Sequential Fuzzy Diagnosis for Plant Machinery

Abstract

When developing a fuzzy diagnosis system for machinery conditions, the relationship between fault symptoms and fault categories must be defined for fuzzy inference. However, it is not easy to determine the fault symptoms by which all fault categories can be distinguished perfectly and automatically. In order to resolve this problem, we proposed: (1) a new fuzzy diagnosis method called “sequential fuzzy diagnosis”, and (2) an identification method of the membership function of the symptom parameter by possibility theory. The efficiency of the above methods was verified by applying them to the rolling bearing diagnosis system and others. In the system of rolling bearing diagnosis, the symptom parameters are calculated by “goodness of fit” with spectrum analysis. The results of sequential fuzzy diagnosis show the correct conclusions when inputting field data to the system.