Robustness test of an incipient fault detector artificial neural network

  • Mo yuen Chow*
  • , Sui Oi Yee
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

The authors address the issue of robustness in artificial neural networks subject to small input perturbations. The robustness in artificial neural networks is studied using the concept of input-output sensitivity analysis applied to an incipient fault detector artificial neural network (IFDANN). The IFDANN was designed to detect winding insulation fault and bearing wear in single-phase squirrel-cage induction motors. Modification of the IFDANN, with the intention of increasing its robustness to input noise during real-time applications, is discussed. Analytical and simulation results are presented to show the significant improvement in robustness of the modified IFDANN for operation with noisy measurements.

Original languageEnglish
Title of host publicationProceedings. IJCNN-91-Seattle
Subtitle of host publicationInternational Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages73-78
Number of pages6
ISBN (Print)0780301641
StatePublished - 1991

Publication series

NameProceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Robustness test of an incipient fault detector artificial neural network'. Together they form a unique fingerprint.

Cite this