Battery consistency detection method, detection device, computer device and storage medium

Abstract

The present application discloses a method for detecting battery consistency, comprising: receiving battery status data; performing a first processing on the battery status data to select first battery status data under a predetermined working condition; and calculating the current consistency difference between different battery cells in the battery based on the first battery status data. In the battery consistency detection method of the present application, based on the received battery status data, after pre-processing the data, the first battery status data under a predetermined working condition is selected to calculate the current consistency difference between different battery cells in the battery, thereby realizing the detection of battery consistency. The battery consistency detection can be performed without waiting for the battery to be in a specific state, which has strong applicability, increases the chance of estimating battery consistency, and can identify consistency differences in the battery more promptly, thereby performing balancing processing and reducing battery safety hazards.

Description

Technical Field

[0001] The present application relates to the field of batteries, and more specifically, to a battery consistency detection method, detection device, computer equipment, and computer-readable storage medium. Background Art

[0002] With the development of new energy vehicles, safety and battery life are two of the most important concerns for consumers. For battery life, battery cell consistency is a key indicator. Poor consistency between different battery cells in a power battery can lead to reduced battery life and may even cause thermal runaway. Therefore, consistency testing between battery cells is of great significance to both vehicle safety and battery life. Summary of the Invention

[0003] In view of the above problems, the present application provides a battery consistency detection method, detection device, computer equipment and computer-readable storage medium.

[0004] This application provides a battery consistency detection method, including:

[0005] Receive battery status data;

[0006] performing a first processing on the battery status data to select first battery status data under a predetermined operating condition;

[0007] The current consistency differences of different battery cells in the battery are calculated based on the first battery status data.

[0008] In the battery consistency detection method of the present application, after pre-processing the received battery status data, the first battery status data under a predetermined operating condition is selected to calculate the current consistency difference between different battery cells in the battery, thereby realizing the consistency detection of the battery. The detection method of the present application can detect battery consistency without waiting for the battery to be in a specific state, which is highly applicable, increases the opportunity to estimate battery consistency, and can more promptly identify consistency differences in the battery, thereby performing equalization processing and reducing battery safety risks.

[0009] In some embodiments, performing a first processing on the battery status data to select first battery status data under a predetermined operating condition includes:

[0010] Sorting the battery status data according to reporting time;

[0011] Abnormal data processing is performed on the battery status data after the sorting process.

[0012] Thus, for the battery status data, relevant preprocessing is first performed on the data, such as sorting and screening, to eliminate the influence of abnormal data on consistency detection caused by communication reasons and improve the accuracy of calculation.

[0013] In some embodiments, performing a first processing on the battery status data to select first battery status data under a predetermined operating condition includes:

[0014] According to the predetermined operating condition identifier, first battery status data under the predetermined operating condition is selected from the battery status data after the abnormal data processing.

[0015] In this way, a stable operating condition suitable for battery consistency detection is selected from the processed data, and the battery consistency is calculated using the first battery state data under the operating condition.

[0016] In some embodiments, calculating the consistency difference of different battery cells in the battery according to the first battery status data includes:

[0017] Calculating a change relationship of a voltage change value corresponding to a unit state of charge of each battery cell under a predetermined operating condition;

[0018] According to the corresponding change relationship of different battery cells, the consistency difference of different battery cells is calculated.

[0019] In this way, based on the first battery status data, the change relationship of the voltage change value corresponding to the unit state of charge of each battery cell in the battery under a predetermined operating condition is calculated, and the consistency difference between different battery cells is calculated based on the change relationship corresponding to each battery cell.

[0020] In certain embodiments, calculating the consistency difference of different battery cells according to the change relationship corresponding to different battery cells includes:

[0021] According to the change relationship, selecting the maximum value of the voltage change value of each battery cell in a predetermined state of charge interval;

[0022] The charge states corresponding to the maximum values of the voltage variation values of different battery cells are compared, so as to obtain the consistency difference between the different battery cells.

[0023] In this way, the maximum value of the voltage change value in the predetermined state of charge range in the change relationship of each battery cell is selected as the feature point, and the state of charge corresponding to the feature points corresponding to different battery cells is compared to obtain the consistency difference results between the corresponding battery cells and complete the current detection.

[0024] In certain embodiments, the method further comprises:

[0025] When the accumulated number of historical data of battery consistency detection is less than a predetermined number, the consistency difference at that time is used as the detection result of the battery consistency.

[0026] In this way, when there is less historical test data, the calculation result of the consistency difference at that time can be directly used as the test result.

[0027] In certain embodiments, the method further comprises:

[0028] When the accumulated number of historical data of battery consistency detection is greater than or equal to a predetermined number, the battery consistency detection result is obtained according to the historical data and the current consistency difference.

[0029] In this way, considering that there may be errors when only the calculation results of the consistency difference at that time are used as the detection results, after accumulating a certain amount of historical data, the historical data and the calculation results of the consistency difference at that time can be combined to obtain the consistency detection results together, reducing the impact of the single calculation noise error on the results, making the calculation results more accurate.

[0030] In certain embodiments, when the cumulative number of historical data of battery consistency detection is greater than or equal to a predetermined number, obtaining the battery consistency detection result based on the historical data and the current consistency difference includes:

[0031] Regression fitting is performed on the historical data and the current consistency difference to obtain the battery consistency detection result.

[0032] In this way, the regression fitting method can be used to combine historical calculation results to correct the current results, reduce the impact of single calculation error noise, and make the calculation results more accurate.

[0033] In certain embodiments, performing regression fitting on the historical data and the current consistency difference to obtain the battery consistency test result includes:

[0034] Performing regression fitting on the historical data and the current consistency difference using a predetermined regression algorithm to obtain a regression curve with a minimum cost function;

[0035] A calibration value is obtained according to the regression curve, thereby obtaining the battery consistency detection result.

[0036] In this way, regression fitting methods such as linear regression and support vector regression can be used, and the cost function can be used to determine the regression curve, and further obtain the calibration value for the current calculation result, that is, the value after regression fitting, so as to obtain the battery consistency detection result, making the detection result more accurate.

[0037] The present application provides a battery consistency detection device, the detection device comprising:

[0038] A communication module, configured to receive battery status data;

[0039] a processing module, configured to perform a first processing on the battery status data to select first battery status data under a predetermined operating condition;

[0040] A calculation module is used to calculate the consistency difference of different battery cells in the battery according to the first battery status data.

[0041] The present application also provides a computer device, which includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned detection method is implemented.

[0042] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the above-mentioned detection method is implemented.

[0043] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0045] Figure 1 is a flowchart of a method for detecting battery consistency according to certain embodiments of the present application;

[0046] Figure 2 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0047] Figure 3 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0048] Figure 4 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0049] Figure 5 is a charging voltage curve of certain embodiments of the present application;

[0050] Figure 6 is a charging voltage differential curve of certain embodiments of the present application;

[0051] Figure 7 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0052] Figure 8 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0053] Figure 9 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0054] Figure 10 is a schematic flow chart of a detection method according to certain embodiments of the present application;

[0055] Figure 11 is a schematic diagram of a module of a detection device according to certain embodiments of the present application;

[0056] Figure 12 This is a schematic diagram of the connection status of a computer-readable storage medium and a processor in certain embodiments of the present application. DETAILED DESCRIPTION

[0057] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0059] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0060] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0062] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0063] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0064] As the market share of new energy vehicles continues to rise, the proportion of consumers choosing new energy vehicles as their first car is also increasing. For new energy vehicles, safety and battery life are the two aspects that consumers are most concerned about. The consistency of power battery cells is a key indicator of vehicle battery life. Poor consistency between battery cells will lead to reduced battery life. Therefore, it is necessary to identify battery cells with poor consistency and use balancing control to maintain the overall battery consistency within a certain range. In addition, battery consistency affects the battery's charge and discharge depth, which in turn leads to overcharging and overdischarging, shortening battery life, and overcharging can also cause the risk of thermal runaway. Therefore, battery consistency is of great significance to both safety and battery life.

[0065] During the operation of new energy vehicles, single cells are often connected in series and parallel to form a single battery to meet the vehicle's power needs. Since batteries contain multiple single cells, inconsistent consistency between each cell can seriously affect the battery's capacity, energy, voltage drop, range, and service life, thereby affecting the user experience during use. The reasons for battery consistency differences are, on the one hand, the influence of various factors during the battery manufacturing process. The individual cells themselves have certain differences, which are usually manifested in characteristics such as capacity, internal resistance, self-discharge rate, voltage plateau, and charge-discharge curves. On the other hand, the different positions of each cell in the battery and the different operating environments, such as slightly different temperatures, can cause battery inconsistency over time. In related technologies, static consistency is usually considered when selecting battery cell groups, and dynamic consistency is estimated under certain conditions during use. Typically, dynamic consistency estimation requires that the battery's state of charge (SOC) (remaining capacity) is low and in a balanced state. For example, the battery's SOC must be less than 30% and the battery must have been left at rest for at least three hours before the battery's consistency can be estimated. However, this will result in fewer opportunities to calculate battery consistency, leading to an inability to timely update consistency between different battery cells. Understandably, if battery consistency differences are large and there are insufficient calculation opportunities, these differences cannot be identified, and the battery management system will be unable to perform balancing operations to reduce consistency differences. This can lead to shortened battery life and may also cause overcharging and over-discharging, leading to safety issues such as thermal runaway.

[0066] Based on this, the applicant has conducted in-depth research and designed a battery consistency detection method. Based on the reported battery status data, the data under the predetermined working conditions are selected from the data to calculate the battery consistency difference of different battery cells. The battery consistency detection can be performed without relying on specific conditions (low SOC, predetermined static time). This provides more battery consistency calculation opportunities, better monitors the battery status, and timely balances the battery according to the consistency difference to reduce the battery consistency difference.

[0067] The battery cells disclosed in the embodiments of the present application can be used in electrical devices that use batteries as power sources or various energy storage systems that use batteries as energy storage elements. Electrical devices can include, but are not limited to, mobile phones, tablets, laptops, electric toys, electric tools, battery cars, electric cars, ships, spacecraft, etc. Among them, electric toys can include fixed or mobile electric toys, such as game consoles, electric car toys, electric ship toys, and electric airplane toys, etc., and spacecraft can include airplanes, rockets, space shuttles, and spacecraft, etc. For convenience of explanation, the following embodiments are described using a vehicle as an example of an electrical device. The vehicle can be a fuel vehicle, a gas vehicle, or a new energy vehicle. The new energy vehicle can be a pure electric vehicle, a hybrid vehicle, or an extended-range vehicle, etc. A battery is provided inside the vehicle, and the battery can be provided at the bottom, head, or tail of the vehicle. The battery can be used to power the vehicle, for example, the battery can serve as the operating power source of the vehicle. The vehicle can also include a controller and a motor, and the controller is used to control the battery to power the motor, for example, for starting, navigating, and operating power requirements of the vehicle during driving. In addition, the battery can also serve as the driving power source of the vehicle, replacing or partially replacing fuel or natural gas to provide driving power for the vehicle.

[0068] See also Figure 1 , this application provides a battery consistency detection method, comprising the following steps:

[0069] 01: Receive battery status data;

[0070] 02: performing a first processing on the battery status data to select first battery status data under a predetermined working condition;

[0071] 03: Calculate the consistency difference of different battery cells in the battery based on the first battery status data.

[0072] Specifically, the method of the present application can be implemented by a computer device that communicates with the vehicle, such as a vehicle server in the cloud. The vehicle can periodically report battery status data, or report battery status data to the server in response to a data reporting request sent by the server.

[0073] Battery status data may include data collection time, current, minimum voltage, maximum voltage, and charging status flag of each battery cell. The charging status flag is a data field. When the battery is charging, the battery management system sets the variable corresponding to this flag to a certain value. For example, it is set to 1 when the battery is charging and to 0 when the battery is not charging. Therefore, the charging status flag can be used to determine whether the battery is currently charging.

[0074] Understandably, during data communication transmission, some data may be reported missing, uploaded repeatedly, or uploaded in an out-of-order manner due to network issues. Therefore, before performing battery consistency calculation, the reported battery status data needs to be processed first.

[0075] The first processing is the pre-processing of the reported battery status data before the consistency calculation, so that the data that may have abnormalities can be used for the consistency calculation after processing.

[0076] The operating conditions of the battery may include charging conditions, as well as discharging conditions in various usage environments. Among them, the predetermined operating condition refers to the operating condition where the battery status data is stable, such as the charging condition. In one example, the first processed data can be filtered according to the charging flag, the data can be divided into charging condition data and non-charging condition data, and the charging condition data can be filtered. Furthermore, it can be based on the length of time a charging condition usually lasts, such as 2 hours, 3 hours, etc. In the filtered charging condition data, further, complete charging condition data in units of times is obtained, that is, the first battery status data.

[0077] Furthermore, the consistency differences between different batteries can be calculated based on the data from different battery cells under the same complete charging cycle. The consistency difference for that time is also the battery consistency calculated for that time. This difference is only used to distinguish historical data from consistency testing, and does not limit the results of a one-time difference calculation.

[0078] In summary, the battery consistency detection method of the present application, based on the received battery status data, after pre-processing the data, selects the first battery status data under a predetermined operating condition to calculate the current consistency difference between different battery cells in the battery, thereby realizing the consistency detection of the battery. The detection method of the present application can detect battery consistency without waiting for the battery to be in a specific state, has strong applicability, increases the opportunity to estimate battery consistency, and can more promptly identify consistency differences in the battery, thereby performing equalization processing and reducing battery safety hazards.

[0079] See also Figure 2 In some embodiments, step 02 includes:

[0080] 021: Sort the battery status data according to the reporting time;

[0081] 022: Perform abnormal data processing on the sorted battery status data.

[0082] Specifically, as mentioned above, during data communication and transmission, some data may be reported missing, uploaded repeatedly, or uploaded out of sequence due to network issues. Therefore, before performing battery consistency calculations, the reported battery status data must first be processed. This first processing specifically includes sorting and abnormal data processing.

[0083] Sorting can effectively resolve data upload issues caused by out-of-order data. Sorting can restore data that may have been stored out of order. Sorting can arrange data in chronological order based on when it was collected.

[0084] After sorting, abnormal data processing is performed, and abnormal data may be duplicate values, obvious abnormal values, missing values, etc. After eliminating these abnormal data, usable data is obtained, and further processing is performed to screen out the first battery status data under the predetermined working condition.

[0085] Thus, for the battery status data, relevant preprocessing is first performed on the data, such as sorting and screening, to eliminate the influence of abnormal data on consistency detection caused by communication reasons and improve the accuracy of calculation.

[0086] See also Figure 3 In some embodiments, step 02 includes:

[0087] 023: Selecting first battery status data under a predetermined operating condition from the battery status data after abnormal data processing according to the predetermined operating condition identifier.

[0088] Specifically, the reported battery status data, after the sorting process and abnormal data processing as mentioned above, needs to be further screened for data under working conditions suitable for consistency detection. Specifically, it is necessary to select working conditions with stable data status, such as charging conditions. As mentioned above, the reported battery status data includes a charging flag bit, and the data after abnormal processing is divided according to the charging flag bit, and the data is divided into charging condition data and non-charging condition data. And further, the charging condition data is divided into multiple complete charging conditions. Among them, the complete working condition can be divided by time length. For example, data with an interval time of 2 hours between data can be considered as data within a complete charging condition, that is, the first battery status data is determined.

[0089] In this way, a stable operating condition suitable for battery consistency detection is selected from the processed data, and the battery consistency is calculated using the first battery state data under the operating condition.

[0090] See also Figure 4 In some embodiments, step 03 includes:

[0091] 031: Calculate the voltage change relationship of each battery cell corresponding to the unit state of charge under a predetermined operating condition;

[0092] 032: Based on the corresponding change relationship of different battery cells, calculate the consistency difference of different battery cells.

[0093] Specifically, based on the obtained first battery state data, the voltage change value dV / dSOC corresponding to the unit state of charge is calculated from the start time to the end time of the charging condition, dV / dSOC = (V2 – V1) / (SOC2 – SOC1). Where V1 is the charging voltage corresponding to SOC1, and V2 is the charging voltage corresponding to SOC2.

[0094] In the specific implementation process, the charging voltage curve can be obtained according to the corresponding relationship between the medium state of charge SOC and the charging voltage V under the predetermined working condition, such as Figure 5 As shown, the horizontal axis represents the state of charge SOC and the vertical axis represents the charging voltage V. Further, the differential curve of the charging voltage V and the state of charge SOC can be obtained, as shown in FIG. Figure 6 As shown in the figure, the horizontal axis represents the state of charge (SOC), and the vertical axis represents the voltage change per unit SOC (dV / dSOC). It should be noted that the two curves in the figure represent two battery cells and are for illustrative purposes only. In actual calculations, differential curves of the charging voltage V and the state of charge (SOC) for all battery cells can be obtained, and any two curves can be selected from these curves to calculate the consistency difference between the two battery cells.

[0095] In this way, based on the first battery status data, the change relationship of the voltage change value corresponding to the unit state of charge of each battery cell in the battery under a predetermined operating condition is calculated, and the consistency difference between different battery cells is calculated based on the change relationship corresponding to each battery cell.

[0096] See also Figure 7 In some embodiments, step 032 includes:

[0097] 0321: According to the change relationship, select the maximum value of the voltage change value of each battery cell in the predetermined state of charge range;

[0098] 0322: Compare the charge states corresponding to the maximum voltage change values of different battery cells to obtain the consistency differences between different battery cells.

[0099] Specifically, according to Figure 6It can be seen that the differential curve of charging voltage V versus state of charge (SOC) typically has three maximum voltage change points at the beginning, end, and mid-charge stages of charging. The maximum voltage change points at the beginning and end of charging are not target points. The maximum voltage change point in the mid-charge stage, or the maximum value within this interval, is the target point. This target point typically corresponds to the SOC range of [40%, 70%], or the predetermined SOC range of [40%, 70%]. The determination of this range is based on empirical historical data. In the actual calculation process, after obtaining the differential curve of charging voltage V versus state of charge (SOC), the location with the maximum voltage change per unit SOC within the predetermined SOC range (i.e., the SOC range of [40%, 70%]) is selected, along with the corresponding SOC, and this location is recorded as a characteristic point.

[0100] Furthermore, the same processing is performed on the differential curve of the charging voltage V and the state of charge SOC of each battery cell, and the SOC difference corresponding to the characteristic points of any two battery cells is calculated to obtain the calculation result of the consistency difference of the two battery cells. Therefore, by judging the difference in the charged capacity between the characteristic points of the voltage-differential curve between different battery cells, the consistency difference between battery cells can be estimated. The characteristic point is located in the middle interval of the charging process, so that during each charging process, as long as the remaining capacity of the battery cell is less than half, there is an opportunity to estimate the battery consistency. Compared with the related art, which requires the remaining capacity to be less than 30% to estimate the consistency, there are more opportunities.

[0101] It should be understood that [40%, 70%] is only for illustrative purposes. In other embodiments, the predetermined state of charge interval may also be [45%, 70%], [40%, 75%], etc., which is not limited here.

[0102] In this way, the maximum value of the voltage change value in the predetermined state of charge range in the change relationship of each battery cell is selected as the feature point, and the state of charge corresponding to the feature points corresponding to different battery cells is compared to obtain the consistency difference results between the corresponding battery cells and complete the current detection.

[0103] See also Figure 8 In certain embodiments, the method further comprises the steps of:

[0104] 04: When the cumulative number of historical data of battery consistency detection is less than the predetermined number, the consistency difference of the current time is used as the battery consistency detection result.

[0105] Specifically, under normal circumstances, there may be errors in estimating the consistency difference based on only one calculation result. Therefore, in this application, the historical data of consistency difference detection and the consistency difference detection result of the current time will be combined to reduce the error of a single calculation. However, for the case where the cumulative number of historical data in this embodiment is small, the effect of statistical processing may be poor and deviate greatly from the true value. In this case, the consistency difference of the current time will be directly used as the detection result of battery consistency. The predetermined number of times can be 5 times, 8 times, 10 times, etc., which are not limited here.

[0106] In this way, when there is less historical test data, the calculation result of the consistency difference at that time can be directly used as the test result.

[0107] See also Figure 8 In certain embodiments, the method further comprises the steps of:

[0108] 05: When the cumulative number of historical data of battery consistency detection is greater than or equal to the predetermined number, the battery consistency detection result is obtained based on the historical data and the current consistency difference.

[0109] Specifically, when the cumulative number of historical data of consistency detection is greater than or equal to a predetermined number, for example, greater than 5 times, it can be considered that the effect of statistical processing combined with historical detection data is better.

[0110] In this way, considering that there may be errors when only the calculation results of the consistency difference at that time are used as the detection results, after accumulating a certain amount of historical data, the historical data and the calculation results of the consistency difference at that time can be combined to obtain the consistency detection results together, reducing the impact of the single calculation noise error on the results, making the calculation results more accurate.

[0111] See also Figure 9 In some embodiments, step 05 includes:

[0112] 051: Perform regression fitting on historical data and the current consistency difference to obtain the battery consistency test results.

[0113] Specifically, a regression fit can be performed on historical data and the calculation results of the current consistency difference to obtain a function that can represent the consistency test results, so that the curve is closest to all data points under a certain criterion, thereby reducing the possible error of a single measurement.

[0114] In this way, the regression fitting method can be used to combine historical calculation results to correct the current results, reduce the impact of single calculation error noise, and make the calculation results more accurate.

[0115] See also Figure 10In some embodiments, step 051 includes:

[0116] 0511: Use a predetermined regression algorithm to perform regression fitting on historical data and the current consistency difference to obtain the regression curve with the minimum cost function;

[0117] 0512: Obtain a calibration value based on the regression curve to obtain a battery consistency test result.

[0118] Specifically, in this embodiment, according to the data characteristics of consistency detection, linear regression or support vector regression (SVR) can be used. By constructing a loss function of sample labels and model prediction values, the loss function is minimized to determine the regression function. Among them, if linear regression fitting is adopted, its cost function Loss = 1 / n*sum(yi-axi-b), where n represents the sample size, yi represents the SOC value of the sample, axi+b is the linear fitting formula, and i is a positive integer greater than 1. If SVR regression is adopted, its cost function Loss = max(0,r-ε), where r in the cost function represents the interval and ε represents the relaxation vector.

[0119] Using statistical methods such as linear regression or support vector regression algorithms, the consistency calculation results are regressed and fitted to obtain a regression curve with the minimum cost function. Based on this regression curve, the calibration value for the current consistency calculation on the regression curve can be obtained, and this calibration value is used as the current battery consistency test result. Combined with historical calculation results, linear regression or support vector regression algorithms are used to obtain the inter-cell consistency curve with the minimum error, reducing the influence of error noise in a single battery consistency calculation and obtaining more accurate battery consistency results.

[0120] In this way, regression fitting methods such as linear regression and support vector regression can be used, and the cost function can be used to determine the regression curve, and further obtain the calibration value for the current calculation result, that is, the value after regression fitting, so as to obtain the battery consistency detection result, making the detection result more accurate.

[0121] Furthermore, if the consistency difference is large, the battery may be at risk of overcharging or over-discharging. During the actual calculation process, if the calculated consistency difference exceeds a certain threshold, an alarm can be issued to prompt the relevant user to check, reduce overcharging or over-discharging, and extend the battery life.

[0122] For the calculation results combined with history, if the trend of the fitted regression curve is accelerating, it means that the consistency difference between battery cells is increasing and the speed of the difference is accelerating. When the rate of change of the consistency difference reaches a certain threshold, an alarm can be issued to remind the user that the vehicle may be at risk of breaking down or other safety risks.

[0123] Based on the same inventive concept, the present application also provides a battery consistency detection device 100. The solution provided by the detection device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the detection device 100 provided below can be found in the above-mentioned limitations of the detection method and will not be repeated here.

[0124] See also Figure 11 The present application also provides a battery consistency detection device 100 , including: a communication module 101 , a processing module 102 and a calculation module 103 .

[0125] The communication module 101 is used to receive battery status data.

[0126] The processing module 102 is configured to perform a first process on the battery status data to select first battery status data under a predetermined working condition.

[0127] The calculation module 103 is configured to calculate the current consistency difference of different battery cells in the battery according to the first battery status data.

[0128] Thus, in this application, based on the received battery status data, after pre-processing the data, the first battery status data under a predetermined operating condition is selected to calculate the current consistency difference between different battery cells in the battery, thereby realizing the consistency detection of the battery. The detection method of this application can detect battery consistency without waiting for the battery to be in a specific state. It has strong applicability, increases the chance of estimating battery consistency, and can more promptly identify consistency differences in the battery, thereby performing equalization processing and reducing battery safety hazards.

[0129] In some embodiments, the processing module 102 is configured to:

[0130] Sort the battery status data according to the reporting time;

[0131] The battery status data after sorting is processed and abnormal data processing is performed.

[0132] Thus, for the battery status data, relevant preprocessing is first performed on the data, such as sorting and screening, to eliminate the influence of abnormal data on consistency detection caused by communication reasons and improve the accuracy of calculation.

[0133] In some embodiments, the processing module 102 is configured to:

[0134] According to the predetermined operating condition identifier, first battery status data under the predetermined operating condition is selected from the battery status data after abnormal data processing.

[0135] In this way, a stable operating condition suitable for battery consistency detection is selected from the processed data, and the battery consistency is calculated using the first battery state data under the operating condition.

[0136] In some embodiments, the computing module 103 is configured to:

[0137] Calculate the voltage change relationship of each battery cell corresponding to the unit state of charge under a predetermined operating condition;

[0138] According to the corresponding change relationship of different battery cells, the consistency difference of different battery cells is calculated.

[0139] In this way, based on the first battery status data, the change relationship of the voltage change value corresponding to the unit state of charge of each battery cell in the battery under a predetermined operating condition is calculated, and the consistency difference between different battery cells is calculated based on the change relationship corresponding to each battery cell.

[0140] In some embodiments, the computing module 103 is configured to:

[0141] According to the change relationship, the maximum value of the voltage change value of each battery cell in the predetermined state of charge range is selected;

[0142] The states of charge corresponding to the maximum values of the voltage changes of different battery cells are compared to obtain the consistency differences between the different battery cells.

[0143] In this way, the maximum value of the voltage change value in the predetermined state of charge range in the change relationship of each battery cell is selected as the feature point, and the state of charge corresponding to the feature points corresponding to different battery cells is compared to obtain the consistency difference results between the corresponding battery cells and complete the current detection.

[0144] In some embodiments, the computing module 103 is configured to:

[0145] When the accumulated number of historical data of battery consistency detection is less than the predetermined number, the consistency difference at that time is used as the detection result of battery consistency.

[0146] In this way, when there is less historical test data, the calculation result of the consistency difference at that time can be directly used as the test result.

[0147] In some embodiments, the computing module 103 is configured to:

[0148] When the cumulative number of historical data of battery consistency detection is greater than or equal to a predetermined number, a battery consistency detection result is obtained according to the historical data and the current consistency difference.

[0149] In this way, considering that there may be errors when only the calculation results of the consistency difference at that time are used as the detection results, after accumulating a certain amount of historical data, the historical data and the calculation results of the consistency difference at that time can be combined to obtain the consistency detection results together, reducing the impact of the single calculation noise error on the results, making the calculation results more accurate.

[0150] In some embodiments, the computing module 103 is configured to:

[0151] Perform regression fitting on historical data and the current consistency difference to obtain the battery consistency test results.

[0152] In this way, the regression fitting method can be used to combine historical calculation results to correct the current results, reduce the impact of single calculation error noise, and make the calculation results more accurate.

[0153] In some embodiments, the computing module 103 is configured to:

[0154] Use a predetermined regression algorithm to perform regression fitting on historical data and the current consistency difference to obtain the regression curve with the minimum cost function;

[0155] The calibration value is obtained according to the regression curve, thereby obtaining the battery consistency test result.

[0156] In this way, regression fitting methods such as linear regression and support vector regression can be used, and the cost function can be used to determine the regression curve, and further obtain the calibration value for the current calculation result, that is, the value after regression fitting, so as to obtain the battery consistency detection result, making the detection result more accurate.

[0157] Each module in the detection device 100 can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software so that the processor can call and execute the corresponding operations of each module.

[0158] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the battery consistency detection method provided in any of the above embodiments is implemented.

[0159] The computer device provided in the above embodiment has an implementation principle and technical effects similar to those of the above method embodiment, and will not be described in detail here.

[0160] See also Figure 12The present application further provides a computer-readable storage medium 200 including a computer program 201. When the computer program 201 is executed by one or more processors 300, the one or more processors 300 execute the detection method of any of the above embodiments.

[0161] The implementation principle and technical effects of the provided computer-readable storage medium are similar to those of the above-mentioned method embodiment and will not be repeated here.

[0162] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. For purposes of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The processors involved in the various embodiments provided herein may be general-purpose processors, central processing units (CPUs), graphics processors (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like, but are not limited thereto.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for detecting battery consistency, characterized in that: include: Receive battery status data; performing a first processing on the battery status data to select first battery status data under a predetermined operating condition; Calculating the consistency difference of different battery cells in the battery based on the first battery status data; When the cumulative number of historical data of battery consistency detection is greater than or equal to a predetermined number, a predetermined regression algorithm is used to perform regression fitting on the historical data and the current consistency difference to obtain a regression curve with the minimum cost function; a calibration value is obtained based on the regression curve to obtain the battery consistency detection result.

2. The method according to claim 1, characterized in that The performing a first processing on the battery status data to select first battery status data under a predetermined working condition includes: Sorting the battery status data according to reporting time; Abnormal data processing is performed on the battery status data after the sorting process.

3. The method according to claim 2, characterized in that The performing a first processing on the battery status data to select first battery status data under a predetermined working condition includes: According to the predetermined operating condition identifier, first battery status data under the predetermined operating condition is selected from the battery status data after the abnormal data processing.

4. The method according to claim 1, wherein The calculating, based on the first battery status data, the consistency difference of different battery cells in the battery includes: Calculating a change relationship of a voltage change value corresponding to a unit state of charge of each battery cell under a predetermined operating condition; According to the corresponding change relationship of different battery cells, the consistency difference of different battery cells is calculated.

5. The method according to claim 4, characterized in that The calculation of the consistency difference of different battery cells according to the change relationship corresponding to different battery cells includes: According to the change relationship, selecting the maximum value of the voltage change value of each battery cell in a predetermined state of charge interval; The charge states corresponding to the maximum values of the voltage variation values of different battery cells are compared, so as to obtain the consistency difference between the different battery cells.

6. The method according to claim 1, characterized in that The method further comprises: When the accumulated number of historical data of battery consistency detection is less than a predetermined number, the consistency difference at that time is used as the detection result of the battery consistency.

7. A battery consistency detection device, characterized in that: The detection device comprises: A communication module, configured to receive battery status data; a processing module, configured to perform a first processing on the battery status data to select first battery status data under a predetermined operating condition; a calculation module, configured to calculate the consistency difference of different battery cells in the battery based on the first battery status data; When the cumulative number of historical data of battery consistency detection is greater than or equal to a predetermined number, a predetermined regression algorithm is used to perform regression fitting on the historical data and the current consistency difference to obtain a regression curve with the minimum cost function; a calibration value is obtained based on the regression curve to obtain the battery consistency detection result.

8. A computer device, characterized in that: The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the detection method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the detection method according to any one of claims 1 to 6 is implemented.

Images