基于智能信息融合的模拟电路故障定位方法 彭敏放.pdfVIP

2005 11 Vol.20 No.11 20 11 TRANSACTIONS OF CHINA ELECTROTECHNICAL SOCIETY Nov. 2005 410082 BP BP TM131 Fault Location of Analog Circuits Using Intelligent Information Fusion Technology Peng Minfang He Yigang L Jingxiang Hunan University Changsha 410082 China Abstract In order to solve the problems of insufficient test data and low diagnosis accuracy, a fault location approach for analog circuits is developed based on intelligent information fusion technology including data fusion, neural network and fuzzy theory. Using accessible node voltages and circuit gains under different test frequencies respectively, preliminary diagnosis is performed separately by an independent improved BP network employing one kind of test data. According to the preliminary diagnosis results, fault location is accomplished by means of the proposed fuzzy data fusion algorithm and fault recognition method. The proposed approach makes full use of the fault information and has the capability to diagnose multiple and soft faults of analog circuits with satisfactory accuracy. Keywords Fault location, data fusion, neural network, fuzzy theory, BP algorithm, analog circuit 1 [1, 2] 60 [35]