一种基于聚类神经网络的模拟电路故障诊断方法

Analog circuits fault diagnosis approach based on a clustering NN

提出了线性互易电路单一元件软故障的统一特征概念．根据统一特征可将软故障字典建立于本文提出的聚类神经网络之中．这一有限规模的字典，能够诊断每一元件所有的软故障，测前工作量小、诊断过程简单．在一定的条件下，此方法对弱非线性电路小范围软故障也适用．

The general concept of single soft fault in linear reciprocal circuits is presented in this paper. According to this. concept, a 'soft fault dictionary' can be implemented with a kind of clustering neural network proposed. By use of this dictionary of limited size, various soft faults of a single element can be located. Under the certain .condition, this method can also be applied to weakly nonlinear circuits with small soft malt.