Abstract
A fault diagnosis procedure for analog linear circuits is presented. It uses an off-line trained neural network as a classifier. The innovative aspect of the proposed approach is the way the information provided by testability and ambiguity group determination is exploited when choosing the neural network architecture. The effectiveness of the proposed approach is shown by comparing with similar work that has already appeared in the literature.
Similar content being viewed by others
References
Liu RW (1991) Testing and diagnosis of analog circuits and systems. Van Nostrand Reinhold, New York
Bandler JW, Salama AE (1985) Fault diagnosis of analog circuits. P IEEE 73:1279–1325
Liu D, Starzyk JA (2002) A generalized fault diagnosis method in dynamic analog circuits. Int J Circ Theor App 30:487–510
Spina R, Upadhyaya S (1997) Linear circuit fault diagnosis using neuromorphic analyzers. IEEE T Circuits–II 44:188–196
Aminian M, Aminian F (2000) Neural network based analog-circuit fault diagnosis using wavelet transform as preprocessor. IEEE T Circuits–II 47:151–156
Aminian F, Aminian M, Collin HW (2002) Analog fault diagnosis of actual circuits using neural networks. IEEE T Instrum Meas 51:544–550
Catelani M, Fort A (2002) Soft fault detection and isolation in analog circuits: some results and a comparison between a fuzzy approach and radial basis function networks. IEEE T Instrum Meas 51:196–202
Alippi C, Catelani M, Fort A, Mugnaini M (2002) SBT soft fault diagnosis in analog electronic circuits: a sensitivity-based approach by randomized algorithms. IEEE T Instrum Meas 51:1116–1125
Alippi C, Catelani M, Fort A, Mugnaini M (2003) Methods for the automated selection of test frequencies for fault diagnosis in analog electronic circuits: a comparison. In: Proc 20th IEEE Instrumentation and Measurement Technology Conf, Vail, CO, 20–22 May, 2003, pp 60–64
Sen N, Saeks R (1979) Fault diagnosis for linear systems via multifrequency measurement. IEEE T Circuits Syst 26:457–465
Chen H, Saeks R (1979) A search algorithm for the solution of multifrequency fault diagnosis equations. IEEE T Circuits Syst 26:589–594
Fedi G, Manetti S, Piccirilli MC, Starzyk J (1999) Determination of an optimum set of testable components in the fault diagnosis of analog linear circuit. IEEE T Circuits–I 46:779–787
Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York
Fanni A, Giua A, Marchesi M, Montisci A (1999) A neural network diagnosis approach for analog circuits. Appl Intell 11:169–186
Dague Ph, Jehl O, Deves Ph, Luciani P, Taillibert P (1991) When oscillators stop oscillating. In: Proc 12th Int Joint Conf on Artificial Intelligence, Sydney, Australia, 24–30 August 1991, pp 1109–1115
Kirkland LV, Dean JS (1994) Monitoring power supply current and using a neural network routine to diagnose circuit faults. AUTOTESTCON’94, Anaheim, CA, 20–22 September 1994, pp 649–651
Spence HF, Burris DP, Lopez J, Houston RA (1991) An artificial neural network printed circuit board diagnostic system based on infrared energy emission. AUTOTESTCON’91 Anheim, CA, 24–26 September 1991, pp 41–45
Spence HF (1994) Printed circuit board diagnosis using artificial neural networks and circuit magnetic fields. IEEE Aero El Sys Mag 9:20–24
The Mathworks, Inc. (2004) Matlab user’s guide, Rel 13. The Mathworks, Inc., Natick, MA
Meador J, Wu A, Tseng CT, Lin TS (1991) Fast diagnosis of integrated circuit faults using feedforward neural networks. In: IEEE Int Joint Conf on Neural Networks, Seattle, WA, 18–21 November 1991, pp 269–273
Rutkowsky G (1992) A neural network approach to fault location in non linear DC circuits. In: 3rd Int Conf on Artificial Neural Networks, Brighton, UK, 4–7 September 1992, pp 1123–1126
Czaja Z, Zielonko R (2003) Fault diagnosis in electronic circuits based on bilinear transformation in 3-D and 4-D spaces. IEEE T Instrum Meas 52:97–102
Liberatore A, Manetti S, Piccirilli MC (1994) A new efficient method for analog circuit testability measurement. In: IEEE Instrumentation and Measurements Technology Conf (IMTC), Hamamatsu, Japan, 10–12 May 1994, pp 193–196
Manetti S, Piccirilli MC (2003) A singular-value decomposition approach for ambiguity group determination in analog circuits. IEEE T Circuit–I 50:477–487
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cannas, B., Fanni, A., Manetti, S. et al. Neural network-based analog fault diagnosis using testability analysis. Neural Comput & Applic 13, 288–298 (2004). https://doi.org/10.1007/s00521-004-0423-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-004-0423-2