基于模糊逻辑和证据理论的故障诊断方法  

Fault diagnosis method based on fuzzy logic and evidence theory

作　　者：吴晓平[1] 郑之松[1,2] 付钰[1] 

机构地区：[1]海军工程大学电子工程学院,武汉430033 [2]海军司令部军训部,北京100841

出　　处：《海军工程大学学报》2012年第1期10-14,51,共6页Journal of Naval University of Engineering

基　　金：国家自然科学基金资助项目(60774029)

摘　　要：针对故障诊断过程中信息损失的问题和D-S证据理论在处理模糊信息时的局限性,在模糊逻辑的基础上,将决策级信息融合技术应用于故障诊断系统中,提出了一种基于模糊逻辑和D-S证据理论相结合的多传感器信息融合综合故障诊断方法。该方法以模糊隶属函数来实现基本可信度分配,充分利用各种传感器的冗余和互补信息,可显著提高故障诊断的准确率,实例验证了该方法的合理性和有效性。Aiming at the problem of information missing in the process of fault diagnosis and the limitation of D-S evidence theory in dealing with fuzzy information,a method of synthetical fault diagnosis using multi-sensor fusion is proposed based on the fuzzy logic and D-S evidence theory.The method uses fuzzy membership function to realize the basic reliability distribution.Also the redundancy and complementarities for information of multi-sensor is fully used to improve the accuracy of fault diagnosis.The results show that the method is reasonable and effective.

关 键 词：模糊逻辑 D-S证据理论 故障诊断 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]