Online Condition Monitoring of Induction Motor through WPD Technique

Fault diagnosis is a very important technology in the field of electrical equipment maintenance. Earlier method for motor fault diagnosis algorithms is usually employ FFT and deterministic thresholds. Now a days research trends show that AI techniques will have a greater role in electric equipment diagnostic system with advanced practicability, sensitivity, reliability. AI technique reduces a tedious manual works and inaccuracy to the application. This paper we focuses the spectral analysis of vibration signal by a new approach to detect the faults of induction motors based on Wavelet Packet Decomposition (WPD). The novelty of the proposed method lies in the fact that by using WPD in the inherent non stationary nature of vibration signal the feature co-efficient are calculated for healthy and faulty motor. From the comparison result of the feature coefficients we differentiate between healthy and faulty condition of an induction motor.