Fault diagnosis based on wavelet packet energy and PNN analysis method for rolling bearing

Abstract

A combined approach based on wavelet packet energy and probabilistic neural network (WPE-PNN) is presented to diagnose faults in the rolling bearing vibration signal research. Firstly wavelet packet is used to decompose rolling bearing vibration signals into three-layer, and extract the energy characteristics. Then PNN is proposed to diagnose faults. Finally, remote fault diagnosis is realized by virtual instrument technology. The proposed method can provide an accepted degree of accuracy in fault classification under different fault conditions and can be operated remotely from another station connected to the server via the World Wide Web.