Method and device for lithium battery anomaly prediction, electronic equipment and readable storage medium

Abstract

The application relates to a lithium battery anomaly prediction method and device, electronic equipment and readable storage medium, and relates to the technical field of lithium battery detection. The method comprises the following steps: acquiring current charging current data and current charging time data corresponding to each lithium battery respectively, establishing a first corresponding relationship of the current charging current data and the current charging time data, then inputting the first corresponding relationship, the current charging time data and the current charging current data into a prediction model, determining an anomaly prediction battery and anomaly prediction charging data, acquiring position information of the anomaly prediction battery, and controlling the display of the position information and the anomaly prediction charging data. The lithium battery anomaly prediction method, device, electronic equipment and readable storage medium provided by the application can discover the anomaly of the lithium battery in advance, so that the lithium battery anomaly can be avoided.

Description

Technical Field

[0001] This application relates to the field of lithium battery testing technology, and in particular to a method, apparatus, electronic device, and readable storage medium for predicting lithium battery anomalies. Background Technology

[0002] With the development of science and technology, the lithium battery industry, as an important part of the new energy field, has received increasing attention for the performance of lithium batteries. Lithium battery capacity is an important indicator for measuring lithium battery performance. During use, lithium battery cells will experience aging and degradation, resulting in a decrease in lithium battery capacity. Lithium batteries can also be damaged by external impacts, i.e., lithium batteries will malfunction.

[0003] During their research, the inventors discovered that with the widespread use of lithium batteries, people have increasingly higher requirements for their capacity. However, due to the inability to predict lithium battery malfunctions, the capacity of lithium batteries has decreased. Therefore, how to prevent lithium batteries from malfunctioning has become a key issue. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, electronic device, and readable storage medium for predicting abnormalities in lithium batteries, in order to solve at least one of the above problems.

[0005] The above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0006] Firstly, a method for predicting anomalies in lithium batteries is provided, the method comprising:

[0007] Obtain the current charging data for each lithium battery, including: current charging current data and current charging time data;

[0008] Establish a first correspondence between the current charging current data and the current charging time data;

[0009] The first correspondence, the current charging current data, and the current charging time data are input into the prediction model to determine the abnormal predicted battery and the abnormal predicted charging data.

[0010] Obtain the location information of the abnormal prediction battery, and control the display of the location information and the abnormal prediction charging data.

[0011] In one possible implementation, the step of inputting the first correspondence, the current charging current data, and the current charging time data into the prediction model to determine the abnormal prediction battery and the abnormal prediction charging data includes: normalizing the current charging current data and the current charging time data.

[0012] The first correspondence, along with the normalized current charging current data and the current charging time data, are input into the prediction model to obtain the abnormal prediction battery.

[0013] In another possible implementation, before inputting the first correspondence relationship and the normalized current charging current data and the current charging time data into the prediction model to obtain the abnormal prediction battery, the method further includes: obtaining the historical abnormal charging data corresponding to each lithium battery, wherein the historical abnormal charging data includes: historical abnormal charging current data and historical abnormal charging time data.

[0014] Establish a second correspondence between the historical abnormal charging current data and the historical abnormal charging time data;

[0015] The historical abnormal charging current data and the historical abnormal charging time data are normalized.

[0016] The second correspondence, along with the normalized historical abnormal charging current data and the historical abnormal charging time data, are input into the original model for training to obtain the trained prediction model.

[0017] In another possible implementation, after establishing the first correspondence between the current charging current data and the current charging time data, the method further includes:

[0018] The current charging current data is compared with the corresponding first preset threshold to determine the current abnormal charging current data.

[0019] Based on the first correspondence and the current abnormal charging current data, the current charging time data is compared with the corresponding second preset threshold to determine the current abnormal charging time data;

[0020] Based on the current abnormal charging current data and the current abnormal charging time data, the current first abnormal battery is determined.

[0021] In another possible implementation, the method further includes:

[0022] Obtain the historical causes of anomalies for each lithium battery;

[0023] Based on the second correspondence, a third correspondence is established between the historical anomaly cause and at least one of the historical anomaly charging time data and the historical anomaly charging current data;

[0024] Based on the historical abnormal charging data, the historical abnormal causes, the third correspondence, and the current charging data corresponding to the current first abnormal battery, the current abnormal cause is determined.

[0025] In another possible implementation, the current battery charging data further includes: the current battery charging power; the step of determining the current first abnormal battery based on the current abnormal charging time data further includes:

[0026] Obtain the connection relationships between the various lithium batteries;

[0027] Based on the current first abnormal battery and the connection relationship, a matching battery is determined from the normal batteries;

[0028] Based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, a replacement battery is determined from the matching batteries.

[0029] In another possible implementation, based on the current abnormal charging current data and the current abnormal charging time data, a current first abnormal battery is determined, and then the process further includes:

[0030] Based on the current first abnormal battery and the connection relationship, the battery to be monitored is determined;

[0031] Based on the preset weight corresponding to the current charging data, the current second abnormal battery is determined.

[0032] Secondly, an apparatus for predicting lithium battery anomalies is provided, the apparatus comprising:

[0033] The first acquisition module is used to acquire the current charging data corresponding to each lithium battery, wherein the current charging data includes: current charging current data and current charging time data;

[0034] The first establishment module is used to establish a first correspondence between the current charging current data and the current charging time data;

[0035] The first determining module is used to input the first correspondence, the current charging current data and the current charging time data into the prediction model to determine the abnormal predicted battery and the abnormal predicted charging data.

[0036] The control display module is used to acquire the location information of the abnormal prediction battery and control the display of the location information and the abnormal prediction charging data.

[0037] In one possible implementation, when the first determining module inputs the first correspondence, the current charging current data, and the current charging time data into the prediction model to determine the abnormal predicted battery and the abnormal predicted charging data, it is specifically used for:

[0038] The current charging current data and the current charging time data are normalized.

[0039] The first correspondence, along with the normalized current charging current data and the current charging time data, are input into the prediction model to obtain the abnormal prediction battery.

[0040] In another possible implementation, the apparatus further includes: a second acquisition module, a second establishment module, a normalization processing module, and a training module, wherein,

[0041] The second acquisition module is used to acquire historical abnormal charging data corresponding to each lithium battery. The historical abnormal charging data includes historical abnormal charging current data and historical abnormal charging time data.

[0042] The second establishment module is used to establish a second correspondence between the historical abnormal charging current data and the historical abnormal charging time data;

[0043] The normalization processing module is used to normalize the historical abnormal charging current data and the historical abnormal charging time data.

[0044] The training module is used to input the second correspondence, the normalized historical abnormal charging current data, and the historical abnormal charging time data into the original model for training, so as to obtain the trained prediction model.

[0045] In another possible implementation, the apparatus further includes: a first comparison module, a second comparison module, and a second determination module, wherein,

[0046] The first comparison module is used to compare the current charging current data with the corresponding first preset threshold to determine the current abnormal charging current data;

[0047] The second comparison module is used to compare the current charging time data with the corresponding second preset threshold based on the first correspondence and the current abnormal charging current data, and to determine the current abnormal charging time data.

[0048] The second determining module is used to determine the current first abnormal battery based on the current abnormal charging time data.

[0049] In another possible implementation, the apparatus further includes: a third acquisition module, a third establishment module, and a third determination module, wherein,

[0050] The third acquisition module is used to acquire the historical abnormality reasons corresponding to each lithium battery.

[0051] The third establishing module is used to establish a third correspondence relationship between the historical anomaly cause and at least one of the historical anomaly charging time data and the historical anomaly charging current data, based on the second correspondence relationship.

[0052] The third determining module is used to determine the current abnormal cause based on the historical abnormal charging data, the historical abnormal cause, the third correspondence relationship, and the current charging data corresponding to the current first abnormal battery.

[0053] In another possible implementation, the current battery charging data further includes: the current battery charging power;

[0054] The device further includes: a fourth acquisition module, a fourth determination module, and a matching module, wherein,

[0055] The fourth acquisition module is used to acquire the connection relationship between each lithium battery;

[0056] The fourth determining module is used to determine a matching battery from the normal batteries based on the current first abnormal battery and the connection relationship;

[0057] The matching module is used to match a replaceable battery from the matching batteries based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, respectively.

[0058] In another possible implementation, the apparatus further includes: a fifth determining module and a sixth determining module, wherein,

[0059] The fifth determining module is used to determine the battery to be monitored based on the current first abnormal battery and the connection relationship;

[0060] The sixth determining module is used to determine the current second abnormal battery based on the preset weight corresponding to the current charging data.

[0061] Thirdly, an electronic device is provided, the electronic device comprising:

[0062] One or more processors;

[0063] Memory;

[0064] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform operations corresponding to the lithium battery anomaly prediction method as shown in any possible implementation of the first aspect.

[0065] Fourthly, a computer-readable storage medium is provided, the storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement a method for predicting lithium battery anomalies as shown in any possible implementation of the first aspect.

[0066] In summary, this application includes at least one of the following beneficial technical effects:

[0067] This application provides a method, apparatus, electronic device, and readable storage medium for predicting lithium battery anomalies. Compared with related technologies, in this application, by acquiring the current charging current data and current charging time data corresponding to each lithium battery, and establishing a first correspondence between the current charging current data and current charging time data, the first correspondence, the current charging current data, and the current charging time data are input into the prediction model to promptly determine the abnormal prediction battery and the abnormal prediction charging data corresponding to the abnormal battery. Then, the location information of the abnormal prediction battery is acquired, and the location information and abnormal prediction charging data of the abnormal prediction battery are controlled and displayed. That is, in this application, abnormal batteries are determined in advance, thereby avoiding lithium battery anomalies. Attached Figure Description

[0068] Figure 1 This is a schematic flowchart of a method for predicting anomalies in lithium batteries provided in an embodiment of this application.

[0069] Figure 2 This is a schematic diagram of a lithium battery anomaly prediction device provided in an embodiment of this application.

[0070] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0071] The present application will be further described in detail below with reference to the accompanying drawings.

[0072] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0073] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0074] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0075] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0076] This application provides a method for predicting lithium battery anomalies, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method may include:

[0077] Step S101: Obtain the current charging data corresponding to each lithium battery.

[0078] The current charging data includes: current charging current data and current charging time data.

[0079] In the embodiments of this application, the electronic device can acquire the current charging data corresponding to each lithium battery in real time, or acquire the current charging data corresponding to each lithium battery at specific intervals, or acquire the current charging data corresponding to each lithium battery when a user trigger command is detected. In the embodiments of this application, the current charging current data can be the current data of the lithium battery during current charging, and the current charging time data can be the charging time of the lithium battery when it is fully charged.

[0080] Step S102: Establish the first correspondence between the current charging current data and the current charging time data.

[0081] In this embodiment of the application, the current charging current data and current charging time data are different for different lithium batteries. After establishing a first correspondence between the current charging current data and the current charging time data, the first correspondence can be stored in a database. For example, the current charging current data of lithium battery 1, 50.3A, corresponds to a current charging time of 2 hours.

[0082] Step S103: Input the first correspondence, current charging current data and current charging time data into the prediction model to determine the abnormal prediction battery and abnormal prediction charging data.

[0083] In this embodiment of the application, the abnormal prediction battery is a lithium battery that will become abnormal in the future. The abnormal prediction charging data is the abnormal prediction charging data corresponding to each abnormal prediction battery. As time changes, the charging current and charging time of the lithium battery continuously decrease, that is, the lithium battery becomes abnormal. According to the time series, the first correspondence between the current charging current data and the current charging time data and the current charging data are input into the prediction model to obtain the abnormal prediction battery and the abnormal prediction charging data corresponding to the abnormal prediction battery. The abnormal prediction charging data includes: abnormal prediction charging current data and abnormal prediction charging time data.

[0084] Step S104: Obtain the location information of the abnormal prediction battery, and control the display of the location information and abnormal prediction charging data.

[0085] In this embodiment of the application, the location information of the abnormal prediction battery in a battery pack can be the specifications of the abnormal prediction battery, such as 18650 / 2200mAh / 3.7V, where 2200mAh represents the lithium battery capacity, 3.7V represents the lithium battery voltage, and 18650 represents the cylindrical shape of the battery, specifically a diameter of 18mm and a height of 65mm. The location information of the abnormal prediction battery can be obtained from local storage, from other devices, or manually input by the user. After identifying the abnormal prediction battery, its location information is retrieved, and the corresponding location information and predicted charging data are displayed. This allows the user to determine a repair plan in advance based on the abnormal prediction battery and its corresponding predicted charging data, thus preventing lithium battery malfunctions.

[0086] This application provides a method for predicting lithium battery anomalies. Compared with related technologies, in this application, the current charging current data and current charging time data corresponding to each lithium battery are obtained, and a first correspondence between the current charging current data and the current charging time data is established. The first correspondence, the current charging current data, and the current charging time data are input into the prediction model to promptly determine the abnormal prediction battery and the abnormal prediction charging data corresponding to the abnormal battery. Then, the location information of the abnormal prediction battery is obtained, and the location information and abnormal prediction charging data of the abnormal prediction battery are controlled and displayed. That is, in this application embodiment, the abnormal battery is determined in advance, thereby avoiding lithium battery anomalies.

[0087] One possible implementation of this application embodiment is that in step S103, the first correspondence, the current charging current data, and the current charging time data are input into the prediction model to determine the abnormal prediction battery and the abnormal prediction charging data. Specifically, this may include steps S1031 (not shown in the figure) and S1032 (not shown in the figure), wherein...

[0088] Step S1031: Normalize the current charging current data and the current charging time data.

[0089] In the embodiments of this application, since the current charging current data and the current charging time data have different units, in order to facilitate the processing of the current charging current data and the current charging time data, the current charging current data and the current charging time data are normalized to make the obtained abnormal battery prediction more accurate. For example, the current charging current data and the current charging time data are (20A, 50min) respectively, and the normalized current charging current data and the current charging time data are (0.425, 0.625) respectively.

[0090] Step S1032: Input the first correspondence relationship, the normalized current charging current data, and the current charging time data into the prediction model to obtain the abnormal prediction battery and the abnormal prediction charging data.

[0091] In this embodiment, the first correspondence between the current charging current data and the current charging time data, as well as the normalized current charging current data and the current charging time data, are input into the prediction model. The normalized current charging current data and the normalized current charging data are in one-to-one correspondence. The current charging current data and the corresponding current charging time data are converted into a feature matrix, and the feature matrix is ​​input into the prediction model to obtain the abnormal prediction battery and abnormal prediction charging data. By normalizing the current charging current data and the current charging time data, and inputting the normalized data into the prediction model, the abnormal prediction battery and abnormal prediction charging data can be determined in advance, making the obtained abnormal prediction battery and abnormal prediction charging data more accurate.

[0092] Another possible implementation of this application embodiment is to input the first correspondence relationship and the normalized current charging current data and current charging time data into the prediction model to obtain the abnormal prediction battery and abnormal prediction charging data. Before this, it may also include: step Sa1 (not shown in the figure), step Sa2 (not shown in the figure), step Sa3 (not shown in the figure) and step Sa4 (not shown in the figure), wherein step Sa2 can be executed before step Sa3, step Sa2 can be executed after step Sa3, and step Sa2 can also be executed simultaneously with step Sa3.

[0093] Step Sa1: Obtain the historical abnormal charging data corresponding to each lithium battery.

[0094] The historical abnormal charging data includes: historical abnormal charging current data and historical abnormal charging time data.

[0095] In this embodiment of the application, the historical abnormal charging data corresponding to each lithium battery can be obtained from local storage, from other devices, or from the historical abnormal charging data corresponding to each lithium battery input by the user. In this embodiment of the application, the historical abnormal charging data can be the historical abnormal charging data of the previous hour or the previous month corresponding to the current battery charging data. The specific time range is not limited in this embodiment of the application.

[0096] Step Sa2: Establish a second correspondence between historical abnormal charging current data and historical abnormal charging time data.

[0097] In this embodiment of the application, after establishing a second correspondence between historical abnormal charging current data and historical abnormal charging time data, the second correspondence can be stored in a database. For example, the historical abnormal charging current data of 20A corresponds to historical abnormal charging time of 50 minutes.

[0098] Step Sa3: Normalize the historical abnormal charging current data and historical abnormal charging time data.

[0099] In this embodiment of the application, in order to stabilize the values, the historical abnormal charging current data and the historical abnormal charging time data are normalized.

[0100] Specifically, there are two forms of normalization methods: one is to transform numbers into decimals between (0, 1), and the other is to transform dimensional expressions into dimensionless expressions. These methods are mainly proposed for the convenience of data processing, mapping data to the range of 0 to 1 for processing, which is more convenient and faster.

[0101] The specific normalization method is as follows: based on Determine the normalized abnormal charging current data, where x'1 is used to characterize the normalized abnormal charging current data, and x1 is used to characterize the abnormal charging current data. Used to characterize the smallest abnormal charging current data among all abnormal charging current data. Used to characterize the largest abnormal charging current data among all abnormal charging current data; based on Determine the abnormal charging time data after normalization, where x'2 is used to characterize the abnormal charging time data after normalization. Used to characterize the smallest abnormal charging time data among all abnormal charging time data. Used to characterize the largest abnormal charging time data among all abnormal charging time data.

[0102] Step Sa4: Input the second correspondence, the normalized historical abnormal charging current data, and the historical abnormal charging time data into the original model for training to obtain the trained prediction model.

[0103] In this embodiment of the application, since historical abnormal charging current data and historical abnormal charging time data are time-related, different historical abnormal charging current data correspond to different historical abnormal charging data. The second correspondence, along with the normalized historical abnormal charging current data and historical abnormal charging time data, are input into the original model for training according to time order. Specifically, the historical abnormal charging current data and the corresponding historical abnormal charging time data are input into the original model for training according to time order. The historical abnormal charging current data and historical abnormal charging time data are converted into a feature matrix, and this feature matrix is ​​input into the original model for training. Based on... The feature matrix is ​​obtained, where a represents the historical abnormal charging current data and b represents the historical abnormal charging time data corresponding to the historical abnormal charging current data.

[0104] For the embodiments of this application, the original model can be a Long Short-Term Memory (LSTM) neural network. Normalized historical abnormal charging current data features and historical abnormal charging time data are used as the input training set of the neural network. The input training set is input into the LSTM for training to obtain the trained prediction model. By training on historical abnormal charging data, the obtained prediction model is made more accurate.

[0105] Another possible implementation of this application embodiment is to establish a first correspondence between the current charging current data and the current charging time data, and then may include: step Sb1 (not shown in the figure), step Sb2 (not shown in the figure) and step Sb3 (not shown in the figure), wherein step Sb1 may be executed after step Sa1, step Sb1 may be executed before step Sa1, and step Sb1 may be executed simultaneously with step Sa1.

[0106] Step Sb1: Compare the current charging current data with the corresponding first preset threshold to determine the current abnormal charging current data.

[0107] In this embodiment of the application, the first preset threshold is the charging current data of the lithium battery when it is working normally. The first preset thresholds corresponding to each lithium battery can be partially the same, all the same, or all different. In this embodiment of the application, the current charging current data corresponding to each lithium battery is compared with the corresponding first preset threshold. When the difference between the current current data and the first preset threshold is less than the corresponding first preset range, the current charging current data is abnormal charging current data. The first preset range is the fluctuation range of the charging current corresponding to each lithium battery when it is working normally.

[0108] Step Sb2: Based on the first correspondence and the current abnormal charging current data, compare the current charging time data with the corresponding second preset threshold to determine the current abnormal charging time data.

[0109] In this embodiment of the application, after determining the current abnormal charging current data, based on the first correspondence between the current charging current data and the current charging time data, the current charging time data corresponding to the current abnormal charging current data is determined, and the current charging time data is compared with a second preset threshold. When the difference between the current charging time data and the second preset threshold is less than a second preset range, the current charging time data is the current abnormal charging time data. In this embodiment of the application, the second preset threshold is the charging time data when the lithium battery is working normally. The second preset thresholds corresponding to each lithium battery can be partially the same, all the same, or all different. The second preset range is the difference range corresponding to the difference between the charging time data when each lithium battery is working normally and the second preset threshold.

[0110] Step Sb3: Based on the current abnormal charging time data, determine the current first abnormal battery.

[0111] In the embodiments of this application, when the current charging time data corresponding to a certain lithium battery is the current abnormal charging time data, the lithium battery is the first abnormal battery. By comparing the current charging current data with the first preset threshold and comparing the current charging time data with the second preset threshold, the determination of the current first abnormal battery is made more accurate.

[0112] Another possible implementation of this application embodiment is that the method may further include: step Sc1 (not shown in the figure), step Sc2 (not shown in the figure), and step Sc3 (not shown in the figure), wherein step Sc1 may be executed after step Sb1, step Sc1 may be executed before step Sb1, and step Sc1 may be executed simultaneously with step Sb1.

[0113] Step Sc1: Obtain the historical causes of anomalies for each lithium battery.

[0114] For the embodiments of this application, the historical abnormal reasons corresponding to each lithium battery can be obtained from local storage, or the historical abnormal reasons corresponding to each lithium battery can be obtained from other devices, or the historical abnormal reasons corresponding to each lithium battery input by the user can be obtained.

[0115] Step Sc2: Based on the second correspondence, establish a third correspondence between the historical anomaly cause and at least one of the historical anomaly charging time data and historical anomaly charging current data.

[0116] In the embodiments of this application, after establishing a third correspondence between historical anomaly causes and at least one of historical abnormal charging time data and historical abnormal charging current data, the third correspondence can be stored in a database. For example, if the historical anomaly cause is a decrease in battery capacity, the corresponding historical abnormal charging current data is 20A and the historical abnormal charging time data is 50 minutes.

[0117] Step Sc3: Based on historical abnormal charging data, historical abnormal causes, the third correspondence, and the current charging data corresponding to the current first abnormal battery, determine the current abnormal cause.

[0118] In this embodiment of the application, the current charging data and historical abnormal charging data corresponding to the current first abnormal battery are matched, that is, the current abnormal charging current data and the historical abnormal charging current data are matched, and the current abnormal charging time data and the historical abnormal charging time data are matched to determine the matched historical abnormal charging current data and historical abnormal charging time data. Based on the third correspondence between the matched historical abnormal charging current data and historical abnormal charging time data and the historical abnormal causes, the current abnormal cause is determined from the historical abnormal causes. By determining the current abnormal cause through historical abnormal causes and historical abnormal charging data, the determined current abnormal cause is more accurate, saving users the trouble of analyzing abnormal causes and improving the repair efficiency of the current first abnormal battery.

[0119] In another possible implementation of this application embodiment, the current battery charging data further includes: the current battery charging power;

[0120] Based on the current abnormal charging time data, the first abnormal battery is identified. The process may then include steps Sd1 (not shown in the figure), Sd2 (not shown in the figure), and Sd3 (not shown in the figure). Step Sd1 can be executed before or after step Sc2, or it can be executed simultaneously with step Sc2.

[0121] Step Sd1: Obtain the connection relationship between each lithium battery.

[0122] In the embodiments of this application, a battery pack may contain at least two lithium batteries, and the connection relationship between the lithium batteries may include: series connection. After obtaining the connection relationship between the lithium batteries, the connection relationship can be stored in a database.

[0123] Step Sd2: Based on the current first abnormal battery and its connection relationship, determine the matching battery from the normal batteries.

[0124] In the embodiments of this application, after determining the first abnormal battery, a matching battery is determined from the normal batteries based on the connection relationship between the first abnormal battery and the normal battery. For example, if the first abnormal battery 1 is connected to normal battery 1 and normal battery 2, then the matching batteries for the first abnormal battery 1 are normal battery 1 and normal battery 2.

[0125] Step Sd3: Based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, determine the replaceable battery from the matching batteries.

[0126] In the embodiments of this application, when there is one matching battery, the matching battery is determined as a replaceable battery. When there are at least two matching batteries, the battery charging power corresponding to the matching battery is compared with the current battery power corresponding to the current first abnormal battery. When the battery charging power corresponding to the matching battery and the current battery power corresponding to the current first abnormal battery are the same, the matching battery is a replaceable battery. After determining the current first abnormal battery, the maintenance efficiency of the current first abnormal battery is further improved by determining the replaceable battery.

[0127] Another possible implementation of this application embodiment is to determine the current first abnormal battery based on the current abnormal charging time data, and then further include: step Se1 (not shown in the figure) and step Se2 (not shown in the figure), wherein step Se1 can be executed before step Sd1, step Se1 can be executed after step Sd1, or step Se1 can be executed simultaneously with step Sd1.

[0128] Step Se1: Based on the current first abnormal battery and its connection relationship, determine the battery to be monitored.

[0129] In the embodiments of this application, the lithium batteries in each battery pack are interconnected. After a battery malfunctions (i.e., the current first malfunctioning battery is identified), the probability of the batteries connected to the current first malfunctioning battery malfunctioning increases. Therefore, after identifying the current first malfunctioning battery, it is necessary to identify the batteries that may malfunction (i.e., the batteries to be monitored). For example, if the current first malfunctioning battery 1 is connected to batteries 2 and 3, then batteries 2 and 3 are identified as the batteries to be monitored.

[0130] Step Se2: Determine the current second abnormal battery based on the preset weight corresponding to the current charging data.

[0131] For the embodiments of this application, based on Y i =ρ0*a i +(1-ρ0)*b i Y = maxY i Identify the current second abnormal battery, Y i a is used to characterize the total preset weight value corresponding to each monitored battery. i Used to characterize the current charging current data corresponding to each battery to be monitored, ρ0 is used to characterize the preset weight corresponding to the current charging current data, b i The current charging time data corresponding to each battery to be monitored is used to characterize the current charging time data, (1-ρ0) is used to characterize the preset weight corresponding to the current charging time data, and Y is used to characterize the maximum total weight value determined from the total preset weight values ​​corresponding to all batteries to be monitored.

[0132] The above embodiments describe a method for predicting lithium battery anomalies from the perspective of process flow. The following embodiments describe a device for predicting lithium battery anomalies from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0133] This application provides a device for predicting lithium battery anomalies, such as... Figure 2 As shown, the lithium battery anomaly prediction device 20 may specifically include: a first acquisition module 21, a first establishment module 22, a first determination module 23, and a control and display module 24, wherein,

[0134] The first acquisition module 21 is used to acquire the current charging data corresponding to each lithium battery. The current charging data includes: current charging current data and current charging time data.

[0135] The first establishment module 22 is used to establish a first correspondence between the current charging current data and the current charging time data;

[0136] The first determining module 23 is used to input the first correspondence, the current charging current data and the current charging time data into the prediction model to determine the abnormal prediction battery and the abnormal prediction charging data.

[0137] The control display module 24 is used to acquire the location information of the abnormal prediction battery and control the display of the location information and abnormal prediction charging data.

[0138] In one possible implementation of this application embodiment, when the first determining module 23 inputs the first correspondence, current charging current data, and current charging time data into the prediction model to determine the abnormal predicted battery and abnormal predicted charging data, it is specifically used for:

[0139] Normalize the current charging current data and the current charging time data;

[0140] The first correspondence, along with the normalized current charging current data and current charging time data, are input into the prediction model to obtain the abnormal prediction battery.

[0141] In another possible implementation of this application embodiment, the apparatus 20 further includes: a second acquisition module, a second establishment module, a normalization processing module, and a training module, wherein...

[0142] The second acquisition module is used to acquire the historical abnormal charging data corresponding to each lithium battery. The historical abnormal charging data includes: historical abnormal charging current data and historical abnormal charging time data.

[0143] The second module is used to establish a second correspondence between historical abnormal charging current data and historical abnormal charging time data; the normalization module is used to normalize the historical abnormal charging current data and historical abnormal charging time data; the training module is used to input the second correspondence and the normalized historical abnormal charging current data and historical abnormal charging time data into the original model for training, so as to obtain the trained prediction model.

[0144] In another possible implementation of this application embodiment, the apparatus 20 further includes: a first comparison module, a second comparison module, and a second determination module, wherein...

[0145] The first comparison module is used to compare the current charging current data with the corresponding first preset threshold to determine the current abnormal charging current data.

[0146] The second comparison module is used to compare the current charging time data with the corresponding second preset threshold based on the first correspondence and the current abnormal charging current data, and to determine the current abnormal charging time data.

[0147] The second determining module is used to determine the current first abnormal battery based on the current abnormal charging time data.

[0148] In another possible implementation of this application embodiment, the apparatus 20 further includes: a third acquisition module, a third establishment module, and a third determination module, wherein...

[0149] The third acquisition module is used to acquire the historical abnormality reasons corresponding to each lithium battery.

[0150] The third module is used to establish a third correspondence relationship between historical anomaly causes and at least one of historical anomaly charging time data and historical anomaly charging current data, based on the second correspondence relationship.

[0151] The third determination module is used to determine the current abnormal cause based on historical abnormal charging data, historical abnormal causes, the third correspondence, and the current charging data corresponding to the current first abnormal battery.

[0152] In another possible implementation of this application embodiment, the current battery charging data further includes: the current battery charging power;

[0153] Device 20 further includes: a fourth acquisition module, a fourth determination module, and a matching module, wherein,

[0154] The fourth acquisition module is used to acquire the connection relationships between the various lithium batteries;

[0155] The fourth determination module is used to determine a matching battery from the normal batteries based on the current first abnormal battery and the connection relationship;

[0156] The matching module is used to match a replaceable battery from the matching batteries based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, respectively.

[0157] In another possible implementation of this application embodiment, the apparatus 20 further includes: a fifth determining module and a sixth determining module, wherein...

[0158] The fifth determination module is used to determine the battery to be monitored based on the current first abnormal battery and its connection relationship;

[0159] The sixth determination module is used to determine the current second abnormal battery based on the preset weight corresponding to the current charging data.

[0160] This application provides a device for predicting lithium battery anomalies. Compared with related technologies, in this application embodiment, by acquiring the current charging current data and current charging time data corresponding to each lithium battery, and establishing a first correspondence between the current charging current data and the current charging time data, the first correspondence, the current charging current data, and the current charging time data are input into the prediction model to promptly determine the abnormal prediction battery and the abnormal prediction charging data corresponding to the abnormal battery. Then, the location information of the abnormal prediction battery is acquired, and the location information and abnormal prediction charging data of the abnormal prediction battery are controlled to be displayed. That is, in this application embodiment, the abnormal battery is determined in advance, thereby avoiding lithium battery anomalies.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the lithium battery anomaly prediction device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0162] This application provides an electronic device, such as... Figure 3 As shown, Figure 3The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of this application.

[0163] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0164] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0165] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0166] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0167] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0168] This application provides a computer-readable storage medium storing a computer program. When the program is run on a computer, it enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, in this application embodiment, by acquiring the current charging current data and current charging time data corresponding to each lithium battery, and establishing a first correspondence between the current charging current data and current charging time data, the first correspondence, the current charging current data, and the current charging time data are input into a prediction model to promptly determine abnormal predicted batteries and their corresponding abnormal predicted charging data. Then, the location information of the abnormal predicted batteries is acquired, and the location information and abnormal predicted charging data of the abnormal predicted batteries are controlled for display. That is, in this application embodiment, abnormal batteries are determined in advance, thereby avoiding lithium battery abnormalities.

[0169] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0170] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of lithium battery anomaly prediction, characterized by, include: Obtain the current charging data for each lithium battery, including current charging current data and current charging time data. Establish a first correspondence between the current charging current data and the current charging time data; The current charging current data and the current charging time data are normalized. Obtain historical abnormal charging data corresponding to each lithium battery, including historical abnormal charging current data and historical abnormal charging time data. Establish a second correspondence between the historical abnormal charging current data and the historical abnormal charging time data; The historical abnormal charging current data and the historical abnormal charging time data are normalized. The second correspondence, the normalized historical abnormal charging current data, and the historical abnormal charging time data are input into the original model for training to obtain the trained prediction model. The first correspondence, the normalized current charging current data, and the current charging time data are input into the prediction model to determine the abnormal prediction battery and the abnormal prediction charging data. The abnormal prediction battery is a lithium battery that will become abnormal in the future. Obtain the location information of the abnormal prediction battery, and control the display of the location information and the abnormal prediction charging data; The abnormal predicted charging data includes: abnormal predicted charging current data and abnormal predicted charging time data; The process of establishing a first correspondence between the current charging current data and the current charging time data further includes: The current charging current data is compared with the corresponding first preset threshold to determine the current abnormal charging current data. Based on the first correspondence and the current abnormal charging current data, the current charging time data is compared with the corresponding second preset threshold to determine the current abnormal charging time data; Based on the current abnormal charging time data, the current first abnormal battery is determined; The current charging data also includes: the current battery charging power; Based on the current abnormal charging time data, the process of determining the current first abnormal battery further includes: Obtain the connection relationships between the various lithium batteries; Based on the current first abnormal battery and the connection relationship, a matching battery is determined from the normal batteries; Based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, a replacement battery is determined from the matching batteries.

2. The method of claim 1, wherein, The method further includes: Obtain the historical causes of anomalies for each lithium battery; Based on the second correspondence, a third correspondence is established between the historical anomaly cause and at least one of the historical anomaly charging time data and the historical anomaly charging current data; Based on the historical abnormal charging data, the historical abnormal causes, the third correspondence, and the current charging data corresponding to the current first abnormal battery, the current abnormal cause is determined.

3. The method of claim 1, wherein, Based on the current abnormal charging time data, the first abnormal battery is determined, and the process further includes: Based on the current first abnormal battery and the connection relationship, the battery to be monitored is determined; Based on the preset weights corresponding to the current charging data, the current second abnormal battery is determined.

4. An apparatus for lithium battery anomaly prediction, the apparatus comprising: include: The first acquisition module is used to acquire the current charging data corresponding to each lithium battery, wherein the current charging data includes: current charging current data and current charging time data; The first establishment module is used to establish a first correspondence between the current charging current data and the current charging time data; The first normalization processing module is used to normalize the current charging current data and the current charging time data; The second acquisition module is used to acquire the historical abnormal charging data corresponding to each lithium battery, the historical abnormal charging data including: historical abnormal charging current data and historical abnormal charging time data. The second establishment module is used to establish a second correspondence between the historical abnormal charging current data and the historical abnormal charging time data; The second normalization processing module is used to normalize the historical abnormal charging current data and the historical abnormal charging time data. The model training module is used to input the second correspondence, the normalized historical abnormal charging current data, and the historical abnormal charging time data into the original model for training, so as to obtain the trained prediction model. The first determining module is used to input the first correspondence, the normalized current charging current data and the current charging time data into the prediction model to determine the abnormal prediction battery and the abnormal prediction charging data. The abnormal prediction battery is a lithium battery that will become abnormal in the future. The control display module is used to acquire the location information of the abnormal prediction battery and control the display of the location information and the abnormal prediction charging data; The abnormal predicted charging data includes: abnormal predicted charging current data and abnormal predicted charging time data; The process of establishing a first correspondence between the current charging current data and the current charging time data further includes: The current charging current data is compared with the corresponding first preset threshold to determine the current abnormal charging current data. Based on the first correspondence and the current abnormal charging current data, the current charging time data is compared with the corresponding second preset threshold to determine the current abnormal charging time data; Based on the current abnormal charging time data, the current first abnormal battery is determined; The current charging data also includes: the current battery charging power; Based on the current abnormal charging time data, the process of determining the current first abnormal battery further includes: Obtain the connection relationships between the various lithium batteries; Based on the current first abnormal battery and the connection relationship, a matching battery is determined from the normal batteries; Based on the current battery charging power corresponding to the current first abnormal battery and the matching battery, a replacement battery is determined from the matching batteries.

5. An electronic device, comprising: include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: perform a method for predicting lithium battery anomalies according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements a method for predicting lithium battery anomalies as described in any one of claims 1 to 3.

Images