Combining neuro-fuzzy and machine learning for fault diagnosis of a DC motor

An approach for the diagnosis of faults in dynamic systems based on a neuro-fuzzy scheme is presented. The simple structure that represents fuzzy rules in a neural network uses a rule extraction mechanism varying from most other approaches as it is based on concepts of machine learning. An additional, straightforward optimization eventually enhances the performance of the diagnosis. The approach is especially designed for the needs of technical fault diagnosis using parity space, observer and parameter estimation techniques. It evaluates parameter as well as parity space residuals and other information from the faulty process. Priory knowledge can easily be included as rules due to the simple structure of the scheme. The approach is tested on an electrical DC motor test bench to which several different faults can be applied