International Journal of Computational Intelligence Research (IJCIR)

Volume 2, Number 1 (2006)


Fault diagnosis in analog circuits based on testability analysis and multi-frequency 

TPG using neural networks

Xie Yong-Le, Wang Cheng, Chen Guang-Ju

University of Electronic Science and Technology of China, School of Automation Engineering ChengD SiChuan Province, People's Republic of China


Testability analysis and multi-frequency TPG are essential to fault diagnosis in analog circuits. A fault diagnosis technique for analog circuits is presented. First, using testability analysis test nodes are properly chosen and ambiguity groups are determined in analog circuits. Then, test vectors are generated through sensitivity computation. Finally, under the condition of components tolerance, using neural networks (NNs) to fuse fault feature of each test node, fault components are detected and located. Simulation results illustrate that this method is feasible and efficient.

Key words
fault diagnosis in analog circuits, testability analysis, sensitivity computation, neural networks, multi-frequency test.