Automatic fault detection and diagnosis implementation based on intelligent approaches

Automatic fault detection and diagnosis has always been a challenge when monitoring rotating machinery. Specifically, bearing diagnostics have seen an extensive research in the field of fault detection and diagnosis. In this paper we present two automatic diagnosis procedures-a fuzzy classifier and a neural network-which deal with different implementation questions: the use of a priori knowledge, the computation cost, and the decision making process. The challenge is not only to be capable of diagnosing automatically but also to generalize the process regardless of the measured signals. Two actions are taken in order to achieve some kind of generalization of the application target: the use of normalized signals and the study of Basis Pursuit feature extraction procedure