关键词：模拟电路;故障诊断;故障定位;数据融合
摘 要：In fault diagnosis of circuit,fault diagnosis system using multi-sensor data fusion may not give reliable fault diagnosis result in cases when processing on inconsistent data carry inconsistent.In order to deal with such problems,This paper has developed an analog-circuit fault diagnostic system based on transferable belief model (TBM) and K-nearest neighbor rule from TBM.The proposed system has the capability to detect and identify fault components in an analog electronic circuit by analyzing its working temperature and testable voltage.Using K-nearest neighbor(KNN) rule to process the working temperature of component drastically enhances the testable information for fault detect,satisfying the need of fusing data from distinct evidence sources.The experimental results show that this system performs significantly better in fault diagnosis of analog circuits due to the proposed techniques.