Battery voltage anomaly detection method and related equipment

Abstract

The invention provides a battery voltage anomaly detection method and related equipment, and relates to the technical field of battery detection. The method comprises the following steps: collecting battery monomer data, wherein the battery monomer data comprises a voltage value and charge-discharge state information of each battery monomer; calculating a local outlier factor based on the voltage value of each battery monomer; determining abnormal data based on the local outlier factor; and based on the charging and discharging state information and the abnormal data, determining a single voltage inconsistency result in the charging and discharging window. According to the method, the local outlier factor is calculated based on the original voltage value of each single battery, so that the local outlier factor can be accurately determined based on original voltage value data characteristics, the troubleshooting precision of abnormal data of the battery voltage is improved, and a single voltage inconsistency result in the charging and discharging window is determined based on the charging and discharging state information and the abnormal data; the battery is prevented from being in an over-charging or over-discharging abnormal working state for a long time, the battery performance is optimized, and the service life of the battery is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and more specifically, to a battery voltage abnormality detection method, a battery voltage abnormality detection device, an electronic device and a storage medium. Background Art

[0002] Battery voltage anomaly detection is an important part of the battery management system (BMS). It is used to monitor the voltage of single cells in the battery pack to ensure that the battery operates within a safe range and prevent overcharging, over-discharging, etc.

[0003] In the related art, the battery voltage anomaly detection process mostly relies on specially processed non-original data and ignores the influence of window factors and charging and discharging status factors, which leads to data distortion and low accuracy of battery voltage anomaly detection, making the battery more likely to be in an overcharged or over-discharged state, affecting battery performance and shortening battery life. Summary of the invention

[0004] The present application provides a battery voltage anomaly detection method, a battery voltage anomaly detection device, an electronic device and a storage medium. Based on the original voltage value of each battery cell, a local outlier factor is calculated, which is conducive to accurately determining the local outlier factor based on the original voltage value data characteristics, improving the accuracy of troubleshooting battery voltage anomaly data, and determining the cell voltage inconsistency results within the charge and discharge window based on the charge and discharge state information and abnormal data, avoiding the battery from being in an abnormal working state of overcharge or overdischarge for a long time, optimizing battery performance and extending battery life.

[0005] In a first aspect, the present invention proposes a battery voltage anomaly detection method, comprising: collecting battery cell data, the battery cell data including the voltage value and charge and discharge status information of each battery cell; calculating a local outlier factor based on the voltage value of each battery cell; determining abnormal data based on the local outlier factor; and determining a cell voltage inconsistency result within a charge and discharge window based on the charge and discharge status information and the abnormal data.

[0006] In some embodiments, a local outlier factor is calculated based on the voltage value of each battery cell, including: calculating the Euclidean distance between first voltage data and second voltage data based on the row voltage data in the voltage value of the battery cell, wherein the first voltage data is any voltage data in the row voltage data, and the second voltage data is the remaining voltage data in the row voltage data except the first voltage data; determining the k distance of the first voltage data based on the Euclidean distance; determining the k distance neighborhood based on the k distance; determining the local reachable distance of the first voltage data based on the k distance neighborhood; determining the local reachable density based on the k distance, the k distance neighborhood and the local reachable distance; and determining the local outlier factor based on the local reachable density.

[0007] In some embodiments, before calculating the local outlier factor based on the voltage value of each battery cell, the method further includes: obtaining a sequence table of voltage changes over time based on the battery cell data; and removing energy storage state data in the sequence table to construct a voltage matrix.

[0008] In some implementations, the method further includes: performing unit conversion on the voltage value; and performing standardization on the converted voltage value.

[0009] In some embodiments, the method further includes: marking abnormal data; determining a single cell voltage inconsistency result within a charge and discharge window based on the charge and discharge status information and the abnormal data, including: when the charge and discharge status information is used as a statistical window, counting the abnormal data within each window based on the marking; and determining a single cell voltage inconsistency result based on the statistical result.

[0010] In some embodiments, the abnormal data includes abnormal number information and / or abnormal frequency information.

[0011] In some embodiments, the method further includes determining an alarm level based on the cell voltage inconsistency result to issue an alarm; and recording and saving the abnormal data.

[0012] On the second aspect, a battery voltage anomaly detection device is also proposed, including: an acquisition module for collecting battery cell data, the battery cell data including the voltage value and charge and discharge status information of each battery cell; a calculation module for calculating the local outlier factor based on the voltage value of each battery cell; an abnormality judgment module for determining the abnormal data based on the local outlier factor; a result determination module for determining the cell voltage inconsistency result within the charge and discharge window based on the charge and discharge status information and the abnormal data.

[0013] In a third aspect, an electronic device is also proposed, including a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are used by the processor to execute the battery voltage abnormality detection method as described above when the processor is running.

[0014] In a fourth aspect, a storage medium is also proposed, on which program instructions are stored, and the program instructions are used to execute the battery voltage abnormality detection method as described above when running.

[0015] The present application discloses a battery voltage anomaly detection method, a battery voltage anomaly detection device, an electronic device and a storage medium, wherein the method comprises: calculating a local outlier factor based on the original voltage value of each battery cell, which is conducive to accurately determining the local outlier factor based on the original voltage value data characteristics, improving the accuracy of troubleshooting battery voltage anomaly data, and determining the cell voltage inconsistency result within the charge and discharge window based on the charge and discharge state information and abnormal data, which is conducive to avoiding the battery from being in an abnormal working state of overcharge or overdischarge for a long time, optimizing battery performance and extending battery service life.

[0016] The battery voltage abnormality detection method of the present invention, other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by those skilled in the art through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the exemplary embodiments below. The accompanying drawings are only for the purpose of illustrating exemplary embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0020] Figure 1 A schematic flow chart of a battery voltage abnormality detection method provided in an embodiment of the present application;

[0021] Figure 2 A schematic flow chart of another battery voltage abnormality detection method provided in an embodiment of the present application;

[0022] Figure 3 A schematic flow chart of another battery voltage abnormality detection method provided in an embodiment of the present application;

[0023] Figure 4A schematic diagram of a single cell voltage inconsistency result provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the relationship between a k value and a cell voltage inconsistency result provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of a result of cell voltage inconsistency when the k value is 10 provided in an embodiment of the present application;

[0026] Figure 7 A schematic block diagram of a battery voltage abnormality detection device according to an embodiment of the present invention is shown; and

[0027] Figure 8 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0028] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0031] Battery voltage anomaly detection is an important part of the battery management system (BMS). It is used to monitor the voltage of single cells in the battery pack to ensure that the battery operates within a safe range and prevent overcharging, over-discharging, etc.

[0032] In the related art, the battery voltage abnormality detection process mostly relies on specially processed non-original data and ignores the influence of window factors and charging and discharging status factors, which leads to data distortion and low accuracy of battery voltage abnormality inspection results, making the battery more likely to be in an overcharged or over-discharged state, affecting battery performance and shortening battery life.

[0033] In view of this, the present application provides a battery voltage anomaly detection method, a battery voltage anomaly detection device, an electronic device and a storage medium. The present application calculates the local outlier factor based on the original voltage value of each battery cell, which is conducive to accurately determining the local outlier factor based on the original voltage value data characteristics, improving the accuracy of troubleshooting battery voltage anomaly data, and determining the cell voltage inconsistency results within the charge and discharge window based on the charge and discharge status information and abnormal data, avoiding the battery from being in an abnormal working state of overcharge or over-discharge for a long time, optimizing battery performance, and extending battery life.

[0034] According to a first aspect of the present application, a method for detecting abnormal battery voltage is proposed. Figure 1 FIG. 1 is a schematic flow chart of a battery voltage abnormality detection method 100 proposed in an embodiment of the present application. Figure 1 As shown, method 100 may include the following steps.

[0035] Step S110 , collecting battery cell data, where the battery cell data includes the voltage value and charge and discharge status information of each battery cell.

[0036] For example, the battery cell data can be acquired by a battery management system (BMS) based on a preset acquisition frequency, wherein the preset acquisition frequency can be set according to the actual application requirements of the user and is not specifically limited here.

[0037] Step S120 , calculating a local outlier factor based on the voltage value of each battery cell.

[0038] Exemplarily, the charge and discharge voltage matrix can be determined based on the voltage value of each battery cell and the charge and discharge state information, and the local outlier factor can be calculated based on the local outlier factor (LOF) algorithm. It should be noted that the charge and discharge voltage matrix can include a charge voltage matrix and a discharge voltage matrix. The charge voltage matrix includes row voltage data and column voltage data in the charge state, and the discharge voltage matrix includes row voltage data and column voltage data in the discharge state.

[0039] In some feasible implementations, the local outlier factor may be calculated based on a local outlier factor algorithm according to row voltage data and / or column voltage data in the charging voltage matrix.

[0040] Step S130, determining abnormal data based on the local outlier factor.

[0041] Exemplarily, abnormal data may be determined based on a density deviation of a row voltage data point or a column voltage data point relative to its neighborhood in the charge and discharge voltage matrix.

[0042] Specifically, when the density deviation value of a row voltage data point or a column voltage data point relative to its neighborhood in the above-mentioned charge and discharge voltage matrix is ​​greater than a preset threshold, the current row voltage data point or column voltage data point is determined to be abnormal data.

[0043] Step S140 , determining a cell voltage inconsistency result within the charge and discharge window based on the charge and discharge state information and the abnormal data.

[0044] Exemplarily, the cell voltage inconsistency result within the above-mentioned charge and discharge windows may include the number of abnormal voltages of each cell within each charge window in the charge state, and the number of abnormal voltages of each cell within each discharge window in the discharge state.

[0045] In some feasible implementations, the state information of each cell voltage may be determined according to the number of abnormalities of each cell voltage, wherein the state information may include: normal state, abnormal state, abnormal level, etc.

[0046] Based on this, the battery voltage anomaly detection method proposed in the present application includes: calculating the local outlier factor based on the original voltage value of each battery cell, which is conducive to accurately determining the local outlier factor based on the original voltage value data characteristics, improving the accuracy of troubleshooting battery voltage anomaly data, and determining the cell voltage inconsistency results within the charge and discharge window based on the charge and discharge status information and abnormal data, avoiding the battery from being in abnormal working states such as overcharging or over-discharging for a long time, optimizing battery performance, and extending battery life.

[0047] For example, Figure 2A schematic flow chart of another battery voltage abnormality detection method provided in an embodiment of the present application, such as Figure 2 As shown, step S120 may include calculating the local outlier factor based on the voltage value of each battery cell:

[0048] Step S121, based on the row voltage data in the voltage value of the battery cell, calculate the Euclidean distance between the first voltage data and the second voltage data, wherein the first voltage data is any voltage data in the row voltage data, and the second voltage data is the remaining voltage data in the row voltage data except the first voltage data.

[0049] Exemplarily, the Euclidean distance between the first voltage data and the second voltage data may be calculated based on the following formula according to the row voltage data in the charge and discharge voltage matrix:

[0050] distance(x 1 ,x 2 )=|x 1 -x 2 | (1)

[0051] Among them, x 1 is the first voltage data, x 2 is the second voltage data.

[0052] Step S122: determining the k distance of the first voltage data based on the Euclidean distance.

[0053] Exemplarily, the k-distance of the first voltage data is the minimum distance between the first row voltage data and its k nearest neighbors. Specifically, taking row voltage data point A as an example, the k-distance can be expressed as k-distance(A).

[0054] Step S123: determining a k-distance neighborhood based on the k-distance.

[0055] Exemplarily, the k-distance neighborhood may be a set of k row voltage data points closest to the row voltage data point. Specifically, taking row voltage data point A as an example, the k-distance neighborhood may be expressed as N k (A), where k is the distance neighborhood N k (A) can be determined based on the following formula:

[0056] N k (A)={x∈D|distance(x,A)≤k-distance(A)} (2)

[0057] Among them, N k(A) is the k-distance neighborhood of the row voltage data point A, D is all row voltage data sets in the charge and discharge voltage matrix, distance(x,A) is the Euclidean distance from the row voltage data point x to the row voltage data point A, and k-distance(A) is the k-distance of the row voltage data point A.

[0058] Step S124: determining a local reachable distance of the first voltage data based on the k-distance neighborhood.

[0059] Exemplarily, taking row voltage data point A and row voltage data point B as an example, the above local reachable distance can be determined based on the following formula:

[0060] dist(A,B)=max{k-distance(B),distance(A,B)} (3)

[0061] Wherein, dist(A,B) is the local reachable distance between row voltage data point A and row voltage data point B, k-distance(B) is the k distance of row voltage data B, and distance(A,B) is the Euclidean distance between voltage data point A and voltage data point B.

[0062] Step S125, determining the local reachability density based on the k-distance, the k-distance neighborhood and the local reachability distance.

[0063] Exemplarily, taking row voltage data point A and row voltage data point B as an example, the above local reachable density can be determined based on the following formula:

[0064]

[0065] Where LRD(A) is the local reachability density of the row voltage data point A, k is the number of the nearest neighbors of the row voltage data point A, and N k (A) is the k-distance neighborhood of the row voltage data point A, and dist(A,B) is the local reachable distance between the row voltage data point A and the row voltage data point B.

[0066] Step S126, determining a local outlier factor based on the local reachable density.

[0067] Exemplarily, taking row voltage data point A and row voltage data point B as an example, the local outlier factor may be determined based on the following formula:

[0068]

[0069] Where LOF(A) is the local outlier factor of row voltage data point A, LRD(A) is the local reachable density of row voltage data point A, LRD(B) is the local reachable density of row voltage data point B, N k(A) is the k-distance neighborhood of the row voltage data point A, where k is the number of nearest neighbors to the row voltage data point A.

[0070] In some feasible embodiments, when the deviation value between the local outlier factor of the target row voltage data point and the preset threshold is greater than the preset deviation threshold, the target row voltage data point is determined to be abnormal data; when the deviation value between the local outlier factor of the target row voltage data point and the preset threshold is less than or equal to the preset deviation threshold, the target row voltage data point is determined to be normal data.

[0071] Exemplarily, the preset threshold may be 1. Specifically, when the deviation value of the local outlier factor of the target row voltage data point from 1 is greater than the preset deviation threshold, the target row voltage data point is determined to be abnormal data; when the deviation value of the local outlier factor of the target row voltage data point from 1 is less than or equal to the preset deviation threshold, the target row voltage data point is determined to be normal data.

[0072] It should be noted that the above-mentioned preset deviation threshold can be defined according to the accuracy requirement of abnormal data screening, wherein the above-mentioned preset deviation threshold is negatively correlated with the accuracy requirement of abnormal data screening, that is, the higher the accuracy requirement of abnormal data screening, the smaller the above-mentioned preset deviation threshold.

[0073] Based on this, the above method is based on the original row voltage data in the voltage value of the battery cell, which is conducive to accurately determining the Euclidean distance between the first voltage data and the second voltage data, the k distance of the first voltage data, the k distance neighborhood, the local reachable distance of the first voltage data, the local reachable density and the local outlier factor based on the original row voltage value data characteristics, thereby improving the determination accuracy of the local outlier factor, thereby improving the detection accuracy of abnormal battery cell voltage data, avoiding the battery from being in abnormal working states such as overcharging or over-discharging for a long time, keeping the battery in a safe working state, and extending the battery life.

[0074] In some embodiments, before calculating the local outlier factor based on the voltage value of each battery cell in step S120, the method further includes:

[0075] Based on the battery cell data, a sequence table of voltage changes over time is obtained.

[0076] In some feasible implementations, a sequence table of voltage changes over time at a preset time can be obtained based on battery cell data, wherein the preset time can be defined according to actual needs of the user and is not specifically limited here.

[0077] The energy storage state data in the sequence table are eliminated to construct the voltage matrix.

[0078] Exemplarily, the energy storage state data includes: voltage data of a battery cell in a non-charging state or a non-discharging state.

[0079] Specifically, based on the sequence table after eliminating the energy storage state data, an [m×n] voltage matrix can be constructed, wherein the m is the number of voltage samples and n is the number of single cell voltage values.

[0080] Based on this, the above method constructs a voltage matrix by eliminating the energy storage state data in the sequence table of voltage changes over time. Under the condition of the original voltage value data characteristics, the invalid battery cell voltage data in the voltage matrix is ​​reduced, which is beneficial to improve the construction accuracy of the voltage matrix, reduce the data processing amount and save data calculation steps in the process of determining the local outlier factor, improve the calculation accuracy of the local outlier factor, and improve the troubleshooting efficiency and troubleshooting accuracy of abnormal battery cell voltage data.

[0081] In some embodiments, the above method may further include:

[0082] Convert voltage values ​​to different units.

[0083] Exemplarily, the unit of the voltage value may be converted from millivolts to volts.

[0084] In some feasible implementations, the unit of the row voltage data in the voltage matrix may be converted from millivolts to volts. Alternatively, the unit of the column voltage data in the voltage matrix may also be converted from millivolts to volts.

[0085] The converted voltage value is standardized.

[0086] Exemplarily, the standardization process may include normalization, Z-Score standardization, etc., which are not specifically limited herein. Specifically, taking Z-Score standardization as an example, based on Z-Score standardization, the average value of the row voltage value data or the column voltage data is 0, and the standard deviation between the row voltage value data or the column voltage data is 1.

[0087] It is understandable that the converted row voltage values ​​may be standardized to determine the local outlier factor for checking abnormal data. Alternatively, the converted column voltage values ​​may be standardized to determine the local outlier factor for checking abnormal data.

[0088] Specifically, the converted voltage value can be standardized based on the following formula:

[0089]

[0090] Where x is the voltage value, μ is the mean value of the voltage, and δ is the standard deviation of the voltage.

[0091] Based on this, the above method can improve the intuitiveness of the battery cell voltage data in the voltage matrix, reduce the influence of the extreme battery cell voltage data in the voltage matrix on the determination of the local outlier factor, and improve the standardization of the voltage value, thereby improving the determination accuracy and efficiency of the local outlier factor, and improving the troubleshooting accuracy and efficiency of the battery cell voltage abnormal data.

[0092] In some embodiments, the above method may further include:

[0093] Mark abnormal data.

[0094] It is understandable that the above abnormal data can be marked in a marking form different from that of normal data, and the specific marking form is not specifically limited here.

[0095] Specifically, a '*' sign may be added after the abnormal data to mark the abnormal data.

[0096] Figure 3 A schematic flow chart of another battery voltage abnormality detection method provided in an embodiment of the present application. Figure 3 As shown, step S140 determines the cell voltage inconsistency result within the charge and discharge window based on the charge and discharge state information and the abnormal data, and may include:

[0097] Step S141 , when the charge and discharge state information is used as a statistical window, abnormal data in each window is counted based on the mark.

[0098] It should be noted that the statistical window needs to be distinguished according to the charging state and the discharging state.

[0099] In some embodiments, the above-mentioned abnormal data may also include abnormal number information and / or abnormal frequency information.

[0100] It should be noted that the above abnormal data includes abnormal number information and / or abnormal frequency information, which can realize multi-dimensional monitoring and troubleshooting of abnormal voltage values ​​of battery cells based on abnormal number and / or abnormal frequency, thereby improving the troubleshooting accuracy of abnormal data.

[0101] Step S142: determining the cell voltage inconsistency result based on the statistical result.

[0102] In some feasible implementations, the abnormal situation and abnormal level of the single cell voltage can be determined based on the abnormal number information in each window.

[0103] For example, the number of abnormalities of a single battery cell in window i is recorded as p i Specifically, in p i Greater than or equal to 0, less than or equal to μ 1In the case of p, it is judged that the single battery voltage is normal; i Greater than μ 1 , less than or equal to μ 2 In the case of p, it is judged that the single battery voltage is abnormally low; i Greater than or equal to μ 2 , less than or equal to μ 3 In the case of p, it is judged that the single battery voltage is medium abnormal; i Greater than μ 3 In the case of , it is judged that the single cell voltage is abnormal. 1 , μ 2 and μ 3 This is a preset abnormal number threshold, which is not specifically limited here.

[0104] In some feasible implementations, the abnormal situation and abnormal level of the single cell voltage may also be determined based on the abnormal frequency information in each window, which will not be described in detail here.

[0105] in, Figure 4 This is a schematic diagram of a single cell voltage inconsistency result provided by an embodiment of the present application. Figure 4 As shown in the figure, the horizontal axis is the battery cell ID, where there are 120 battery cells in total, and the vertical axis is the number of abnormalities in each window, where different colors represent different window IDs, and windows 1 to 10 are the discharge, charge, discharge, charge... states that change over time. Figure 4 It can be seen that battery cell 56, battery cell 66, battery cell 67, battery cell 68, battery cell 97, battery cell 100, and battery cell 108 have high-level voltage inconsistency anomalies. Based on the curve color analysis, it can be seen that window 7 has a higher abnormality frequency than other windows. Based on the area analysis of the area surrounded by the curve, battery cell 90 and battery cell 100 have regional inconsistency anomalies.

[0106] Based on this, the above method can be used to count the number of abnormalities and / or abnormal frequency in the charging window or discharging window of each battery cell when the charging and discharging status information is used as the statistical window, thereby realizing differentiated processing of the voltage value data of the battery cell based on the voltage characteristics in the charging state or the discharging state, thereby improving the accuracy of detecting battery cell voltage abnormalities in the charging state or the discharging state, and there is no need to wait until the battery cell is completed charging and discharging to judge the voltage abnormality, which is beneficial to improving the efficiency of judging battery cell voltage abnormalities.

[0107] in, Figure 5 A schematic diagram of the relationship between the k value and the cell voltage inconsistency result provided in an embodiment of the present application. Figure 6This is a schematic diagram of the results of cell voltage inconsistency when the k value is 10 provided in an embodiment of the present application. Figure 5-Figure 6 As shown, the horizontal axis is the battery cell ID, where there are 120 battery cells in total, and the vertical axis is the number of abnormalities in each window. Figure 5 It can be seen that when the value of k is 10, 20 or 50, the abnormal number statistics have roughly the same change trend. It can be seen that a smaller k value is more sensitive to local abnormal data points, which will increase noise and local fluctuations, and the false alarm rate is high. On the contrary, a larger k value curve is smoother and more sensitive to global data, which will cause some local abnormal points to be ignored, resulting in a high false alarm rate. Based on this, it has been proved through multiple experiments that when the k value is 10 and the preset threshold λ value is 2, the single cell voltage inconsistency result in the charge and discharge window is more accurate.

[0108] In some embodiments, the method may further include:

[0109] Based on the cell voltage inconsistency result, an alarm level is determined to issue an alarm.

[0110] It should be noted that the above alarm level is positively correlated with the abnormal level of the single cell voltage. Specifically, when the single cell voltage is judged to be normal, no alarm is issued; when the single cell voltage is judged to be low-level abnormal, a low-level alarm is issued; when the single cell voltage is judged to be medium-level abnormal, a medium-level alarm is issued; when the single cell voltage is judged to be high-level abnormal, a high-level alarm is issued. Among them, the above alarm form can be in the form of a prompt sound or a warning light, which is not specifically limited here. Specifically, when the alarm form is a prompt sound, the volume of the above prompt sound is normal with the above alarm level, that is, the higher the alarm level, the louder the prompt sound volume. When the alarm form is a warning light, the flashing frequency or flashing duration of the above warning light is positively correlated with the alarm level, that is, the higher the alarm level, the faster the flashing frequency of the warning light or the longer the flashing duration of the warning light.

[0111] Record and save abnormal data.

[0112] Exemplarily, data such as abnormal battery cell number, abnormal time, and abnormal voltage value corresponding to the abnormal data may be recorded and saved.

[0113] Based on this, the above method can realize intuitive observation of abnormal data conditions and record and save abnormal data by determining the alarm level based on the single cell voltage inconsistency result to issue an alarm, which can facilitate the subsequent retrieval of abnormal data.

[0114] According to the second aspect of the present application, a battery voltage abnormality detection device is also proposed. Figure 7 Schematic block diagram of a battery voltage abnormality detection device 700 proposed in an embodiment of the present application. Figure 7 As shown, the apparatus 700 may include:

[0115] The acquisition module 710 is used to acquire battery cell data, where the battery cell data includes the voltage value and charge and discharge status information of each battery cell;

[0116] A calculation module 720, configured to calculate a local outlier factor based on a voltage value of each battery cell;

[0117] An abnormality determination module 730, used to determine abnormal data based on local outlier factors;

[0118] The result determination module 740 is used to determine the cell voltage inconsistency result within the charge and discharge window based on the charge and discharge state information and the abnormal data.

[0119] According to a third aspect of the present invention, an electronic device is also provided. Figure 8 FIG. 8 is a schematic block diagram of an electronic device 800 according to an embodiment of the present invention. Figure 8 As shown, the electronic device 800 may include a processor 810 and a memory 820. The memory 820 stores computer program instructions, which are used by the processor 810 to execute the battery voltage abnormality detection method described above when the processor 810 is running.

[0120] According to a fourth aspect of the present invention, a storage medium is also provided, on which program instructions are stored, and the program instructions are used to execute the battery voltage abnormality detection method as described above when running. The storage medium may include, for example, a storage component of a tablet computer, a hard disk of a computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0121] A person skilled in the art may understand the specific details and beneficial effects of the battery voltage abnormality detection device, the electronic device and the storage medium by reading the above description of the battery voltage abnormality detection method, which will not be described here for the sake of brevity.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed devices and / or equipment can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0126] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting abnormal battery voltage, characterized in that: include: Collecting battery cell data, wherein the battery cell data includes voltage value and charge and discharge status information of each battery cell; Calculating a local outlier factor based on the voltage value of each battery cell; Based on the local outlier factor, determining abnormal data; Based on the charge and discharge state information and the abnormal data, a cell voltage inconsistency result within a charge and discharge window is determined.

2. The battery voltage abnormality detection method according to claim 1, characterized in that: The calculating of the local outlier factor based on the voltage value of each battery cell includes: Calculating the Euclidean distance between first voltage data and second voltage data based on row voltage data in the voltage value of the battery cell, wherein the first voltage data is any voltage data in the row voltage data, and the second voltage data is the remaining voltage data in the row voltage data except the first voltage data; Based on the Euclidean distance, determining a k distance of the first voltage data; Based on the k distance, determining a k distance neighborhood; Determining a local reachable distance of the first voltage data based on the k-distance neighborhood; Determining a local reachability density based on the k-distance, the k-distance neighborhood, and the local reachability distance; The local outlier factor is determined based on the local reachable density.

3. The battery voltage abnormality detection method according to claim 1, characterized in that: Before calculating the local outlier factor based on the voltage value of each battery cell, the method further includes: Based on the battery cell data, obtaining a sequence table of voltage changes over time; The energy storage state data in the sequence table is eliminated to construct a voltage matrix.

4. The battery voltage abnormality detection method according to claim 3, characterized in that: The method further comprises: Performing unit conversion on the voltage value; The converted voltage value is standardized.

5. The battery voltage abnormality detection method according to claim 1, characterized in that: The method further comprises: Marking the abnormal data; The determining, based on the charge and discharge state information and the abnormal data, a result of the cell voltage inconsistency within the charge and discharge window includes: In the case where the charge and discharge state information is used as a statistical window, counting the abnormal data in each window based on the mark; Based on the statistical results, the cell voltage inconsistency result is determined.

6. The battery voltage abnormality detection method according to claim 5, characterized in that: The abnormal data includes abnormal number information and / or abnormal frequency information.

7. The battery voltage abnormality detection method according to claim 5 or 6, characterized in that: The method further comprises: Based on the cell voltage inconsistency result, determining an alarm level to issue an alarm; The abnormal data is recorded and saved.

8. A battery voltage abnormality detection device, characterized in that: include: A collection module, used to collect battery cell data, wherein the battery cell data includes the voltage value and charge and discharge status information of each battery cell; A calculation module, configured to calculate a local outlier factor based on the voltage value of each battery cell; An abnormality judgment module, used for determining abnormal data based on the local outlier factor; The result determination module is used to determine the cell voltage inconsistency result within the charge and discharge window based on the charge and discharge state information and the abnormal data.

9. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are used by the processor to execute the battery voltage abnormality detection method as claimed in any one of claims 1 to 7 when the processor is running.

10. A storage medium having program instructions stored thereon, wherein the program instructions are used to execute the battery voltage abnormality detection method according to any one of claims 1 to 7 when running.

Images