Class-based neural network method for fault location of large-scale analogue circuits

A new method for fault diagnosis of lar e scale analo ue circuits based on the class concept is %&eloped in phis aper. A large analogue circuit is decomposed into hockslsub-circuits and the nodes between the blocks are classified into three classes. Only those sub-circuits related to the faultv class need to be treated. Node , ~~ ~ ~~~~ ~ ~ ~~~ ;lassibc&on reduces the scope of search for faults, thus reduced aner-test time. 'The proposed method is more suitable for real-time testing and can deal with both hard and soft faults. Tolerance effects are taken into account in the method. The class-hased fault diagnosis principle and neural network based method are described in some details. Two non-trivial circuit exam les are presented, showing that the proposed method is gasible.