RETRACTED: Identification of Fault Based on Wavelet Neural Network with Increased Momentum (Retracted Article)

Aiming at the complicated uncertain underwater environment, wavelet neural network with increased momentum is proposed to construct the motion model of underwater vehicle in this paper. The wavelet neural network has the capability of approximation and catching detail changes of the function by adjusting the scale and shift factors of wavelet. Then fault diagnose are put forward by comparing the residuals error between the estimated output of neural network and the real state value. The results show that the fault diagnosis method based on wavelet neural network with increased momentum is feasible and effective. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Organizers of 2011 International Conference on Energy and Environmental Science.