Fault diagnosis plays an important role in the dependability of modern dynamic systems. Numerous diagnosis schemes and architectures have been developed and applied to the benchmark DAMADICS. One of the key issues in designing a fault diagnosis system is the system modeling. Neural networks combined with other methods have been widely investigated for that purpose. The main contribution of this paper is to develop a fault detection and diagnosis schema with a bank of fault free and faulty reference models designed according to neural networks. Fault detection is obtained according to the comparison of measured signals with the behavior of fault free reference model. Then, calculation of Euclidean norms of the output error signals resulting from the faulty models leads to fault isolation. The effectiveness of this approach is illustrated with simulations on DAMADICS benchmark.
5th Mosharaka International Conference on Communications, Propagation, and Electronics (MIC-CPE 2012)
Congress
2012 Global Congress on Communications, Propagation, and Electronics (GC-CPE 2012), 3-5 February 2012, Istanbul, Turkey
Pages
11-16
Topics
Fault-Tolerant Systems Modeling, Estimation and Prediction
ISSN
2227-331X
DOI
BibTeX
@inproceedings{241CPE2012,
title={Faults Diagnosis Based on Faulty Models Design:
Application to DAMADICS.},
author={Yahia Kourd, and Dimitri Lefebvre, and Noureddine Guersi},
booktitle={2012 Global Congress on Communications, Propagation, and Electronics (GC-CPE 2012)},
year={2012},
pages={11-16},
doi={}},
organization={Mosharaka for Research and Studies}
}