Model-based fault detection using hierarchical artificial neural network

In this paper, a two-stage approach integrating a neural network dynamic estimator and a neural network fault classifier is proposed to overcome the problem of malfunction in sensors. The process estimator is designed to predict the dynamic behaviour of the normal or fault-free operating process eve...

Full description

Bibliographic Details
Main Authors: Ahmad, Arshad, Leong, Wah Heng
Format: Conference or Workshop Item
Language:English
Published: 2001
Subjects:
Online Access:http://eprints.utm.my/967/
http://eprints.utm.my/967/1/RSCE2001.pdf
_version_ 1848890036202766336
author Ahmad, Arshad
Leong, Wah Heng
author_facet Ahmad, Arshad
Leong, Wah Heng
author_sort Ahmad, Arshad
building UTeM Institutional Repository
collection Online Access
description In this paper, a two-stage approach integrating a neural network dynamic estimator and a neural network fault classifier is proposed to overcome the problem of malfunction in sensors. The process estimator is designed to predict the dynamic behaviour of the normal or fault-free operating process even in the presence of sensor failures. The difference between this estimated “normal� values and the actual process measurements, termed the residuals are fed to the classifier for fault detection purposes. The classifier then identifies the source of faults. The scheme was implemented under dynamic operating conditions of the Tennessee Eastman challenge process and was successful in detecting various sensor faults introduced within the system.
first_indexed 2025-11-15T20:35:41Z
format Conference or Workshop Item
id utm-967
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:35:41Z
publishDate 2001
recordtype eprints
repository_type Digital Repository
spelling utm-9672017-09-11T02:58:22Z http://eprints.utm.my/967/ Model-based fault detection using hierarchical artificial neural network Ahmad, Arshad Leong, Wah Heng TP Chemical technology In this paper, a two-stage approach integrating a neural network dynamic estimator and a neural network fault classifier is proposed to overcome the problem of malfunction in sensors. The process estimator is designed to predict the dynamic behaviour of the normal or fault-free operating process even in the presence of sensor failures. The difference between this estimated “normal� values and the actual process measurements, termed the residuals are fed to the classifier for fault detection purposes. The classifier then identifies the source of faults. The scheme was implemented under dynamic operating conditions of the Tennessee Eastman challenge process and was successful in detecting various sensor faults introduced within the system. 2001-10-29 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/967/1/RSCE2001.pdf Ahmad, Arshad and Leong, Wah Heng (2001) Model-based fault detection using hierarchical artificial neural network. In: Regional Symposium on Chemical Enginering, 29-31 October 2001, Bandung.
spellingShingle TP Chemical technology
Ahmad, Arshad
Leong, Wah Heng
Model-based fault detection using hierarchical artificial neural network
title Model-based fault detection using hierarchical artificial neural network
title_full Model-based fault detection using hierarchical artificial neural network
title_fullStr Model-based fault detection using hierarchical artificial neural network
title_full_unstemmed Model-based fault detection using hierarchical artificial neural network
title_short Model-based fault detection using hierarchical artificial neural network
title_sort model-based fault detection using hierarchical artificial neural network
topic TP Chemical technology
url http://eprints.utm.my/967/
http://eprints.utm.my/967/1/RSCE2001.pdf