AN IMPROVED APPROACH FOR GEARBOX CONDITION MONITORING BASED ON WAVELET-FRACTAL ANALYSIS

This paper has classified the acceleration signals of different working states of gearbox based on the wavelet-fractal analysis. Considering the similarity of the power spectrums between bearing vibration signals and 1/f processes signals, the principles based on wavelet-fractal analysis for gearbox fault diagnosis are explored. The improved approach mainly includes three following steps: the discrete wavelet transform (DWT) is first performed on vibration signals gathered by accelerometer from gearbox to achieve a series of detailed signals at different scales; the variances of multiscale detailed signals are then calculated; finally, the improved approach slope features are estimated from the slope of logarithmic variances. The presented features reveal an inherent structure within the power spectra of vibration signals. The effectiveness of the proposed feature was verified by experiment on gear wear diagnosis. Experimental results show that the improved approach features have the merits of high accuracy and stability in classifying different fault conditions of gearbox, and thus are valuable for machine fault diagnosis.