Fault diagnosis of analog circuits using artificial neural networks as signature analyzers

Author

Spina, Robert ; Upadhyaya, Shambhu

Author_Institution

Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA

fYear

1992

Firstpage

355

Lastpage

358

Abstract

Experimental results using neural networks to provide go/no-go testing and fault diagnosis of analog circuits are presented. The primary focus is on reducing test time and providing a simple mechanism for automatic test pattern generation. Networks of reasonable dimension are shown to be capable of robust diagnosis of analog circuits, including effects due to tolerances and nonlinearities. The concepts are extended to include an approach to built-in test of analog or mixed signal ASICs

Keywords

analogue circuits; application specific integrated circuits; automatic testing; built-in self test; fault location; integrated circuit testing; linear integrated circuits; mixed analogue-digital integrated circuits; neural nets; analog circuits; artificial neural networks; fault diagnosis; go/no-go testing; signature analyzers; Analog circuits; Artificial neural networks; Automatic test pattern generation; Automatic testing; Circuit faults; Circuit testing; Fault diagnosis; Frequency response; System testing; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

ASIC Conference and Exhibit, 1992., Proceedings of Fifth Annual IEEE International

Conference_Location

Rochester, NY

Print_ISBN

0-7803-0768-2

Type

conf

DOI

10.1109/ASIC.1992.270220

Filename

270220