By Topic

Neural fault detection of an adaptive controlled beam

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Nobrega, E.G. ; Dept. of Comput. Mech., State Univ. of Campinas, Brazil ; Alves, M.A., Jr. ; Grigoriadis, K.M.

Model-based observers seem to be the most evolving techniques during the past years, but depending on the complexity of the monitored system, they may become impractical. Non-model-based methods for fault detection are suitable for these complex cases, and artificial neural networks are likely to provide the necessary features. A comparison between these two methods is conducted in this paper, focusing on the structural fault detection in a cantilevered beam. This system, despite being a simple structure, permits a good insight of the characteristics of the two methods. Two structural faults are presented: a simulated crack on a finite element model of the beam, and a mass variation on an experimental test-bed. Both the simulation and the experimental results infer that neural networks may be a good option for fault detection in complex systems

Published in:

American Control Conference, 2000. Proceedings of the 2000  (Volume:6 )

Date of Conference: