A Kind Integrated Adaptive Fuzzy Neural Network Tolerance Analog Circuit Fault Diagnosis Method

摘要：

Combining fuzzy theory and neural network is an effective way to be applied in fault diagnosis of analog circuit. For tolerance analog circuit fault, this paper proposed a kind new based on integrated adaptive fuzzy neural network the diagnosis method. The method first uses wavelet transform to extract the signal from the output sample, and characteristics of fault feature vectors are normalized. Then it uses the principal element analysis to reduce the fault sample dimension, the network architecture can be simplified, the computation complexity can be reduced. Afterward training and testing integrated adaptive fuzzy neural network with the preprocessed fault characteristic data. Experimentation indicates that the method has higher diagnosis nicety rate and effectively solves fault tolerance of ambiguity and problems.

关键词： c Fault diagnosis Principal Component Analysis Wavelet Transform Integrated adaptive fuzzy neural network

作者: Xuefeng Qin Baoru Han Lei Cui

作者单位: Department of Electronic Engineering Hainan Software Profession Institute Qionghai, 571400, China The college of Information Science and Engineering, Yanshan University,Qin Huangdao, 0 66004, China

会议类型: 国际会议

会议名称: 2011 IEEE 2nd International Conference on Computing，Control and Industrial Engineering(CCIE 2011)(第二届计算、控制与工业工程国际会议)

会议地点: 武汉

会议语种:英文

页码: 180-183

在线出版日期: 2011-08-20（万方平台首次上网日期，不代表论文的发表时间）