Abstract
A novel intelligent method based on wavelet neural network (WNN) was proposed to identify the gear crack degradation in gearbox in this paper. The wavelet packet analysis (WPA) is applied to extract the fault feature of the vibration signal, which is collected by two acceleration sensors mounted on the gearbox along the vertical and horizontal direction. The back-propagation (BP) algorithm is studied and applied to optimize the scale and translation parameters of the Morlet wavelet function, the weight coefficients, threshold values in WNN structure. Four different gear crack damage levels under three different loads and three various motor speeds are presented to obtain the different gear fault modes and gear crack degradation in the experimental system. The results show the feasibility and effectiveness of the proposed method by the identification and classification of the four gear modes and degradation.
Highlights
Gearbox is one of the most important components to transmit power and torque effectively from one shaft to another in mechanical system
There are a lot of theories and methods about fault diagnosis and condition monitoring of the rotating machinery based on artificial intelligence techniques [2,3]
The method based on wavelet neural network (WNN) is studied to identify the gear fault modes and damage levels under three different loads and rotational speeds of gearbox
Summary
Gearbox is one of the most important components to transmit power and torque effectively from one shaft to another in mechanical system. Compared with the two above methods, the robust and simple intelligent method in this paper is proposed to identify the more gear crack levels under the separate operating conditions with the different loads and rotational speeds. The method based on WNN is studied to identify the gear fault modes and damage levels under three different loads and rotational speeds of gearbox. By calculating the full wavelet packet decomposition of a discrete time signal x(t), 2j sets of WPA coefficients at j level are obtained. The original signal is decomposed by wavelet packet, the 2j orthogonal frequency bands from low frequency to high frequency at jth level are obtained, that is the energy of the original vibration signal is decomposed into 2j different orthogonal frequency bands. The procedures that extract the feature parameters of vibration signal by wavelet packet decomposition as follows:.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
