Application of radial basis function network to the preventive maintenance of electronic analog circuits

Author

Catelani, M. ; Fort, A. ; Nosi, G.

Author_Institution

Dipt. di Ingegneria Electron., Florence Univ., Italy

Volume

1

fYear

1999

fDate

1999

Firstpage

510

Abstract

The ability to detect soft fault is an important task in the preventive maintenance. In this paper a neural network based approach to fault detection of both linear and non linear circuits is presented. In particular Radial Basis Functions (RBF) networks are used to analyse circuit input-output measurements, and to localise faulty element. These methods exploit the capabilities, typical of neural networks, to analyze and classify signatures acid to deal with problems involving poorly defined system models, noisy input environment and non-linear behaviors

Keywords

analogue circuits; automatic testing; circuit analysis computing; circuit testing; fault diagnosis; maintenance engineering; neural net architecture; pattern classification; radial basis function networks; electronic analog circuits; fault detection; faulty element; input-output measurements; linear circuits; neural network; noisy input; nonlinear circuits; preventive maintenance; radial basis function network; signatures; soft fault; Circuit analysis; Circuit faults; Circuit noise; Electrical fault detection; Fault detection; Linear circuits; Neural networks; Particle measurements; Preventive maintenance; Radial basis function networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 1999. IMTC/99. Proceedings of the 16th IEEE

Conference_Location

Venice

ISSN

1091-5281

Print_ISBN

0-7803-5276-9

Type

conf

DOI

10.1109/IMTC.1999.776803

Filename

776803