Deakin University
Browse

File(s) not publicly available

Fault detection and diagnosis using an art-based neural network

conference contribution
posted on 2010-07-20, 00:00 authored by K S Yap, M T Au, Chee Peng LimChee Peng Lim, J M Saleh
The Generalized Adaptive Resonance Theory (GART) network is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. It is capable of online learning, and is effective in tackling classification as well as regression tasks, as demonstrated in our previous work. In this paper, we further enhance the capability of the GART network with the Laplacian functions and with new vigilance and match-tracking mechanisms. In addition, a rule extraction procedure is incorporated into its dynamics, and its applicability to fault detection and diagnosis tasks is assessed. IF-THEN rules can be extracted from the weights of the trained GART network after a pruning process. The classification and rule extraction capability of GART are evaluated using one benchmark data set from medical application, and one real data set collected from a power generation plant. These results are then compared with those reported by other methods. The outcomes demonstrate that GART is able to produce high classification rates with quality rules for tackling fault detection and diagnosis problems.

History

Pagination

118 - 125

Publisher

ACTA Press

Location

Innsbruck, Austria

Place of publication

Calgary, Canada

Start date

2010-02-15

End date

2010-02-17

ISBN-13

9780889868182

Publication classification

EN.1 Other conference paper

Title of proceedings

Proceedings of the 10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC