CN-115372831-B - Lithium battery abnormality prediction method, lithium battery abnormality prediction device, electronic equipment and readable storage medium

CN115372831BCN 115372831 BCN115372831 BCN 115372831BCN-115372831-B

Abstract

The application relates to a method and a device for predicting abnormality of a lithium battery, electronic equipment and a readable storage medium, and relates to the technical field of lithium battery detection. The method comprises the steps of obtaining current charging current data and current charging time data corresponding to each lithium battery respectively, establishing a first corresponding relation between the current charging current data and the current charging time data, inputting the first corresponding relation, the current charging time data and the current charging current data into a prediction model, determining an abnormal prediction battery and the abnormal prediction charging data, and controlling and displaying the position information and the abnormal prediction charging data by obtaining position information of the abnormal prediction battery. The method, the device, the electronic equipment and the readable storage medium for predicting the abnormality of the lithium battery can discover the abnormality of the lithium battery in advance so as to avoid the abnormality of the lithium battery.

Inventors

Kang Qinlong
ZHANG YANG
HE YONGKANG
LIU CHONG
CAO LONG

Assignees

湖南华美兴泰科技有限责任公司
湖南华美兴泰科技有限责任公司

Dates

Publication Date: 20260421
Application Date: 20220916
Priority Date: 20220916

Claims (6)

1. A method for lithium battery anomaly prediction, comprising: acquiring current charging data corresponding to each lithium battery respectively, wherein the current charging data comprises current charging current data and current charging time data; Establishing a first corresponding relation between the current charging current data and the current charging time data; normalizing the current charging current data and the current charging time data; acquiring historical abnormal charging data corresponding to each lithium battery, wherein the historical abnormal charging data comprises historical abnormal charging current data and historical abnormal charging time data; Establishing a second corresponding relation between the historical abnormal charging current data and the historical abnormal charging time data; normalizing the historical abnormal charging current data and the historical abnormal charging time data; Inputting the second corresponding relation, the historical abnormal charging current data and the historical abnormal charging time data after normalization processing into an original model for training to obtain a trained prediction model; Inputting the first corresponding relation, the current charging current data after normalization processing and the current charging time data into the prediction model, and determining an abnormal prediction battery and abnormal prediction charging data, wherein the abnormal prediction battery is a lithium battery with abnormality in a future period of time; Acquiring the position information of the abnormal prediction battery, and controlling and displaying the position information and the abnormal prediction charging data; The abnormal predicted charge data includes abnormal predicted charge current data and abnormal predicted charge time data; the establishing the first correspondence between the current charging current data and the current charging time data further includes: Comparing the current charging current data with a corresponding first preset threshold value to determine current abnormal charging current data; Comparing the current charging time data with a corresponding second preset threshold value based on a first corresponding relation and the current abnormal charging current data to determine current abnormal charging time data; determining a current first abnormal battery based on the current abnormal charge time data; the current charging data also comprises current battery charging power; The determining, based on the current abnormal charging time data, a current first abnormal battery, and then further includes: obtaining connection relations among all lithium batteries; Determining a matching battery from normal batteries based on the current first abnormal battery and the connection relation; and determining a replaceable battery from the matched battery based on the current battery charging power respectively corresponding to the current first abnormal battery and the matched battery.
2. The method according to claim 1, wherein the method further comprises: acquiring historical abnormality reasons corresponding to the lithium batteries respectively; establishing a third correspondence between the historical anomaly cause and at least one of the historical anomaly charge time data and the historical anomaly charge current data based on the second correspondence; And determining a current abnormal reason based on the historical abnormal charging data, the historical abnormal reason, the third corresponding relation and the current charging data corresponding to the current first abnormal battery.
3. The method of claim 1, wherein determining a current first abnormal battery based on the current abnormal charge time data, further comprising: Determining a battery to be monitored based on the current first abnormal battery and the connection relation; and determining the current second abnormal battery based on the preset weight corresponding to the current charging data.
4. An apparatus for lithium battery anomaly prediction, comprising: the first acquisition module is used for acquiring current charging data corresponding to each lithium battery respectively, wherein the current charging data comprises current charging current data and current charging time data; The first establishing module is used for establishing a first corresponding relation between the current charging current data and the current charging time data; The first normalization processing module is used for performing normalization processing on the current charging current data and the current charging time data; The second acquisition module is used for acquiring historical abnormal charging data corresponding to each lithium battery respectively, wherein the historical abnormal charging data comprises historical abnormal charging current data and historical abnormal charging time data; the second establishing module is used for establishing a second corresponding relation between the historical abnormal charging current data and the historical abnormal charging time data; The second normalization processing module is used for performing normalization processing on the historical abnormal charging current data and the historical abnormal charging time data; The model training module is used for inputting the second corresponding relation, the historical abnormal charging current data and the historical abnormal charging time data after normalization processing into an original model for training, and obtaining a trained prediction model; The first determining module is used for inputting the first corresponding relation, the current charging current data after normalization processing and the current charging time data into the prediction model, and determining an abnormal prediction battery and abnormal prediction charging data, wherein the abnormal prediction battery is a lithium battery with abnormality in a future period of time; The control display module is used for acquiring the position information of the abnormal prediction battery and controlling and displaying the position information and the abnormal prediction charging data; The abnormal predicted charge data includes abnormal predicted charge current data and abnormal predicted charge time data; the establishing the first correspondence between the current charging current data and the current charging time data further includes: Comparing the current charging current data with a corresponding first preset threshold value to determine current abnormal charging current data; Comparing the current charging time data with a corresponding second preset threshold value based on a first corresponding relation and the current abnormal charging current data to determine current abnormal charging time data; determining a current first abnormal battery based on the current abnormal charge time data; the current charging data also comprises current battery charging power; The determining, based on the current abnormal charging time data, a current first abnormal battery, and then further includes: obtaining connection relations among all lithium batteries; Determining a matching battery from normal batteries based on the current first abnormal battery and the connection relation; and determining a replaceable battery from the matched battery based on the current battery charging power respectively corresponding to the current first abnormal battery and the matched battery.
5. An electronic device, comprising: One or more processors; A 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 configured to perform a method of lithium battery anomaly prediction according to any one of claims 1-3.
6. A computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements a method of lithium battery anomaly prediction as claimed in any one of claims 1 to 3.

Description

Lithium battery abnormality prediction method, lithium battery abnormality prediction device, electronic equipment and readable storage medium Technical Field The present application relates to the field of lithium battery detection technologies, and in particular, to a method and apparatus for predicting abnormality of a lithium battery, an electronic device, and a readable storage medium. Background With the development of science and technology, the lithium battery industry is taken as an important component in the new energy field, the performance of the lithium battery is more and more concerned, the capacity of the lithium battery is an important index for measuring the performance of the lithium battery, and the battery core of the lithium battery can be aged and degenerated in the use process of the lithium battery, so that the capacity of the lithium battery can be lowered, the lithium battery can be impacted and damaged by external force, namely, the lithium battery is abnormal. The inventor finds that with the wide application of the lithium battery, the capacity requirement of the lithium battery is higher and higher, and the capacity of the lithium battery is lower because the abnormality of the lithium battery cannot be predicted, so that the problem of how to avoid the abnormality of the lithium battery becomes a key problem. Disclosure of Invention The application aims to provide a method, a device, electronic equipment and a readable storage medium for predicting abnormality of a lithium battery, which are used for solving at least one of the problems. The above object of the present application is achieved by the following technical solutions: in a first aspect, a method for predicting abnormality of a lithium battery is provided, the method comprising: acquiring current charging data corresponding to each lithium battery respectively, wherein the current charging data comprises current charging current data and current charging time data; Establishing a first corresponding relation between the current charging current data and the current charging time data; Inputting the first corresponding relation, the current charging current data and the current charging time data into a prediction model, and determining an abnormal prediction battery and abnormal prediction charging data; and acquiring the position information of the abnormal prediction battery, and controlling and displaying the position information and the abnormal prediction charging data. In one possible implementation manner, the first correspondence, the current charging current data and the current charging time data are input into a prediction model to determine an abnormal prediction battery and abnormal prediction charging data, and the method comprises the steps of normalizing the current charging current data and the current charging time data; and inputting the first corresponding relation, the current charging current data and the current charging time data after normalization processing into a prediction model to obtain an abnormal prediction battery. In another possible implementation manner, the step of inputting the current charging current data and the current charging time data after the first correspondence and the normalization processing into a prediction model to obtain an abnormal prediction battery, wherein the step of obtaining historical abnormal charging data corresponding to each lithium battery respectively includes historical abnormal charging current data and historical abnormal charging time data; Establishing a second corresponding relation between the historical abnormal charging current data and the historical abnormal charging time data; normalizing the historical abnormal charging current data and the historical abnormal charging time data; and inputting the second corresponding relation, the historical abnormal charging current data and the historical abnormal charging time data after normalization processing into an original model for training, and obtaining a trained prediction model. In another possible implementation manner, the establishing a first correspondence between the current charging current data and the current charging time data further includes: Comparing the current charging current data with a corresponding first preset threshold value to determine current abnormal charging current data; Comparing the current charging time data with a corresponding second preset threshold value based on a first corresponding relation and the current abnormal charging current data to determine current abnormal charging time data; And determining a current first abnormal battery based on the current abnormal charge current data and the current abnormal charge time data. In another possible implementation, the method further includes: acquiring historical abnormality reasons corresponding to the lithium batteries respectively; establishing a third correspondence between the historical anomaly ca