Fault detection and diagnosis using an art-based neural network
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...
Saved in:
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference paper |
| Published: |
Acta Press
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833410228407762944 |
|---|---|
| author | Yap K.S. Au M.T. Lim C.P. Saleh J.M. |
| author2 | 24448864400 |
| author_facet | 24448864400 Yap K.S. Au M.T. Lim C.P. Saleh J.M. |
| author_sort | Yap K.S. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | 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. |
| format | Conference paper |
| id | my.uniten.dspace-30697 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2023 |
| publisher | Acta Press |
| record_format | dspace |
| spelling | my.uniten.dspace-306972023-12-29T15:51:30Z Fault detection and diagnosis using an art-based neural network Yap K.S. Au M.T. Lim C.P. Saleh J.M. 24448864400 9742020600 55666579300 6505808410 Adaptive resonance theory Fault detection and diagnosis Network pruning Rule extraction 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. Final 2023-12-29T07:51:30Z 2023-12-29T07:51:30Z 2010 Conference paper 10.2316/p.2010.674-102 2-s2.0-77954581394 https://www.scopus.com/inward/record.uri?eid=2-s2.0-77954581394&doi=10.2316%2fp.2010.674-102&partnerID=40&md5=2176ea73f290265c751508c98a1d0ee5 https://irepository.uniten.edu.my/handle/123456789/30697 118 125 Acta Press Scopus |
| spellingShingle | Adaptive resonance theory Fault detection and diagnosis Network pruning Rule extraction Yap K.S. Au M.T. Lim C.P. Saleh J.M. Fault detection and diagnosis using an art-based neural network |
| title | Fault detection and diagnosis using an art-based neural network |
| title_full | Fault detection and diagnosis using an art-based neural network |
| title_fullStr | Fault detection and diagnosis using an art-based neural network |
| title_full_unstemmed | Fault detection and diagnosis using an art-based neural network |
| title_short | Fault detection and diagnosis using an art-based neural network |
| title_sort | fault detection and diagnosis using an art-based neural network |
| topic | Adaptive resonance theory Fault detection and diagnosis Network pruning Rule extraction |
| url_provider | http://dspace.uniten.edu.my/ |