Title :
Study on Fault Diagnosis of Rotating Machinery Based on Wavelet Neural Network
Author_Institution :
Coll. of Inf. Eng., Jinhua Coll. of Profession & Technol., Jinhua, China
Abstract :
A wavelet neural network is constructed based on wavelet transform principle. A fault diagnosis method based on a wavelet neural network is put forward, the model and algorithms of the network is given. After collecting the vibration signal and computing the spectrum characteristics parameters in frequency domain of the rotating machinery, the samples are learned to train the constructed wavelet neural network for realizing the mapping relationship between the fault and the spectrum characteristic, which can used in fault diagnosis. Using the wavelet neural network and BP neural network in the fault diagnosis experiments, the results show that the proposed method in this article has a better diagnostic, fast performance.
Keywords :
backpropagation; fault diagnosis; mechanical engineering computing; neural nets; turbomachinery; BP neural network; fault diagnosis; rotating machinery; vibration signal; wavelet neural network; Artificial neural networks; Biological neural networks; Fault diagnosis; Humans; Machinery; Neural networks; Signal resolution; Wavelet analysis; Wavelet domain; Wavelet transforms; BP neural network; fault diagnose; rotating machine; wavelet neural network;
Conference_Titel :
Information Technology and Computer Science, 2009. ITCS 2009. International Conference on
Conference_Location :
Kiev
Print_ISBN :
978-0-7695-3688-0
DOI :
10.1109/ITCS.2009.287