Using artificial neural networks or Lagrange interpolation to characterizethe faults in an analog circuit: An experimental study

Citation
Y. Maidon et al., Using artificial neural networks or Lagrange interpolation to characterizethe faults in an analog circuit: An experimental study, IEEE INSTR, 48(5), 1999, pp. 932-938
Citations number
6
Categorie Soggetti
Instrumentation & Measurement
Journal title
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
ISSN journal
00189456 → ACNP
Volume
48
Issue
5
Year of publication
1999
Pages
932 - 938
Database
ISI
SICI code
0018-9456(199910)48:5<932:UANNOL>2.0.ZU;2-9
Abstract
A technique for diagnosing multiple faults in analog circuits from their im pulse response function using a fault dictionary was developed, Dirac impul se input to the circuit was simulated and time domain features of the outpu t response were used to build the dictionary, The test of a real circuit by means of a fault dictionary gives realistic results provided the simulated and measured values are similar. Consequently, the choice of the model use d in the simulation is important. The precautions to realize the measuremen t are described.