Diagnosis of Sensor Fault Based on Wavelet Packet and RBF Neural Network

摘要：

A diagnosis method based on wavelet packet transform and RBF neural network was proposed to detect and identify sensor fault based on the character of sensor fault The sensor fault signals are decomposed in different frequency bands by wavelet packet decomposition and reconstruction, and the energy of every band is used as the eigenvector of condition monitoring as well as input of RBF(Radial Basis Function) neural network. The classification of sensor fault is conducted by using the best RBF neural network. Experiment results prove that the method has good tracking ability of nonlinear system and higher diagnosis accuracy.

关键词： Wavelet packet transform neural network fault diagnosis sensor

作者: Ma Tianbing Zhang Xin

作者单位: College of Mechanical Engineering,Anhui University of Science and Technology,Huainan 232001 China

会议类型: 国际会议

会议名称: The Third International Symposium on Test Automation & Instrumentation(第三届国际自动化测试与仪器仪表学术会议 2010 ISTAI)

会议地点: 厦门

会议语种:英文

页码: 1219-1223

在线出版日期: 2010-05-22（万方平台首次上网日期，不代表论文的发表时间）