汽车工程 ›› 2023, Vol. 45 ›› Issue (10): 1975-1983.doi: 10.19562/j.chinasae.qcgc.2023.10.018

所属专题: 底盘&动力学&整车性能专题2023年

• • 上一篇    下一篇

基于模糊BN和改进证据理论的车辆故障定位方法

胡杰1,2,3(),张潇1,2,3,魏敏1,2,3,4,陈林1,2,3,卿海华1,2,3,高长斌4   

  1. 1.武汉理工大学,现代汽车零部件技术湖北省重点实验室,武汉  430070
    2.武汉理工大学,现代零部件技术湖北省协同创新中心,武汉  430070
    3.新能源与智能网联车湖北工程技术研究中心,武汉  430070
    4.上汽通用五菱汽车股份有限公司,柳州  545000
  • 收稿日期:2023-02-01 修回日期:2023-03-17 出版日期:2023-10-25 发布日期:2023-10-23
  • 通讯作者: 胡杰 E-mail:auto_hj@163.com

Vehicle Fault Location Method Based on Fuzzy BN and Improved Evidence Theory

Jie Hu1,2,3(),Xiao Zhang1,2,3,Min Wei1,2,3,4,Lin Chen1,2,3,Haihua Qing1,2,3,Changbin Gao4   

  1. 1.Wuhan University of Technology,Hubei Key Laboratory of Modern Auto Parts Technology,Wuhan  430070
    2.Wuhan University of Technology,Auto Parts Technology Hubei Collaborative Innovation Center,Wuhan  430070
    3.Hubei Technology Research Center of New Energy and Intelligent Connected Vehicle Engineering,Wuhan  430070
    4.SAIC-GM-Wuling Automobile Company Limited,Liuzhou  545000
  • Received:2023-02-01 Revised:2023-03-17 Online:2023-10-25 Published:2023-10-23
  • Contact: Jie Hu E-mail:auto_hj@163.com

摘要:

为解决车辆售后维修过程中由于车辆部件的关联故障而产生大量杂乱故障码,导致通过分析故障码进行源头故障部件定位困难的问题,本文提出一种基于模糊BN和改进证据理论的车辆故障定位方法。首先,根据历史数据及专家经验构建模糊BN模型并得到其后验概率。其次,将后验概率作为改进证据理论的基本概率赋值输入,提出融合邓熵和Pignistic概率距离的修正系数对证据修正,解决证据不确定性及证据间冲突问题。然后,采用基于矩阵分析的证据合成规则,避免大量证据合成失败情况的同时减少计算量,得到故障定位结果。最后,以ABS系统为例,验证该方法的可行性。本文所提出的方法可为维修人员提供指导进行快速定位故障。

关键词: 故障码, 模糊贝叶斯网络, D-S证据理论, 故障定位

Abstract:

This paper proposes a vehicle fault location method based on fuzzy BN and improved evidence theory, in order to solve the problem of difficulty in locating the source fault parts by analyzing the fault codes due to generation of a large number of chaotic diagnosis trouble codes by the associated faults of vehicle parts in the process of vehicle after-sales maintenance. Firstly, the fuzzy BN model is constructed according to historical data and expert experience and the posterior probability is obtained. Secondly, the posterior probability is input as the basic probability assignment of the improved evidence theory, and the correction coefficient combining Deng entropy and Pignistic probability distance is proposed to correct the evidence, so as to solve the problems of the uncertainty of the evidence itself and the conflict between evidences. Then, the evidence synthesis rule based on matrix analysis is adopted to avoid a large number of evidence synthesis failures and reduce the amount of computation, and the fault location results are obtained. Finally, the ABS system is taken as an example to verify the feasibility of this method, which can provide guidance for maintenance personnel to locate faults quickly.

Key words: diagnosis trouble code, fuzzy Bayesian network, D-S evidence theory, fault location