ENHANCEMENT OF SIGNAL DENOISING AND FAULT DETECTION IN WIND TURBINE PLANETARY GEARBOX USING WAVELET TRANSFORM

De-noising and extraction of the weak signature are crucial to fault diagnostics and prognostics in which case features are often very weak and masked by noise. The wavelet transform has been widely used in signal de-noising due to its extraordinary time-frequency representation capability. In this paper, a method for the fault diagnosis of the wind turbine planetary gearbox components is proposed based on wavelet transform analysis. Emphasis is given on the signal processing of the acquired vibration signal in order to extract novel parameters-features of potential diagnostic value from the monitored waveforms. Innovative wavelet- based parameters-features are proposed utilizing the continuous wavelet transform (CWT). Gearbox components faults of planet gear tooth crack, planet carrier crack and main bearing inner race crack were tested under accelerated fault conditions, and filtered time domain technique is applied to the component vibrations to indicate the presence and progression of the fault. The evolution of selected parameters/ features versus test time is provided and evaluated. The parameters of diagnostic techniques; namely spectrum comparisons, spectral kurtosis analysis and crest factor analysis are used for the filtered vibration signals. The test results demonstrate that the applying of de-noising to vibration signals is a very powerful and reliable method and hence estimating fault type on wind turbine planetary gearbox components accurately and quickly. Moreover, tests results show that RMS value is a very reliable filtered time-domain diagnostic technique.