Application of statistical parameters and discrete wavelet transform to gear damage diagnosis

Gear is one of the most commonly used and important components in machine system. Mainly gear failure may cause serious damage of the whole equipment, even huge economic losses. Therefore, it is important to detect the gear damage as early as possible. This paper provides a method of diagnosis and location for gear damage based on statistical approach and discrete wavelet transform (DWT). The vibration signals of gear box and bearing box are measured as analytical data. To emphasize the failure features of the measured signal, gear motion residual signal is obtained from the raw signal and provides a better indication of the existence of failures. Additionally, the method of discrete wavelet transform is employed to reduce the noise from the residual signal and decompose the signal into several decomposition levels. Because of the good sensitivity to the altering of vibration signal, statistical parameters such as standard deviation, kurtosis and so on are extracted from the raw signal and the reconstructed signal by DWT as failure features for detecting the gear damage. For a comparison of the raw signal and the reconstructed signal, the variation of statistical parameters among different kinds of test gears is also discussed by the significance test. The validity of the presented method is testified by some experiments under different conditions. Three kinds of gears namely normal gear, spot damaged gear and pitted gear are tested on the power circulating type gear testing machine, and the vibration acceleration on both gear box and bearing box is obtained. The experimental results show the effectiveness of this method on the diagnosis of gear damage.