Valve stiction detection through improved pattern recognition using neural networks

A non-invasive method for detecting valves suffering from stiction using multi-layer feed-forward neural networks (NN) is proposed, via a simple class-based diagnosis. The proposed Stiction Detection Network (SDN) uses a transformation of PV (process variable) and OP (controller output) operational...

Full description

Main Authors: Mohd Amiruddin, A.A.A., Zabiri, H., Jeremiah, S.S., Teh, W.K., Kamaruddin, B.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.24980 /
Published: Elsevier Ltd 2019
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067911670&doi=10.1016%2fj.conengprac.2019.06.008&partnerID=40&md5=452b38cf250195cc2f4f992801634202
http://eprints.utp.edu.my/24980/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.24980
recordtype eprints
spelling utp-eprints.249802021-08-27T08:35:11Z Valve stiction detection through improved pattern recognition using neural networks Mohd Amiruddin, A.A.A. Zabiri, H. Jeremiah, S.S. Teh, W.K. Kamaruddin, B. A non-invasive method for detecting valves suffering from stiction using multi-layer feed-forward neural networks (NN) is proposed, via a simple class-based diagnosis. The proposed Stiction Detection Network (SDN) uses a transformation of PV (process variable) and OP (controller output) operational data. Verification of the proposed SDN model's detection accuracy is done through cross-validation with generated samples and benchmarking with various industrial loops. The industrial loop benchmark predictions of the proposed SDN method has a combined accuracy of 78 (75 in predicting stiction, and 81 for non-stiction) in predicting loop condition, matching capabilities of other established methods in accurately predicting realistic industrial loops suffering from stiction, while also being applicable to all types of oscillatory control signals. © 2019 Elsevier Ltd 2019 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067911670&doi=10.1016%2fj.conengprac.2019.06.008&partnerID=40&md5=452b38cf250195cc2f4f992801634202 Mohd Amiruddin, A.A.A. and Zabiri, H. and Jeremiah, S.S. and Teh, W.K. and Kamaruddin, B. (2019) Valve stiction detection through improved pattern recognition using neural networks. Control Engineering Practice, 90 . pp. 63-84. http://eprints.utp.edu.my/24980/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description A non-invasive method for detecting valves suffering from stiction using multi-layer feed-forward neural networks (NN) is proposed, via a simple class-based diagnosis. The proposed Stiction Detection Network (SDN) uses a transformation of PV (process variable) and OP (controller output) operational data. Verification of the proposed SDN model's detection accuracy is done through cross-validation with generated samples and benchmarking with various industrial loops. The industrial loop benchmark predictions of the proposed SDN method has a combined accuracy of 78 (75 in predicting stiction, and 81 for non-stiction) in predicting loop condition, matching capabilities of other established methods in accurately predicting realistic industrial loops suffering from stiction, while also being applicable to all types of oscillatory control signals. © 2019
format Article
author Mohd Amiruddin, A.A.A.
Zabiri, H.
Jeremiah, S.S.
Teh, W.K.
Kamaruddin, B.
spellingShingle Mohd Amiruddin, A.A.A.
Zabiri, H.
Jeremiah, S.S.
Teh, W.K.
Kamaruddin, B.
Valve stiction detection through improved pattern recognition using neural networks
author_sort Mohd Amiruddin, A.A.A.
title Valve stiction detection through improved pattern recognition using neural networks
title_short Valve stiction detection through improved pattern recognition using neural networks
title_full Valve stiction detection through improved pattern recognition using neural networks
title_fullStr Valve stiction detection through improved pattern recognition using neural networks
title_full_unstemmed Valve stiction detection through improved pattern recognition using neural networks
title_sort valve stiction detection through improved pattern recognition using neural networks
publisher Elsevier Ltd
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067911670&doi=10.1016%2fj.conengprac.2019.06.008&partnerID=40&md5=452b38cf250195cc2f4f992801634202
http://eprints.utp.edu.my/24980/
_version_ 1741196899945283584
score 11.62408

Similar Items