Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines

This study aims at generating and validating a universal pressure drop model at pipelines under three phase flow conditions. There is a pressing need for estimating the pressure drop in pipeline systems using a simple procedure that would eliminate the tedious and yet the non accurate and cumberso...

Full description

Main Authors: Ayoub, Mohammed A. Ayoub, Demiral, Birol M. Demiral
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.10572 /
Published: UNIVERSITY of KHARTOUM 2011
Subjects:
Online Access: http://eprints.utp.edu.my/10572/1/115-408-1-PB.pdf
http://ejournals.uofk.edu
http://eprints.utp.edu.my/10572/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.10572
recordtype eprints
spelling utp-eprints.105722017-03-20T01:59:36Z Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines Ayoub, Mohammed A. Ayoub Demiral, Birol M. Demiral TA Engineering (General). Civil engineering (General) This study aims at generating and validating a universal pressure drop model at pipelines under three phase flow conditions. There is a pressing need for estimating the pressure drop in pipeline systems using a simple procedure that would eliminate the tedious and yet the non accurate and cumbersome methods. In this study resilient back-propagation Artificial Neural Network technique will be utilized as a powerful modeling tool to establish the complex relationship between input parameters and the pressure drop in pipeline systems under wide range of angles of inclination. A total number of data points consists of 335 sets has been used for generating, validating, and testing the ANN model. A model performance has been evaluated against the best empirical correlations and mechanistic models (Xiao et al., Gomez et al., and Beggs and Brill). A series of statistical and graphical analysis were conducted to show the significance of the generated model. The new developed model outperforms all investigated models with correlation coefficient reaches 98.82%. UNIVERSITY of KHARTOUM 2011-10 Article PeerReviewed application/pdf http://eprints.utp.edu.my/10572/1/115-408-1-PB.pdf http://ejournals.uofk.edu Ayoub, Mohammed A. Ayoub and Demiral, Birol M. Demiral (2011) Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines. UNIVERSITY of KHARTOUM ENGINEERING JOURNAL (UOKEJ), 1 (2). pp. 9-21. ISSN 1858-6333 http://eprints.utp.edu.my/10572/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Ayoub, Mohammed A. Ayoub
Demiral, Birol M. Demiral
Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
description This study aims at generating and validating a universal pressure drop model at pipelines under three phase flow conditions. There is a pressing need for estimating the pressure drop in pipeline systems using a simple procedure that would eliminate the tedious and yet the non accurate and cumbersome methods. In this study resilient back-propagation Artificial Neural Network technique will be utilized as a powerful modeling tool to establish the complex relationship between input parameters and the pressure drop in pipeline systems under wide range of angles of inclination. A total number of data points consists of 335 sets has been used for generating, validating, and testing the ANN model. A model performance has been evaluated against the best empirical correlations and mechanistic models (Xiao et al., Gomez et al., and Beggs and Brill). A series of statistical and graphical analysis were conducted to show the significance of the generated model. The new developed model outperforms all investigated models with correlation coefficient reaches 98.82%.
format Article
author Ayoub, Mohammed A. Ayoub
Demiral, Birol M. Demiral
author_sort Ayoub, Mohammed A. Ayoub
title Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
title_short Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
title_full Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
title_fullStr Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
title_full_unstemmed Application of Resilient Back-Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipelines
title_sort application of resilient back-propagation neural networks for generating a universal pressure drop model in pipelines
publisher UNIVERSITY of KHARTOUM
publishDate 2011
url http://eprints.utp.edu.my/10572/1/115-408-1-PB.pdf
http://ejournals.uofk.edu
http://eprints.utp.edu.my/10572/
_version_ 1741196124684812288
score 11.62408