eprintid: 14948
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/49/48
datestamp: 2023-11-10 03:29:32
lastmod: 2023-11-10 03:29:32
status_changed: 2023-11-10 01:58:14
type: conference_item
metadata_visibility: show
creators_name: Fadhli, M.
creators_name: Pedapati, S.R.
creators_name: Hamdan, H.
title: Development of models for oil and gas pipeline condition prediction using regression analysis
ispublished: pub
note: cited By 1; Conference of 6th International Conference on Green Design and Manufacture 2020, IConGDM 2020 ; Conference Date: 23 July 2020 Through 24 July 2020; Conference Code:168752
abstract: In order to maintain a pipeline in safe condition, frequent inspections are mandatory. However, inspection procedures that requires human operators are costly and time consuming due to high complexity of pipeline system. A good prediction models for oil and gas pipeline is essential for simulating and predicting the condition of a pipeline. Most prediction models lack the objectivity in predicting different failures types of pipelines due to solely focusing on single critical factor in their model. Regression model is used for modelling oil pipelines condition prediction. Two Linear models with different factors selection are developed in this study viz., Model 1 with factors comprises of mixture of continuous and discrete value, Model 2 with factors only restricted to continuous value. Results from this study shows that Model 2 yields better performance than Model 1 with performance of 95.56 compared to Model 1 with 83.03. © 2021 American Institute of Physics Inc.. All rights reserved.
date: 2021
publisher: American Institute of Physics Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85105643032&doi=10.1063%2f5.0044773&partnerID=40&md5=5683670574d31bbbe8a1aa7190ec4408
id_number: 10.1063/5.0044773
full_text_status: none
publication: AIP Conference Proceedings
volume: 2339
refereed: TRUE
isbn: 9780735440913
issn: 0094243X
citation:   Fadhli, M. and Pedapati, S.R. and Hamdan, H.  (2021) Development of models for oil and gas pipeline condition prediction using regression analysis.  In: UNSPECIFIED.