Neuro-fuzzy modeling for fault diagnosis in rotating machinery

Malfunctions in machinery are often sources of reduced productivity and increased maintenance costs in various industrial applications. For this reason, machine condition monitoring has been developed to recognize incipient fault states. In this paper, the fault diagnostic problem is tackled within a neuro-fazzy approach to pattern classification. Besides the primary purpose of a high rate of correct classification, the proposed neuro-fuzzy approach aims at obtaining also a transparent classification model. To this aim, appropriate coverage and distinguishability constraints on the fuzzy input partitioning interface are used to achieve the physical interpretability of the membership functions and of the associated inference rules. The approach is applied to a case of motor bearing fault classification.