A novel fuzzy classification solution for fault diagnosis

Abstract

This paper introduces a novel fuzzy classification methodology for fault diagnosis. The main advantages of the proposed fuzzy classifier are the high accuracy of defining the areas corresponding to different categories and the fine precision of discrimination inside overlapping areas. The fuzzy sets used by the classifier are built upon a similarity measure between the objects in the problem space. Another advantage of the classifier is its capability to handle either single or hybrid similarity measures. The methodology has been validated by application to a fault diagnosis problem. The classifier has shown excellent performances in diagnosing faults to a control flow valve from an industrial device.