Battery early warning method, computer equipment and readable storage medium

Abstract

The invention discloses a battery early warning method, computer equipment and a readable storage medium, and belongs to the technical field of power batteries, the battery early warning method comprises the following steps: determining a classification threshold based on acquired voltage data of each battery cell in a battery pack under a driving condition; classifying the voltage data, obtained in real time, of each battery cell in the battery pack based on the classification threshold to determine a battery cell classification result; calculating a battery pack entropy value at each moment based on the battery cell classification result; and carrying out battery early warning according to the change of the entropy value of the battery pack in the time sequence. The battery early warning method provided by the invention neglects the calculation accuracy and precision of the SOC of the battery and neglects the reserved standards of different manufacturers, can directly represent the state of each battery cell in the battery pack, can timely perform early warning on the lying risk caused by the vehicle battery, improves the safety in the driving process of the electric vehicle, and improves the safety of the electric vehicle. And the use experience of the user on the electric vehicle is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of power batteries, and in particular, relates to a battery early warning method, a computer device, and a readable storage medium. Background Art

[0002] With the development of power battery technology, the energy density of batteries has increased, the charging time has been shortened, and the driving range has increased, making electric vehicles more attractive. In addition, the cost of batteries has continued to decline, which has promoted the popularization of electric vehicles. In order to give full play to the power performance of the battery system, prevent overcharging and over-discharging of the battery, extend the service life, optimize driving and improve the driving performance of electric vehicles, it is necessary to accurately estimate the state of charge of the battery. The remaining charge (SOC) of the battery refers to the energy currently stored in the battery. The SOC state estimation of the battery is very important for the application of electric vehicle power batteries.

[0003] At present, the low battery warning strategy of electric vehicles is usually based on SOC state estimation for battery warning, that is, when the current SOC of the battery is low, an alarm is issued, usually when the remaining battery power percentage is 10%-20%, to prompt the user to charge. However, in practical applications, SOC is difficult to measure directly under actual working conditions, and it is still a big challenge to accurately estimate the SOC of the power battery on the actual vehicle, especially under various vehicle operating conditions and differences between different battery cells. The battery SOC estimation is inaccurate, and each electric vehicle manufacturer reserves different remaining mileage when the meter displays 0% SOC. Therefore, users often have great anxiety when driving to low SOC, and sometimes the meter displays a non-0% SOC but the vehicle breaks down, resulting in a bad user experience. Summary of the invention

[0004] In order to overcome the above-mentioned defects, the battery warning method, computer device and storage medium proposed in this application can solve or at least partially solve the technical problem that the battery SOC estimation is inaccurate and the user cannot be warned in a timely and accurate manner, resulting in the vehicle breaking down.

[0005] In a first aspect, the present application provides a battery early warning method, comprising:

[0006] Determine a classification threshold based on the acquired voltage data of each battery cell in the battery pack under driving conditions;

[0007] Classifying the voltage data of each battery cell in the battery pack acquired in real time based on the classification threshold to determine a battery cell classification result;

[0008] Calculate the entropy value of the battery pack at each moment based on the battery cell classification result;

[0009] A battery early warning is performed according to the change in the entropy value of the battery pack in time sequence.

[0010] In some embodiments, determining the classification threshold based on the acquired voltage data of each battery cell in the battery pack under driving conditions includes:

[0011] Obtaining voltage data of each battery cell in the battery pack under driving conditions, and calculating voltage percentiles of each battery cell in the battery pack based on the voltage data;

[0012] Calculating the cell voltage fluctuation difference according to the voltage percentile of each cell in the battery pack;

[0013] A plurality of cell voltage fluctuation differences are calculated based on a preset time period, and a classification threshold is selected therefrom.

[0014] In some embodiments, classifying the voltage data of each battery cell in the battery pack acquired in real time based on the classification threshold to determine the battery cell classification result includes:

[0015] Based on the voltage data of each battery cell in the battery pack obtained in real time, the mode value of the battery cell voltage at each moment is calculated;

[0016] Determine the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment;

[0017] At each moment, each battery cell in the battery pack is divided according to the corresponding relationship between the voltage data and the battery cell classification interval to determine the battery cell classification result at each moment.

[0018] Further, the determining the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment includes:

[0019] The first reference value and the second reference value are calculated according to the classification threshold and the cell voltage mode value, and the calculation formula is as follows:

[0020] The first reference value = Mode_V-(1 / 2)ΔV, the second reference value = Mode_V+(1 / 2)ΔV, wherein Mode_V represents the mode value of the cell voltage, and ΔV represents the classification threshold;

[0021] A cell classification interval is determined according to the first reference value and the second reference value.

[0022] Furthermore, dividing each battery cell in the battery pack according to the correspondence between the voltage data and the battery cell classification intervals to determine the battery cell classification results at each moment includes:

[0023] When the value of the voltage data of the battery cell corresponds to the first interval, a first mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the second interval, a second mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the third interval, a third mark is set for the battery cell;

[0024] The individual cells in the battery pack are classified based on the marks set for the cells to determine the cell classification results at each moment.

[0025] Furthermore, dividing each battery cell in the battery pack according to the correspondence between the voltage data and the battery cell classification intervals to determine the battery cell classification results at each moment also includes: when the voltage data of the battery cell has no correspondence with the first interval, the second interval or the third interval, setting a fourth mark for the battery cell.

[0026] In some embodiments, the calculating of the entropy value of the battery pack at each moment based on the battery cell classification result includes:

[0027] The entropy value H(X) of the battery pack is calculated according to the following formula:

[0028]

[0029] Wherein, t1 represents the current time, x represents any battery cell classification result, and P(x) is the probability of any battery cell classification result occurring.

[0030] In some implementation schemes, the battery warning according to the time series change of the entropy value of the battery pack includes: issuing a warning notification when the entropy value of the battery pack has an increasing trend and the entropy value of the battery pack reaches a warning threshold.

[0031] In a second aspect, the present application provides a computer device, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the battery warning method described in any one of the technical solutions of the above-mentioned battery warning method is implemented.

[0032] In a third aspect, the present application provides a computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the battery warning method described in any one of the technical solutions of the above-mentioned battery warning method.

[0033] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0034] In the technical solution for implementing the present application, a classification threshold is determined based on the voltage data of each battery cell in the battery pack under driving conditions; based on the classification threshold, the voltage data of each battery cell in the battery pack obtained in real time is classified to determine the battery cell classification result, and the battery pack entropy value at each moment is calculated based on the battery cell classification result; and a battery warning is performed according to the change in the battery pack entropy value in time series. The present invention mainly adopts the statistics of voltage fluctuations in the front section of driving conditions to provide a reference for the classification of each battery cell, and performs a battery warning based on the performance of the voltage entropy value of the classified battery cell, which can effectively evaluate the risk of breakdown. The battery warning method provided by the present invention ignores the accuracy and precision of the battery SOC calculation and the standards reserved by different manufacturers, and can directly characterize the state of each battery cell in the battery pack, realizing accurate and timely warning of the risk of breakdown caused by the vehicle battery, improving the safety of electric vehicles during driving, and enhancing the user experience of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The disclosure of the present application will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the drawings are used to represent similar components, among which:

[0036] Figure 1 This is a schematic flow chart of the main steps of the battery warning method according to an embodiment of the present application;

[0037] Figure 2 It is a schematic diagram of the effect corresponding to the implementation of the battery warning method of the present application in a specific application scenario;

[0038] Figure 3 This is a schematic diagram of the effect corresponding to the implementation of the battery warning method of the present application in another specific application scenario;

[0039] Figure 4 It is a schematic block diagram of a battery warning device according to an embodiment of the present application;

[0040] Figure 5 It is a schematic block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0042] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, 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, hardware or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.

[0043] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0044] The battery warning method provided in this application is a solution suitable for real-time monitoring and risk warning of power batteries of new energy vehicles. It is intended to be aimed at the difficult to accurately estimate the SOC of lithium iron phosphate power batteries. In the scenario where each automobile manufacturer displays different reserved mileages at 0% SOC, it realizes the early warning of the risk of the user's car breaking down when driving at low SOC. At present, a battery management system (BMS) is usually installed in the battery pack of the vehicle, which can facilitate the battery pack to record and upload the current, voltage, temperature and other information of the whole pack of batteries to the cloud in real time during the operation of the market end. Therefore, the battery warning method of the present invention can be implemented both in the cloud and inside the vehicle. Preferably, it can be based on the voltage data of the battery cells in the battery pack collected and uploaded to the cloud by the BMS, and the power battery of the vehicle under driving conditions is monitored in real time and the risk of breaking down when the vehicle is driving to a low SOC (also known as the remaining power) is warned to remind the user to replenish energy in time.

[0045] Embodiment 1

[0046] See attached Figure 1 , Figure 1 This is a main step flow of a battery warning method of an embodiment of the present application, which mainly includes the following steps S11 to S14.

[0047] Step S11: determining a classification threshold based on voltage data of each battery cell in the battery pack under driving conditions;

[0048] In this embodiment, the voltage data used to determine the classification threshold can be data collected within a period of time after the driving condition starts. The time can be customized according to actual application needs, and the customized time is usually not less than 10 minutes. For example, taking the data collection time as 30 minutes, this step specifically obtains the voltage data of all cells in the battery pack within 30 minutes after the driving condition starts, and then determines the classification threshold based on the obtained voltage data.

[0049] Optionally, the above step S11 may specifically include steps 111 to 113:

[0050] Step 111: obtaining voltage data of each battery cell in the battery pack under driving conditions, and calculating voltage percentiles of each battery cell in the battery pack based on the voltage data;

[0051] Step 112: Calculating a cell voltage fluctuation difference according to the voltage percentile of each cell in the battery pack;

[0052] Exemplarily, the cell voltage fluctuation difference is calculated based on the 5th percentile and the 95th percentile, and is recorded as ΔV'.

[0053] Step 113: Calculate a plurality of cell voltage fluctuation differences based on a preset time period, and select a classification threshold therefrom.

[0054] Exemplarily, the preset time period is the data collection time, such as 60 minutes. Based on the preset time period, multiple cell voltage fluctuation differences, i.e., multiple ΔV', can be calculated, and the percentiles of multiple ΔV' are counted, and the 95th percentile is taken as the classification threshold, recorded as ΔV.

[0055] It should be understood that the percentile statistical method is used in the embodiment of the present application to calculate the above ΔV' and ΔV. In actual application scenarios, other percentile values ​​other than the 95th percentile can be used to calculate the above ΔV' and ΔV as needed.

[0056] Step S12: classifying the voltage data of each battery cell in the battery pack acquired in real time based on the classification threshold to determine the battery cell classification result;

[0057] Optionally, this step S12 may specifically include steps 121 to 123:

[0058] Step 121: Counting the mode value of the cell voltage at each moment based on the voltage data of each cell in the battery pack acquired in real time;

[0059] Specifically, in this embodiment, for the values ​​of the voltage data of each battery cell in the battery pack obtained at each moment, the voltage value with the highest frequency of occurrence is statistically calculated as the battery cell voltage mode value, which is recorded as Mode_V. For example, among the 100 voltage values ​​corresponding to the 100 battery cells in the battery pack, the voltage value with the highest frequency of occurrence is 3V, then Mode_V=3V.

[0060] Step 122: determining the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment;

[0061] Optionally, this step 122 may specifically include:

[0062] The first reference value and the second reference value are calculated according to the classification threshold and the cell voltage mode value, and the calculation formula is as follows:

[0063] The first reference value = Mode_V-(1 / 2)ΔV, the second reference value = Mode_V+(1 / 2)ΔV, wherein Mode_V represents the mode value of the cell voltage, and ΔV represents the classification threshold;

[0064] A cell classification interval is determined according to the first reference value and the second reference value.

[0065] Optionally, a numerical interval with values ​​less than the first reference value is determined as a first interval; a numerical interval with values ​​greater than or equal to the first reference value and less than or equal to the second reference value is determined as a second interval; and a numerical interval with values ​​greater than the second reference value is determined as a third interval.

[0066] Step 123: for each moment, the battery cells in the battery pack are divided according to the correspondence between the voltage data and the battery cell classification intervals to determine the battery cell classification result at each moment.

[0067] Specifically in this embodiment, for the voltage data of each battery cell in the battery pack obtained at each moment, the value of the voltage data of each battery cell is compared with the battery cell classification interval, and a mark is set for the battery cell according to the comparison result to achieve classification of the battery cells, wherein battery cells with the same mark are classified into the same battery cell classification result.

[0068] Optionally, dividing the cells in the battery pack according to the correspondence between the voltage data and the cell classification intervals to determine the cell classification results at each moment may include:

[0069] When the value of the voltage data of the battery cell corresponds to the first interval, a first mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the second interval, a second mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the third interval, a third mark is set for the battery cell;

[0070] Exemplarily, when the value of the voltage data of the battery cell is less than Mode_V-(1 / 2)ΔV, the mark K1 is set for the battery cell; when the value of the voltage data of the battery cell is in the interval [Mode_V-(1 / 2)ΔV, Mode_V+(1 / 2)ΔV], the mark K2 is set for the battery cell; when the value of the voltage data of the battery cell is greater than Mode_V+(1 / 2)ΔV, the mark K3 is set for the battery cell.

[0071] Optionally, when the voltage data of the battery cell does not correspond to the first interval, the second interval, or the third interval, a fourth mark is set for the battery cell. In actual application scenarios, the voltage data of individual battery cells may be abnormal data, such as a null value when data is missing. In this case, by adding a fourth mark to divide the battery cell separately, the accuracy of subsequent warnings based on entropy value changes can be improved.

[0072] The individual cells in the battery pack are classified based on the marks set for the cells to determine the cell classification results at each moment.

[0073] Exemplarily, the battery cells with mark K1 are classified as battery cell classification result 1, the battery cells with mark K2 are classified as battery cell classification result 2, the battery cells with mark K3 are classified as battery cell classification result 3, and the battery cells with mark K4 are classified as battery cell classification result 4.

[0074] Step S13: calculating the entropy value of the battery pack at each moment based on the battery cell classification result;

[0075] Optionally, this step S13 specifically includes:

[0076] The entropy value H(X) of the battery pack is calculated according to the following formula:

[0077]

[0078] Wherein, t1 represents the current time, x represents any battery cell classification result, and P(x) is the probability of any battery cell classification result occurring.

[0079] Exemplarily, if the battery pack contains n single cells, the voltage of each cell in the battery pack at time t1 is Cell_V_i (i=1,2,3…n), and the cell classification results are: there are x cells marked with K1, y cells marked with K2, z cells marked with K3, and w cells marked with K4, where x+y+z+w=n; the probability of occurrence of each cell classification result is P1=x / n, P2=y / n, P3=z / n, P4=w / n; then the overall entropy value H(X) of the battery pack at time t1 can be calculated according to the above entropy formula.

[0080] Step S14: Performing battery warning according to the time series change of the entropy value of the battery pack.

[0081] Specifically, in this embodiment, this step may include: issuing a warning notification when the entropy value of the battery pack has a rising trend and the entropy value of the battery pack reaches the warning threshold. The entropy value of the battery pack reaching the warning threshold may refer to the battery pack entropy value in the time series averaging and exceeding the warning threshold, for example, the warning threshold is 1 bit.

[0082] For example, when the entropy value of the battery pack has a rising trend and the average value of the entropy value of the battery pack exceeds 1 bit, a warning is issued to the user; or when the entropy value of the battery pack has a rising trend and the average value of the entropy value of the battery pack exceeds 1 bit three times, a warning is issued to the user to prompt the user to replenish energy in time or arrange rescue in advance. It should be understood that the warning threshold, the number of times exceeding the warning threshold, and the method or number of times of issuing the warning can be set according to actual application needs.

[0083] Optionally, before the above steps S11 to S14, the following may also be included: monitoring the battery SOC, and when a low SOC is detected, such as SOC <40%, real-time monitoring of the change in entropy value of the battery pack is started in the timing, that is, executing the steps S11 to S14, so as to provide an early warning to the user of the risk of the vehicle breaking down in the application scenario of low SOC.

[0084] It should be understood that according to the definition of entropy, the more equal the probability distribution in the system, the greater the entropy value, and vice versa. Reflected in the battery pack, that is, the more discrete the voltage of each battery cell, the more battery cell classifications there are, and the greater the entropy value. For example, when the battery cell classification probability P1=P2=P3=P4=0.25, the maximum entropy value is 2bit; the more consistent the voltage of each battery cell is, the more concentrated it will be in the battery cell classification category marked with K2. When all the batteries are classified into the battery cell classification category marked with K2, the minimum entropy value is 0bit.

[0085] Furthermore, if Figure 2 and Figure 3The figure shows the effect diagram corresponding to the battery warning method of the present application when it is implemented in two specific application scenarios provided by the embodiment of the present application. Figure 2 and Figure 3 It can be seen that when the change in the entropy value of the battery pack shows an upward trend in time series and shows large fluctuations and exceeds the warning threshold (for example, 1bit), it coincides with the moment when the voltage of a certain battery cell in the battery pack drops significantly. Therefore, the battery warning method based on the present application can accurately and timely issue risk warnings for the battery under driving conditions to prevent the occurrence of vehicle breakdown incidents.

[0086] Embodiment 2

[0087] See attached Figure 4 , Figure 4 This is a main structural block diagram of a battery warning device according to an embodiment of the present application, and the device mainly includes:

[0088] The data acquisition module 201 is used to acquire the voltage data of each battery cell in the battery pack under driving conditions, and determine the classification threshold based on the acquired data;

[0089] A cell classification module 202, configured to classify the voltage data of each cell in the battery pack acquired in real time based on the classification threshold determined by the data acquisition module 201 to determine a cell classification result;

[0090] An entropy value calculation module 203, used to calculate the entropy value of the battery pack at each moment based on the battery cell classification result determined by the battery cell classification module 202;

[0091] The early warning monitoring module 204 is used to perform battery early warning according to the time series change of the battery pack entropy value calculated by the entropy value calculation module 203. Exemplarily, when the battery pack entropy value has a rising trend and the battery pack entropy value reaches the early warning threshold, an early warning notification is issued.

[0092] Optionally, the data acquisition module 201 may include an acquisition unit, a calculation unit and a selection unit, wherein:

[0093] The acquisition unit is used to acquire voltage data of each battery cell in the battery pack under driving conditions, and calculate the voltage percentile of each battery cell in the battery pack based on the voltage data;

[0094] The calculation unit is used to calculate the cell voltage fluctuation difference according to the voltage percentile of each cell in the battery pack;

[0095] The selection unit is used to calculate a plurality of cell voltage fluctuation differences based on a preset time period and select a classification threshold therefrom.

[0096] Optionally, the battery cell classification module 202 may include a statistical unit, a determination unit and a division unit, wherein:

[0097] The statistical unit is used to count the mode value of the cell voltage at each moment based on the voltage data of each cell in the battery pack acquired in real time;

[0098] The determining unit is used to determine the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment;

[0099] The division unit is used to divide the battery cells in the battery pack according to the corresponding relationship between the voltage data and the battery cell classification intervals at each moment to determine the battery cell classification result at each moment.

[0100] For ease of explanation, the introduction to the above-mentioned battery warning device only shows the part related to the embodiment of the present application. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application.

[0101] It should be understood that since the setting of each module or unit is only for illustrating the functional units of the present application, the physical devices corresponding to these modules or units may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0102] It is understood by those skilled in the art that each module or unit in the device can be adaptively split or merged. Such splitting or merging of specific modules or units will not cause the technical solution to deviate from the principle of the present application, and therefore, the technical solution after splitting or merging will fall within the protection scope of the present application.

[0103] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.

[0104] Furthermore, the present application also provides a computer device.

[0105] In an embodiment of a computer device according to the present application, the computer device may include at least one processor; and a memory connected to the at least one processor in communication; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any of the above embodiments is implemented. For ease of explanation, only the parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. See the attached Figure 5 , Figure 5 FIG. 4 exemplarily shows that the memory 11 and the processor 12 are communicatively connected via a bus.

[0106] In the embodiment of the present application, the computer device may be a control device device including various electronic devices. In some possible implementations, the computer device may include multiple memories and multiple processors. The program for executing the battery warning method of the above method embodiment may be divided into multiple subprograms, each of which may be loaded and run by a processor to execute different steps of the battery warning method of the above method embodiment. Specifically, each subprogram may be stored in different memories, and each processor may be configured to execute programs in one or more memories to jointly implement the battery warning method of the above method embodiment, that is, each processor executes different steps of the battery warning method of the above method embodiment to jointly implement the battery warning method of the above method embodiment.

[0107] The above-mentioned multiple processors may be processors deployed on the same device. For example, the above-mentioned computer device may be a high-performance device composed of multiple processors, and the above-mentioned multiple processors may be processors configured on the high-performance device. In addition, the above-mentioned multiple processors may also be processors deployed on different devices. For example, the above-mentioned computer device may be a server cluster, and the above-mentioned multiple processors may be processors on different servers in the server cluster.

[0108] Furthermore, the present application also provides a computer-readable storage medium.

[0109] In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the battery warning method of the above method embodiment, and the program can be loaded and run by the processor to implement the above battery warning method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For 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-temporary computer-readable storage medium.

[0110] So far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles 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 fall within the protection scope of the present application.

Claims

1. A battery early warning method, characterized in that: The method comprises: Determine a classification threshold based on the acquired voltage data of each battery cell in the battery pack under driving conditions; Classifying the voltage data of each battery cell in the battery pack acquired in real time based on the classification threshold to determine a battery cell classification result; Calculate the entropy value of the battery pack at each moment based on the battery cell classification result; A battery early warning is performed according to the change in the entropy value of the battery pack in time sequence.

2. The battery warning method according to claim 1, characterized in that: The step of determining the classification threshold based on the acquired voltage data of each battery cell in the battery pack under driving conditions includes: Obtaining voltage data of each battery cell in the battery pack under driving conditions, and calculating voltage percentiles of each battery cell in the battery pack based on the voltage data; Calculating the cell voltage fluctuation difference according to the voltage percentile of each cell in the battery pack; A plurality of cell voltage fluctuation differences are calculated based on a preset time period, and a classification threshold is selected therefrom.

3. The battery early warning method according to claim 1, characterized in that: The step of classifying the voltage data of each battery cell in the battery pack acquired in real time based on the classification threshold to determine the battery cell classification result includes: Based on the voltage data of each battery cell in the battery pack obtained in real time, the mode value of the battery cell voltage at each moment is calculated; Determine the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment; At each moment, each battery cell in the battery pack is divided according to the corresponding relationship between the voltage data and the battery cell classification interval to determine the battery cell classification result at each moment.

4. The battery early warning method according to claim 3, characterized in that: The determining of the cell classification interval corresponding to each moment based on the classification threshold and the cell voltage mode value at each moment comprises: The first reference value and the second reference value are calculated according to the classification threshold and the cell voltage mode value, and the calculation formula is as follows: The first reference value = Mode_V-(1 / 2)ΔV, the second reference value = Mode_V+(1 / 2)ΔV, wherein Mode_V represents the mode value of the cell voltage, and ΔV represents the classification threshold; A cell classification interval is determined according to the first reference value and the second reference value.

5. The battery warning method according to claim 4, characterized in that: The dividing each battery cell in the battery pack according to the correspondence between the voltage data and the battery cell classification interval to determine the battery cell classification result at each moment includes: When the value of the voltage data of the battery cell corresponds to the first interval, a first mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the second interval, a second mark is set for the battery cell; when the value of the voltage data of the battery cell corresponds to the third interval, a third mark is set for the battery cell; The battery cells in the battery pack are classified based on the marks set for the battery cells to determine the classification results of the battery cells at each moment.

6. The battery early warning method according to claim 5, characterized in that: The method of dividing each battery cell in the battery pack according to the correspondence between the voltage data and the battery cell classification intervals to determine the battery cell classification results at each moment also includes: when the voltage data of the battery cell does not have a correspondence with the first interval, the second interval or the third interval, setting a fourth mark for the battery cell.

7. The battery early warning method according to claim 1, characterized in that: The calculating of the battery pack entropy value at each moment based on the battery cell classification result includes: The entropy value H(X) of the battery pack is calculated according to the following formula: Wherein, t1 represents the current time, x represents any battery cell classification result, and P(x) is the probability of any battery cell classification result occurring.

8. The battery early warning method according to claim 1, characterized in that: The battery early warning according to the time series change of the battery pack entropy value includes: issuing an early warning notification when the battery pack entropy value has a continuous upward trend and the battery pack entropy value reaches an early warning threshold.

9. A computer device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program, and when the computer program is executed by the at least one processor, the battery warning method according to any one of claims 1 to 8 is implemented.

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

Images