基于模糊逻辑和证据理论的故障诊断方法

摘要

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.%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,充分利用各种传感嚣的冗余和互补信息,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.