Fault prediction method for new energy electric vehicle charging pile

By applying the fault prediction method of SVR prediction model and normal cloud model on the charging pile, the problem of fault prediction of charging piles is solved, and the advance prediction of charging pile failures is achieved, and the safety and reliability of charging piles are improved.

CN119416175AInactive Publication Date: 2025-02-11CHANGCHUN AUTOMOBILE IND INST
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411982356.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-31
Publication Date
2025-02-11
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Due to the extended use time and damage caused by other reasons, electric vehicle users are faced with the situation where charging piles cannot be charged normally, which brings inconvenience to users. Moreover, due to the lack of real-time status evaluation and fault prediction, the maintenance of charging piles is difficult. Increased, insufficient security and reliability.

Method used

The fault prediction method of the normal cloud model based on the SVR prediction model and dynamic membership degree is adopted. By predicting the characteristic index parameters of the charging pile, combined with real-time online monitoring data, the fault status of the charging pile is identified and predicted in advance.

Benefits of technology

Effectively prevent the occurrence of charging pile failures, optimize the maintenance system, reduce the adverse effects of faults on electric vehicles, and make charging piles run safer and more stable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119416175A_ABST
    Figure CN119416175A_ABST
Patent Text Reader

Abstract

The invention discloses a fault prediction method for a new energy electric vehicle charging pile, and the method comprises the steps: 1, building a support vector machine regression prediction model, predicting the change of each characteristic index parameter of the charging pile, and obtaining the change trend of an average relative error through combining with the existing data; and 2, based on the normal cloud model of the dynamic membership degree, identifying the fault state of the charging pile according to the comparison of the fitting degree of the cloud model of the charging pile in each state, and realizing the advanced prediction of the fault of the charging pile. According to the new energy electric vehicle charging pile fault prediction method provided by the invention, the evolution process of the state trend of the charging pile is described through the prediction error of the SVR prediction model, the normal cloud model is introduced, and the prediction of the charging pile from the trend to the fault is completed according to the real-time online monitoring data of the charging pile. The occurrence rate of the charging pile fault can be effectively prevented, a charging pile maintenance system is optimized, the adverse effect of the charging pile fault on the electric vehicle is reduced, and the pre-judgment of the charging pile fault is realized.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Draught fan gear box state on-line evaluation model building method and on-line evaluation method

    CN105205569A

  • Intelligent charging pile management system and method thereof

    CN116664015A

  • Strain sensor temperature compensation method and device and readable storage medium

    CN118153427A

  • Method for measuring water flow velocity

    CN118671376A