Wind Turbine Gearbox Fault Diagnosis Using Adaptive Morlet Wavelet Spectrum

Abstract

Fault diagnosis of a wind turbine gearbox is important to extend the wind turbine system's reliability and useful life. Vibration signals from a gearbox are usually noisy. As a result, it is difficult to find early symptoms of a potential failure in a gearbox. A novel method based on adaptive Morlet wavelet filter for the crack tooth of wind turbine gearbox is presented. In the proposed method, the first step is to optimize the parameters in the Morlet wavelet function based on the kurtosis maximization principle and then use it to filter the gearbox fault resonance features to extract the impulse features; the next step, an averaged autocorrelation spectrum is adopted to highlight the impulsive characteristics related to crack tooth conditions. The performance of this proposed technique is examined by the collected signals corresponding to crack tooth conditions. Test results show that this technique is an effective method in detection of symptoms from vibration signals of a gearbox with early fatigue tooth crack.