Predictive Maintenance Based on Earlier Fault Detection of Multi Phase Induction Machines Using Neural Network Artificial Intelligent Techniques

The area of multiphase variable-speed motor drives in general and multiphase induction Motor drives in particular have experienced a substantial growth since the beginning of this century. Research has been conducted worldwide and numerous interesting developments have been reported in the literature. An attempt is made to provide a detailed overview of the current state-ofthe-art in this area. The elaborated aspects include advantages of multiphase induction machines, modeling of multiphase induction machines. This paper also provides a detailed survey of the control strategies for five-phase and asymmetrical six-phase induction motor drives for the saturated model of the induction motor. However all the old researches in this field are obtained using the approximate linear model of the induction machine which is not exactly accurate because that we are not guarantee that the motor operation is not in the saturation region . These results are also included for clarifying the behavior of the five and six phase using the saturated model of induction machine as an examples of the multi phase machine. Also this paper presents an approach to induction motor fault diagnosis and condition prognosis based on neural network and adaptive neuro-fuzzy inference systems (ANFIS). The ANFIS is a neural network structured upon fuzzy logic principles, which enables the neural fuzzy system to provide the motor condition and fault detection process. This knowledge is provided by the fuzzy parameters of member ship functions and fuzzy rules. By using the neural network and (ANFIS) techniques, we can detect and locate the inter-turn short circuit fault in the stator winding of an induction motor. Simulation results are presented to demonstrate the effectiveness of the proposed method.