Gas pipeline safety management system based on neural network

The risk of leakage poses a grave threat to natural gas pipeline safety. The high compressibility of gases combined with unsteady boundary conditions makes detecting leaks in pipelines a challenging endeavor. To date, in the literature, only a limited number of studies have focused on leak detection...

Full description

Main Authors: Mujtaba, S.M., Lemma, T.A., Vandrangi, S.K.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.28969 /
Published: John Wiley and Sons Inc 2022
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122650664&doi=10.1002%2fprs.12334&partnerID=40&md5=f3ccc0bf7d7abfcb2854c621385d73ad
http://eprints.utp.edu.my/28969/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.28969
recordtype eprints
spelling utp-eprints.289692022-03-17T04:21:49Z Gas pipeline safety management system based on neural network Mujtaba, S.M. Lemma, T.A. Vandrangi, S.K. The risk of leakage poses a grave threat to natural gas pipeline safety. The high compressibility of gases combined with unsteady boundary conditions makes detecting leaks in pipelines a challenging endeavor. To date, in the literature, only a limited number of studies have focused on leak detection and diagnostics in gas mixture pipelines. The present study provides a system for detecting, locating, and estimating the size of small gas leaks from a compressible and dynamic natural gas flow in pipelines with improved accuracy. As a case study, a long natural gas pipeline of 80 km is simulated with leak sizes of 0, 2, and 5. The safety system is developed using mass flow rate, temperature, and pressure measurements. Six classes for faulty cases and one class for no fault case were considered for the study. A shallow neural network classifier (SNNC) is trained to identify a specific fault class. The SNNC is based on a two-layered network with 20 and 7 neurons. An input vector of 15 variables is provided to the system, and the output is one of the seven possible classes. Leakage as low as 2 at various locations are correctly diagnosed with more than 99 correct classification rate. © 2022 American Institute of Chemical Engineers. John Wiley and Sons Inc 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122650664&doi=10.1002%2fprs.12334&partnerID=40&md5=f3ccc0bf7d7abfcb2854c621385d73ad Mujtaba, S.M. and Lemma, T.A. and Vandrangi, S.K. (2022) Gas pipeline safety management system based on neural network. Process Safety Progress . http://eprints.utp.edu.my/28969/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description The risk of leakage poses a grave threat to natural gas pipeline safety. The high compressibility of gases combined with unsteady boundary conditions makes detecting leaks in pipelines a challenging endeavor. To date, in the literature, only a limited number of studies have focused on leak detection and diagnostics in gas mixture pipelines. The present study provides a system for detecting, locating, and estimating the size of small gas leaks from a compressible and dynamic natural gas flow in pipelines with improved accuracy. As a case study, a long natural gas pipeline of 80 km is simulated with leak sizes of 0, 2, and 5. The safety system is developed using mass flow rate, temperature, and pressure measurements. Six classes for faulty cases and one class for no fault case were considered for the study. A shallow neural network classifier (SNNC) is trained to identify a specific fault class. The SNNC is based on a two-layered network with 20 and 7 neurons. An input vector of 15 variables is provided to the system, and the output is one of the seven possible classes. Leakage as low as 2 at various locations are correctly diagnosed with more than 99 correct classification rate. © 2022 American Institute of Chemical Engineers.
format Article
author Mujtaba, S.M.
Lemma, T.A.
Vandrangi, S.K.
spellingShingle Mujtaba, S.M.
Lemma, T.A.
Vandrangi, S.K.
Gas pipeline safety management system based on neural network
author_sort Mujtaba, S.M.
title Gas pipeline safety management system based on neural network
title_short Gas pipeline safety management system based on neural network
title_full Gas pipeline safety management system based on neural network
title_fullStr Gas pipeline safety management system based on neural network
title_full_unstemmed Gas pipeline safety management system based on neural network
title_sort gas pipeline safety management system based on neural network
publisher John Wiley and Sons Inc
publishDate 2022
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122650664&doi=10.1002%2fprs.12334&partnerID=40&md5=f3ccc0bf7d7abfcb2854c621385d73ad
http://eprints.utp.edu.my/28969/
_version_ 1741197177088114688
score 11.62408

Similar Items