Battery early warning method, device and platform and storage medium

Abstract

The embodiment of the invention discloses a battery early warning method and device, a platform and a storage medium. The battery early warning method comprises the steps of obtaining battery working condition data of a to-be-detected battery in a preset time period; performing feature extraction on the battery working condition data to obtain trend change features of the to-be-detected battery; comparing the trend change characteristic with a preset rule to obtain a comparison result, the preset rule being the trend change of the battery in a normal state; and carrying out early warning on the to-be-detected battery according to a comparison result. The trend change characteristics of the to-be-detected battery can be monitored in real time, so that whether the to-be-detected battery is abnormal or not is determined according to the trend change characteristics, early warning can be performed in time before the to-be-detected battery has a fault, and occurrence of battery faults is effectively avoided.

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a battery early warning method, device, platform and storage medium. Background Art

[0002] The battery system mechanism is complex. Multiple participants act on the battery in different ways and affect the battery status. When the battery is running, various faults may occur. Therefore, how to improve battery fault detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present invention provide a battery early warning method, device, platform and storage medium, aiming to solve the technical problem of poor battery fault detection effect.

[0004] In a first aspect, an embodiment of the present application provides a battery early warning method, the battery early warning method comprising:

[0005] Obtaining battery operating condition data of the battery to be tested within a preset time period;

[0006] Extracting features of the battery operating condition data to obtain trend change features of the battery to be tested;

[0007] Comparing the trend change feature with a preset rule to obtain a comparison result, wherein the preset rule is a trend change of the battery in a normal state;

[0008] An early warning is issued to the battery to be detected according to the comparison result.

[0009] This embodiment proposes a battery early warning method, which includes: obtaining battery operating condition data of a battery to be detected within a preset time period; extracting features from the battery operating condition data to obtain trend change features of the battery to be detected; comparing the trend change features with preset rules to obtain comparison results, where the preset rules are trend changes of the battery under normal conditions; and issuing an early warning to the battery to be detected based on the comparison results. The trend change features of the battery to be detected can be monitored in real time, so as to determine whether the battery to be detected is abnormal based on the trend change features, and an early warning can be issued in time before the battery to be detected fails, effectively avoiding the occurrence of battery failure.

[0010] In some embodiments, extracting features from the battery operating condition data to obtain trend change features of the battery to be detected includes:

[0011] Performing feature extraction on the battery operating condition data within the preset time period to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period;

[0012] Calculating difference data between the first battery operating condition data and the second battery operating condition data;

[0013] The difference data is used as the trend change feature of the battery to be detected.

[0014] In this embodiment, the steps of performing feature extraction on the battery operating condition data to obtain the trend change characteristics of the battery to be detected include: performing feature extraction on the battery operating condition data within the preset time period to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; calculating difference data between the first battery operating condition data and the second battery operating condition data; using the difference data as the trend change characteristics of the battery to be detected, and by performing feature extraction on the battery operating condition data within the preset time period, thereby calculating the difference data within this time period, the trend change characteristics of the battery to be detected can be intuitively understood based on the difference data.

[0015] In some embodiments, extracting features from the battery operating condition data to obtain trend change features of the battery to be detected includes:

[0016] Dividing the battery operating condition data within the preset time period according to a preset division rule to obtain a preset number of divided data;

[0017] Extracting features from each divided data to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period;

[0018] Calculating difference data between the first battery operating condition data and the second battery operating condition data;

[0019] The difference data is used as the trend change feature of the battery to be detected.

[0020] In this embodiment, the steps of performing feature extraction on the battery operating condition data to obtain the trend change characteristics of the battery to be detected include: performing data division on the battery operating condition data within the preset time period according to a preset division rule to obtain a preset number of divided data; performing feature extraction on each divided data to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; calculating difference data between the first battery operating condition data and the second battery operating condition data; using the difference data as the trend change characteristics of the battery to be detected, dividing the battery operating condition data into multiple intervals by performing data division on the battery operating condition data, and performing feature extraction on the divided data of each interval to calculate the difference data of each interval within the preset time period, so that the trend change characteristics of the battery to be detected can be intuitively understood based on the difference data.

[0021] In some embodiments, the trend change feature includes difference data, and the preset rule includes: a preset standard deviation;

[0022] The step of comparing the trend change feature with a preset rule to obtain a comparison result includes:

[0023] Calculate the mean variance of the difference data;

[0024] Obtaining a preset standard deviation according to the preset rule;

[0025] Calculate the deviation value by using the difference data and the mean variance;

[0026] The deviation value is compared with the preset standard deviation to obtain a comparison result.

[0027] The trend change characteristics in this embodiment include difference data, and the preset rules include preset standard deviations, so that the difference data and the preset standard deviations are compared, and the mean variance of the difference data is calculated through the difference data, so that the deviation value of each battery can be calculated according to the mean variance and the difference data, and the preset standard deviation is set as the preset rule, and the deviation value is compared with the preset standard deviation to obtain a comparison result, so as to accurately judge the trend change characteristics of the battery according to the characteristics of the mean variance and the preset standard deviation.

[0028] In some embodiments, the step of providing an early warning to the battery to be detected according to the comparison result includes:

[0029] When the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery;

[0030] An early warning is issued for the abnormal battery.

[0031] In this embodiment, when the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery, and the abnormal battery can be quickly detected according to the deviation value, thereby giving an early warning to the abnormal battery, thereby intercepting the potential risks or failures of the abnormal battery in advance, further reducing risks and losses.

[0032] In some embodiments, the step of providing an early warning to the battery to be detected according to the comparison result includes:

[0033] When the deviation value is greater than the preset standard deviation, the batteries to be detected corresponding to the deviation value are counted to obtain a preset number of abnormal batteries;

[0034] When the preset number is greater than or equal to the set number, an early warning is issued for the preset number of abnormal batteries.

[0035] In this embodiment, when the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery, and the number of abnormal batteries is counted, and the statistical results are merged until the number of abnormal batteries is greater than or equal to the set number, and a unified warning is issued for the preset number of abnormal batteries to avoid repeated warnings.

[0036] In some embodiments, the step of providing an early warning to the battery to be detected according to the comparison result includes:

[0037] Acquire a battery pack number corresponding to the abnormal battery and an identification number of the abnormal battery based on the battery operating condition data;

[0038] Determining the abnormal cause of the abnormal battery according to the deviation value;

[0039] The abnormal battery is warned according to the battery pack number, the identification number and the abnormal cause.

[0040] In this embodiment, the battery operating condition data is analyzed to determine the battery pack number corresponding to the abnormal battery and the identification number of the abnormal battery, and the abnormal cause of the abnormal battery is determined based on the deviation value, so that the abnormal battery can be quickly located through the battery pack number and the identification number, and the abnormal cause can be obtained. The potential risks and abnormal causes of the abnormal battery can be quickly located, effectively avoiding the occurrence of faults and improving the processing efficiency of abnormal batteries.

[0041] In some embodiments, the step of providing an early warning to the battery to be detected according to the comparison result includes:

[0042] Acquire an abnormal timestamp corresponding to the abnormal battery based on the battery operating condition data;

[0043] determining an abnormality level of the abnormal battery according to the deviation value;

[0044] The abnormal battery is warned according to the battery pack number, the identification number, the abnormal cause, the abnormal timestamp and the abnormal level.

[0045] In this embodiment, when an early warning is issued for the battery to be detected, the abnormal timestamp corresponding to the abnormal battery is obtained through the battery operating condition data, and the abnormal level of the abnormal battery is determined according to the deviation value, so that the abnormal battery can be quickly located through the battery pack number and the identification number, and the time when the abnormal battery is abnormal can be quickly determined through the abnormal timestamp, and the degree of abnormality of the abnormal battery can be determined according to the abnormal level, and the abnormal battery can be processed according to the abnormal cause and the abnormal level, so as to effectively avoid the occurrence of faults and improve the processing efficiency of abnormal batteries.

[0046] In some embodiments, the battery warning method further includes:

[0047] Collect deviation value sample data of abnormal batteries;

[0048] classifying the abnormal battery into a plurality of abnormal levels based on the deviation value sample data;

[0049] Establishing a first correspondence between a deviation value and a plurality of abnormal levels based on the sample deviation sample data;

[0050] Accordingly, determining the abnormality level of the abnormal battery according to the deviation value includes:

[0051] The abnormality level of the abnormal battery is obtained according to the deviation value and the first corresponding relationship.

[0052] In this embodiment, deviation value sample data of abnormal batteries are collected in advance, so that the abnormal batteries are divided into multiple abnormal levels through the deviation value sample data. The levels can be divided according to the degree of deviation, so as to establish a first corresponding relationship between the deviation value and the abnormal level, so as to quickly obtain the abnormal level of the abnormal battery in the current battery to be detected based on the deviation value and the first corresponding relationship.

[0053] In some embodiments, determining the abnormal cause of the abnormal battery according to the deviation value includes:

[0054] Analyze the deviation value sample data to obtain abnormal cause data;

[0055] Establishing a second corresponding relationship between the deviation value and the abnormal cause based on the abnormal cause data and the deviation value sample data;

[0056] The abnormality cause data is queried through the deviation value and the second corresponding relationship to obtain the abnormality cause of the abnormal battery.

[0057] In this embodiment, the deviation value samples are analyzed in advance to obtain the abnormal causes that may occur in various abnormal batteries, and a second corresponding relationship between the deviation value and the abnormal cause is established, so that the deviation value and the second corresponding relationship can be used to quickly query the abnormal cause data, and the abnormal cause of the abnormal battery can be accurately and quickly obtained.

[0058] In some embodiments, the battery warning method further includes:

[0059] Collect the original battery operating data of each battery;

[0060] Preprocessing the original battery operating condition data to obtain multi-dimensional aggregated battery operating condition data;

[0061] The multi-dimensionally aggregated battery operating condition data is classified according to preset classification standards to obtain classified battery operating condition data.

[0062] In this embodiment, after collecting the original battery operating condition data of each battery, the original battery operating condition data is preprocessed and classified to obtain accurate battery operating condition data.

[0063] In some embodiments, the step of obtaining the battery operating condition data of the battery to be detected within a preset time period includes:

[0064] In response to the detection instruction, obtaining the operating condition of the battery to be detected;

[0065] Based on the operating condition, collecting operating data of the battery to be tested within a preset time period;

[0066] Based on the battery to be detected, query corresponding configuration data from the classified battery operating condition data;

[0067] The operating data and the configuration data are used as battery operating condition data of the battery to be detected within a preset time period.

[0068] In this embodiment, when it is necessary to test the battery, the operating condition of the battery to be tested can be obtained, so that the operating data of the battery to be tested within a preset time period can be collected according to the operating condition, and the corresponding configuration data can be queried from the classified battery condition data, so that the battery condition data of the battery to be tested within the preset time period can be obtained according to the configuration data and the operating data, and different operating data can be collected according to different battery operating conditions, so that early warnings can be issued for various battery operating conditions, thereby improving the applicability of battery early warnings.

[0069] In some embodiments, the preprocessing includes data cleaning and data standardization;

[0070] The preprocessing of the original battery operating condition data to obtain multi-dimensionally aggregated battery operating condition data includes:

[0071] Performing data cleaning on the original battery operating condition data to obtain cleaned battery operating condition data;

[0072] The battery operating condition data after cleaning is standardized to obtain multi-dimensional aggregated battery operating condition data.

[0073] In this embodiment, the original operating condition data is cleaned and standardized to obtain multi-dimensional aggregated battery operating condition data, thereby improving the comprehensiveness and accuracy of the collected battery operating condition data.

[0074] In some embodiments, the battery operating condition data includes: battery charging data.

[0075] In this embodiment, the battery operating condition data includes battery charging data, so that the abnormality of the battery to be detected being charged is detected according to the battery charging data, and a charging warning is issued for the battery to be detected being charged.

[0076] In some embodiments, the battery operating condition data includes: battery charging voltage data.

[0077] In this embodiment, the battery operating condition data includes battery charging voltage data, so that the voltage abnormality of the battery to be detected being charged is detected according to the battery charging voltage data, and a voltage warning is issued for the battery to be detected being charged.

[0078] In a second aspect, an embodiment of the present invention further provides a battery warning device, the battery warning device comprising:

[0079] An acquisition module is used to acquire the battery operating condition data of the battery to be tested within a preset time period;

[0080] An extraction module, used for performing feature extraction on the battery operating condition data to obtain trend change features of the battery to be detected;

[0081] A comparison module, used to compare the trend change feature with a preset rule to obtain a comparison result, wherein the preset rule is a trend change of the battery in a normal state;

[0082] The early warning module is used to issue an early warning to the battery to be detected according to the comparison result.

[0083] The battery warning device in this embodiment obtains the battery operating condition data of the battery to be detected within a preset time period through an acquisition module, and performs feature extraction on the battery operating condition data through an extraction module to obtain the trend change characteristics of the battery to be detected; compares the trend change characteristics with preset rules through a comparison module to obtain a comparison result, wherein the preset rule is the trend change of the battery under a normal state; and issues a warning to the battery to be detected according to the comparison result through a warning module, so that the trend change characteristics of the battery to be detected can be monitored in real time, so as to determine whether the battery to be detected has an abnormality according to the trend change characteristics, and can issue a warning in time before the battery to be detected fails, thereby effectively avoiding the occurrence of battery failure.

[0084] In a third aspect, an embodiment of the present invention further provides a battery early warning platform, which is used to execute the battery early warning method as described above.

[0085] In a fourth aspect, an embodiment of the present invention further provides a storage medium, on which a battery warning program is stored, and when the battery warning program is executed by a processor, the battery warning method as described above is implemented.

[0086] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, 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 invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0088] Figure 1 A structural block diagram of an embodiment of a battery early warning platform proposed in an embodiment of the present invention;

[0089] Figure 2 A schematic diagram of a flow chart of an embodiment of a battery early warning method proposed in an embodiment of the present invention;

[0090] Figure 3 A flowchart of another embodiment of the battery warning method proposed in an embodiment of the present invention;

[0091] Figure 4 A flowchart of another embodiment of the battery warning method proposed in an embodiment of the present invention;

[0092] Figure 5 A schematic diagram of voltage variation trend of an embodiment of a battery early warning method according to an embodiment of the present invention;

[0093] Figure 6 A flowchart of another embodiment of the battery warning method proposed in an embodiment of the present invention;

[0094] Figure 7 A flowchart of another embodiment of the battery warning method proposed in an embodiment of the present invention;

[0095] Figure 8 This is a schematic diagram of the overall process of an embodiment of a battery warning method according to an embodiment of the present invention;

[0096] Fig. 9 This is a flow chart of another embodiment of the battery early warning method proposed in the embodiment of the present invention.

[0097] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0098] The following embodiments of the technical solution of the present invention 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 invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0099] 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 the present invention belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "including" and "having" in the specification and claims of the present invention and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0100] In the description of the embodiments of the present invention, 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 invention, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0101] 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 invention. The appearance of the phrase in various places 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.

[0102] In the description of the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may 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.

[0103] In the description of the embodiments of the present invention, 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).

[0104] In the description of the embodiments of the present invention, 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, and are only for the convenience of describing the embodiments of the present invention 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 limiting the embodiments of the present invention.

[0105] In the description of the embodiments of the present invention, 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, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0106] At present, battery fault detection is to diagnose the fault that has already occurred. By collecting data of the battery under various fault conditions and analyzing and diagnosing the collected data, it is impossible to predict the impending battery failure in advance, resulting in the inability to intercept potential risks or faults of the battery in advance, and the user experience is poor.

[0107] Based on the above considerations, in order to improve the effect of battery fault detection, after in-depth research, a battery early warning method, device, platform and storage medium are proposed, which are suitable for various scenarios of battery early warning during the actual use of the battery, for example, in the specific application scenario of early warning of the battery of an electric vehicle during driving or charging.

[0108] In order to better understand the embodiments of the present application, the battery warning method, device, platform and storage medium provided according to the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0109] The execution subject of the battery warning method provided in the embodiment of the present application can be a battery warning platform, which can be used to warn the batteries of electric vehicles, energy storage cabinets, and mobile power banks, and can also warn the batteries of other terminals or devices. The battery warning platform is a cloud platform, which stores full-link big data of the battery life cycle. The battery warning platform can collect the battery operating condition data of the battery to be tested under different working conditions, thereby determining the trend change characteristics of the battery to be tested based on the battery operating condition data, determining whether the battery to be tested has abnormalities based on the trend change characteristics, predicting the impending failure of the battery in advance, and conducting forward-looking analysis of the failure and trend prediction, so as to intercept potential risks or failures in advance, and effectively improve the user experience.

[0110] For the sake of convenience, here we use Figure 1 The battery warning platform shown serves as a specific application environment of the battery warning method provided in this embodiment. The battery warning platform is only a possible example, and does not limit the specific application environment of the battery warning method provided in the embodiment of the present application. The battery warning method provided in the embodiment of the present application can also be applied to other battery warning platforms.

[0111] like Figure 1 As shown, the battery early warning platform may include a collection layer, a processing layer, and an application layer.

[0112] The collection layer, processing layer and application layer are arranged in sequence. The collection layer is used as the interface for data collection in the battery early warning method. The battery operating condition data of the battery to be detected is collected through the collection layer. The collection layer can obtain the data source of the battery, including upstream and downstream related parties, from battery raw materials, battery equipment manufacturers, electric vehicle manufacturers, energy storage operators, charging pile equipment parties, operators, electric vehicle operators, users, battery recycling companies, etc., through different interfaces and standards, to collect the configuration data, measurement data, event data and other related battery operating condition data of each battery. The battery configuration data includes the vehicle series, model, manufacturer, vehicle battery type and vehicle battery model, etc., and may also include other configuration data. The measurement data may include the current data and voltage data of the battery under various working conditions. The time data includes starting charging and ending charging, etc. The collection layer of the cloud platform can collect data from various upstream and downstream links of the battery. The data source is various third parties related to the battery. Compared with obtaining single data from a single terminal, the data collected by the cloud platform is more comprehensive and covers a wider range.

[0113] The processing layer receives the battery operating condition data collected by the collection layer, pre-processes the collected data, and converts it into a physical model for unified persistent storage. The processing layer is embedded with an algorithm layer. When performing battery warning, the processing layer calls the algorithm layer and extracts features from the battery operating condition data through the algorithm service to generate feature set data. The feature set data can be the trend change features of the battery to be detected, or other feature set data, etc. This embodiment does not limit this. The processing layer of the cloud platform can process big data. Compared with the terminal, the cloud platform has a large amount of data calculation and higher calculation efficiency, so it can process and calculate the collected battery operating condition data more quickly.

[0114] The application layer receives the feature set data transmitted by the processing layer, and uses the business rules to match the feature set data generated by the algorithm layer in the application layer. Once there is feature set data that does not conform to the business rules, an early warning is generated and notified to the user, completing the generation and contact of battery failure early warning. Business rules can be set by yourself and adjusted according to user needs.

[0115] In some embodiments of the present invention, reference Figure 2 , an embodiment of the present invention proposes a battery early warning method, which may include:

[0116] Step S10: obtaining battery operating condition data of the battery to be tested within a preset time period.

[0117] It should be noted that the preset time period can be set according to the collection requirements, such as 1h, 3h, etc., and this embodiment does not limit this. The battery condition data refers to the operation data of the battery to be detected during this time period and the configuration data of the battery to be detected. The battery condition data of the battery to be detected may include the alarm data of the battery that has failed and the battery condition data of the battery that is currently operating normally.

[0118] The battery to be tested may include one battery pack or multiple battery packs, and the battery pack may include multiple battery cells. The battery to be tested may also include multiple battery cells. By testing each battery cell inside the battery pack, it is determined whether there is any abnormality in the battery cells in the battery pack.

[0119] In one example, for example, a certain automobile OEM (Original Equipment Manufacturer) manufacturer uses a new energy battery from a certain manufacturer. The relationship between the vehicle and the battery pack and the cells in the battery pack is uniformly managed by the BMS (Battery Management System). For example, during the statistical time period, multiple battery packs of the vehicle fail, resulting in alarms for several cells under the multiple battery packs. For example, there are 20W alarm data. 20W alarm data are collected through the data layer in the battery early warning platform, and 50W configuration data and measurement data of the OEM manufacturer are collected. The algorithm layer of the processing layer calculates and generates 20W various fault warning data. Therefore, the data layer collects 70W battery operating condition data of the OEM manufacturer during the statistical time period, and various algorithm layers of the processing layer generate 30W warning data. A large amount of battery operating condition data is quickly collected through the collection layer of the battery early warning platform, thereby obtaining data for the entire life cycle of the battery, enriching the range of battery operating condition data, and improving the accuracy and comprehensiveness of calculations.

[0120] Step S20: extracting features from the battery operating condition data to obtain trend change features of the battery to be tested.

[0121] It should be understood that feature extraction of battery operating condition data may include feature extraction of all measurement data of the battery to be tested in the battery operating condition data, and feature extraction may also be performed on part of the measurement data of the battery to be tested, thereby obtaining a trend characterization of the battery to be tested, that is, a trend change characteristic of the battery to be tested.

[0122] Feature extraction can be performed through statistics, dimensionality reduction, or using a feature extraction model.

[0123] The trend change characteristics of the battery to be tested may be represented in the form of a line graph, a pie chart or a table, or in other forms, which are not limited in this embodiment.

[0124] The trend change characteristics of the battery to be detected can indicate the current operating state of the battery to be detected and the operating state in the future.

[0125] Step S30: Compare the trend change characteristics with a preset rule to obtain a comparison result, where the preset rule is the trend change of the battery in a normal state.

[0126] In one example, the preset rules may be defined according to the application scenario of the battery to be detected, and the preset rules may be defined differently for different application scenarios.

[0127] For example, if the feature extracted from the battery operating condition data is a trend change feature, the preset rule is defined as the trend change of the battery under a normal state.

[0128] Optionally, by comparing the trend change characteristics with preset rules, a comparison result is obtained, so that it is sufficient to determine whether the battery to be tested has an abnormality based on the comparison.

[0129] Step S40: issuing an early warning to the battery to be detected according to the comparison result.

[0130] It is understandable that when the trend change characteristics meet the preset rules, it can be determined that the battery to be detected has no abnormality, there is no need to issue an early warning for the battery to be detected, and the trend change characteristics of the battery to be detected continue to be monitored.

[0131] When the trend change characteristics do not conform to the preset rules, it is determined that there are abnormal batteries in the batteries to be detected, and an early warning is issued for the abnormal batteries in the batteries to be detected. The early warning method can generate the cause of the abnormality and the information of the abnormal battery, etc., and can also include other information, such as the abnormality level reflecting the degree of abnormality of the abnormal battery.

[0132] The trend change feature conforming to the preset rule may be that the error between the trend change feature and the trend change of the preset rule is less than a set error, or the trend change feature is completely consistent with the trend change of the preset rule.

[0133] The battery warning method proposed in this embodiment obtains the battery operating condition data of the battery to be detected within a preset time period; extracts features from the battery operating condition data to obtain the trend change features of the battery to be detected; compares the trend change features with preset rules to obtain comparison results, where the preset rules are the trend changes of the battery under normal conditions; and warns the battery to be detected based on the comparison results. The trend change features of the battery to be detected can be monitored in real time, so as to determine whether the battery to be detected is abnormal based on the trend change features, and can issue a warning in time before the battery to be detected fails, effectively avoiding the occurrence of battery failure.

[0134] In some embodiments, reference Figure 3 Specifically, the steps of extracting features from the battery operating condition data to obtain trend change features of the battery to be tested include:

[0135] Step S201: extracting features of battery operating condition data within a preset time period to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period.

[0136] It can be understood that feature extraction of battery operating condition data within a preset time period may include extracting battery operating condition data at the start time of the preset time period and extracting battery operating condition data at the end time of the preset time period, and may also extract battery operating condition data at other times, which is not limited in this embodiment.

[0137] Optionally, the first battery operating condition data refers to the operating condition data of each battery cell in each battery pack at the starting time, and the second battery operating condition data refers to the operating condition data of each battery cell in each battery pack at the ending time. For example, the operating condition data is voltage data, the first battery operating condition data is the voltage data of each battery cell in each battery pack at the starting time, and the second battery operating condition data is the voltage data of each battery cell in each battery pack at the ending time.

[0138] Step S202: Calculate the difference data between the first battery operating condition data and the second battery operating condition data.

[0139] It should be noted that the difference between the first battery operating condition data and the second battery operating condition data is calculated, and the absolute value of the difference between the first battery operating condition data and the second battery operating condition data is taken as the difference data between the first battery operating condition data and the second battery operating condition data.

[0140] Step S203: taking the difference data as the trend change feature of the battery to be detected.

[0141] It can be understood that after obtaining the difference data, the changes of the battery to be tested within the preset time period can be determined through the difference data of the battery to be tested within the preset time period, and the change trend of the battery to be tested in each time period can be obtained based on the difference data, so as to obtain the trend change characteristics of the battery to be tested.

[0142] In this embodiment, the step of performing feature extraction on the battery operating condition data to obtain the trend change characteristics of the battery to be detected includes: performing feature extraction on the battery operating condition data within the preset time period to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; the processing layer in the cloud platform calls the algorithm layer to perform feature extraction on the battery operating condition data. Compared with the terminal, the algorithm layer in the cloud platform can quickly perform feature extraction on all battery operating condition data, with a larger amount of calculation and faster efficiency, and calculate the difference data between the first battery operating condition data and the second battery operating condition data; using the difference data as the trend change characteristics of the battery to be detected, and extracting the characteristics of the battery operating condition data within the preset time period to calculate the difference data within this time period, so that the trend change characteristics of the battery to be detected can be intuitively understood based on the difference data.

[0143] In some embodiments, the battery operating status data includes: battery charging data.

[0144] It should be understood that the battery operating condition data may be battery charging data, battery discharging data, or other data.

[0145] By acquiring the battery operating condition data of the battery to be detected under different operating conditions, the abnormalities of the battery to be detected under different operating conditions can be detected in real time, and early warnings can be issued in time for batteries with abnormalities.

[0146] In this embodiment, the battery operating condition data includes battery charging data, so that the abnormality of the battery to be detected being charged is detected according to the battery charging data, and a charging warning is issued for the battery to be detected being charged.

[0147] In some embodiments, reference Figure 4 Specifically, the steps of extracting features from the battery operating condition data to obtain trend change features of the battery to be tested include:

[0148] Step S201 ′: dividing the battery operating condition data within a preset time period according to a preset division rule to obtain a preset number of divided data.

[0149] It is understandable that in order to improve the accuracy of extracting the trend change characteristics of the battery to be detected, the battery operating condition data within a preset time period may be divided first.

[0150] The preset classification rules refer to the rules set in advance for dividing the battery operating condition data. The preset classification rules can be one or more combinations of battery pack number, vehicle type, battery SOC (State of charge), battery type, or other classification rules. They can be set according to user needs and the status of the battery to be tested.

[0151] After the preset division rule is determined, the battery operating condition data within the preset time period can be divided according to the preset division rule, and the battery operating condition data can be divided into multiple intervals to obtain a preset number of divided data. The divided data refers to the battery operating condition data of each interval, and the number of intervals can be adjusted according to the modification of the division rule.

[0152] In one example, if the preset division rule is to divide the data according to the SOC of the battery to be detected, multiple division data are obtained. For example, the data is divided according to the SOC of the battery to be detected, and six division data are obtained: [40,45], [50,55], [60,65], [70,75], [80,85], [90,95]. The SOC of the battery to be detected can also be divided to obtain three division data: [10,30], [40,60], [70,90], etc. Different division data can be obtained according to different division dimensions.

[0153] Step S202 ′: extracting features from each divided data to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period.

[0154] It should be noted that the first battery operating condition data at the start time of the preset time period and the second battery operating condition data at the end time of each divided data can be extracted respectively, and the first battery operating condition data in each divided data and the second battery operating condition data in each divided data can be summarized to obtain the first battery operating condition data at the start time of the preset time period and the second battery operating condition data at the end time of the preset time period.

[0155] Step S203 ′: Calculate the difference data between the first battery operating condition data and the second battery operating condition data.

[0156] It should be noted that the difference between the first battery operating condition data and the second battery operating condition data is calculated, and the absolute value of the difference between the first battery operating condition data and the second battery operating condition data is taken as the difference data between the first battery operating condition data and the second battery operating condition data.

[0157] Step S204 ′: taking the difference data as the trend change feature of the battery to be tested.

[0158] The change of the battery to be detected within the preset time period is determined by the difference data of the battery to be detected within the preset time period, and the change trend of the battery to be detected in each time period can be obtained according to the difference data, so as to obtain the trend change characteristics of the battery to be detected.

[0159] In this embodiment, the steps of extracting features from the battery operating condition data to obtain the trend change features of the battery to be detected include: dividing the battery operating condition data within a preset time period according to a preset division rule to obtain a preset number of divided data; extracting features from each divided data to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; calculating difference data between the first battery operating condition data and the second battery operating condition data; using the difference data as the trend change features of the battery to be detected, dividing the battery operating condition data into multiple intervals by dividing the battery operating condition data, and extracting features from the data of each interval to calculate the difference data of each interval within the preset time period, so that the trend change features of the battery to be detected can be intuitively understood based on the difference data.

[0160] In some embodiments, the battery operating condition data includes battery charging voltage data.

[0161] In an example, the battery operating condition data may be voltage data when the battery is charging, or current data, power data, etc. when the battery is charging. This embodiment does not limit this. This embodiment is described by taking voltage data when the battery is charging as an example.

[0162] During normal charging of a battery pack, the voltage trend changes should be similar. If a battery has a consistency difference, such as inconsistent internal resistance or capacity of the battery cell, or lithium deposition or short circuit, the voltage trend of the battery during charging will be different from the voltage trend of the battery in normal state. Figure 5 As shown, Figure 5 It is the voltage change trend in the charging data of each battery to be detected within a preset time period. During this time period, the voltage change trends of battery 2, battery 3 and battery 4 are roughly the same, and there are certain deviations between battery 1 and battery 5. Battery 1 and battery 5 may be abnormal. The voltage change trend of battery 1 and the voltage change trend of battery 5 can be further compared with the preset rules, and whether battery 1 and battery 5 are abnormal can be judged according to the comparison results, so as to warn the abnormal batteries.

[0163] In this embodiment, the battery operating condition data includes battery charging voltage data, so that the voltage abnormality of the battery to be detected being charged is detected according to the battery charging voltage data, and a voltage warning is issued for the battery to be detected being charged.

[0164] In some embodiments, reference Figure 6 ,The trend change characteristics include difference data, and the preset rules include: preset standard deviation;

[0165] The steps of comparing the trend change characteristics with the preset rules and obtaining the comparison results include:

[0166] Step S301: Calculate the mean variance of the difference data.

[0167] It should be noted that the trend change characteristics can be represented by difference data, and the preset rules can be represented by preset standard deviations.

[0168] The mean variance feature can be used to determine whether there are batteries that do not meet the preset rules, so the mean variance of the difference data can be calculated.

[0169] Step S302: Obtaining a preset standard deviation according to a preset rule.

[0170] The preset rule can be represented by a preset standard deviation, so the preset standard deviation can be obtained according to the preset rule. A comparison multiple N can also be set, and N times the preset standard deviation is used as the final preset standard deviation.

[0171] Step S303: Calculate the deviation value through the difference data and the mean variance.

[0172] After the mean variance is calculated, the deviation value of each battery to be tested can be calculated through the difference data and the mean variance.

[0173] It should be noted that, for example, if the difference data is Δm, the mean variance calculated based on the difference data is μ, and the deviation value is: |Δm-μ|.

[0174] Step S304: Compare the deviation value with the preset standard deviation to obtain a comparison result.

[0175] In a specific implementation, the deviation value may be compared with a preset standard deviation to obtain a comparison result.

[0176] The comparison result may be that the deviation value is greater than a preset standard deviation or the deviation value is less than or equal to the preset standard deviation.

[0177] The trend change characteristics in this embodiment include difference data, and the preset rules include preset standard deviations, so that the difference data and the preset standard deviations are compared, and the mean variance of the difference data is calculated through the difference data, so that the deviation value of each battery can be calculated according to the mean variance and the difference data, and the preset standard deviation is set as the preset rule, and the deviation value is compared with the preset standard deviation to obtain a comparison result, so as to accurately judge the trend change characteristics of the battery according to the characteristics of the mean variance and the preset standard deviation.

[0178] In some embodiments, reference Figure 7 The steps of giving an early warning to the battery to be tested according to the comparison result include:

[0179] Step S401: when the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery.

[0180] Step S402: Issue an early warning for abnormal batteries.

[0181] It can be understood that when the deviation value is greater than the preset standard deviation, it is considered that the battery to be detected corresponding to this deviation value does not meet the preset rules, and the battery to be detected corresponding to the deviation value is regarded as an abnormal battery, and the abnormal battery is an outlier battery whose deviation value deviates from the preset standard deviation.

[0182] The number of abnormal batteries may be one or more, and the warning method may be to immediately warn the abnormal battery when one abnormal battery is detected.

[0183] Considering that there may be multiple abnormal batteries, the number of abnormal batteries can be counted after the abnormal batteries are detected. When the number of abnormal batteries reaches a set value, a unified warning is issued for the abnormal batteries.

[0184] In some embodiments, the step of issuing an early warning to the battery to be detected according to the comparison result further includes:

[0185] When the deviation value is greater than the preset standard deviation, the batteries to be detected corresponding to the deviation value are counted to obtain a preset number of abnormal batteries; when the preset number is greater than the set number, the preset number of abnormal batteries are warned.

[0186] The preset number can be 10, 20, etc., and this embodiment does not limit this. The set number can be adjusted according to the number of abnormal batteries. When the preset number of abnormal batteries is greater than or equal to the set number, an abnormal battery warning is triggered. When the preset number of abnormal batteries is less than the set number, the remaining batteries to be detected continue to be detected.

[0187] It can be understood that when the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery, and the number of abnormal batteries is counted, and the statistical results are merged until the number of abnormal batteries is greater than the set number, and a unified warning is issued for the preset number of abnormal batteries to avoid repeated warnings.

[0188] like Figure 8 As shown, Figure 8 The overall flow chart of the battery early warning method is as follows. For example, the battery operating condition data is the voltage data of the battery charging. The voltage data of the battery charging collected within a preset time period are grouped, and the feature extraction is performed on the grouped voltage data to obtain the voltage trend change feature ΔV, and the mean square error of the voltage trend change feature ΔV is calculated. The voltage deviation value is obtained by the mean square error and the voltage trend change feature ΔV, and the voltage deviation value is compared with the preset standard deviation. When the voltage deviation value is greater than the preset standard deviation, the abnormal result of the battery abnormality is determined, and the number of abnormal batteries is combined and counted. When the number of abnormal batteries is greater than the set number, the abnormal cause and the information of the abnormal battery are output for early warning.

[0189] In this embodiment, when the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery, and the abnormal battery can be quickly detected according to the deviation value, thereby giving an early warning to the abnormal battery, thereby intercepting the potential risks or failures of the abnormal battery in advance, further reducing risks and losses.

[0190] In one example, after an abnormal battery is determined, information about the abnormal battery can be obtained, so that when an abnormal battery is warned, the information about the abnormal battery is output, making it convenient for a user to quickly locate the abnormal battery based on the information about the abnormal battery.

[0191] In some embodiments, reference Fig. 9 The steps of giving an early warning to the battery to be tested according to the comparison result include:

[0192] Step S403: Obtain the battery pack number corresponding to the abnormal battery and the identification number of the abnormal battery based on the battery operating condition data.

[0193] The battery operating condition data includes the configuration data of the battery to be tested. The battery pack number of the abnormal battery and the identification number of the abnormal battery can be obtained based on the configuration data of the battery to be tested. The identification number of the abnormal battery is a unique identification number for identifying the abnormal battery. Each battery has a unique identification number. Therefore, the abnormal battery can be quickly queried among the batteries to be tested through the identification number of the abnormal battery.

[0194] Step S404: Determine the abnormal cause of the abnormal battery according to the deviation value.

[0195] It should be noted that the deviation value of the abnormal battery can be analyzed to determine the abnormal cause of the abnormal battery.

[0196] For example, the battery operating condition data of the battery to be tested is the voltage data when the battery is charging. The voltage deviation value is obtained by calculating the voltage data. If the voltage deviation value is greater than the preset standard deviation, the battery corresponding to this voltage deviation value may have abnormal reasons such as consistency difference, lithium deposition and internal short circuit.

[0197] Step S405: Issue an early warning to abnormal batteries based on the battery pack number, identification number and abnormality cause.

[0198] It is understandable that after obtaining the battery pack number where the abnormal cause is located, the identification number of the abnormal battery and the abnormal cause of the abnormal battery, the battery pack number, identification number and abnormal cause can be output to warn the abnormal battery. The abnormal battery can be a battery that has already failed or a battery that may fail in the future. The abnormal cause can be used to locate the fault of the abnormal battery, and the battery that may fail in the future can be analyzed in advance and the trend can be predicted.

[0199] In this embodiment, the battery operating condition data is analyzed to determine the battery pack number corresponding to the abnormal battery and the identification number of the abnormal battery, and the abnormal cause of the abnormal battery is determined based on the deviation value, so that the abnormal battery can be quickly located through the battery pack number and the identification number, and the abnormal cause can be obtained. The potential risks and abnormal causes of the abnormal battery can be quickly located, effectively avoiding the occurrence of faults and improving the processing efficiency of abnormal batteries.

[0200] In some embodiments, in order to more accurately warn of abnormal batteries, the step of warning of abnormal batteries further includes:

[0201] Obtaining an abnormal timestamp corresponding to an abnormal battery based on battery operating condition data;

[0202] Determine the abnormal level of the abnormal battery according to the deviation value;

[0203] Abnormal batteries are warned through battery pack number, identification number, abnormal cause, abnormal timestamp and abnormal level.

[0204] It should be noted that the battery operating condition data also includes the event data of abnormal batteries, such as the time when the trend change characteristics of the abnormal battery begin to not conform to the preset rules, or the time when the trend change characteristics of the abnormal battery end to not conform to the preset rules. Thus, the abnormal timestamp corresponding to the abnormal battery is obtained. The abnormal level of the abnormal battery can be queried by the deviation value. The abnormal level represents the degree to which the deviation value of the abnormal battery deviates from the preset standard deviation. The greater the deviation value of the abnormal battery deviates from the preset standard deviation, the higher the abnormal level.

[0205] By using the abnormal timestamp and abnormal level as warning information, the time when the abnormality exists can be quickly queried based on the abnormal time difference, and the priority of abnormal battery processing can be determined based on the abnormal level.

[0206] In this embodiment, when an early warning is issued for the battery to be detected, the abnormal timestamp corresponding to the abnormal battery is obtained through the battery operating condition data, and the abnormal level of the abnormal battery is determined according to the deviation value, so that the abnormal battery can be quickly located through the battery pack number and the identification number, and the time when the abnormal battery is abnormal can be quickly determined through the abnormal timestamp, and the degree of abnormality of the abnormal battery can be determined according to the abnormal level, and the abnormal battery can be processed according to the abnormal cause and the abnormal level, so as to effectively avoid the occurrence of faults and improve the processing efficiency of abnormal batteries.

[0207] In some embodiments, the battery warning method further includes:

[0208] Collect deviation value sample data of abnormal batteries;

[0209] The deviation value sample data of the battery can be collected in advance, and the deviation value sample data refers to the deviation values ​​of each abnormal battery counted in advance.

[0210] Classifying abnormal batteries into multiple abnormal levels based on deviation value sample data;

[0211] By dividing the deviation value sample data, the abnormal batteries are divided into multiple levels. For example, the deviation value sample data includes 1 to 4. By dividing the abnormal batteries into three levels according to the deviation value sample data, the deviation value corresponding to the abnormal battery of the first level is [1, 2), the deviation value corresponding to the abnormal battery of the second level is [2, 3), and the deviation value corresponding to the abnormal battery of the third level is [3, 4). Therefore, the abnormal batteries can be divided into multiple abnormal levels based on the deviation value sample data, so as to determine the abnormal level of the abnormal battery according to the deviation value.

[0212] Establishing a first correspondence between the deviation value and a plurality of abnormal levels based on the sample deviation sample data;

[0213] By establishing a mapping relationship between the deviation value and a plurality of abnormal levels, ie, a first corresponding relationship, the abnormal level of the abnormal battery can be quickly obtained according to the deviation value.

[0214] Accordingly, the abnormal level of the abnormal battery is determined according to the deviation value, including:

[0215] The abnormality level of the abnormal battery is obtained according to the deviation value and the first corresponding relationship.

[0216] In one example, each abnormal level can be queried through the deviation value of the abnormal battery and the first corresponding relationship, so as to quickly determine which abnormal level the abnormal battery is in.

[0217] In this embodiment, deviation value sample data of abnormal batteries are collected in advance, so that the abnormal batteries are divided into multiple abnormal levels through the deviation value sample data. The levels can be divided according to the degree of deviation, so as to establish a first corresponding relationship between the deviation value and the abnormal level, so as to quickly obtain the abnormal level of the abnormal battery in the current battery to be detected based on the deviation value and the first corresponding relationship.

[0218] In some embodiments, determining the abnormal cause of the abnormal battery according to the deviation value includes:

[0219] Analyze the deviation value sample data to obtain abnormal cause data;

[0220] The deviation value sample data is the deviation value corresponding to the battery abnormalities caused by multiple different reasons. The deviation values ​​of the abnormal batteries can be analyzed through experiments to determine the reasons for the abnormalities of each abnormal battery, and the reasons are counted to obtain abnormal reason data.

[0221] Establishing a second corresponding relationship between the deviation value and the abnormal cause based on the abnormal cause data and the deviation value sample data;

[0222] The abnormal cause data and the deviation value sample data are used to correspond the abnormal cause to the deviation value one by one, thereby establishing a mapping relationship between the deviation value and the abnormal cause, that is, a second corresponding relationship.

[0223] The abnormality cause data is queried through the deviation value and the second corresponding relationship to obtain the abnormality cause of the abnormal battery.

[0224] All abnormality cause data can be queried through the deviation value and the mapping relationship between the deviation value and the abnormality cause, so as to obtain the abnormality cause of the abnormal battery.

[0225] In this embodiment, the deviation value samples are analyzed in advance to obtain the abnormal causes that may occur in various abnormal batteries, and a second corresponding relationship between the deviation value and the abnormal cause is established, so that the deviation value and the second corresponding relationship can be used to quickly query the abnormal cause data, and the abnormal cause of the abnormal battery can be accurately and quickly obtained.

[0226] In some embodiments, the battery warning method further includes:

[0227] Collect the original battery operating data of each battery;

[0228] Preprocess the original battery operating condition data to obtain multi-dimensional aggregated battery operating condition data;

[0229] The multi-dimensionally aggregated battery operating condition data is classified according to preset classification standards to obtain classified battery operating condition data.

[0230] Raw battery condition data refers to data that has not been screened or processed. Since raw electromagnetic condition data may contain a large amount of invalid or duplicate data, the raw battery condition data can be preprocessed through the processing layer in the battery early warning platform to filter out useless data. Preprocessing may include data cleaning, data conversion, data standardization, and data integration of raw battery condition data. The processing layer of the battery early warning platform preprocesses a large amount of raw battery condition data to obtain multi-dimensional aggregated battery condition data. Compared with terminal data processing, the battery early warning platform has a larger processing volume and faster processing efficiency.

[0231] Since the collected battery operating condition data comes from different providers and is relatively messy, it is necessary to organize and classify the data to obtain classified battery operating condition data.

[0232] The preset classification standards can be classified according to the prescribed unified standards, and can also be added or modified according to needs. For example, multi-dimensional aggregated battery operating condition data can be classified according to the "National Standard GBT 32960.3-2016-Unified Standard for Extension of Technical Specifications for Electric Vehicle Remote Service and Management Systems".

[0233] In this embodiment, after collecting the original battery operating condition data of each battery, the original battery operating condition data is preprocessed and classified to obtain accurate battery operating condition data.

[0234] In some embodiments, obtaining battery operating condition data of a battery to be detected within a preset time period includes:

[0235] In response to the detection instruction, obtaining the operating condition of the battery to be detected;

[0236] The detection instruction is an instruction sent by the user to test the battery. After receiving the detection instruction, the battery to be tested can be determined, and the operating condition of the battery to be tested can be obtained. The operating condition can be a charging condition, a discharging condition, a standby condition, etc.

[0237] Collecting the operating data of the battery to be tested within a preset time period based on the operating conditions;

[0238] After the operating condition is determined, the operating data of the battery to be tested within a preset time period may be collected. For example, if the operating condition is a charging condition, the charging data of the battery to be tested within the preset time period may be collected.

[0239] Based on the battery to be detected, query corresponding configuration data from the classified battery operating condition data;

[0240] The operating data and the configuration data are used as the battery operating condition data of the battery to be tested within a preset time period.

[0241] When testing the battery to be tested, it is also necessary to obtain information such as the type, quantity, identification number, etc. of the battery to be tested, so as to facilitate subsequent inquiries about abnormal conditions of the battery to be tested. Therefore, the corresponding configuration data can be queried from the classified battery operating condition data based on the battery to be tested. Since the classified battery operating condition data is data of different battery packs, the classified battery operating condition data can be queried based on the battery to be tested to obtain the configuration data belonging to the battery to be tested.

[0242] Thereby, the operating data and configuration data of the battery to be detected are used as the battery operating condition data of the battery to be detected within a preset time period.

[0243] In this embodiment, when it is necessary to test the battery, the operating condition of the battery to be tested can be obtained, so that the operating data of the battery to be tested within a preset time period can be collected according to the operating condition, and the corresponding configuration data can be queried from the classified battery condition data, so that the battery condition data of the battery to be tested within the preset time period can be obtained according to the configuration data and the operating data, and different operating data can be collected according to different battery operating conditions, so that early warnings can be issued for various battery operating conditions, thereby improving the applicability of battery early warnings.

[0244] In some embodiments, preprocessing includes data cleaning and data standardization; the step of preprocessing the original battery operating condition data to obtain multi-dimensional aggregated battery operating condition data includes:

[0245] Performing data cleaning on the original battery operating condition data to obtain cleaned battery operating condition data;

[0246] The battery operating condition data after cleaning is standardized to obtain multi-dimensional aggregated battery operating condition data.

[0247] Data cleaning can be achieved through binning, clustering and regression methods. For example, the original battery operating condition data can be cleaned through clustering, thereby eliminating the data far away from the cluster center to obtain the cleaned battery operating condition data.

[0248] The battery operating condition data after cleaning contains less or no repeated and irrelevant data, thereby improving the accuracy of detection.

[0249] Data standardization can be done by normalization processing, centralization processing, etc. By standardizing the battery operating condition data after cleaning, standard multi-dimensional aggregated battery operating condition data can be obtained.

[0250] In this embodiment, the original operating condition data is cleaned and standardized to obtain multi-dimensional aggregated battery operating condition data, thereby improving the comprehensiveness of the collected battery operating condition data.

[0251] To achieve the above purpose, an embodiment of the present invention further provides a battery warning device, the battery warning device comprising:

[0252] An acquisition module is used to acquire the battery operating condition data of the battery to be tested within a preset time period;

[0253] An extraction module is used to extract features from battery operating condition data to obtain trend change features of the battery to be tested;

[0254] A comparison module, used to compare the trend change characteristics with a preset rule to obtain a comparison result, wherein the preset rule is a trend change of the battery in a normal state;

[0255] The early warning module is used to issue an early warning to the battery to be detected according to the comparison result.

[0256] To achieve the above objective, an embodiment of the present invention further provides a battery early warning platform, which is used to execute the battery early warning method as described above.

[0257] To achieve the above objective, an embodiment of the present invention further provides a storage medium, on which a battery warning program is stored. When the battery warning program is executed by a processor, the battery warning method as described above is implemented.

[0258] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A battery early warning method, characterized in that: The battery early warning method comprises: Obtaining battery operating condition data of the battery to be tested within a preset time period; Extracting features of the battery operating condition data to obtain trend change features of the battery to be tested; Comparing the trend change feature with a preset rule to obtain a comparison result, wherein the preset rule is a trend change of the battery in a normal state; An early warning is issued to the battery to be detected according to the comparison result.

2. The battery early warning method according to claim 1, characterized in that: The extracting features of the battery operating condition data to obtain trend change features of the battery to be detected includes: Performing feature extraction on the battery operating condition data within the preset time period to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; Calculating difference data between the first battery operating condition data and the second battery operating condition data; The difference data is used as the trend change feature of the battery to be detected.

3. The battery early warning method according to claim 1, characterized in that: The extracting features of the battery operating condition data to obtain trend change features of the battery to be detected includes: Dividing the battery operating condition data within the preset time period according to a preset division rule to obtain a preset number of divided data; Extracting features from each divided data to obtain first battery operating condition data at the start time of the preset time period and second battery operating condition data at the end time of the preset time period; Calculating difference data between the first battery operating condition data and the second battery operating condition data; The difference data is used as the trend change feature of the battery to be detected.

4. The battery early warning method according to claim 1, characterized in that: The trend change feature includes difference data, and the preset rules include: a preset standard deviation; The step of comparing the trend change feature with a preset rule to obtain a comparison result includes: Calculate the mean variance of the difference data; Obtaining a preset standard deviation according to the preset rule; Calculate the deviation value by using the difference data and the mean variance; The deviation value is compared with the preset standard deviation to obtain a comparison result.

5. The battery early warning method according to claim 4, characterized in that: The step of issuing an early warning to the battery to be detected according to the comparison result includes: When the deviation value is greater than the preset standard deviation, the battery to be detected corresponding to the deviation value is regarded as an abnormal battery; An early warning is issued for the abnormal battery.

6. The battery early warning method according to claim 4, characterized in that: The step of issuing an early warning to the battery to be detected according to the comparison result includes: When the deviation value is greater than the preset standard deviation, the batteries to be detected corresponding to the deviation value are counted to obtain a preset number of abnormal batteries; When the preset number is greater than or equal to the set number, an early warning is issued for the preset number of abnormal batteries.

7. The battery early warning method according to claim 5 or 6, characterized in that: The step of issuing an early warning to the battery to be detected according to the comparison result includes: Acquire a battery pack number corresponding to the abnormal battery and an identification number of the abnormal battery based on the battery operating condition data; Determining the abnormal cause of the abnormal battery according to the deviation value; The abnormal battery is warned according to the battery pack number, the identification number and the abnormal cause.

8. The battery early warning method according to claim 7, characterized in that: The step of issuing an early warning to the battery to be detected according to the comparison result includes: Acquire an abnormal timestamp corresponding to the abnormal battery based on the battery operating condition data; determining an abnormality level of the abnormal battery according to the deviation value; The abnormal battery is warned according to the battery pack number, the identification number, the abnormal cause, the abnormal timestamp and the abnormal level.

9. The battery early warning method according to claim 8, characterized in that: The battery early warning method further includes: Collect deviation value sample data of abnormal batteries; classifying the abnormal battery into a plurality of abnormal levels based on the deviation value sample data; Establishing a first correspondence between a deviation value and a plurality of abnormal levels based on the sample deviation sample data; Accordingly, determining the abnormality level of the abnormal battery according to the deviation value includes: The abnormality level of the abnormal battery is obtained according to the deviation value and the first corresponding relationship.

10. The battery early warning method according to claim 9, characterized in that: The determining the abnormal cause of the abnormal battery according to the deviation value includes: Analyze the deviation value sample data to obtain abnormal cause data; Establishing a second corresponding relationship between the deviation value and the abnormal cause based on the abnormal cause data and the deviation value sample data; The abnormality cause data is queried through the deviation value and the second corresponding relationship to obtain the abnormality cause of the abnormal battery.

11. The battery early warning method according to any one of claims 1 to 10, characterized in that: The battery early warning method further includes: Collect the original battery operating data of each battery; Preprocessing the original battery operating condition data to obtain multi-dimensional aggregated battery operating condition data; The multi-dimensionally aggregated battery operating condition data is classified according to preset classification standards to obtain classified battery operating condition data.

12. The battery early warning method according to claim 11, characterized in that: The step of obtaining the battery operating condition data of the battery to be detected within a preset time period includes: In response to the detection instruction, obtaining the operating condition of the battery to be detected; Based on the operating condition, collecting operating data of the battery to be tested within a preset time period; Based on the battery to be detected, query corresponding configuration data from the classified battery operating condition data; The operating data and the configuration data are used as battery operating condition data of the battery to be detected within a preset time period.

13. The battery early warning method according to claim 11, characterized in that: The preprocessing includes data cleaning and data standardization; The preprocessing of the original battery operating condition data to obtain multi-dimensionally aggregated battery operating condition data includes: Performing data cleaning on the original battery operating condition data to obtain cleaned battery operating condition data; The battery operating condition data after cleaning is standardized to obtain multi-dimensional aggregated battery operating condition data.

14. The battery warning method according to any one of claims 1 to 13, characterized in that: The battery operating condition data includes: battery charging data.

15. The battery warning method according to any one of claims 1 to 13, characterized in that: The battery operating condition data includes: battery charging voltage data.

16. A battery warning device, characterized in that: The battery early warning device comprises: An acquisition module is used to acquire the battery operating condition data of the battery to be tested within a preset time period; An extraction module, used for performing feature extraction on the battery operating condition data to obtain trend change features of the battery to be detected; A comparison module, used to compare the trend change feature with a preset rule to obtain a comparison result, wherein the preset rule is a trend change of the battery in a normal state; The early warning module is used to issue an early warning to the battery to be detected according to the comparison result.

17. A battery early warning platform, characterized in that: The battery early warning platform is used to execute the battery early warning method according to any one of claims 1 to 15.

18. A storage medium, characterized in that: The storage medium stores a battery warning program, and when the battery warning program is executed by the processor, the battery warning method according to any one of claims 1 to 15 is implemented.

Images