Fault early warning method, device and equipment of new energy vehicle electric drive system and medium

By generating a baseline efficiency and combining it with real-time efficiency analysis and a fault mechanism mapping library, the problem of limited coverage and response delay in fault early warning of electric drive systems for new energy vehicles is solved, thereby improving the accuracy and robustness of the early warning.

CN122402247APending Publication Date: 2026-07-17上海松鼠创科技术有限责任公司
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
上海松鼠创科技术有限责任公司
Filing Date
2026-06-04
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing fault warning technologies for electric drive systems in new energy vehicles suffer from problems such as limited fault coverage, delayed warning response, poor robustness under operating conditions, weak fault attribution ability, and reliance on manually set fixed thresholds, making it difficult to identify hidden faults and provide accurate warnings under complex operating conditions.

Method used

By generating baseline efficiencies corresponding to operating conditions based on a partitioned adaptive model library, combining real-time operating efficiency to perform efficiency trend and structural anomaly analysis, and using a fault mechanism mapping library to locate faulty components, fault early warning can be achieved.

Benefits of technology

It has improved the fault coverage, shortened the early warning response time, enhanced the accuracy of early warning and fault attribution ability under complex operating conditions, and reduced the false alarm rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122402247A_ABST
    Figure CN122402247A_ABST
Patent Text Reader

Abstract

The application provides a new energy vehicle electric drive system fault early warning method, device, equipment and medium, relates to the technical field of fault early warning, and comprises the following steps: based on the current operation condition of the vehicle electric drive system, calling a target efficiency benchmark model matched with the operation condition from a partition adaptive model library to generate a first benchmark efficiency corresponding to the operation condition; based on the real-time operation efficiency of the vehicle electric drive system and the first benchmark efficiency, performing efficiency trend anomaly analysis and component structure anomaly analysis to determine an anomaly confidence; if the anomaly confidence meets a preset fault positioning condition, extracting the efficiency anomaly features corresponding to the vehicle electric drive system, and combining a fault mechanism mapping library to locate the fault components in the vehicle electric drive system and the corresponding fault early warning results. The application can effectively improve the technical problems in the prior art, such as limited fault coverage, delayed early warning response, poor operation condition robustness, weak fault attribution ability, and dependence on manually set fixed thresholds.
Need to check novelty before this filing date? Find Prior Art