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

Abstract

The invention relates to the technical field of batteries, particularly provides a single battery detection method and device, computer equipment and a storage medium, and aims to solve the problem that a detection result of safety failure of a single battery is inaccurate by an existing method. In order to achieve the purpose, the single battery detection method is applied to the power battery, the power battery comprises a plurality of single batteries, and the method comprises the steps that historical data of the power battery is acquired; determining a reference monomer electric quantity based on the historical data; determining a feature image of the single battery based on the reference single electric quantity and the historical data; and based on the feature image of the single battery, judging whether the single battery is a risk single battery. According to the method, the feature image of each single battery is determined based on the historical data of the power battery, so that judgment can be carried out based on the feature images of the single batteries, the abnormal risk single batteries in the power battery are determined, and analysis errors caused by attenuation inconsistency of the single batteries are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of batteries, and specifically provides a method and device for detecting single cells, a computer device, and a storage medium. Background Art

[0002] As the power source of the entire vehicle system of an electric vehicle, the importance of the safety of power batteries is becoming increasingly prominent. As one of the main components of power batteries, the safety of single cells often determines the reliability of power batteries. Currently, there are various solutions for detecting abnormalities in single cells of power batteries. For example, during the battery life cycle, the relative inconsistency of the peak shift of the dv / dq curve of a single cell during the charging process is used to evaluate the abnormal attenuation of the single cell. Or, during the battery life cycle, the relative inconsistency of the differential curve of the relaxation voltage curve at the end of charging is used to evaluate the abnormal lithium plating of the single cell. Or, during the battery life cycle, the DC internal resistance is calculated by current pulses under fixed working conditions, and its inconsistency is compared to evaluate the inconsistency of the change in the internal resistance of the single cell.

[0003] However, due to the very small differences in the external characteristics that characterize the inconsistency of battery attenuation at the mechanism level, it is extremely easy to be submerged by sensor noise during the actual operation of power batteries. In addition, since the external characteristics during the battery life cycle will lose relative comparability with the change of operating conditions, in actual application scenarios, it is also difficult to normalize the external characteristics of single cells among multiple working conditions. Therefore, the results of evaluating single cell abnormalities by the above several solutions are not accurate and comprehensive enough.

[0004] Correspondingly, there is a need in the art for a new single cell abnormality detection solution to solve the above problems. Summary of the Invention

[0005] In order to overcome the above defects, the present application is proposed to provide a solution to solve or at least partially solve the above technical problems.

[0006] In a first aspect, the present application provides a method for detecting a single cell, which is applied to a power battery, the power battery includes a plurality of single cells, and the method includes:

[0007] Obtain historical data of the power battery;

[0008] Determine a reference single cell power based on the historical data;

[0009] Determine a characteristic image of the single cell based on the reference single cell power and the historical data;

[0010] Based on the characteristic image of the single cell, determine whether the single cell is a risk single cell.

[0011] In a technical solution of the above single-cell battery detection method, the historical data includes the power of the single-cell battery during the static stage;

[0012] Determining the reference single-cell power based on the historical data includes:

[0013] Determining the power range of each static stage based on the power of the single-cell battery during the static stage;

[0014] Determining the reference single-cell set based on the power and the power range;

[0015] Determining the reference single-cell power based on the reference single-cell set, where the reference single-cell power is the average value of the single-cell powers in the reference single-cell set for each static stage.

[0016] In a technical solution of the above single-cell battery detection method, determining the characteristic image of the single-cell battery based on the reference single-cell power and the historical data includes:

[0017] Determining a first mapping relationship between the single-cell voltage of the single-cell battery and the reference single-cell power based on the reference single-cell power;

[0018] Determining the characteristic image of the single-cell battery based on the first mapping relationship between the single-cell voltage of the single-cell battery and the reference single-cell power.

[0019] In a technical solution of the above single-cell battery detection method, the historical data includes the single-cell voltage during the static stage;

[0020] Determining the first mapping relationship between the single-cell voltage of the single-cell battery and the reference single-cell power based on the reference single-cell power includes:

[0021] Obtaining a second mapping relationship between the single-cell voltage of the single-cell battery and the reference single-cell power in a preset data period based on the single-cell voltage and the reference single-cell power in the preset data period;

[0022] Performing feature extraction on the second mapping relationship to obtain the first mapping relationship between the single-cell voltage of the single-cell battery and the reference single-cell power.

[0023] In a technical solution of the above single-cell battery detection method, the historical data includes the state of charge;

[0024] The method further includes:

[0025] Dividing the historical data based on the state of charge and a preset state of charge threshold to obtain a plurality of preset data periods, where the state of charge of each preset data period is equal.

[0026] In one technical solution of the above single cell detection method, determining the characteristic image of the single cell based on the first mapping relationship between the single cell voltage and the reference single cell power of the single cell includes:

[0027] Determining an initial image based on the first mapping relationship;

[0028] Performing image superposition on the initial images of each preset data period to obtain the characteristic image.

[0029] In one technical solution of the above single cell detection method, determining the initial image based on the first mapping relationship includes:

[0030] Assigning chromaticity values to the first mapping relationship based on a preset assignment rule;

[0031] Projecting the first mapping relationship after assigning chromaticity values to obtain the initial image of each preset data period of the single cell.

[0032] In a second aspect, a single cell detection device is provided, which is applied to a power battery. The power battery includes a plurality of single cells. The device includes:

[0033] An acquisition module, configured to acquire historical data of the power battery;

[0034] A first determination module, configured to determine a reference single cell power based on the historical data;

[0035] A second determination module, configured to determine the characteristic image of the single cell based on the reference single cell power and the historical data;

[0036] A judgment module, configured to judge whether the single cell is a risk single cell based on the characteristic image of the single cell.

[0037] In a third aspect, a computer device is provided. The computer device includes a processor and a memory. The memory is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the single cell detection method described in any one of the technical solutions of the above single cell detection method.

[0038] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores multiple program codes, and the program codes are adapted to be loaded and run by a processor to execute the single cell detection method described in any one of the technical solutions of the above single cell detection method.

[0039] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:

[0040] The single-cell detection method provided by this application includes: obtaining the historical data of the power battery; determining the reference single-cell power based on the historical data; determining the characteristic image of the single cell based on the reference single-cell power and the historical data; and determining whether the single cell is a risk single cell based on the characteristic image of the single cell. This application first obtains the historical data of the power battery and determines the characteristic image of each single cell in the power battery based on the historical data, which can extract the characteristic performance of each single cell in the entire life cycle of the power battery based on the historical data, providing a more accurate analysis basis for subsequent analysis of whether the single cell is abnormal; furthermore, it can make a judgment based on the characteristic image of the single cell to determine the risk single cell with abnormalities in the power battery, reducing the analysis error caused by the inconsistent attenuation of the single cells, and thus avoiding serious accidents caused by the out-of-control of the power battery due to the safety failure of the single cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Referring to the accompanying drawings, the disclosure of this application will become easier to understand. 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 protection scope of this application. In addition, similar numbers in the drawings are used to represent similar components, where:

[0042] Figure 1 is a schematic flowchart of the main steps of the single-cell detection method according to an embodiment of this application;

[0043] Figure 2 is a schematic diagram of the historical data of the power battery according to an embodiment of this application;

[0044] Figure 3 is a schematic diagram of the reference single-cell power according to an embodiment of this application;

[0045] Figure 4 is a schematic diagram of the second mapping relationship according to an embodiment of this application;

[0046] Figure 5 is a schematic diagram of the first mapping relationship according to an embodiment of this application;

[0047] Figure 6 is a schematic diagram of dividing the preset data period according to an embodiment of this application;

[0048] Figure 7 is a schematic diagram of determining the initial image according to an embodiment of this application;

[0049] Figure 8 is a schematic diagram of superimposing the initial image according to an embodiment of this application;

[0050] Figure 9Schematic diagram of a detection network for judging a feature image according to an embodiment of the present application;

[0051] Figure 10 Schematic diagram of a normal feature image sample according to an embodiment of the present application;

[0052] Figure 11 Schematic diagram of an abnormal feature image sample according to an embodiment of the present application;

[0053] Figure 12 Schematic diagram of the main structure of a single cell detection device according to an embodiment of the present application;

[0054] Figure 13 Schematic diagram of the main structure of a computer device according to an embodiment of the present application.

[0055] List of Reference Signs :

[0056] 10: Acquisition module; 20: First determination module; 30: Second determination module; 40: Judgment module. Detailed implementation manners

[0057] The following describes some implementation manners of the present application with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.

[0058] In the description of the present application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, memories, and may also include a software part, such as program code, 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, in hardware, or in a combination of both. The non-transitory computer-readable storage medium includes any suitable medium for storing program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and so on. The term "A and / or B" represents 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 meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "this" may also include the plural form.

[0059] Due to the very small external feature differences in the battery degradation inconsistency characterized at the mechanism level, it is extremely easy to be submerged by sensor noise during the actual operation of power batteries. Additionally, since the external feature performance of power batteries during the battery life cycle will lose relative comparability with the change of operating conditions, in actual application scenarios, it is also difficult to normalize the external features of single cells among multiple operating conditions. Therefore, the existing evaluation methods for the safety failure detection of single cells in power batteries cannot accurately evaluate the safety failure of single cells.

[0060] The single cell detection method provided by this application includes: obtaining the historical data of the power battery; determining the reference single cell power based on the historical data; determining the characteristic image of the single cell based on the reference single cell power and the historical data; and judging whether the single cell is a risky single cell based on the characteristic image of the single cell. This application first obtains the historical data of the power battery and determines the characteristic image of each single cell in the power battery based on the historical data, which can extract the characteristic performance of each single cell during the entire life cycle of the power battery based on the historical data, providing a more accurate analysis basis for subsequent analysis of whether the single cell is abnormal. Furthermore, it can judge based on the characteristic image of the single cell to determine the risky single cells with abnormalities in the power battery, reducing the analysis error caused by the inconsistency of single cell degradation and avoiding serious accidents caused by the out-of-control of the power battery due to the safety failure of the single cell.

[0061] Refer to the appendix Figure 1 , Figure 1 which is a schematic diagram of the main steps of the single cell detection method according to an embodiment of this application.

[0062] As Figure 1 shown, the single cell detection method in the embodiment of this application is applied to a power battery, and the power battery includes multiple single cells. The method mainly includes the following steps S101 - step S104.

[0063] Step S101: Obtain the historical data of the power battery.

[0064] A power battery is composed of several single cells, a CSC information acquisition system, a battery management control unit (BMU), a battery high-voltage distribution unit, a cooling system, etc. A single cell is the smallest unit that constitutes a power battery and is composed of a positive electrode, a negative electrode, an organic electrolyte, etc. Several single cells are connected in parallel to form a battery module, several battery modules are connected in series to form a battery unit, and then several battery units are connected in series to form the total assembly of the power battery. In this embodiment, the historical data of the power battery can be the full life cycle data of the power battery, that is, the historical data from the battery leaving the factory to the present.

[0065] Step S102: Determine the reference single cell power based on the historical data.

[0066] In this embodiment, a reference single-cell power is determined based on the historical data of the power battery. The reference single-cell power may be the power of a relatively average single battery in the power battery.

[0067] Step S103: Determine the characteristic image of the single battery based on the reference single-cell power and the historical data.

[0068] In this embodiment, the characteristic images of each single battery in the power battery are determined based on the reference single-cell power and the historical data of the power battery, so as to further understand the characteristic performance of each single battery in the power battery during the entire life cycle of the power battery.

[0069] Step S104: Determine whether the single battery is a risk single battery based on the characteristic image of the single battery.

[0070] In this embodiment, it is determined whether the single battery is abnormal based on the characteristic image of the single battery, and whether the single battery is a risk single battery is determined according to the determination result.

[0071] Based on the above steps S101 - S104, the present application first obtains the historical data of the power battery, and determines the characteristic images of each single battery in the power battery based on the historical data, and can extract the characteristic performance of each single battery in the entire life cycle of the power battery based on the historical data, providing a more accurate analysis basis for subsequent analysis of whether the single battery is abnormal; furthermore, it can be determined based on the characteristic image of the single battery, and the risk single battery with abnormalities in the power battery is determined, reducing the analysis error caused by the inconsistent attenuation of the single battery, and avoiding serious accidents caused by the out-of-control of the power battery due to the safety failure of the single battery.

[0072] The above steps S101 and S104 will be further described below.

[0073] For step S101, obtain the historical data of the power battery.

[0074] Specifically, the historical data of the power battery may be the usage data of the entire life cycle of the power battery, that is, the data of the power battery from factory to present. Exemplarily, as Figure 2 shown, the entire life cycle of the power battery is divided into several stages. The obtained historical data of the power battery includes a charging stage, a discharging stage, and a static stage. The charging stage is the charging period when the power battery is charging, the discharging stage is the discharging period when the power battery is working, and the static stage is the static period when the power battery is not working. By obtaining the historical data of the power battery, more comprehensive data support can be provided for subsequent extraction of the characteristic performance of the single battery, improving the reliability of single battery detection.

[0075] The above is the description of step S101. Next, further description of step S102 will be continued.

[0076] Regarding step S102, the historical data includes the power of the single cell during the static stage; determining the reference single cell power based on the historical data includes: determining the power range of each static stage based on the power of the single cell during the static stage; determining the reference single cell set based on the power and the power range; determining the reference single cell power based on the reference single cell set, and the reference single cell power is the average value of the single cell powers in the reference single cell set for each static stage.

[0077] The power of the single cell during the static stage can be determined by the relationship curve between the single cell voltage and the power and the open circuit voltage (SOC-OCV). The single cell voltage is the open circuit voltage OCV. The power SOC of the single cell corresponding to the single cell voltage is determined in the relationship curve between the power and the open circuit voltage through the single cell voltage.

[0078] Specifically, first, sort the powers of all single cells in each static stage from high to low to obtain the power sequences of multiple static stages. Take the median in the power sequence of each static stage. The median is the value in the middle position of a set of data arranged in order, and then obtain the power medians of multiple static stages. Determine the power range of each static stage based on the preset range of the power median of each static stage. The preset range can be the power median ±2%. For example, if the determined power median is 60%, then when determining the range, 60% minus 2% can be used to determine the lower limit, and 60% plus 2% can be used to determine the upper limit, so the determined power range is 58% to 62%.

[0079] Then, use the power range of each static stage to find the single cells whose powers are within this power range among all single cells in the corresponding static stage, obtain the set of single cells that meet the conditions for each static stage, take the intersection of the sets of single cells of all static stages to obtain the reference single cell set, and finally use the average value of the powers of all single cells in the reference single cell set in each static stage to determine the reference single cell power for each static stage. Exemplarily, as Figure 3 shown, each static stage has a reference single cell power (SOC).

[0080] By finding the single cells whose powers are within the power range in the static stage of the historical data of the power battery, and then forming the reference single cell set of the entire power battery by the intersection of these single cells, the single cells in the reference single cell set are the single cells whose characteristic performances are all at the medium level during the entire life cycle of the power battery. Determining the reference single cell power for each static stage based on the reference single cell set reduces the sampling noise to a certain extent.

[0081] Regarding step S103, determining the characteristic image of the single cell based on the reference single cell power and the historical data includes: determining a first mapping relationship between the single cell voltage of the single cell and the reference single cell power based on the reference single cell power; and determining the characteristic image of the single cell based on the first mapping relationship between the single cell voltage of the single cell and the reference single cell power.

[0082] Specifically, based on the reference single cell power of each rest stage and the single cell voltages of all single cells in the power battery during the corresponding rest stage, a first mapping relationship between the single cell voltage of the single cell and the reference single cell power is determined, and then the characteristic image of the single cell is determined through the first mapping relationship between the single cell voltage of the single cell and the reference single cell power. By analyzing the historical data of the power battery, the reference single cell power is obtained, and the characteristic image of each single cell is determined based on the reference single cell power, so that the characteristic performance of each single cell in the power battery during the entire life cycle of the power battery can be known.

[0083] In some embodiments, the historical data includes the single cell voltage during the rest stage; determining the first mapping relationship between the single cell voltage of the single cell and the reference single cell power based on the reference single cell power includes: obtaining a second mapping relationship between the single cell voltage and the reference single cell power in a preset data period based on the single cell voltage and the reference single cell power in the preset data period; and performing feature extraction on the second mapping relationship to obtain the first mapping relationship between the single cell voltage and the reference single cell power.

[0084] Specifically, the single cell voltage during the rest stage is the open circuit voltage of the single cell. The second mapping relationship of the single cell is obtained through the reference single cell power and the single cell voltage of each rest stage in the preset data period. The second mapping relationship is a mapping relationship between the reference single cell power and the single cell voltage during the rest stage, and the second mapping relationship can be represented in the form of a curve, a table, etc., which is not limited here.

[0085] In some specific embodiments, taking the single cell voltage as the abscissa and the reference single cell power as the ordinate, the coordinate point positions of each rest stage are determined through the reference single cell power and the single cell voltage of each rest stage, and then the coordinate point positions of the single cell are filtered. The adaptive filter can be used for filtering according to needs. The voltages corresponding to the coordinate point positions are input into the adaptive filter from high to low, and the adaptive filter outputs a relatively smooth curve, and the obtained curve is used as the second mapping relationship.

[0086] Exemplarily, such as Figure 4As shown, in this embodiment, the historical data is divided into three preset data periods based on the charging depth and the preset charging depth threshold, and the charging depth of each preset data period is equal. According to the reference single cell power and the single cell voltage in the static stage of each preset data period, the second mapping relationship of each preset data period of the single cell is determined, and the second mapping relationship is represented in the form of a curve.

[0087] Then, feature extraction is performed on the second mapping relationship of the single cell battery to obtain the first mapping relationship of the single cell battery. The first mapping relationship is the mapping relationship after feature extraction of the second mapping relationship. Feature extraction can be to differentiate the second mapping relationship. The morphological features of the curve after differentiation are more obvious, which is conducive to the subsequent judgment of the feature image. The first mapping relationship can be expressed in the form of curves, tables, etc., which is not limited here.

[0088] In this embodiment, when the second mapping relationship is represented by a curve of reference single cell power and single cell battery voltage, the curve of reference single cell power and single cell battery voltage is differentiated to obtain a differential curve of reference single cell power and single cell battery voltage, and the differential curve is used as the first mapping relationship of the single cell battery. It can be understood that the reduction in the peak value of the differential curve of reference single cell power and single cell battery voltage reflects that the battery capacity attenuation is strongly correlated with the safety of the single cell battery.

[0089] For example, Figure 5 As shown, in this embodiment, the second mapping relationship of the single cell battery is represented by a curve of the reference single cell battery capacity and the single cell battery voltage. After differentiating the curve of the reference single cell battery capacity and the single cell battery voltage, a differential curve of the reference single cell battery capacity and the single cell battery voltage is obtained, and the differential curve is used as the first mapping relationship of the single cell battery.

[0090] In some embodiments, the historical data includes a charging depth; the method further includes: dividing the historical data based on the charging depth and a preset charging depth threshold to obtain a plurality of preset data periods, wherein the charging depth of each preset data period is equal.

[0091] Specifically, the depth of charge is the ratio of the amount of electricity received by the power battery from the external circuit during the charging process to the amount of electricity when the power battery is fully charged. For example, if the power battery is currently charged at 20%, and it is charged from 20% to 100%, the depth of charge is 80%. In this embodiment, by setting a preset depth of charge threshold, the historical data is divided into multiple preset data periods, and each preset data period after division contains multiple static stages, and the depth of charge of each preset data period is equal.

[0092] For example, Figure 6As shown, in some specific embodiments, first, the static stage in the historical data of the power battery is retained. Then, according to a preset charge depth threshold, the historical data is divided into multiple preset data cycles. Each of the divided preset data cycles contains multiple static stages, and the charge depth of each preset data cycle is equal. In this embodiment, the historical data is divided into 3 preset data cycles.

[0093] In some embodiments, determining the characteristic image of the single battery based on the first mapping relationship between the single battery voltage and the reference single battery charge of the single battery includes: determining an initial image based on the first mapping relationship; performing image superposition on the initial images of each preset data cycle to obtain the characteristic image.

[0094] Specifically, first, the first mapping relationship of the single battery is converted into an image to obtain the initial image of the single battery. Then, all the initial images of the single battery in each preset data cycle obtained are superimposed into one image, and the superimposed image is used as the characteristic image of the single battery. This characteristic image can reflect the characteristic performance of the same single battery throughout the life cycle of the power battery.

[0095] In some embodiments, determining the initial image based on the first mapping relationship includes: assigning a chromaticity value to the first mapping relationship based on a preset assignment rule; projecting the first mapping relationship after assigning the chromaticity value to obtain the initial image of each preset data cycle of the single battery.

[0096] Specifically, the order of the preset data cycles is determined based on the time sequence of the historical data, and based on the order of the preset data cycles and the preset assignment rule, the first mapping relationship of the single battery in each preset data cycle is assigned a chromaticity value. The preset assignment rule can be set according to the number of preset data cycles, the time sequence, and the preset chromaticity value.

[0097] In some specific embodiments, the preset chromaticity values of the preset assignment rule are the green and red of the RGB chromaticity values. The RGB chromaticity value of green is (0, 255, 0), and the RGB chromaticity value of red is (255, 0, 0). When assigning a chromaticity value to the first mapping relationship of the preset data cycle, first, the horizontal coordinate scale of the first mapping relationship is set to 1 millivolt, and the vertical coordinate scale is set to 0.1. Then, the chromaticity value of each preset data cycle is determined according to the preset assignment rule, and the pixel size of the bitmap is set according to the relationship curve between the charge and the open-circuit voltage (SOC-OCV). The first mapping relationship is projected onto the horizontal axis to obtain the pixel matrix of the first mapping relationship of each preset data cycle. In this embodiment, the shaded area of the projection is used as the charge of the single battery.

[0098] Then, the pixel matrix of the first mapping relationship of each preset data period is assigned colors based on the corresponding chromaticity values using the HSV model (Hue, Saturation, Value). When assigning colors, only the Hue is modified. The brightness of all images is equal, and the sum of the brightness weights of all preset data periods is 1. The initial image of the preset data period finally obtained shows a color effect where, according to the time change from early to late, the green component gradually weakens and the red component gradually increases.

[0099] Exemplarily, as Figure 7 shown, the order of the preset data periods is determined based on the chronological order of the historical data. Based on the order of the preset data periods and the preset assignment rules, the chromaticity values are assigned to the first mapping relationship of the single battery in 3 preset data periods. In this embodiment, the chromaticity value of the first preset data period determined according to the preset assignment rules is green (0, 255, 0), the chromaticity value of the second preset data period is (255 / 3, 255*2 / 3, 0), and the chromaticity value of the third preset data period is (255, 0, 0). The first mapping relationship is projected in the horizontal axis direction to obtain the pixel matrices of the first mapping relationship of the three preset data periods. Then, the pixel matrices of the first mapping relationship of the three preset data periods are respectively assigned colors based on the corresponding chromaticity values using the HSV model (Hue, Saturation, Value). When assigning colors, only the Hue is modified. The brightness of all images is equal, and the sum of the brightness weights of all preset data periods is 1. The brightness weights of the 3 preset data periods in this embodiment are all 1 / 3. Finally, the initial images of the three preset data periods show a color effect where, according to the time change from early to late, the green component gradually weakens and the red component gradually increases.

[0100] Exemplarily, as Figure 8 shown, in some embodiments, image superposition is performed on the initial image of each preset data period to obtain a feature image, including: superimposing the 3 initial images of the single battery obtained in 3 preset data periods into one image, and using the superimposed image as the feature image of the single battery.

[0101] The above is the description of step S103. Next, step S104 will be further described.

[0102] Regarding step S104, based on the feature image of the single battery, it is determined whether the single battery is a risk single battery.

[0103] Exemplarily, as Figure 9As shown, in some embodiments, by inputting the characteristic image of a single battery into a pre-trained detection network, the detection network outputs the result of whether the single battery is a risky single battery. By analyzing the characteristic image of the single battery through the detection network, big data identification is realized to replace manual confirmation, improving the identification efficiency and increasing the amount of reference data.

[0104] In some embodiments, before inputting the characteristic image of the single battery into the detection network, the method further includes: obtaining a sample of characteristic images, where the sample of characteristic images includes a normal characteristic image sample and an abnormal characteristic image sample; training a convolutional neural network based on the sample of characteristic images to obtain a detection network, and the detection network is used to predict abnormal risky single batteries.

[0105] Specifically, multiple samples of characteristic images are collected in advance. Among the multiple samples of characteristic images, there are normal characteristic image samples (as Figure 10 shown) and abnormal characteristic image samples (as Figure 11 shown). The multiple samples of characteristic images are input into a CNN convolutional neural network for supervised model training. When the convolutional neural network recognizes a normal characteristic image sample, the output is 0, and when it recognizes an abnormal characteristic image sample, the output is 1. After completing the model training, a detection network is obtained. The detection network can be used to predict the characteristic image of the single battery, and then determine the risky single battery with abnormal attenuation based on the output result.

[0106] Further, the present application can also upload the first mapping relationship of the single battery from the vehicle end to the cloud server. The cloud server stores the first mapping relationship and executes the detection task of the single battery detection method.

[0107] It should be noted that although the above steps are described in a specific order in the above embodiments, those skilled in the art can understand that in order to achieve the effects of the present application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these changes are all within the protection scope of the present application.

[0108] Furthermore, the present application also provides a single battery detection device.

[0109] Referring to the appendix Figure 12 , Figure 12 is the main structural schematic diagram of the single battery detection device according to an embodiment of the present application.

[0110] As Figure 12As shown in the figure, the single battery detection device in the embodiments of the present application mainly includes an acquisition module 10, a first determination module 20, a second determination module 30, and a judgment module 40. In some embodiments, one or more of the acquisition module 10, the first determination module 20, the second determination module 30, and the judgment module 40 may be combined into one module. In some embodiments, the acquisition module 10 may be configured to acquire the historical data of the power battery. The first determination module 20 may be configured to determine the reference single battery power based on the historical data. The second determination module 30 may be configured to determine the characteristic image of the single battery based on the reference single battery power and the historical data. The judgment module 40 may be configured to judge whether the single battery is a risk single battery based on the characteristic image of the single battery. In one implementation manner, the description of the specific implementation functions may refer to the steps S101 - S104 of the single battery detection method.

[0111] The above single battery detection device is used to execute Figure 1 the single battery detection method embodiments shown in the figure. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process and related descriptions of the single battery detection device can refer to the content described in the embodiments of the single battery detection method, which will not be elaborated here.

[0112] Those skilled in the art can understand that all or part of the processes of the methods in the above embodiments of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code. It should be noted that the content included 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, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0113] Referring to the attached Figure 13 , Figure 13 is the main structural schematic diagram of a computer device embodiment according to the present application.

[0114] AsFigure 13 As shown in the figure, the computer device in the embodiment of the present application mainly includes a memory 11 and a processor 12. The memory 11 can be configured to store a program for executing the single-cell battery detection method in the above method embodiment, and the processor 12 can be configured to execute the program in the memory 11. This program includes, but is not limited to, the program for executing the single-cell battery detection method in the above method embodiment. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of the present application.

[0115] In the embodiment of the present application, the computer device can be a computer device formed by various electronic devices. In some possible implementation manners, the computer device can include multiple memories 11 and multiple processors 12. And the program for executing the single-cell battery detection method in the above method embodiment can be divided into multiple sub-programs, and each sub-program can be loaded and run by the processor to execute different steps of the single-cell battery detection method in the above method embodiment. Specifically, each sub-program can be stored in a different memory 11 respectively, and each processor 12 can be configured to execute the program in one or more memories 11 to jointly implement the single-cell battery detection method in the above method embodiment, that is, each processor 12 respectively executes different steps of the single-cell battery detection method in the above method embodiment to jointly implement the single-cell battery detection method in the above method embodiment.

[0116] The above multiple processors 12 can be processors deployed on the same device. For example, the above computer device can be a high-performance device composed of multiple processors, and the above multiple processors 12 can be the processors configured on the high-performance device. In addition, the above multiple processors 12 can also be processors deployed on different devices. For example, the above computer device can be a server cluster, and the above multiple processors 12 can be the processors on different servers in the server cluster.

[0117] Furthermore, the present application also provides a computer-readable storage medium. In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the single-cell battery detection method in the above method embodiment. This program can be loaded and run by the processor to implement the single-cell battery detection method. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-transitory computer-readable storage medium.

[0118] Furthermore, it should be understood that since the settings of the respective modules are only for illustrating the functional units of the device of the present application, the physical devices corresponding to these modules can 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 illustrative.

[0119] Those skilled in the art can understand that the respective modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principle of the present application. Therefore, the technical solutions after splitting or combining will all fall within the protection scope of the present application.

[0120] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, 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 all fall within the protection scope of the present application.

Claims

1. A method for detecting a single cell, applied to a power battery, the power battery including a plurality of single cells, characterized in that, The method includes: Obtaining historical data of the power battery; Determining a reference single-cell state of charge based on the historical data; Determining a characteristic image of the single cell based on the reference single-cell state of charge and the historical data; Judging whether the single cell is a risky single cell based on the characteristic image of the single cell.

2. The method for detecting a single cell according to claim 1, characterized in that, The historical data includes the state of charge during the static stage of the single cell; The determining the reference single-cell state of charge based on the historical data includes: Determining a state-of-charge range for each static stage based on the state of charge during the static stage of the single cell; Determining a reference single-cell set based on the state of charge and the state-of-charge range; Determining a reference single-cell state of charge based on the reference single-cell set, where the reference single-cell state of charge is the average value of the state of charge of the single cells in the reference single-cell set for each static stage.

3. The method for detecting a single cell according to claim 1, characterized in that, The determining the characteristic image of the single cell based on the reference single-cell state of charge and the historical data includes: Determining a first mapping relationship between the single-cell voltage of the single cell and the reference single-cell state of charge based on the reference single-cell state of charge; Determining the characteristic image of the single cell based on the first mapping relationship between the single-cell voltage of the single cell and the reference single-cell state of charge.

4. The method for detecting a single cell according to claim 3, characterized in that, The historical data includes the single-cell voltage during the static stage; The determining the first mapping relationship between the single-cell voltage of the single cell and the reference single-cell state of charge based on the reference single-cell state of charge includes: Obtaining a second mapping relationship between the single-cell voltage and the reference single-cell state of charge for a preset data period based on the single-cell voltage and the reference single-cell state of charge in the preset data period; Performing feature extraction on the second mapping relationship to obtain the first mapping relationship between the single-cell voltage and the reference single-cell state of charge.

5. The method for detecting a single cell according to claim 4, characterized in that, The historical data includes the depth of charge; The method further includes: Dividing the historical data based on the depth of charge and a preset depth-of-charge threshold to obtain a plurality of preset data periods, where the depth of charge of each preset data period is equal.

6. The method for detecting a single cell according to claim 4, characterized in that, The determining the characteristic image of the single cell based on the first mapping relationship between the single-cell voltage of the single cell and the reference single-cell state of charge includes: Determining an initial image based on the first mapping relationship; Performing image superposition on the initial images for each preset data period to obtain the characteristic image.

7. The method for detecting a single cell according to claim 6, characterized in that, The determining the initial image based on the first mapping relationship includes: Assigning a chromaticity value to the first mapping relationship based on a preset assignment rule; Performing projection on the first mapping relationship after the chromaticity value is assigned to obtain the initial image of the single cell for each preset data period.

8. A device for detecting a single cell, applied to a power battery, the power battery including a plurality of single cells, characterized in that, The device includes: An obtaining module, configured to obtain historical data of the power battery; A first determining module, configured to determine a reference single-cell state of charge based on the historical data; A second determining module, configured to determine a characteristic image of the single cell based on the reference single-cell state of charge and the historical data; A judging module, configured to judge whether the single cell is a risky single cell based on the characteristic image of the single cell.

9. A computer device, comprising at least one processor and at least one memory, the memory being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to execute the single-cell detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, in which a plurality of program codes are stored, characterized in that, The program code is adapted to be loaded and run by a processor to execute the single cell detection method according to any one of claims 1 to 7.

Images