CN-121978554-A - Abnormality detection method, abnormality detection device, abnormality detection apparatus, and storage medium

CN121978554ACN 121978554 ACN121978554 ACN 121978554ACN-121978554-A

Abstract

The application relates to an abnormality detection method, device and equipment and a storage medium, wherein the method comprises the steps of obtaining relevant index data of a vehicle battery, using a preset first abnormality identification model to identify the relevant index data to obtain an abnormality identification result, determining the abnormality index data to be used according to an abnormality index related to the abnormality identification result when the abnormality identification result indicates that the vehicle battery is abnormal, wherein the abnormality index data at least comprises data fragments cut from a historical index data sequence corresponding to the abnormality index, using a preset second abnormality identification model to identify the abnormality index data to obtain a target abnormality score of the vehicle battery, and detecting whether the vehicle battery is abnormal according to the target abnormality score. The application can avoid the interference of invalid data, thereby improving the accuracy of vehicle battery detection.

Inventors

CUI JUN
YANG XUN
YUAN YANHUI

Assignees

重庆蓝电汽车科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260408

Claims (10)

1. An anomaly detection method, the method comprising: acquiring related index data of a vehicle battery; Using a preset first abnormality identification model to identify the related index data to obtain an abnormality identification result; Determining abnormal index data to be used according to an abnormal index related to the abnormal identification result when the abnormal identification result indicates that the vehicle battery is abnormal, wherein the abnormal index data at least comprises data fragments cut from a historical index data sequence corresponding to the abnormal index; identifying the abnormal index data by using a preset second abnormal identification model to obtain a target abnormal score of the vehicle battery; and detecting whether the vehicle battery is abnormal according to the target abnormal score.
2. The method according to claim 1, wherein determining the abnormality index data to be used based on the abnormality index to which the abnormality identification result relates includes: Determining a first time window corresponding to the abnormal index according to the abnormal evolution period corresponding to the abnormal index, wherein the time length of the abnormal evolution period and the time length of the first time window are in positive correlation; and determining the to-be-used abnormal index data in the historical index data sequence corresponding to the abnormal index according to the first time window.
3. The method according to claim 2, wherein determining, in the historical index data sequence corresponding to the abnormality index, abnormality index data to be used according to the first time window includes: determining a target abnormal time point corresponding to the abnormal index; When the time length from the target abnormal time point to the current time point is smaller than the target time length, aligning the ending time point of the first time window with the current time point, and extracting the historical index data of the corresponding time point in the first time window from the historical index data sequence corresponding to the abnormal index as the abnormal index data to be used; And under the condition that the time length from the target abnormal time point to the current time point is greater than or equal to the target time length, determining a target time point according to the target abnormal time point and the target time length, aligning the ending time point of the first time window with the target time point, and extracting historical index data of the corresponding time point in the first time window from a historical index data sequence corresponding to the abnormal index as abnormal index data to be used.
4. The method according to claim 2, wherein determining, in the historical index data sequence corresponding to the abnormality index, abnormality index data to be used according to the first time window includes: determining a target abnormal time point corresponding to the abnormal index; under the condition that the target abnormal time point is not the current time point, determining a target type corresponding to the abnormal index; When the target type indicates that the target abnormal time point is the ending time point of the first time window, aligning the ending time point of the first time window with the target abnormal time point, and extracting historical index data of the corresponding time point in the first time window from a historical index data sequence corresponding to the abnormal index as abnormal index data to be used; Detecting whether the time from the target abnormal time point to the current time point is longer than the first time window or not under the condition that the target type indicates that the target abnormal time point is the starting time point of the first time window, obtaining a first detection result, and determining abnormal index data to be used in a historical index data sequence corresponding to the abnormal index according to the first detection result and the first time window; and under the condition that the target type indicates that the target abnormal time point is the middle time point of the first time window, detecting whether the time from the target abnormal time point to the current time point is longer than the target time length, obtaining a second detection result, and determining abnormal index data to be used in a historical index data sequence corresponding to the abnormal index according to the second detection result and the first time window.
5. The method according to claim 2, wherein determining, in the historical index data sequence corresponding to the abnormality index, abnormality index data to be used according to the first time window includes: determining an abnormal time point set corresponding to the abnormal index; When the abnormal time point set comprises a plurality of abnormal time points, determining a first time length according to a minimum time point and a maximum time point in the abnormal time point set, and adjusting the time length of the first time window to be the first time length when the first time length is longer than the time length of the first time window; and determining the to-be-used abnormal index data in the historical index data sequence corresponding to the abnormal index according to the adjusted first time window.
6. The method of claim 5, wherein determining the anomaly index data to be used in the historical index data sequence corresponding to the anomaly index according to the adjusted first time window comprises: aligning the termination time point of the adjusted first time window with the maximum time point, and extracting the historical index data of the corresponding time point in the adjusted first time window from the historical index data sequence corresponding to the abnormal index as the abnormal index data to be used; or aligning the initial time point of the adjusted first time window with the minimum time point, and extracting the historical index data of the corresponding time point in the adjusted first time window from the historical index data sequence corresponding to the abnormal index as the abnormal index data to be used.
7. The method according to claim 1, wherein determining the abnormality index data to be used based on the abnormality index to which the abnormality identification result relates includes: determining a preset index according to the abnormal index; determining a second time window to be used according to an abnormality grade indicated by the abnormality identification result, wherein the abnormality grade is positively correlated with the duration of the second time window; and determining abnormal index data to be used in a historical index data sequence corresponding to the preset index according to the current time point and the second time window.
8. An abnormality detection apparatus, characterized by comprising: An acquisition unit configured to acquire relevant index data of a vehicle battery; The first recognition unit is used for recognizing the related index data by using a preset first abnormal recognition model to obtain an abnormal recognition result; A determining unit, configured to determine, according to an abnormality indicator related to the abnormality identification result, abnormality indicator data to be used, where the abnormality identification result indicates that the vehicle battery has an abnormality, where the abnormality indicator data includes at least a data segment cut from a historical indicator data sequence corresponding to the abnormality indicator; The second recognition unit is used for recognizing the abnormal index data by using a preset second abnormal recognition model to obtain a target abnormal score of the vehicle battery; and the detection unit is used for detecting whether the vehicle battery is abnormal or not according to the target abnormal score.
9. An anomaly detection device comprising at least one communication interface, at least one bus coupled to the at least one communication interface, at least one processor coupled to the at least one bus, and at least one memory coupled to the at least one bus, wherein the processor is configured to: acquiring related index data of a vehicle battery; Using a preset first abnormality identification model to identify the related index data to obtain an abnormality identification result; Determining abnormal index data to be used according to an abnormal index related to the abnormal identification result when the abnormal identification result indicates that the vehicle battery is abnormal, wherein the abnormal index data at least comprises data fragments cut from a historical index data sequence corresponding to the abnormal index; identifying the abnormal index data by using a preset second abnormal identification model to obtain a target abnormal score of the vehicle battery; and detecting whether the vehicle battery is abnormal according to the target abnormal score.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the abnormality detection method according to any one of claims 1 to 7.

Description

Abnormality detection method, abnormality detection device, abnormality detection apparatus, and storage medium Technical Field The present application relates to the field of computer technologies, and in particular, to an anomaly detection method, apparatus, device, and storage medium. Background At the moment of rapid development of technology, vehicles have become an important tool indispensable to people's daily life and social operations. As a core source of vehicle power, the performance and health state of the battery directly affect the overall performance of the whole vehicle. Taking an electric automobile as an example, the endurance, charge and discharge efficiency and stability of the battery determine the use experience and application range of the vehicle. The conventional vehicle battery detection method focuses on appearance inspection, such as whether obvious anomalies such as breakage and bulge exist or not, and potential hidden hazards inside the battery are difficult to find, so that the detection accuracy is low. Disclosure of Invention The application provides an anomaly detection method, an anomaly detection device, anomaly detection equipment and a storage medium, which can avoid interference of invalid data, thereby improving the accuracy of vehicle battery detection. In a first aspect, the present application provides an anomaly detection method, the method comprising: acquiring related index data of a vehicle battery; Using a preset first abnormality identification model to identify the related index data to obtain an abnormality identification result; Determining abnormal index data to be used according to an abnormal index related to the abnormal identification result when the abnormal identification result indicates that the vehicle battery is abnormal, wherein the abnormal index data at least comprises data fragments cut from a historical index data sequence corresponding to the abnormal index; identifying the abnormal index data by using a preset second abnormal identification model to obtain a target abnormal score of the vehicle battery; and detecting whether the vehicle battery is abnormal according to the target abnormal score. In a second aspect, the present application provides an abnormality detection apparatus comprising: An acquisition unit configured to acquire relevant index data of a vehicle battery; The first recognition unit is used for recognizing the related index data by using a preset first abnormal recognition model to obtain an abnormal recognition result; A determining unit, configured to determine, according to an abnormality indicator related to the abnormality identification result, abnormality indicator data to be used, where the abnormality identification result indicates that the vehicle battery has an abnormality, where the abnormality indicator data includes at least a data segment cut from a historical indicator data sequence corresponding to the abnormality indicator; The second recognition unit is used for recognizing the abnormal index data by using a preset second abnormal recognition model to obtain a target abnormal score of the vehicle battery; and the detection unit is used for detecting whether the vehicle battery is abnormal or not according to the target abnormal score. In a third aspect, the application provides an anomaly detection device comprising at least one communication interface, at least one bus connected to the at least one communication interface, at least one processor connected to the at least one bus, and at least one memory connected to the at least one bus, wherein the processor is configured to: acquiring related index data of a vehicle battery; Using a preset first abnormality identification model to identify the related index data to obtain an abnormality identification result; Determining abnormal index data to be used according to an abnormal index related to the abnormal identification result when the abnormal identification result indicates that the vehicle battery is abnormal, wherein the abnormal index data at least comprises data fragments cut from a historical index data sequence corresponding to the abnormal index; identifying the abnormal index data by using a preset second abnormal identification model to obtain a target abnormal score of the vehicle battery; and detecting whether the vehicle battery is abnormal according to the target abnormal score. In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described abnormality detection method. Compared with the prior art, the technical scheme provided by the embodiment of the application has the advantages that related index data of a vehicle battery are obtained, a preset first abnormality identification model is used for identifying the related index data to obtain an abnormality identification result, the abnormality ind