Research method of circuit fault diagnosis based on FCM

作     者：周德新 李伟 

作者机构：College of Aeronautical AutomationCivil Aviation University of China 

出 版 物：《中南大学学报（自然科学版）》 (Journal of Central South University:Science and Technology)

年 卷 期：2009年第40卷第S1期

页      面：290-294页

核心收录：

学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术] 

基　　金：Project (MHRD0705) supported by the Science Foundation by Civil Aviation Administrator of China Project (07ZCKFGX01500) supported by Tianjin Science Foundation and Technology Key Project 

主　　题：C cluster algorithm neural network analog circuit fault diagnosis 

摘      要：Using fuzzy C cluster mean (FCM), fuzzy theory and neural network, a fault diagnosis method was proposed, which was based on fuzzy C-means clustering algorithm of neural network that was applied in non-linear analog circuits and in diagnoses the ARNIC 429 reception circuit of aviation aircraft avionics. The C cluster algorithm can make the amount of the fuzzy rule automatically and can create an initial fuzzy rule database of fault diagnosis. A type of fuzzy neural network and a fault tree were generated. The algorithm avoids the disadvantage that gets into the part of optimum circumstance. A validate application was implemented, which proves that the method is effective. Therefore, the method is superior to the traditional methods in fault diagnosis, and the efficiency is heavily improved.