Abnormal single cell detection method, device, electric vehicle and medium

Abstract

The present invention provides an abnormal single cell detection method, equipment, electric vehicle and medium, including determining the ideal single cell set of the power battery pack to be detected in the current stage of life cycle according to the remaining power of each single cell in each static period in the power battery pack to be detected; determining the remaining power of the ideal single cell in each static period according to the remaining power of the single cell in the ideal single cell set in each static period; forming a single cell characteristic curve of each single cell in the current stage of life cycle according to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period; inputting each single cell characteristic curve into a pre-trained single cell abnormality recognition model of the current stage of life cycle to detect abnormal single cells. In this way, the noise caused by the uncontrolled operating conditions of the power battery and the asynchronous signal can be weakened, the abnormal single cell can be accurately detected, and the overall performance of the battery pack can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power batteries, and specifically provides a method and equipment for detecting abnormal single cells, an electric vehicle and a medium. Background Art

[0002] As the source of energy for electric vehicles, power batteries are the most core components in the field of new energy vehicles. Power battery packs usually combine dozens or even hundreds of single battery modules in series to meet power output requirements. Due to slight differences in production and assembly and inconsistencies in the actual charging and discharging process, each single battery module will show different characteristics over time. According to the barrel principle, the overall charging and discharging performance of the entire battery pack will be limited by individual single batteries in poor health. At this time, identifying these abnormal single batteries and taking corresponding measures, such as replacement or balancing, can make up for the shortcomings and effectively improve the overall performance of the battery pack.

[0003] In the related art, abnormal single cells are usually detected in the following ways:

[0004] 1. During the battery life cycle, the relative inconsistency of the peak shift of the single-cell dv / dq curve during the charging process is used to evaluate the single-cell attenuation inconsistency and detect abnormal single-cell batteries.

[0005] 2. During the battery life cycle, the inconsistency of monomer attenuation is evaluated through the relative inconsistency of the relaxation voltage curve at the end of charging, thereby detecting abnormal monomer batteries.

[0006] 3. During the battery life cycle, the DC impedance is calculated by current pulses under fixed working conditions and its inconsistency is compared to evaluate the inconsistency of single cell attenuation and detect abnormal single cells.

[0007] However, since the differences in the external characteristics of battery attenuation inconsistency characterized at the mechanism level are very small, they are easily drowned out by sensor noise during the actual operation of the power battery. In addition, since the external characteristics of the above methods in the battery life cycle will lose relative comparability as the operating conditions change, in actual application scenarios, it is difficult to normalize the external characteristics of single-cell attenuation between multiple operating conditions, resulting in low reliability of the detection results of abnormal single-cell batteries, thereby reducing the overall performance of the battery pack. Summary of the invention

[0008] In order to overcome the above-mentioned defects, the present invention is proposed to provide an abnormal single cell detection method, device, electric vehicle and medium that solves or at least partially solves the technical problem in the related art that the reliability of the detection results of abnormal single cells is low, thereby reducing the overall performance of the battery pack.

[0009] In a first aspect, the present invention provides a method for detecting abnormal single cells, comprising:

[0010] Acquire multiple rest periods in the life cycle of the power battery pack to be detected and the remaining power of each single battery in the power battery pack to be detected in each rest period;

[0011] Determine an ideal set of single cells of the power battery pack to be tested in the current stage of its life cycle according to the remaining power of each single cell in each static period of the power battery pack to be tested;

[0012] Determine the remaining power of the ideal single battery in each rest period according to the remaining power of the single battery in the ideal single battery set in each rest period;

[0013] According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of life cycle is formed;

[0014] Each of the monomer characteristic curves is input into a pre-trained monomer battery abnormality recognition model of the current stage of the life cycle to detect abnormal monomer batteries.

[0015] In a second aspect, the present invention provides an abnormal single cell battery detection device, characterized in that it includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute any of the above-mentioned abnormal single cell battery detection methods.

[0016] In a third aspect, an electric vehicle is provided, comprising the abnormal single cell detection device as described above.

[0017] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute the abnormal single cell detection method described in any one of the above technical solutions.

[0018] Solution 1. A method for detecting abnormal single cells, comprising:

[0019] Acquire multiple rest periods in the life cycle of the power battery pack to be detected and the remaining power of each single battery in the power battery pack to be detected in each rest period;

[0020] Determine an ideal set of single cells of the power battery pack to be tested in the current stage of its life cycle according to the remaining power of each single cell in each static period of the power battery pack to be tested;

[0021] Determine the remaining power of the ideal single battery in each rest period according to the remaining power of the single battery in the ideal single battery set in each rest period;

[0022] According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of life cycle is formed;

[0023] Each of the monomer characteristic curves is input into a pre-trained monomer battery abnormality recognition model of the current stage of the life cycle to detect abnormal monomer batteries.

[0024] Solution 2. The abnormal single cell detection method according to Solution 1 is characterized in that, according to the remaining power of each single cell in each static period, an ideal set of single cells of the power battery pack to be detected in the current stage of the life cycle is determined, including:

[0025] Selecting single cells that meet the first preset condition to form a set of single cells in each rest period;

[0026] According to the single battery set in each rest period, single batteries that meet the second preset condition are selected to form the ideal single battery set.

[0027] Solution 3. The abnormal single cell detection method according to Solution 2 is characterized in that the step of selecting single cells that meet the first preset condition to form a single cell set for each rest period comprises:

[0028] After arranging the remaining power of each single battery in each rest period in descending order, single batteries within a preset range are selected to form a single battery set for each rest period;

[0029] The lower limit of the preset range is the difference between the sorted median and the first preset value, and the upper limit of the preset range is the sum of the sorted median and the second preset value.

[0030] Solution 4. The abnormal single cell detection method according to Solution 2 is characterized in that the step of selecting single cells that meet a second preset condition to form the ideal single cell set according to the single cell set in each static period comprises:

[0031] The single cell battery corresponding to the intersection of all the single cell battery sets in the static period is selected to form the ideal single cell battery set.

[0032] Solution 5. The abnormal single cell detection method according to Solution 1 is characterized in that, according to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of the life cycle is formed, including:

[0033] According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a fitting curve of the remaining power of the ideal single cell and the single cell voltage of each single cell in the current stage of the life cycle is formed;

[0034] The fitting curve of the remaining power of the ideal cell and the cell voltage is differentiated to obtain a differential curve of the remaining power of the ideal cell and the cell voltage as the cell characteristic curve.

[0035] Solution 6. The abnormal single cell detection method according to Solution 1 is characterized in that the remaining power of the ideal single cell in each static period is determined according to the remaining power of the single cells in the ideal single cell set in each static period, including:

[0036] The average remaining power of the single cells in the ideal single cell set in each rest period is used as the remaining power of the ideal single cell in each rest period.

[0037] Solution 7. The abnormal single cell detection method according to Solution 1 is characterized in that the acquisition process of each static period includes:

[0038] According to the preset static period condition, determining whether each traversal cycle in the current stage life cycle belongs to the static period;

[0039] Wherein, the static period conditions include:

[0040] The vehicle is stationary for a period longer than a preset period, the absolute value of the current of each single cell is less than a preset current value, and the standard deviation of the open circuit voltage sequence of each single cell in each traversal cycle is less than a preset standard deviation.

[0041] Solution 8. The abnormal single cell detection method according to Solution 1 is characterized in that each single cell characteristic curve is input into a pre-trained single cell abnormality recognition model of the current stage of the life cycle to detect abnormal single cells, including:

[0042] Extracting the current voltage kurtosis of the single cell and the current voltage skewness of the single cell from the single cell characteristic curve;

[0043] Calculating the kurtosis difference between the current voltage skewness and the factory voltage kurtosis of the single cell, and the skewness difference between the current voltage skewness and the factory voltage skewness of the single cell;

[0044] Determining an abnormality score of a single cell according to the kurtosis difference and the skewness difference;

[0045] If the abnormality score of the single cell is greater than a set threshold, the single cell is determined to be an abnormal single cell.

[0046] Solution 9. An abnormal single cell battery detection device, characterized in that it includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the abnormal single cell battery detection method described in any one of Solutions 1 to 8.

[0047] Solution 10. An electric vehicle, characterized in that it includes the abnormal single cell battery detection device as described in Solution 9.

[0048] Solution 11. A computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the abnormal single cell detection method described in any one of Solutions 1 to 8.

[0049] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0050] In the technical solution of the present invention, by obtaining multiple static periods in the current stage of the life cycle of the power battery pack to be detected and the remaining power of each single cell of the power battery pack to be detected in each static period, the remaining power of the single cell is sampled under a relatively stable working condition, and the ideal single cell set of the power battery pack to be detected in the current stage of the life cycle can be determined according to the remaining power of each single cell of the power battery pack to be detected in each static period; the remaining power of the ideal single cell in each static period is determined according to the remaining power of the single cell in the ideal single cell set in each static period, which reduces the sampling noise to a certain extent; then, according to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of the life cycle is formed; each single cell characteristic curve is input into the pre-trained single cell abnormality recognition model of the current stage of the life cycle, and the abnormal single cell is output. The technical solution of the present invention can weaken the noise caused by the uncontrolled operating conditions of the power battery and the asynchronous signal, so that the abnormal single cell can be accurately detected, thereby improving the overall performance of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

[0052] Figure 1is a schematic flow chart of main steps of a method for detecting abnormal single cells according to an embodiment of the present invention;

[0053] Figure 2 yes Figure 1 Schematic diagram of illustration corresponding to steps 101 to 104;

[0054] Figure 3 FIG. 4 is a main structural block diagram of an abnormal single cell detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0056] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0057] Normally, abnormal single cells are detected in the following ways:

[0058] 1. During the battery life cycle, the relative inconsistency of the peak shift of the single-cell dv / dq curve during the charging process is used to evaluate the single-cell attenuation inconsistency and detect abnormal single-cell batteries.

[0059] 2. During the battery life cycle, the inconsistency of monomer attenuation is evaluated through the relative inconsistency of the relaxation voltage curve at the end of charging, thereby detecting abnormal monomer batteries.

[0060] 3. During the battery life cycle, the DC impedance is calculated by current pulses under fixed working conditions and its inconsistency is compared to evaluate the inconsistency of single cell attenuation and detect abnormal single cells.

[0061] However, since the differences in the external characteristics of battery attenuation inconsistency characterized at the mechanism level are very small, they are easily drowned out by sensor noise during the actual operation of the power battery. In addition, since the external characteristics of the above methods in the battery life cycle will lose relative comparability as the operating conditions change, in actual application scenarios, it is difficult to normalize the external characteristics of single-cell attenuation between multiple operating conditions, resulting in low reliability of the detection results of abnormal single-cell batteries, thereby reducing the overall performance of the battery pack.

[0062] Therefore, in order to solve the above technical problems, the present invention provides the following technical solutions:

[0063] See attached Figure 1 , Figure 1 It is a schematic flow chart of main steps of a method for detecting abnormal single cells according to an embodiment of the present invention. Figure 2 yes Figure 1 Schematic diagram of the corresponding illustration of steps 101 to 104. Figure 1 As shown, the abnormal single cell detection method in the embodiment of the present invention mainly includes the following steps 101 to 105.

[0064] Step 101, obtaining a plurality of rest periods in the life cycle of the power battery pack to be tested and the remaining power of each single battery in the power battery pack to be tested in each rest period;

[0065] In a specific implementation process, the power battery pack is a lithium-ion battery pack used for electric vehicles. The lithium-ion batteries of the lithium-ion battery pack can be lithium iron phosphate, ternary lithium and lithium titanate batteries, etc. The power battery pack generally groups dozens or even hundreds of single cells in series to meet the power output requirements of the electric vehicle.

[0066] In a specific implementation process, the whole life cycle can be divided into multiple stages of life cycle (see Figure 2 The battery management system (BMS) is used to obtain the data record of the power battery pack to be tested in the current stage of its life cycle, including the voltage, current and open circuit voltage of each single cell of the power battery pack to be tested at each moment in the current stage of its life cycle, and the high charge period, low discharge period and rest period are confirmed from the full life cycle according to the current of the power battery pack to be tested and the open circuit voltage of each single cell (see Figure 2 The corresponding diagram in part (a) of the figure) and retain multiple static periods of the power battery pack to be tested in the current stage of its life cycle (see Figure 2 ), using the State Of Charge-Open Circuit Voltage (SOC-OCV) curve and the open circuit voltage of the single cell, the remaining power of each single cell of the power battery pack to be tested during each static period is found.

[0067] In a specific implementation process, the acquisition process of each static period may include:

[0068] According to the preset static period condition, determining whether each traversal cycle in the current stage life cycle belongs to the static period;

[0069] Wherein, the static period conditions include:

[0070] The vehicle is stationary for a period longer than a preset period, which may be 3 minutes; the absolute value of the current of each single cell is less than a preset current value, which may be 2A; and the standard deviation of the open circuit voltage sequence of each single cell in each traversal cycle is less than a preset standard deviation, which may be 0.002.

[0071] Step 102: Determine an ideal set of single cells of the power battery pack to be tested in the current stage of its life cycle according to the remaining power of each single cell in each static period of the power battery pack to be tested;

[0072] In a specific implementation process, the ideal battery cell set of the power battery pack to be tested in the current stage of the life cycle can be determined according to the following steps:

[0073] (1) selecting single cells that meet a first preset condition to form a set of single cells for each rest period;

[0074] Specifically, the remaining power of each single battery in each rest period can be arranged in descending order, and then the single batteries within a preset range are selected to form a single battery set for each rest period; wherein the lower limit of the preset range is the difference between the sorted median and the first preset value, and the upper limit of the preset range is the sum of the sorted median and the second preset value. In other words, for each rest period, the single battery whose SOC is always at the median of the rest period is selected to form a single battery set for each rest period.

[0075] (2) According to the battery cell set in each static period, the battery cells that meet the second preset condition are selected to form the ideal battery cell set.

[0076] After obtaining the single cell set of each rest period, the single cells in the single cell set of any rest period, although their SOC is near the median in the rest period, may not be the single cells at the median in other rest periods. Therefore, the single cells corresponding to the intersection of the single cell sets of all rest periods can be selected to form the ideal single cell set. In other words, the single cells whose SOC is always at the median are selected for all rest periods to form the single cell set of each rest period.

[0077] In a specific implementation process, there are three rest periods (the first rest period, the second rest period, and the third rest period), and the power battery pack has 1 to 10 single cells. In the first rest period, battery cell 1, battery cell 2, battery cell 3, battery cell 4, and battery cell 5 are located near the median, forming a set. In the second rest period, battery cell 2, battery cell 3, battery cell 4, battery cell 5, and battery cell 6 are located near the median, forming a set. In the rest segment 3, battery cell 1, battery cell 2, battery cell 3, battery cell 4, and battery cell 6 are located near the median, forming a set. After taking the intersection, battery cell 2, battery cell 3, and battery cell 4 are ideal single cell battery sets.

[0078] Step 103, determining the remaining power of the ideal single battery in each static period according to the remaining power of the single battery in the ideal single battery set in each static period;

[0079] In a specific implementation process, the average remaining power of the cells in the ideal cell set in each rest period can be used as the remaining power of the ideal cell in each rest period. (See Figure 2 The corresponding diagram in part (d) is shown in the figure. The upper part in part (d) is the remaining capacity of an ideal single cell during each static period).

[0080] Step 104, forming a cell characteristic curve of each cell in the current stage of its life cycle according to the remaining power of the ideal cell in each rest period and the open circuit voltage of each cell in each rest period;

[0081] In a specific implementation process, a fitting curve of the remaining power of the ideal single cell and the single cell voltage of each single cell in the current stage of the life cycle can be formed according to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period. Figure 2 Then, the fitting curve of the remaining power of the ideal monomer and the monomer battery voltage is differentiated to obtain the differential curve of the remaining power of the ideal monomer and the monomer battery voltage as the monomer characteristic curve. Figure 2 Figure 10.2 shows the diagram corresponding to part (f) in the figure).

[0082] Step 105 , input each of the monomer characteristic curves into a pre-trained monomer battery abnormality recognition model for the current stage of the life cycle to detect abnormal monomer batteries.

[0083] In a specific implementation process, abnormal single cells can be detected according to the following steps:

[0084] (21) extracting the current voltage peak of the single cell and the current voltage skewness of the single cell from the single cell characteristic curve;

[0085] In a specific implementation process, the single cell abnormality recognition model of the current stage of the life cycle can be a model based on the isolation forest algorithm, and feature extraction can be performed by window splitting to obtain the current voltage kurtosis of the single cell and the current voltage skewness of the single cell. Among them, the current voltage kurtosis is a statistic that describes the steepness of the distribution form of all values ​​in the population. This statistic needs to be compared with the normal distribution. The current voltage kurtosis is 0, which means that the overall data distribution is the same as the steepness of the normal distribution; the current voltage kurtosis is greater than 0, which means that the overall data distribution is steeper than the normal distribution, and it is a sharp peak; the current voltage kurtosis is less than 0, which means that the overall data distribution is flatter than the normal distribution, and it is a flat peak. The larger the absolute value of the current voltage kurtosis, the greater the difference between the steepness of its distribution form and the normal distribution. The current voltage skewness is a statistic that describes the data distribution form, which describes the symmetry of a certain population value distribution. This statistic also needs to be compared with the normal distribution. If the current voltage skewness is 0, it means that the data distribution form has the same degree of skewness as the normal distribution; if the current voltage skewness is greater than 0, it means that the data distribution form is positively skewed or right-skewed compared with the normal distribution, that is, there is a long tail on the right, and there are more extreme values ​​on the right end of the data; if the current voltage skewness is less than 0, it means that the data distribution form is negatively skewed or left-skewed compared with the normal distribution, that is, there is a long tail on the left, and there are more extreme values ​​on the left end of the data. The larger the absolute value of the current voltage skewness, the greater the degree of skewness of its distribution form. The calculation method of the current voltage skewness and the current voltage kurtosis can refer to the existing related technology, which will not be repeated here.

[0086] (22) calculating the kurtosis difference between the current voltage skewness and the factory voltage kurtosis of the single cell, and the skewness difference between the current voltage skewness and the factory voltage skewness of the single cell;

[0087] (23) determining an abnormality score of the single cell according to the kurtosis difference and the skewness difference;

[0088] After normalizing the kurtosis difference and the skewness difference, the abnormality score of the single cell can be obtained based on the isolation forest algorithm. The implementation process of performing normalization and obtaining the abnormality score of the single cell based on the isolation forest algorithm can refer to the existing related technology and will not be repeated here.

[0089] (24) If the abnormality score of the single cell is greater than a set threshold, the single cell is determined to be an abnormal single cell.

[0090] In a specific implementation process, the process of training the single-cell battery abnormality recognition model includes:

[0091] (31) Obtain multiple sample rest periods of the sample test power battery pack in the entire life cycle and the remaining power of each sample single cell in each sample rest period;

[0092] (32) selecting an ideal set of sample single cells for the entire life cycle based on the remaining power of each sample single cell during the static period of each sample;

[0093] (33) Using the cumulative preset number of full charge depths of the sample power battery pack as a scale, the entire life cycle is divided into multiple stages of life cycle;

[0094] (34) determining the remaining power of the sample ideal single cell in each sample rest period in each stage of the life cycle according to the remaining power of the sample single cell in the set of sample ideal single cells in each sample rest period in each stage of the life cycle;

[0095] (35) forming a cell characteristic curve of each sample cell battery at each stage of the life cycle according to the remaining power of the sample ideal cell at each sample rest period at each stage of the life cycle and the open circuit voltage of each sample cell battery at each sample rest period at each stage of the life cycle;

[0096] (36) extracting the kurtosis and skewness of the cell characteristic curve of each sample cell at each stage of the life cycle;

[0097] (37) According to the kurtosis and skewness of the monomer characteristic curve of each sample monomer battery at each stage of the life cycle, the pre-built neural network is trained to obtain a monomer battery abnormality recognition model at each stage of the life cycle.

[0098] The abnormal single cell detection method of this embodiment realizes sampling of the residual power of single cells under a relatively stable working condition by acquiring multiple static periods in the current stage of the life cycle of the power battery pack to be detected and the residual power of each single cell of the power battery pack to be detected in each static period, and can determine the ideal single cell set of the power battery pack to be detected in the current stage of the life cycle according to the residual power of each single cell of the power battery pack to be detected in each static period; determine the residual power of the ideal single cell in each static period according to the residual power of the single cell in the ideal single cell set in each static period, and reduce the sampling noise to a certain extent; then form a single cell characteristic curve of each single cell in the current stage of the life cycle according to the residual power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period; input each single cell characteristic curve into the pre-trained single cell abnormal recognition model of the current stage of the life cycle, and output the abnormal single cell. The technical solution of the present invention can weaken the noise caused by the uncontrolled operating conditions of the power battery and the asynchronous signal, so that the abnormal single cell can be accurately detected, thereby improving the overall performance of the battery pack.

[0099] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0100] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0101] Furthermore, the present invention also provides an abnormal single cell detection device.

[0102] See attached Figure 3 , Figure 3 FIG. 1 is a main structural block diagram of an abnormal single cell detection device according to an embodiment of the present invention. Figure 3 As shown, the abnormal single cell detection device of the embodiment of the present invention may include a processor 30 and a storage device 31. The storage device 30 may be configured to store a program for executing the abnormal single cell detection method of the above method embodiment, and the processor 31 may be configured to execute the program in the storage device, which includes but is not limited to the program for executing the abnormal single cell detection method of the above method embodiment. For ease of explanation, only the part related to the embodiment of the present invention is shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The abnormal single cell detection device may be a control device formed by various electronic devices.

[0103] Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the abnormal single cell battery detection method of the above method embodiment, and the program can be loaded and run by a processor to implement the above abnormal single cell battery detection method. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0104] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0105] Those skilled in the art will appreciate that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0106] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for detecting abnormal single cells, characterized in that: include: Acquire multiple rest periods in the life cycle of the power battery pack to be detected and the remaining power of each single battery in the power battery pack to be detected in each rest period; Determine an ideal set of single cells of the power battery pack to be tested in the current stage of its life cycle according to the remaining power of each single cell in each static period of the power battery pack to be tested; Determine the remaining power of the ideal single battery in each rest period according to the remaining power of the single battery in the ideal single battery set in each rest period; According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of life cycle is formed; Each of the monomer characteristic curves is input into a pre-trained monomer battery abnormality recognition model of the current stage of the life cycle to detect abnormal monomer batteries.

2. The abnormal single cell detection method according to claim 1, characterized in that: According to the remaining power of each single cell in each static period, the ideal single cell set of the power battery pack to be tested in the current stage of the life cycle is determined, including: Selecting single cells that meet the first preset condition to form a set of single cells in each rest period; According to the single battery set in each rest period, single batteries that meet the second preset condition are selected to form the ideal single battery set.

3. The abnormal single cell detection method according to claim 2, characterized in that: The step of selecting the single cells satisfying the first preset condition to form a set of single cells in each rest period comprises: After arranging the remaining power of each single battery in each rest period in descending order, single batteries within a preset range are selected to form a single battery set for each rest period; The lower limit of the preset range is the difference between the sorted median and the first preset value, and the upper limit of the preset range is the sum of the sorted median and the second preset value.

4. The abnormal single cell detection method according to claim 2, characterized in that: The selecting, according to the single battery set in each static period, single batteries that meet the second preset condition to form the ideal single battery set comprises: The single cell battery corresponding to the intersection of all the single cell battery sets in the static period is selected to form the ideal single cell battery set.

5. The abnormal single cell detection method according to claim 1, characterized in that: According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a single cell characteristic curve of each single cell in the current stage of life cycle is formed, including: According to the remaining power of the ideal single cell in each static period and the open circuit voltage of each single cell in each static period, a fitting curve of the remaining power of the ideal single cell and the single cell voltage of each single cell in the current stage of the life cycle is formed; The fitting curve of the remaining power of the ideal cell and the cell voltage is differentiated to obtain a differential curve of the remaining power of the ideal cell and the cell voltage as the cell characteristic curve.

6. The abnormal single cell detection method according to claim 1, characterized in that: According to the remaining power of the single cells in the ideal single cell set in each rest period, the remaining power of the ideal single cell in each rest period is determined, including: The average remaining power of the single cells in the ideal single cell set in each rest period is used as the remaining power of the ideal single cell in each rest period.

7. The abnormal single cell detection method according to claim 1, characterized in that: The acquisition process for each rest period includes: According to the preset static period condition, determining whether each traversal cycle in the current stage life cycle belongs to the static period; Wherein, the static period conditions include: The vehicle is stationary for a period longer than a preset period, the absolute value of the current of each single cell is less than a preset current value, and the standard deviation of the open circuit voltage sequence of each single cell in each traversal cycle is less than a preset standard deviation.

8. The abnormal single cell detection method according to claim 1, characterized in that: Input each of the monomer characteristic curves into a pre-trained monomer battery abnormality recognition model of the current stage of the life cycle to detect abnormal monomer batteries, including Extracting the current voltage kurtosis of the single cell and the current voltage skewness of the single cell from the single cell characteristic curve; Calculating the kurtosis difference between the current voltage skewness and the factory voltage kurtosis of the single cell, and the skewness difference between the current voltage skewness and the factory voltage skewness of the single cell; Determining an abnormality score of a single cell according to the kurtosis difference and the skewness difference; If the abnormality score of the single cell is greater than a set threshold, the single cell is determined to be an abnormal single cell.

9. An abnormal single cell detection device, characterized in that: The method comprises a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, and the program codes are suitable for being loaded and run by the processor to execute the abnormal single cell detection method according to any one of claims 1 to 8.

10. An electric vehicle, characterized in that: It includes the abnormal single cell detection device as claimed in claim 9.

11. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the abnormal single cell detection method according to any one of claims 1 to 8.

Images