Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (2): 261-265.DOI: 10.3778/j.issn.1002-8331.1810-0120

Previous Articles     Next Articles

Dynamic Fault Diagnosis Algorithm for Improved Evidence Update Rules

WANG Hui, LI Yingshun   

  1. 1.College of Electrical and Information Engineering, Guangxi University of Science and Technology, Liuzhou, Guangxi 545000, China
    2.School of Control Science and Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China
  • Online:2020-01-15 Published:2020-01-14

改进型证据更新规则的动态故障诊断算法

王卉,李英顺   

  1. 1.广西科技大学 电气与信息工程学院,广西 柳州 545000
    2.大连理工大学 控制科学与工程学院,辽宁 大连 116024

Abstract: The cause of the failure of the artillery filling system is complicated, and the single-factor and single-model fault diagnosis methods have been insufficient. This paper proposes a dynamic fault diagnosis method of improved evidence update rules, and applies the artificial intelligence method to the artillery automatic filling fault diagnosis system. The method determines the identification framework of fault diagnosis by describing the fuzzy rule base, applies the new fuzzy reasoning method to generate diagnostic evidence, and dynamically updates the diagnostic evidence at the time before and after the acquisition through the evidence update rule, and updates the merged evidence. Fault decision is made to solve the uncertainty of fault characteristics, fault pattern diversity and dynamic fault diagnosis. The case study proves that the method achieves the purpose of effectively improving the diagnosis rate of fault diagnosis.

Key words: artillery filling system, artificial intelligence, dynamic fault diagnosis, new fuzzy reasoning, improved evidence update

摘要: 火炮装填系统故障的成因复杂,单因素、单模型的故障诊断方法已显其不足。提出了改进型证据更新规则的动态故障诊断算法,并将所述的人工智能方法应用到火炮自动装填故障诊断系统中。该方法通过对模糊规则库的描述来确定故障诊断的辨识框架,应用新型的模糊推理方法生成诊断证据,并通过证据更新规则对所获取前后时刻的诊断证据进行动态更新,将更新融合后的证据进行故障决策,从而解决了故障特征的不确定性、故障模式多样性以及动态故障诊断问题。实例分析证明:该方法达到了有效提高故障诊断确诊率的目的。

关键词: 火炮装填系统, 人工智能, 动态故障诊断, 新型模糊推理, 改进证据更新规则