FPGA Based Intelligent Condition Monitoring of Induction Motors: Detection, Diagnosis, and Prognosis

Abstract

This paper presents three intelligent methods for condition monitoring of induction motors in real-time. A structured neural network has been designed to prognosis of instantaneous faults. The inputs of neural network are the standard deviation and mean of feature signal obtained by Hilbert transform of one phase current signal. The stator related faults have been diagnosed by designing fuzzy logic. The amplitudes of three phase currents have been given to fuzzy logic and the condition of stator has been diagnosed. The last algorithm uses the phase space of the Hilbert transform of one phase current and detects broken rotor bar faults using negative selection algorithm. The contribution of the algorithm is the development of synchronously worked algorithms, optimized for low-cost Field Programmable Gate Array (FPGA) implementation. Extensive simulations were applied to test the performance of each algorithm, and the results show that the algorithms give high accuracy in detecting whether a possible fault has occurred in any component of the motor. The average detection time of the faults is above within 2 milliseconds or less.