Induction motor fault detection and diagnosis using supervised and unsupervised neural networks

Successful and reliable motor fault detection and diagnosis requires expertise and knowledge. Neural network technologies can be used to provide inexpensive but effective fault detection mechanism This paper presents two neural networks algorithms: supervised and unsupervised types with applications to induction motor fault detection and diagnosis problems. The detection algorithm was simulated and its performance verified on various fault types. Simulation results illustrated that, after training the neural network, the system is able to detect the faulty machine.