of the following occurs, the detection result of the battery pack is abnormal:

[0066] The target outlier probability value corresponding to the voltage of the battery pack is greater than or equal to a preset voltage threshold value, the target outlier probability value corresponding to the current is greater than or equal to a preset current threshold value, and the target outlier probability value corresponding to the battery temperature is greater than or equal to a preset battery temperature threshold value, the target outlier probability value corresponding to the battery capacity of the battery pack is greater than or equal to a preset battery capacity threshold value, the target outlier probability value corresponding to the battery energy of the battery pack is greater than or equal to a preset battery energy threshold value, and the target outlier probability value corresponding to the battery SOH of the battery pack is greater than or equal to a preset battery SOH threshold value.

[0067] It should be noted that the size of the preset voltage threshold value, the preset current threshold value, the preset battery temperature threshold value, the preset battery capacity threshold value, the preset battery energy threshold value, and the preset battery SOH threshold value determines the tightness of the judgment of the out-of-range of the corresponding running parameter. The greater the preset voltage threshold value, the preset current threshold value, the preset battery temperature threshold value, the preset battery capacity threshold value, the preset battery energy threshold value, and the preset battery SOH threshold value, the more stringent the out-of-range standard of the corresponding running parameter, and vice versa.

[0068] Specifically, according to the target outlier probability value, the detection result of each battery pack is obtained, including: if the target outlier probability value corresponding to the voltage of the battery pack is less than a preset voltage threshold, the target outlier probability value corresponding to the current of the battery pack is less than a preset current threshold, the target outlier probability value corresponding to the battery temperature of the battery pack is less than a preset battery temperature threshold, the target outlier probability value corresponding to the battery power of the battery pack is less than a preset battery power threshold, the target outlier probability value corresponding to the battery energy of the battery pack is less than a preset battery energy threshold, and the target outlier probability value corresponding to the battery SOH of the battery pack is less than a preset battery SOH threshold, the detection result of the battery pack is that there is no abnormality.

[0069] In this embodiment, by judging the target outlier probability values of the voltage, current, battery temperature, battery power, battery energy and battery SOH of the battery pack at the same time, the reliability of the early warning of safety problems such as thermal runaway can be improved, and the error rate of triggering the early warning can be reduced.

[0070] In some embodiments, according to the operating parameters of each battery pack, K nearest neighbor algorithm is used to obtain K metric distances adjacent to the operating parameters of each battery pack, including:

[0071] S21, calculating the metric distance between each operating parameter.

[0072] Specifically, the metric distance is Manhattan distance.

[0073] S22, searching the metric distance between each operating parameter by K nearest neighbor algorithm to obtain K metric distances adjacent to the operating parameters of each battery pack.

[0074] Specifically, searching the metric distance between each operating parameter by K nearest neighbor algorithm includes:

[0075] S221, constructing a KD tree data structure according to the metric distance between each operating parameter.

[0076] S222, searching in the KD tree data structure by K nearest neighbor algorithm.

[0077] Specifically, after calculating the metric distance between each operating parameter, the metric distances corresponding to each battery pack are sorted in sequence to obtain a sorted sequence corresponding to each battery pack; and K metric distances adjacent to the operating parameters of each battery pack are taken out from the sorted sequence corresponding to each battery pack in sequence.

[0078] In this embodiment, the metric distance between each operating parameter is stored by KD tree data structure, which can reduce the search range and improve the efficiency of K nearest neighbor algorithm.

[0079] Next, this application uses the voltage data of ten battery packs inside a container of a lithium-ion energy storage power station as an example to illustrate the detection process of the battery pack anomaly detection method of the present invention.

[0080] A1, obtain the voltage of the ten battery packs at the current moment, defined as V={u1, u2, u3, ..., u m}. Where m is less than or equal to 10. Here, m is less than or equal to 10 because it is not always possible to collect the voltage of all battery packs at the current moment.

[0081] A2, calculate the Manhattan distance d between the voltages of each battery pack. i，j ,get:

[0082]

[0083] Where, d i,j =d j，i ,i,j∈{1,2,...,m}.

[0084] A3. Construct a KD-tree data structure based on matrix D.

[0085] A4 uses the K-nearest neighbor algorithm to search within the KD-tree data structure to obtain the K nearest neighbor metrics that are adjacent to the voltage of each battery pack. For example, each row of data in D {d i，1 d i,2 , ..., d i,m The distances between this battery pack and other battery packs are represented by the numbers {d(i, 1), d(i, 2), ..., d(i, m)}, which can be sorted in ascending order to obtain a sorted sequence {d(i, 1), d(i, 2), ..., d(i, m)}, where d(i, 1) < d(i, 2) < ... < d(i, n). The first K distance metrics are selected from the sorted sequence.

[0086] A5, through the formula The average distance corresponding to the voltage of each battery pack is obtained by averaging the K metric distances corresponding to each battery pack.

[0087] A6, through formula The average distance corresponding to the voltage of each battery pack is normalized sequentially to obtain the outlier probability of each battery pack.

[0088] A7 places the obtained outlier probabilities into the data queues corresponding to each battery pack.

[0089] A8. Set a sliding window and update the sliding window with the latest n outlier probabilities from the data queue, resulting in SW = {P} i，1 P i,2 , ..., P i，nIt should be noted that when the running parameter is current or voltage, the size of the vernier window can be 10, and when the running parameter is battery temperature, the size of the vernier window can be 20.

[0090] A9, obtain the outlier probability in the vernier window and sum up to obtain the target outlier probability value.

[0091] A10, determine whether the target outlier probability value corresponding to the voltage of each battery pack is greater than or equal to a preset voltage threshold τ. Specifically, the state of the battery pack can be represented as 1 represents that the voltage at this moment is in an outlier state; 0 represents that the voltage at this moment is not in an outlier state.

[0092] It should be noted that when the running parameter is voltage, the preset voltage threshold can be set to 6, when the running parameter is current, the preset current threshold can be set to 7, and when the running parameter is battery temperature, the preset battery temperature threshold can be set to 16. The preset voltage threshold is set to 6, which means that the outlier probability of each voltage value of the battery pack needs to reach 60% or more on average, so as to be judged that the voltage of the battery pack is an outlier.

[0093] In addition, the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the battery pack anomaly detection method.

[0094] The computer readable storage medium of the embodiment of the present application can detect the running state of the battery pack in real time, so as to discover abnormal conditions in time. At the same time, by calculating the K metric distances of each battery pack and its adjacent battery pack and averaging these distances, the overall running state of the battery pack can be more accurately reflected, and the detection accuracy is improved.

[0095] In addition, the present application also provides an electronic device, such as Figure 2 As shown in the figure, the electronic device 100 includes a memory 101, a processor 102 and a computer program stored in the memory 101. The memory 101 and the processor 102 are connected, such as through a bus 103. Optionally, the electronic device 100 can also include a transceiver 104. The computer program is executed by the processor 102 to realize the battery pack anomaly detection method. It should be noted that in actual application, the transceiver 104 is not limited to one, and the structure of the electronic device 100 does not constitute a limitation on the embodiments of the present application.

[0096] The processor 102 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the present disclosure. The processor 102 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0097] The bus 103 can include a path for transmitting information between the above-mentioned components. The bus 103 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 103 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 2 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0098] The memory 101 is used to store a computer program corresponding to the battery pack abnormality detection method of the above-mentioned embodiments of the present application, which is controlled and executed by the processor 102. The processor 102 is used to execute the computer program stored in the memory 101 to realize the content shown in the above-mentioned battery pack abnormality detection method embodiments.

[0099] Among them, Figure 2 The electronic device 100 shown is only an example, and should not bring any limitation to the function and use range of the embodiments of the present application.

[0100] The electronic device 100 of the embodiments of the present application can detect the running state of the battery pack in real time by executing the battery pack abnormality detection method, so as to discover abnormal conditions in time. At the same time, by calculating the K metric distances of each battery pack and its adjacent battery pack and averaging these distances, the overall running state of the battery pack can be more accurately reflected, and the detection accuracy is improved.

[0101] In addition, the present application also provides a computer program product, including a computer program or instructions, wherein when the computer program or instructions are executed, any one of the above-mentioned battery pack abnormality detection methods is realized.

[0102] The computer program product of the embodiment of the application can detect the running state of the battery pack in real time by executing the battery pack abnormality detection method, so as to discover abnormal conditions in time.

[0103] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the example embodiments are only exemplary and are not intended to limit the scope of the application. Those of ordinary skill in the art can make various changes and modifications without departing from the scope and spirit of the application. All such changes and modifications are intended to be included within the scope of the application as claimed.

[0104] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be realized by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and design constraints of the technical solution. Those of ordinary skill in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the application.

[0105] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0106] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order not to obscure the understanding of the specification.

[0107] Similarly, it should be understood that, in order to simplify the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of the present application should not be interpreted as reflecting an intention that the claimed application requires more features than those explicitly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a certain disclosed single embodiment. Therefore, the claims following the specific embodiments are hereby expressly incorporated into the specific embodiments, wherein each claim itself is a separate embodiment of the present application.

[0108] Those skilled in the art will appreciate that all features described herein (including all features cited in any claims, as well as any method or process or step of any such method or process) can be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Each feature disclosed in this specification, including any "means for" function disclosed by any claim, can be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

[0109] Furthermore, those skilled in the art will recognize that references in the specification to "one embodiment", "an embodiment", "an example embodiment", etc., mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily referring to the same embodiment.

[0110] Various components of the present application can be implemented in hardware, or as software modules running in one or more processors, or combinations thereof. Those skilled in the art will appreciate that some or all of the functionality of some of the modules according to embodiments of the present application can be implemented using a microprocessor or a digital signal processor (DSP) in practice. The present application can also be implemented as a program (for example, a computer program and a computer program product) for executing any or all of the methods described herein on a computer. Such a program implementing the present application can be stored on a computer readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier wave, or in any other form.

[0111] It is noted that the foregoing examples have been provided merely for the purpose of explanation and are in no way to be construed as limiting of the present application. While the application has been described with reference to preferred embodiments, it is understood that the words that have been used herein are words of description, and that changes can be made within the scope and spirit of the application. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word comprising does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the system claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not imply any order. These words have been used to name the elements for the sake of ease of reading only.

[0112] The above merely provides specific implementation manners or specific implementation manners of the present application, and the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all should be covered in the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A battery pack abnormality detection method, the battery pack including at least two battery groups, characterized by, The method comprises: According to the operation parameters of each battery pack at the same time, the K nearest neighbor algorithm is used to obtain the K measurement distances of the operation parameters of each battery pack and the corresponding operation parameters of the remaining battery packs; The K measurement distances corresponding to each battery pack are averaged to obtain the average distance corresponding to the operation parameters of each battery pack; The average distance corresponding to the operation parameters of each battery pack is sequentially normalized; According to the normalization result, the outlier probability of each battery pack is obtained; According to the outlier probability of each battery pack, the detection result of each battery pack is obtained through a sliding window.

2. The battery pack abnormality detection method according to claim 1, characterized by, According to the outlier probability of each battery pack, the detection result of each battery pack is obtained through a sliding window, which comprises: The obtained outlier probability is placed in the data queue corresponding to each battery pack, wherein the data queue is composed of historical outlier probabilities of the battery pack; The sliding window is set, wherein the size of the sliding window is n, and n is greater than or equal to 1; The latest n outlier probabilities in the data queue are updated to the sliding window, the outlier probabilities in the sliding window are obtained and summed to obtain a target outlier probability value; According to the target outlier probability value, the detection result of each battery pack is obtained.

3. The battery pack abnormality detection method according to claim 2, characterized by, The operation parameters include voltage, current, battery temperature, battery capacity, battery energy and battery SOH.

4. The battery pack abnormality detection method according to claim 3, characterized by, According to the target outlier probability value, the detection result of each battery pack is obtained, which comprises: When at least one of the following occurs, the detection result of the battery pack is abnormal: The target outlier probability value corresponding to the voltage of the battery pack is greater than or equal to a preset voltage threshold, the target outlier probability value corresponding to the current is greater than or equal to a preset current threshold, and the target outlier probability value corresponding to the battery temperature is greater than or equal to a preset battery temperature threshold, the target outlier probability value corresponding to the battery capacity of the battery pack is greater than or equal to a preset battery capacity threshold, the target outlier probability value corresponding to the battery energy of the battery pack is greater than or equal to a preset battery energy threshold, and the target outlier probability value corresponding to the battery SOH of the battery pack is greater than or equal to a preset battery SOH threshold.

5. The battery pack abnormality detection method according to claim 3, characterized by, According to the target outlier probability value, the detection result of each battery pack is obtained, which comprises: If the target outlier probability value corresponding to the voltage of the battery pack is less than the preset voltage threshold, and the target outlier probability value corresponding to the current of the battery pack is less than the preset current threshold, and the target outlier probability value corresponding to the battery temperature of the battery pack is less than the preset battery temperature threshold, and the target outlier probability value corresponding to the battery capacity of the battery pack is less than the preset battery capacity threshold, and the target outlier probability value corresponding to the battery energy of the battery pack is less than the preset battery energy threshold, and the target outlier probability value corresponding to the battery SOH of the battery pack is less than the preset battery SOH threshold, then the detection result of the battery pack is normal. 6.The battery pack abnormality detection method of claim 1, wherein The average distance corresponding to the operation parameters of the battery pack is normalized by the following formula: wherein P i,t represents the outlier probability of the i-th battery pack in the battery pack at time t, D(i, K) represents the average distance of the i-th battery pack in the battery pack, j represents the battery pack serial number, and n represents the total number of battery packs.

7. The battery pack abnormality detection method according to claim 1, characterized by, The operation parameters of each battery pack at the same time are obtained by a K-neighbor algorithm, and K measurement distances of the operation parameters of each battery pack and the operation parameters of the remaining battery packs are obtained, including: The measurement distances between the operation parameters of each battery pack and the operation parameters of the remaining battery packs are calculated. The measurement distances between the operation parameters are searched by the K-neighbor algorithm, and K measurement distances of the operation parameters of each battery pack and the operation parameters of the remaining battery packs are obtained. 8.The battery pack abnormality detection method of claim 7, wherein The searching of the measurement distances between the operation parameters by the K-neighbor algorithm includes: A KD tree data structure is constructed according to the measurement distances between the operation parameters. The KD tree data structure is searched by the K-neighbor algorithm. 9.The battery pack abnormality detection method of claim 7, The measurement distance is a Manhattan distance.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the battery pack abnormality detection method according to any one of claims 1-9.

11. An electronic device comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The computer program is executed by the processor to implement the battery pack abnormality detection method according to any one of claims 1-9.

12. A computer program product comprising computer programs or instructions, wherein, When the computer program or instructions are executed, the battery pack abnormality detection method according to any one of claims 1-9 is implemented.

Images