Lithium ion battery safety early warning method based on cloud big data and storage medium

Abstract

The invention provides a lithium ion battery safety early warning method based on cloud big data and a storage medium. The method comprises the following steps: acquiring target charging data of a lithium ion battery recorded by the cloud big data; wherein the target charging data comprises continuous charging data fragments of the lithium ion battery voltage in the platform area; obtaining a single voltage at each moment in the continuous charging data segment; and according to the single voltage at each moment in the continuous charging data fragment, whether safety early warning is carried out on the lithium ion battery is judged, so that the safety early warning is carried out on the lithium ion battery based on the continuous charging data fragment of the voltage of the lithium ion battery in the platform area. Therefore, the influence of the initial capacity and initial internal resistance difference of the battery cell on battery charging is reduced, and the accuracy and reliability of battery early warning are improved.

Description

Technical Field

[0001] The present application relates to the field of battery safety technology, and more specifically, to a lithium-ion battery safety early warning method and storage medium based on cloud big data. Background Art

[0002] Many safety hazards of lithium-ion batteries do not appear suddenly, but are caused by gradual degradation over time. This degradation may involve the aging of battery materials, changes in the properties of the electrolyte, loss of active substances, and other aspects. These factors work together to cause the battery performance to gradually deviate from the normal state. Minor abnormal changes inside the battery may indicate abnormal battery performance and be directly or indirectly reflected in its operating data. These data include but are not limited to the battery's charge / discharge curve, operating temperature range, cycle life performance, etc. In order to effectively capture these safety risks, the battery's operating data can be monitored for a long time, and subtle abnormalities in battery performance can be amplified in the early stages of safety failures, thereby identifying potential safety risks and issuing early warnings.

[0003] At present, traditional battery safety determination methods mainly rely on simple temperature monitoring and threshold judgment, lack of accurate assessment of battery status under complex working conditions, and have the problem of low accuracy of battery safety determination methods. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a lithium-ion battery safety warning method and storage medium based on cloud big data, so as to solve the problem that the current traditional battery safety determination method relies on simple temperature monitoring and threshold judgment, lacks accurate assessment of the battery status under complex working conditions, and has low accuracy.

[0005] In a first aspect, the present invention provides a lithium-ion battery safety warning method based on cloud big data, the method comprising: obtaining target charging data of the lithium-ion battery recorded in the cloud big data; wherein the target charging data comprises a continuous charging data segment in which the voltage of the lithium-ion battery is located in a platform area; obtaining a single cell voltage at each moment in the continuous charging data segment; and judging whether to issue a safety warning for the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data segment.

[0006] The above-designed lithium-ion battery safety early warning method based on cloud big data, this scheme records the real-time charging data of the lithium-ion battery through cloud big data, and then obtains the continuous charging data fragments in which the voltage of the lithium-ion battery is in the platform area, and then judges whether to issue a safety early warning for the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data fragments, thereby issuing a safety early warning for the lithium-ion battery based on the continuous charging data fragments in which the voltage of the lithium-ion battery is in the platform area, thereby reducing the impact of the differences in initial capacity and initial internal resistance of each cell of the lithium-ion battery on the charging of the lithium-ion battery, thereby improving the accuracy and reliability of the lithium-ion battery safety early warning.

[0007] In an optional implementation of the first aspect, judging whether to issue a safety warning is based on the cell voltage at each moment in a continuous charging data segment, including: calculating the cell voltage difference between the cell voltages at each moment in the continuous charging data segment based on the cell voltage at each moment in the continuous charging data segment; judging whether there is a cell pressure difference exceeding a preset pressure difference threshold among the cell pressure differences between the cell voltages at each moment in the continuous charging data segment; if it is determined that there is a cell pressure difference exceeding the preset pressure difference threshold, determining to issue a safety warning for the lithium-ion battery.

[0008] In the above implementation mode, this scheme compares the cell voltage difference between the cell voltages at each moment in the continuous charging data segment with the preset voltage difference threshold. When there is a cell voltage difference exceeding the preset voltage difference threshold, it indicates that there is a fault risk in the charging process of the lithium-ion battery, and then directly issues a safety warning for the lithium-ion battery, thereby improving the efficiency of the safety warning of the lithium-ion battery.

[0009] In an optional implementation of the first aspect, after determining whether there is a cell pressure difference exceeding a preset pressure difference threshold among the cell pressure differences between the cell voltages at each moment in a continuous charging data segment, the method further includes: if it is determined that there is no cell pressure difference exceeding the preset pressure difference threshold, generating effective voltage segments for multiple time windows according to the cell voltages at each moment in the continuous charging data segment; wherein the time window includes multiple moments in the continuous charging data segment, and the effective voltage segment is obtained by data enhancement of the cell voltages at each moment in the continuous charging data segment; for each time window, calculating a cell voltage entropy value sequence in the time window based on the effective voltage segment in the time window, and obtaining a cell voltage entropy value sequence in each time window in multiple time windows; and determining whether to issue a safety warning for the lithium-ion battery according to the cell voltage entropy value sequence in each time window in the multiple time windows.

[0010] In the above implementation mode, the magnitude of the voltage entropy value reflects the complexity and unpredictability of the battery voltage fluctuation. This solution obtains effective voltage segments in multiple time windows by performing data enhancement on the single cell voltage at each moment in the continuous charging data segment, and then calculates the single cell voltage entropy value sequence in the corresponding time window based on the effective voltage segment in each time window, thereby accurately reflecting the voltage fluctuation of the corresponding single cell based on the voltage entropy, thereby improving the accuracy of safety warning for lithium-ion batteries.

[0011] In an optional implementation of the first aspect, effective voltage segments of multiple time windows are generated based on the cell voltage at each moment in a continuous charging data segment, including: dividing the cell voltage at each moment in the continuous charging data segment into voltage segments of multiple time windows; calculating the median cell voltage and the cell voltage standard deviation in each of the multiple time windows, and generating an enhanced segment based on the cell voltage median and the cell voltage standard deviation in each time window; adding the enhanced segment before the voltage segment of the time window ranked first in the multiple time windows, and adding the enhanced segment after the voltage segment of the time window ranked last in the multiple time windows, to generate effective voltage segments for the multiple time windows.

[0012] In the above implementation mode, this scheme generates an enhanced segment according to the median voltage of a single cell and the standard deviation of the single cell voltage in each time window, and then adds the enhanced segment before the voltage segment of the time window that is ranked first among multiple time windows, and adds the enhanced segment after the voltage segment of the time window that is ranked last among multiple time windows, to generate effective voltage segments for multiple time windows, thereby ensuring equal use of all charging data in the continuous charging data segment through data enhancement, thereby improving the accuracy of lithium-ion battery early warning.

[0013] In an optional implementation of the first aspect, for each time window, a sequence of single cell voltage entropy values ​​in the time window is calculated based on an effective voltage segment of the time window to obtain a sequence of single cell voltage entropy values ​​in each of the multiple time windows, including: for each time window, obtaining a maximum single cell voltage and a minimum single cell voltage in the effective voltage segment of the time window; taking the minimum single cell voltage as a starting point and using a preset voltage difference as an interval to form multiple voltage intervals until the voltage interval covers the maximum single cell voltage in the time window; counting the frequency of each single cell voltage falling in each voltage interval in the time window to obtain a probability distribution matrix corresponding to the time window; calculating a sequence of single cell voltage entropy values ​​in the time window according to the probability distribution matrix to obtain a sequence of single cell voltage entropy values ​​in each of the multiple time windows.

[0014] In the above implementation mode, when calculating the monomer voltage entropy sequence, this scheme divides the monomer voltage into intervals to calculate the probability distribution, rather than directly using the original voltage value to calculate the probability distribution, thereby reducing the impact caused by hardware sampling errors, etc., and further improving the accuracy of the early warning.

[0015] In an optional implementation of the first aspect, judging whether to issue a safety warning for a lithium-ion battery is based on a sequence of single cell voltage entropy values ​​in each time window among multiple time windows, including: standardizing the sequence of single cell voltage entropy values ​​in each time window using a standard score and taking an absolute value to obtain a maximum standard score in each time window; obtaining a standard score threshold; wherein the standard score threshold is determined based on a distribution of single cell voltage entropy value sequences of all lithium-ion batteries stored in a database; judging whether to issue a safety warning for the lithium-ion battery is based on the maximum standard score and the standard score threshold in multiple time windows.

[0016] In an optional implementation of the first aspect, judging whether to issue a safety warning for the lithium-ion battery is based on the maximum value of the standard scores in multiple time windows and the standard score threshold, including: judging whether the number of times the maximum value of the standard scores in multiple time windows is greater than the standard score threshold exceeds a preset number; if it is determined that the number of times the maximum value of the standard scores in multiple time windows is greater than the standard score threshold exceeds a preset number, then determining to issue a safety warning for the lithium-ion battery.

[0017] In the above implementation mode, this scheme issues a safety warning to the lithium-ion battery based on the fact that the maximum value of the standard score in multiple time windows is greater than the standard score threshold for more than a preset number of times. In this way, if the voltage value of the lithium-ion battery fluctuates violently too many times in different time windows, it means that there is a high probability that the lithium-ion battery will fail. Therefore, a safety warning is issued to the lithium-ion battery, thereby improving the reliability and accuracy of the lithium-ion battery warning.

[0018] In an optional implementation of the first aspect, the method further includes: if it is determined that the number of times that the maximum value of the standard scores in multiple time windows is greater than the standard score threshold does not exceed a preset number, determining not to issue a safety warning for the lithium-ion battery.

[0019] In an optional implementation of the first aspect, the method further includes: obtaining a single cell voltage entropy value sequence of a lithium-ion battery currently calculated; storing the single cell voltage entropy value sequence of a lithium-ion battery currently calculated in a database; and updating the standard score threshold value according to the single cell voltage entropy value sequences of all lithium-ion batteries stored in the database.

[0020] In the above implementation mode, this scheme updates the standard score threshold based on the recorded single cell voltage entropy value sequence of all lithium-ion batteries, thereby realizing dynamic update of the standard threshold score, thereby avoiding the influence of seasonal environmental factors and battery aging factors on lithium-ion battery charging, and further improving the accuracy and reliability of lithium-ion battery safety warning.

[0021] In a second aspect, the present application provides a lithium-ion battery safety warning device based on cloud big data, the device comprising an acquisition module and a determination module, the acquisition module being used to acquire target charging data of the lithium-ion battery recorded in the cloud big data; wherein the target charging data comprises a continuous charging data segment in which the lithium-ion battery voltage is located in a platform area; and acquiring a single cell voltage at each moment in the continuous charging data segment; the determination module being used to determine whether to issue a safety warning to the lithium-ion battery based on the single cell voltage at each moment in the continuous charging data segment.

[0022] The above-designed lithium-ion battery safety warning device based on cloud big data, this scheme records the real-time charging data of the lithium-ion battery through cloud big data, and then obtains the continuous charging data segment in which the voltage of the lithium-ion battery is in the platform area, and then judges whether to issue a safety warning for the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data segment, thereby issuing a safety warning for the lithium-ion battery based on the continuous charging data segment in which the voltage of the lithium-ion battery is in the platform area, thereby reducing the impact of the differences in the initial capacity and initial internal resistance of each cell of the lithium-ion battery on the charging of the lithium-ion battery, thereby improving the accuracy and reliability of the lithium-ion battery safety warning.

[0023] In an optional implementation of the second aspect, the determination module is specifically used to calculate the cell voltage difference between the cell voltages at each moment in the continuous charging data segment based on the cell voltages at each moment in the continuous charging data segment; determine whether there is a cell pressure difference between the cell voltages at each moment in the continuous charging data segment that exceeds a preset pressure difference threshold; if it is determined that there is a cell pressure difference that exceeds the preset pressure difference threshold, determine to issue a safety warning for the lithium-ion battery.

[0024] In an optional implementation of the second aspect, the determination module is further specifically used to generate effective voltage segments for multiple time windows according to the cell voltage at each moment in the continuous charging data segment if it is determined that there is no cell pressure difference exceeding a preset pressure difference threshold; wherein the time window includes multiple moments in the continuous charging data segment, and the effective voltage segment is obtained by data enhancement of the cell voltage at each moment in the continuous charging data segment; for each time window, a cell voltage entropy value sequence in the time window is calculated based on the effective voltage segment of the time window, and a cell voltage entropy value sequence in each time window in the multiple time windows is obtained; and according to the cell voltage entropy value sequence in each time window in the multiple time windows, it is determined whether to issue a safety warning for the lithium-ion battery.

[0025] In an optional implementation of the second aspect, the determination module is further specifically used to divide the cell voltage at each moment in a continuous charging data segment into voltage segments of multiple time windows; calculate the median cell voltage and the cell voltage standard deviation in each time window of the multiple time windows, and generate an enhanced segment based on the median cell voltage and the cell voltage standard deviation in each time window; add the enhanced segment before the voltage segment of the time window ranked first in the multiple time windows, and add the enhanced segment after the voltage segment of the time window ranked last in the multiple time windows, to generate effective voltage segments for the multiple time windows.

[0026] In an optional implementation of the second aspect, the determination module is further specifically used to obtain, for each time window, a maximum value of the single cell voltage and a minimum value of the single cell voltage in a valid voltage segment of the time window; taking the minimum value of the single cell voltage as a starting point and a preset voltage difference as an interval to form a plurality of voltage intervals until the voltage interval covers the maximum value of the single cell voltage in the time window; counting the frequency of each single cell voltage falling in each voltage interval in the time window to obtain a probability distribution matrix corresponding to the time window; calculating a sequence of single cell voltage entropy values ​​under the time window according to the probability distribution matrix to obtain a sequence of single cell voltage entropy values ​​under each time window in the plurality of time windows.

[0027] In an optional implementation of the second aspect, the determination module is further specifically used to standardize the cell voltage entropy value sequence in each time window using a standard score and take an absolute value to obtain a maximum standard score in each time window; obtain a standard score threshold; wherein the standard score threshold is determined based on the distribution of cell voltage entropy value sequences of all lithium-ion batteries stored in a database; and determine whether to issue a safety warning for the lithium-ion battery based on the maximum standard score and the standard score threshold in multiple time windows.

[0028] In an optional implementation of the second aspect, the determination module is further specifically used to determine whether the number of times the maximum value of the standard scores in multiple time windows is greater than the standard score threshold exceeds a preset number of times; if it is determined that the number of times the maximum value of the standard scores in multiple time windows is greater than the standard score threshold exceeds a preset number of times, it is determined to issue a safety warning for the lithium-ion battery.

[0029] In an optional implementation manner of the second aspect, the determination module is further specifically configured to determine not to issue a safety warning for the lithium-ion battery if the number of times that the maximum value of the standard scores in multiple time windows is greater than the standard score threshold does not exceed a preset number.

[0030] In an optional implementation of the second aspect, the acquisition module is further used to obtain the single cell voltage entropy value sequence of the lithium-ion battery currently calculated; the device also includes a storage module and an update module, the storage module is used to store the single cell voltage entropy value sequence of the lithium-ion battery currently calculated in a database; the update module is used to update the standard score threshold according to the single cell voltage entropy value sequence of all lithium-ion batteries stored in the database.

[0031] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes any optional method described in the first aspect when executing the computer program.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs any optional method described in the first aspect.

[0033] In a fifth aspect, the present invention provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, performs the steps of any optional method described in the first aspect.

[0034] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A first flow chart of a lithium-ion battery safety early warning method based on cloud big data provided in an embodiment of the present application; Figure 2 An example diagram of a platform area of ​​a lithium-ion battery provided in an embodiment of the present application; Figure 3 A second flow chart of a lithium-ion battery safety early warning method based on cloud big data provided in an embodiment of the present application; Figure 4 A third flow chart of a lithium-ion battery safety early warning method based on cloud big data provided in an embodiment of the present application; Figure 5 A fourth flow chart of a lithium-ion battery safety early warning method based on cloud big data provided in an embodiment of the present application; Figure 6 A fifth flow chart of a lithium-ion battery safety early warning method based on cloud big data provided in an embodiment of the present application; Figure 7 A schematic diagram of the structure of a lithium-ion battery safety warning device based on cloud big data provided in an embodiment of the present application; Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0037] Icons: 700 - acquisition module; 710 - determination module; 720 - storage module; 730 - update module; 8 - electronic device; 801 - processor; 802 - memory; 803 - communication bus. DETAILED DESCRIPTION

[0038] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field 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" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0040] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0041] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] 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).

[0044] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the embodiments of the present application.

[0045] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0046] Many safety hazards of lithium-ion batteries do not appear suddenly, but are caused by gradual degradation over time. This degradation may involve the aging of battery materials, changes in the properties of the electrolyte, loss of active substances, and other aspects. These factors work together to cause the battery performance to gradually deviate from the normal state. Minor abnormal changes inside the battery may indicate abnormal battery performance and be directly or indirectly reflected in its operating data. These data include but are not limited to the battery's charge / discharge curve, operating temperature range, cycle life performance, etc. In order to effectively capture these safety risks, the battery's operating data can be monitored for a long time, and subtle abnormalities in battery performance can be amplified in the early stages of safety failures, thereby identifying potential safety risks and issuing early warnings.

[0047] At present, traditional battery safety determination methods mainly rely on simple temperature monitoring and threshold judgment, lack of accurate assessment of battery status under complex working conditions, and have the problem of low accuracy of battery safety determination methods.

[0048] Based on the above problems, the present application designs a lithium-ion battery safety warning method and storage medium based on cloud big data. The cloud big data platform can monitor the battery usage status and various performance parameters in real time, and store all historical data. It is a database that preserves the full life cycle records of lithium-ion batteries from production to commissioning to retirement and recycling, and covers a large number of batteries. It has the characteristics of strong real-time performance, large storage capacity and wide coverage. With the help of cloud big data, the current operating performance of the battery can be obtained in real time, and its performance can be diagnosed in real time. It can also evaluate the changes in its usage performance by analyzing the battery's past data performance.

[0049] This scheme records the real-time charging data of lithium-ion batteries through cloud big data, and then obtains the continuous charging data fragments in which the voltage of the lithium-ion battery is located in the platform area, and then determines whether to issue a safety warning to the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data fragment, thereby using the battery voltage recorded by the cloud big data as the original data, reducing the types of data sources relied on while also effectively ensuring data reliability, and based on the continuous charging data fragments in which the voltage of the lithium-ion battery is located in the platform area to issue a safety warning to the lithium-ion battery, thereby reducing the impact of the differences in the initial capacity and initial internal resistance of each cell of the lithium-ion battery on the charging of the lithium-ion battery, thereby improving the accuracy and reliability of the safety warning of the lithium-ion battery. Secondly, this scheme also compares the single cell voltage difference between the single cell voltages at each moment in the continuous charging data fragment with the preset pressure difference threshold, and directly issues a safety warning to the lithium-ion battery in the case of a single cell voltage difference exceeding the preset pressure difference threshold, thereby improving the efficiency of the safety warning of the lithium-ion battery. In addition, in the case of no single cell voltage exceeding the preset pressure difference threshold, this scheme realizes the safety warning of the lithium-ion battery by calculating the single cell voltage entropy, thereby further improving the accuracy and reliability of the safety warning of the lithium-ion battery. Finally, by considering the longitudinal comparison relationship of lithium-ion battery cells themselves on the timeline and the horizontal comparison relationship between different lithium-ion battery cells, a standard score threshold for comprehensive evaluation is set to provide early warning when there is a safety risk in the battery.

[0050] Based on the above ideas, the present application first provides a lithium-ion battery safety early warning method based on cloud big data, which can be applied to computing devices, including but not limited to computers, servers, chips, and cloud servers, etc. Figure 1 As shown, the lithium-ion battery safety early warning method based on cloud big data can be implemented in the following ways, including: Step S100: Acquire target charging data of the lithium-ion battery recorded in the cloud big data, where the target charging data includes a continuous charging data segment where the voltage of the lithium-ion battery is in a platform area.

[0051] Step S110: obtaining the cell voltage at each moment in the continuous charging data segment.

[0052] Step S120: judging whether to issue a safety warning to the lithium-ion battery according to the cell voltage at each moment in the continuous charging data segment.

[0053] In the above implementation, the target charging data selected by the safety warning of this solution includes a continuous charging data segment in which the voltage of the lithium-ion battery is in the platform area, and the platform area represents a relatively stable area on the curve of the voltage change over time (or capacity) during the battery charging and discharging process. Specifically, as a possible implementation, the cloud big data platform can monitor the use status and various performance parameters of the lithium-ion battery in real time. This solution can obtain the voltage and capacity changes of the battery monitored in real time during the charging process of the lithium-ion battery recorded by the cloud big data platform. When it is detected that the battery voltage enters the platform area, it starts to record and obtain the charging data of the lithium-ion battery until it is detected that the battery voltage leaves the platform area.

[0054] As another possible implementation, the present solution may perform an open circuit voltage test on the lithium-ion battery in advance, and calibrate the SOC interval of the platform area of ​​the lithium-ion battery through the open circuit voltage test result curve, for example, Figure 2 As shown, and That is, the platform area of ​​the lithium-ion battery. On this basis, for step S100, this solution can obtain the real-time charging data of the lithium-ion battery during the charging process recorded by the cloud big data platform, and the real-time charging data includes the real-time current, real-time SOC, single cell voltage and single cell temperature of the lithium-ion battery, and then intercept the charging data of the SOC interval of the lithium-ion battery in the real-time charging data where the real-time SOC value is located in the platform area, so as to obtain the target charging data of the lithium-ion battery.

[0055] When the target charging data of the lithium-ion battery is obtained in the above manner, this solution can directly obtain the single cell voltage of the lithium-ion battery at each moment in the continuous charging data segment.

[0056] Specifically, the scheme can express the single cell voltage of the lithium-ion battery at each moment in a continuous charging data segment by the following formula: ; in, Indicates continuous charging data fragment The cell voltage matrix, Indicates the battery cells in this segment The voltage sequence, express Time battery monomer The voltage value, is the number of battery cells in the lithium-ion battery pack, The number of data frames (time moments) in the current segment.

[0057] When the cell voltage at each moment in the continuous charging data segment is obtained in the above manner, this solution can determine whether to issue a safety warning for the lithium-ion battery based on the cell voltage at each moment in the continuous charging data segment.

[0058] The above-designed lithium-ion battery safety early warning method based on cloud big data records the real-time charging data of the lithium-ion battery through cloud big data, and then obtains the continuous charging data fragments in which the voltage of the lithium-ion battery is in the platform area, and then judges whether to issue a safety early warning for the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data fragments, thereby issuing a safety early warning for the lithium-ion battery based on the continuous charging data fragments in which the voltage of the lithium-ion battery is in the platform area, thereby reducing the influence of the differences in the initial capacity and initial internal resistance of each cell of the lithium-ion battery on the charging of the lithium-ion battery, thereby improving the accuracy and reliability of the lithium-ion battery safety early warning.

[0059] In an optional implementation of this embodiment, for step S120, this solution can use the following method to determine whether to issue a safety warning to the lithium-ion battery, such as Figure 3 As shown, including: Step S300: Calculating the cell voltage difference between the cell voltages at each moment in the continuous charging data segments according to the cell voltages at each moment in the continuous charging data segments.

[0060] Step S310: determine whether there is a cell voltage difference between the cell voltages at each moment in the continuous charging data segment that exceeds a preset voltage difference threshold; if so, go to step S320; if not, go to step S400.

[0061] Step S320: Determine to issue a safety warning to the lithium-ion battery.

[0062] In the above-mentioned embodiment, the single cell pressure difference of a lithium-ion battery refers to the voltage difference between different single cells in a lithium-ion battery pack composed of multiple single cells connected in series or in parallel. An excessively large single cell pressure difference between battery cells inside a lithium-ion battery may indicate a risk of failure of the lithium-ion battery. In this regard, the present embodiment first calculates the single cell pressure difference between the single cell voltages at each moment in a continuous charging data segment based on the single cell voltages at each moment in the continuous charging data segment, and then determines whether there is a single cell pressure difference between the single cell voltages at each moment in the continuous charging data segment that exceeds a preset pressure difference threshold. If there is a single cell pressure difference that exceeds the preset pressure difference threshold, it means that the lithium-ion battery has a single cell pressure difference exceeding the limit failure, which further indicates that there is a failure risk in the charging process of the lithium-ion battery. Therefore, the present scheme provides a safety warning for the lithium-ion battery.

[0063] Specifically, it is assumed that the cell voltage at each moment in the continuous charging data segment is as described above: In this case, the single pressure difference at time i calculated by this scheme is Can be: ; The sequence of cell voltage differences in this continuous charging data segment is: ; Based on the above, this solution sets the preset pressure difference threshold in advance. ,determination Is there more than If any single pressure difference exceeds If the single cell pressure difference is large, a safety warning will be issued for the lithium-ion battery.

[0064] In the above implementation mode, this scheme compares the cell voltage difference between the cell voltages at each moment in the continuous charging data segment with the preset voltage difference threshold. When there is a cell voltage difference exceeding the preset voltage difference threshold, it indicates that there is a fault risk in the charging process of the lithium-ion battery, and then directly issues a safety warning for the lithium-ion battery, thereby improving the efficiency of the safety warning of the lithium-ion battery.

[0065] In an optional implementation manner of this embodiment, when it is determined that there is no single cell voltage difference exceeding a preset voltage difference threshold value in the single cell voltage difference between the single cell voltages at each moment in the continuous charging data segment, this scheme can achieve safety warning of the lithium-ion battery in the following manner, such as Figure 4 As shown, including: Step S400: generating a plurality of effective voltage segments in time windows according to the cell voltage at each moment in the continuous charging data segment.

[0066] Step S410: for each time window, a cell voltage entropy value sequence in the time window is calculated based on the effective voltage segments in the time window, and a cell voltage entropy value sequence in each time window of the multiple time windows is obtained.

[0067] Step S420: judging whether to issue a safety warning to the lithium-ion battery according to the cell voltage entropy value sequence in each time window of the multiple time windows.

[0068] The size of the voltage entropy value reflects the complexity and unpredictability of the battery voltage fluctuation. If the voltage change of the lithium-ion battery is relatively regular and stable, its voltage entropy value is low; on the contrary, if the voltage fluctuates violently and without obvious rules, the voltage entropy value is high. Therefore, the voltage fluctuation of the lithium-ion battery charging process can be realized by the size of the voltage entropy value, and then the early warning of the lithium-ion battery charging process can be carried out.

[0069] In the above embodiment, this scheme calculates the voltage entropy of the continuous charging data segment with a fixed time window, and the time window may include multiple moments in the continuous charging data segment. After the current window calculation is completed, this scheme calculates the single cell voltage entropy of the next time window according to the step size set by the time axis movement, and so on, until the end of the time window covers the last moment of the current continuous charging data segment, but in the calculation process, the charging data at the first moment is only included in the calculation once in the first time window, and the charging data at the last moment is also only included in the calculation once in the last time window, but the data at other moments is included in the calculation at least twice, so that the data in the first time window and the last time window are used for calculation less times than the data in other windows. In order to ensure equal use of all charging data to improve the accuracy of lithium-ion battery safety warning, this scheme can first enhance the single cell voltage at each moment in the continuous charging data segment, so as to obtain effective voltage segments of multiple time windows.

[0070] Specifically, the present scheme can achieve data enhancement in the following manner: first, the present scheme can divide the cell voltage at each moment in the continuous charging data segment into voltage segments of multiple time windows, and then calculate the median cell voltage and the standard deviation of the cell voltage in each time window of the multiple time windows, and generate enhanced segments according to the median cell voltage and the standard deviation of the cell voltage in each time window, and finally add the enhanced segments before the voltage segment of the time window ranked first in the multiple time windows, and add the enhanced segments after the voltage segment of the time window ranked last in the multiple time windows, to generate effective voltage segments for the multiple time windows.

[0071] As a specific example, the cell voltage at each moment in the aforementioned continuous charging data segment of this solution is In the case of , the effective voltage fragments of multiple time windows after data enhancement are: ; Among them, the superscript Represents the original fragment The first time window, Represents the original fragment The last time window, represents the median voltage of cell j in the window, represents the standard deviation of the voltage of cell j in the window, Represents a random number between 0 and 1, and L is the length of the time window.

[0072] When valid voltage segments of multiple time windows are obtained in the above manner, this solution can calculate the monomer voltage entropy value sequence in the time window based on the valid voltage segments in the time window for each time window, and obtain the monomer voltage entropy value sequence in each time window in multiple time windows.

[0073] Specifically, this scheme can first obtain the maximum value and minimum value of the single cell voltage in the effective voltage segment of the time window for each time window, and then form multiple voltage intervals with the minimum value of the single cell voltage as the starting point and the preset voltage difference as the interval, until the voltage interval covers the maximum value of the single cell voltage in the time window; then count the frequency of each single cell voltage falling in each voltage interval in the time window to obtain the probability distribution matrix corresponding to the time window; finally, calculate the sequence of single cell voltage entropy values ​​under the time window according to the probability distribution matrix, and obtain the sequence of single cell voltage entropy values ​​under each time window in multiple time windows.

[0074] The above process of calculating the monomer voltage entropy value sequence in each time window can be illustrated by the following example: For the effective voltage fragments of multiple time windows after data enhancement processing , the single cell voltage of a lithium-ion battery within a time window can be expressed as:

[0075] Among them, the superscript Represents the effective voltage fragments of multiple time windows The Lth time window of . For a time window voltage matrix , the voltage entropy value of each monomer in the time window is calculated as follows: The maximum and minimum voltages of all cells are: ; ; The minimum value of the cell voltage in the time window is the starting point, the interval Forming voltage interval: ; Until the maximum value of the single cell voltage within the covering time window , the frequency of each monomer voltage falling in each interval within the statistical time window is obtained to obtain the probability distribution matrix: ; in, Indicates the valid segment q time window Voltage of inner cell j The probability of falling in the kth voltage interval, Indicates the number of voltage intervals; Then the monomer voltage entropy value sequence of the current window is calculated according to the probability matrix: ; ; When the cell voltage entropy value sequence in each of the multiple time windows is obtained in the above manner, this solution determines whether to issue a safety warning for the lithium-ion battery based on the cell voltage entropy value sequence in each of the multiple time windows.

[0076] In the above implementation mode, when calculating the monomer voltage entropy sequence, this scheme divides the monomer voltage into intervals to calculate the probability distribution, rather than directly using the original voltage value to calculate the probability distribution, thereby reducing the impact caused by hardware sampling errors, etc., and further improving the accuracy of the early warning.

[0077] For step S420, the present solution can determine whether to issue a safety warning to the lithium-ion battery based on the cell voltage entropy value sequence in each time window in the multiple time windows in the following manner, such as Figure 5 As shown, including: Step S500: standardize the monomer voltage entropy value sequence in each time window using a standard score and take the absolute value to obtain the maximum value of the standard score in each time window.

[0078] Step S510: Obtain the standard score threshold.

[0079] Step S520: judging whether to issue a safety warning to the lithium-ion battery according to the maximum value of the standard scores and the standard score threshold in the multiple time windows.

[0080] In the above implementation, the present solution can use the standard score method to standardize the monomer voltage entropy value sequence, so as to obtain the maximum standard score in each time window. The maximum standard score represents the value with the largest standard deviation of the monomer voltage entropy value above the average value in the monomer voltage entropy value sequence in the time window, that is, the value with the largest deviation relative to the average value.

[0081] Based on the above, this solution can obtain a standard score threshold, which can be determined based on the distribution of the single cell voltage entropy value sequence of all lithium-ion batteries stored in the cloud database, and then determine whether to issue a safety warning for the lithium-ion battery based on the maximum value of the standard score and the standard score threshold in multiple time windows.

[0082] Specifically, as a possible implementation method, the present solution can determine whether the number of times the maximum value of the standard score in multiple time windows is greater than the standard score threshold exceeds a preset number of times. If it is determined that the number of times the maximum value of the standard score in multiple time windows is greater than the standard score threshold exceeds the preset number of times, it means that the voltage of the lithium-ion battery has fluctuated violently too many times, and the lithium-ion battery has a high probability of failure. Therefore, a safety warning is issued for the lithium-ion battery; if it is determined that the number of times the maximum value of the standard score in multiple time windows is greater than the standard score threshold does not exceed the preset number of times, it means that the voltage of the lithium-ion battery is normal during charging. Therefore, no safety warning is issued for the lithium-ion battery.

[0083] Furthermore, in order to further improve the reliability and accuracy of lithium-ion battery safety warnings, the present solution can also obtain the cell number corresponding to the maximum value of the standard score in each time window that is greater than the standard score threshold, which represents the battery cell with the most violent voltage fluctuation and no obvious regularity in the time window, and then determine to issue a safety warning for the lithium-ion battery and issue a warning message, which includes a warning reminder and the cell number corresponding to the maximum value of the standard score that is greater than the standard score threshold, wherein the warning reminder can be a text message reminder or a buzzer alarm.

[0084] If it is determined that the number of times that the maximum value of the standard score in multiple time windows is greater than the standard score threshold does not exceed the preset number, it means that the fluctuation of the voltage entropy value may be caused by reasonable fluctuations in the charging process, and it is determined that no safety warning is issued for the lithium-ion battery.

[0085] Among them, as a possible implementation manner, the preset number of times required for the aforementioned determination of the present scheme can be determined according to the length of the time window. For example, if the length of the time window is L moments, then the preset number of times can be set to L. As another possible implementation manner, the preset number of times required for the determination of the present scheme can also be determined according to the number of time windows. For example, if the number of time windows is N, then the preset number of times can be set to N / 2. In this way, assuming that the number of times the maximum value of the standard score is greater than the standard score threshold exceeds the preset number of times, it means that the maximum value of the standard score in more than half of the time windows is greater than the standard score threshold.

[0086] In an optional implementation of this embodiment, this solution can also update the standard score threshold described above in real time, such as Figure 6 As shown, the following steps may be specifically included: Step S600: obtaining the currently calculated single cell voltage entropy value sequence of the lithium-ion battery.

[0087] Step S610: storing the currently calculated single cell voltage entropy value sequence of the lithium-ion battery in a database.

[0088] Step S620: updating the standard score threshold according to the cell voltage entropy value sequences of all lithium-ion batteries stored in the database.

[0089] In the above implementation, the cloud big data can record and store the single cell voltage entropy value sequence in each lithium-ion battery calculation process, and then update the standard score threshold based on the recorded single cell voltage entropy value sequence of all lithium-ion batteries, thereby realizing the dynamic update of the standard threshold score, thereby avoiding the impact of seasonal environmental factors and battery aging factors on the charging of lithium-ion batteries, and further improving the accuracy and reliability of lithium-ion battery safety warnings. Specifically, this solution can be based on the mean or standard deviation of the single cell voltage entropy value sequence of all recorded lithium-ion batteries as the standard threshold score, and can also calculate the standard score sequence corresponding to each single cell voltage entropy value sequence based on the recorded single cell voltage entropy value sequence of all lithium-ion batteries, and then based on the mean or standard deviation of all standard score sequences as the standard threshold score.

[0090] Figure 7 The present application provides a schematic structural block diagram of a lithium-ion battery safety warning device based on cloud big data. It should be understood that the device is applied to the computing device described above. Figure 1 and 6 Corresponding to the method embodiment executed in, the steps involved in the aforementioned method can be executed. The specific functions of the device can be found in the description above. To avoid repetition, detailed descriptions are appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device. Specifically, the device includes: an acquisition module 700 and a determination module 710, the acquisition module 700 is used to obtain the target charging data of the lithium-ion battery recorded in the cloud big data; wherein the target charging data includes a continuous charging data segment in which the lithium-ion battery voltage is located in the platform area; and the single cell voltage at each moment in the continuous charging data segment is obtained; the determination module 710 is used to determine whether to issue a safety warning to the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data segment.

[0091] The above-designed lithium-ion battery safety warning device based on cloud big data, this scheme records the real-time charging data of the lithium-ion battery through cloud big data, and then obtains the continuous charging data segment in which the voltage of the lithium-ion battery is in the platform area, and then judges whether to issue a safety warning for the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data segment, thereby issuing a safety warning for the lithium-ion battery based on the continuous charging data segment in which the voltage of the lithium-ion battery is in the platform area, thereby reducing the impact of the differences in the initial capacity and initial internal resistance of each cell of the lithium-ion battery on the charging of the lithium-ion battery, thereby improving the accuracy and reliability of the lithium-ion battery safety warning.

[0092] In an optional implementation of the present embodiment, the determination module 710 is specifically used to calculate the cell voltage difference between the cell voltages at each moment in the continuous charging data segment based on the cell voltages at each moment in the continuous charging data segment; determine whether there is a cell pressure difference between the cell voltages at each moment in the continuous charging data segment that exceeds a preset pressure difference threshold; if it is determined that there is a cell pressure difference that exceeds the preset pressure difference threshold, determine to issue a safety warning for the lithium-ion battery.

[0093] In an optional implementation manner of the present embodiment, the determination module 710 is further specifically used to generate effective voltage segments for multiple time windows according to the cell voltage at each moment in the continuous charging data segment if it is determined that there is no cell pressure difference exceeding a preset pressure difference threshold; wherein the time window includes multiple moments in the continuous charging data segment, and the effective voltage segment is obtained by performing data enhancement on the cell voltage at each moment in the continuous charging data segment; for each time window, a cell voltage entropy value sequence in the time window is calculated based on the effective voltage segment in the time window, and a cell voltage entropy value sequence in each time window in the multiple time windows is obtained; and according to the cell voltage entropy value sequence in each time window in the multiple time windows, it is determined whether to issue a safety warning for the lithium-ion battery.

[0094] In an optional implementation manner of the present embodiment, the determination module 710 is further specifically used to divide the cell voltage at each moment in the continuous charging data segment into voltage segments of multiple time windows; calculate the median cell voltage and the cell voltage standard deviation in each time window of the multiple time windows, and generate an enhanced segment according to the median cell voltage and the cell voltage standard deviation in each time window; add the enhanced segment before the voltage segment of the time window ranked first in the multiple time windows, and add the enhanced segment after the voltage segment of the time window ranked last in the multiple time windows, to generate effective voltage segments for the multiple time windows.

[0095] In an optional implementation manner of the present embodiment, the determination module 710 is further specifically used to obtain, for each time window, a maximum value of a single cell voltage and a minimum value of a single cell voltage in a valid voltage segment of the time window; taking the minimum value of the single cell voltage as a starting point and using a preset voltage difference as an interval to form a plurality of voltage intervals until the voltage interval covers the maximum value of the single cell voltage in the time window; counting the frequency of each single cell voltage falling in each voltage interval in the time window to obtain a probability distribution matrix corresponding to the time window; calculating a sequence of single cell voltage entropy values ​​under the time window according to the probability distribution matrix to obtain a sequence of single cell voltage entropy values ​​under each time window in the plurality of time windows.

[0096] In an optional implementation manner of the present embodiment, the determination module 710 is further specifically used to standardize the cell voltage entropy value sequence in each time window using a standard score and take the absolute value to obtain the maximum standard score in each time window; obtain a standard score threshold; wherein the standard score threshold is determined based on the distribution of the cell voltage entropy value sequence of all lithium-ion batteries stored in the database; and determine whether to issue a safety warning for the lithium-ion battery based on the maximum standard score and the standard score threshold in multiple time windows.

[0097] In an optional implementation of the present embodiment, the determination module 710 is further specifically used to determine whether the number of times the maximum value of the standard score under multiple time windows is greater than the standard score threshold exceeds a preset number of times; if it is determined that the number of times the maximum value of the standard score under multiple time windows is greater than the standard score threshold exceeds a preset number of times, it is determined to issue a safety warning for the lithium-ion battery.

[0098] In an optional implementation manner of this embodiment, the determination module 710 is further specifically configured to determine not to issue a safety warning for the lithium-ion battery if the number of times that the maximum value of the standard scores in multiple time windows is greater than the standard score threshold does not exceed a preset number.

[0099] In an optional implementation manner of the present embodiment, the acquisition module 700 is further used to acquire the single cell voltage entropy value sequence of the lithium-ion battery currently calculated; the device also includes a storage module 720 and an update module 730, the storage module 720 is used to store the single cell voltage entropy value sequence of the lithium-ion battery currently calculated in a database; the update module 730 is used to update the standard score threshold according to the single cell voltage entropy value sequence of all lithium-ion batteries stored in the database.

[0100] According to some embodiments of the present application, Figure 8As shown, the present application provides an electronic device 8, including: a processor 801 and a memory 802, the processor 801 and the memory 802 are interconnected and communicate with each other through a communication bus 803 and / or other forms of connection mechanisms (not shown), the memory 802 stores a computer program executable by the processor 801, and when the computing device is running, the processor 801 executes the computer program to execute a method of any optional implementation method, such as steps S100 to S120: obtaining target charging data of the lithium-ion battery recorded in the cloud big data, the target charging data including a continuous charging data segment in which the lithium-ion battery voltage is located in a platform area; obtaining the single cell voltage at each moment in the continuous charging data segment; judging whether to issue a safety warning to the lithium-ion battery according to the single cell voltage at each moment in the continuous charging data segment.

[0101] The present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0102] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0103] The present application provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the method in any optional implementation manner.

[0104] 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 replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate 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 lithium-ion battery safety early warning method based on cloud big data, characterized in that: The method comprises: Obtaining target charging data of the lithium-ion battery recorded in the cloud big data; wherein the target charging data includes a continuous charging data segment in which the voltage of the lithium-ion battery is in a platform area; Acquiring the cell voltage at each moment in the continuous charging data segment; According to the cell voltage at each moment in the continuous charging data segment, it is determined whether to issue a safety warning to the lithium-ion battery.

2. The method according to claim 1, characterized in that The determining whether to issue a safety warning according to the cell voltage at each moment in the continuous charging data segment includes: Calculating the cell voltage difference between the cell voltages at each moment in the continuous charging data segment according to the cell voltages at each moment in the continuous charging data segment; Determine whether there is a cell voltage difference between the cell voltages at each moment in the continuous charging data segment that exceeds a preset voltage difference threshold; If it is determined that there is a single cell pressure difference exceeding a preset pressure difference threshold, it is determined to issue a safety warning to the lithium-ion battery.

3. The method according to claim 2, characterized in that After determining whether there is a cell voltage difference between the cell voltages at each moment in the continuous charging data segments, the method further includes: If it is determined that there is no single cell voltage difference exceeding the preset voltage difference threshold, then generating multiple effective voltage segments of time windows according to the single cell voltage at each moment in the continuous charging data segment; wherein the time window includes multiple moments in the continuous charging data segment, and the effective voltage segment is obtained by data enhancement of the single cell voltage at each moment in the continuous charging data segment; For each time window, a monomer voltage entropy value sequence in the time window is calculated based on the effective voltage segments in the time window, and a monomer voltage entropy value sequence in each time window in a plurality of time windows is obtained; According to the cell voltage entropy value sequence in each time window of multiple time windows, it is determined whether to issue a safety warning for the lithium-ion battery.

4. The method according to claim 3, characterized in that The generating a plurality of effective voltage segments in time windows according to the cell voltage at each moment in the continuous charging data segments comprises: Dividing the cell voltage at each moment in the continuous charging data segment into voltage segments of a plurality of time windows; Calculating the median of the monomer voltage and the standard deviation of the monomer voltage in each of the multiple time windows, and generating an enhanced segment according to the median of the monomer voltage and the standard deviation of the monomer voltage in each time window; The enhanced segment is added before the voltage segment of the time window ranked first among the multiple time windows, and the enhanced segment is added after the voltage segment of the time window ranked last among the multiple time windows, so as to generate effective voltage segments of the multiple time windows.

5. The method according to claim 3, characterized in that: The step of calculating, for each time window, a cell voltage entropy value sequence in the time window based on an effective voltage segment in the time window, and obtaining a cell voltage entropy value sequence in each of a plurality of time windows comprises: For each time window, obtaining a maximum cell voltage and a minimum cell voltage in a valid voltage segment of the time window; Taking the minimum value of the single cell voltage as the starting point, a plurality of voltage intervals are formed by using the preset voltage difference as the interval, until the voltage interval covers the maximum value of the single cell voltage in the time window; Counting the frequency of each monomer voltage falling in each voltage interval within the time window to obtain a probability distribution matrix corresponding to the time window; The monomer voltage entropy value sequence in the time window is calculated according to the probability distribution matrix, and the monomer voltage entropy value sequence in each time window of multiple time windows is obtained.

6. The method according to claim 3, characterized in that The step of judging whether to issue a safety warning to the lithium-ion battery according to the cell voltage entropy value sequence in each time window of the multiple time windows includes: The standard score is used to standardize the monomer voltage entropy value sequence in each time window and take the absolute value to obtain the maximum value of the standard score in each time window; Obtaining a standard score threshold; wherein the standard score threshold is determined according to the sequence distribution of the single cell voltage entropy values ​​of all lithium-ion batteries stored in the database; Whether to issue a safety warning for the lithium-ion battery is determined according to the maximum value of the standard scores in multiple time windows and the standard score threshold.

7. The method according to claim 6, characterized in that The determining whether to issue a safety warning to the lithium-ion battery according to the maximum value of the standard scores in the multiple time windows and the standard score threshold comprises: Determine whether the number of times that the maximum value of the standard scores in the multiple time windows is greater than the standard score threshold exceeds a preset number; If it is determined that the maximum value of the standard scores in multiple time windows is greater than the standard score threshold for more than a preset number of times, it is determined that a safety warning is issued for the lithium-ion battery.

8. The method according to claim 7, characterized in that The method further comprises: If it is determined that the number of times that the maximum value of the standard scores in multiple time windows is greater than the standard score threshold does not exceed a preset number, it is determined that no safety warning is issued for the lithium-ion battery.

9. The method according to claim 6, characterized in that The method further comprises: Obtain the currently calculated single cell voltage entropy value sequence of the lithium-ion battery; The single cell voltage entropy value sequence of the lithium-ion battery currently calculated is stored in the database; The standard score threshold is updated according to the single cell voltage entropy value sequence of all lithium-ion batteries stored in the database.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images