FAULT DETECTION AND DIAGNOSIS INGEARS USING WAVELET ENVELOPED POWER SPECTRUM AND ANN

In this work, automatic detection and diagnosis of gear condition monitoring technique is presented. T he vibration signals in time domain wereobtained from a fault simulator apparatu s from a healthy gear and an induced faulty gear. T hese time domain signals were processed using Laplace and Morlet wavelet bas ed enveloped power spectrum to detect the faults in gears. The vibration signals obtained were filtered to enhance the signal compon ents before the application of wavelet analysis. Th e time and frequency domain features extracted from Laplace wavelet based wavel et transform are used as input to ANN for gear faul t classification. Genetic algorithm was used to optimize the wavelet and ANN classification parameters. The result shows the suc cessful classification of ANN test process. Index Terms: Continuous wavelet transform, Envelope power spectr um, Wavelet, Filtering, ANN.