Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis

A hybrid network, based on the integration of Fuzzy ARTMAP (FAM) and the Rectangular Basis Function Network (RecBFN), is proposed for rule learning and extraction problems. The underlying idea for such integration is that FAM operates as a classifier to cluster data samples based on similarity, whil...

Full description

Bibliographic Details
Main Authors: Tan, Shing Chiang, Lim, Chee Peng
Format: Article
Published: 2005
Subjects:
Online Access:http://shdl.mmu.edu.my/2386/
_version_ 1848790041796542464
author Tan, Shing Chiang
Lim, Chee Peng
author_facet Tan, Shing Chiang
Lim, Chee Peng
author_sort Tan, Shing Chiang
building MMU Institutional Repository
collection Online Access
description A hybrid network, based on the integration of Fuzzy ARTMAP (FAM) and the Rectangular Basis Function Network (RecBFN), is proposed for rule learning and extraction problems. The underlying idea for such integration is that FAM operates as a classifier to cluster data samples based on similarity, while the RecBFN acts as a "compressor" to extract and refine knowledge learned by the trained FAM network. The hybrid network is capable of classifying data samples incrementally as well as of acquiring rules directly from data samples for explaining its predictions. To evaluate the effectiveness of the hybrid network, it is applied to a fault detection and diagnosis task by using a set of real sensor data collected from a Circulating Water (CW) system in a power generation plant. The rules extracted from the network are analyzed and discussed, and are found to be in agreement with experts' opinions used in maintaining the CW system.
first_indexed 2025-11-14T18:06:19Z
format Article
id mmu-2386
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:06:19Z
publishDate 2005
recordtype eprints
repository_type Digital Repository
spelling mmu-23862011-08-22T07:08:39Z http://shdl.mmu.edu.my/2386/ Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis Tan, Shing Chiang Lim, Chee Peng QA75.5-76.95 Electronic computers. Computer science A hybrid network, based on the integration of Fuzzy ARTMAP (FAM) and the Rectangular Basis Function Network (RecBFN), is proposed for rule learning and extraction problems. The underlying idea for such integration is that FAM operates as a classifier to cluster data samples based on similarity, while the RecBFN acts as a "compressor" to extract and refine knowledge learned by the trained FAM network. The hybrid network is capable of classifying data samples incrementally as well as of acquiring rules directly from data samples for explaining its predictions. To evaluate the effectiveness of the hybrid network, it is applied to a fault detection and diagnosis task by using a set of real sensor data collected from a Circulating Water (CW) system in a power generation plant. The rules extracted from the network are analyzed and discussed, and are found to be in agreement with experts' opinions used in maintaining the CW system. 2005 Article NonPeerReviewed Tan, Shing Chiang and Lim, Chee Peng (2005) Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis. Soft Computing: Methodologies and Applications. pp. 179-191. ISSN 1615-3871 http://dx.doi.org/10.1007/3-540-32400-3_14 doi:10.1007/3-540-32400-3_14 doi:10.1007/3-540-32400-3_14
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Tan, Shing Chiang
Lim, Chee Peng
Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title_full Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title_fullStr Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title_full_unstemmed Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title_short Rule Learning and Extraction Using a Hybrid Neural Network: A Case Study on Fault Detection and Diagnosis
title_sort rule learning and extraction using a hybrid neural network: a case study on fault detection and diagnosis
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2386/
http://shdl.mmu.edu.my/2386/
http://shdl.mmu.edu.my/2386/