Prediction of voltages on mitigated pipelines paralleling electric transmission lines using ANN

A. H. Al-Badi, K. Ellithy, S. Al-Alawi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper describes an artificial neural network (ANN) model developed to predict the total voltage on mitigated pipelines due to the effect of the inductive and conductive AC interference under fault conditions. The pipeline shared right-of-way with high voltage power lines and it is mitigated by gradient control wires. In particular, the developed ANN predicts the mitigated pipeline voltage under different soil resistivities, fault currents and separation distances. The results showed that the R2 value for the training and testing sets were 0.9978 and 0.996, respectively. This indicates that results from the ANN model compared well with the calculated values demonstrating the capability of the ANN simulation techniques. The results also demonstrate that the ANN-based model developed in this work can predict the voltage after applying mitigation system with high accuracy. The accuracy of the predicted voltage is very important to protect the overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.

Original languageEnglish
Pages (from-to)15-22
Number of pages8
JournalInternational Journal of Computers and Applications
Volume32
Issue number1
DOIs
Publication statusPublished - Mar 4 2010

Fingerprint

Electric power transmission
Electric lines
Pipelines
Neural networks
Electric potential
Rights of way
Electric fault currents
Wire
Personnel
Soils
Testing

Keywords

  • Artificial neural network
  • Conductive interference
  • Corrosion
  • Inductive interference
  • Mitigation
  • Pipeline voltages

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Prediction of voltages on mitigated pipelines paralleling electric transmission lines using ANN. / Al-Badi, A. H.; Ellithy, K.; Al-Alawi, S.

In: International Journal of Computers and Applications, Vol. 32, No. 1, 04.03.2010, p. 15-22.

Research output: Contribution to journalArticle

@article{8bdfbb894ae14dbd8e573fce2bed4d4e,
title = "Prediction of voltages on mitigated pipelines paralleling electric transmission lines using ANN",
abstract = "This paper describes an artificial neural network (ANN) model developed to predict the total voltage on mitigated pipelines due to the effect of the inductive and conductive AC interference under fault conditions. The pipeline shared right-of-way with high voltage power lines and it is mitigated by gradient control wires. In particular, the developed ANN predicts the mitigated pipeline voltage under different soil resistivities, fault currents and separation distances. The results showed that the R2 value for the training and testing sets were 0.9978 and 0.996, respectively. This indicates that results from the ANN model compared well with the calculated values demonstrating the capability of the ANN simulation techniques. The results also demonstrate that the ANN-based model developed in this work can predict the voltage after applying mitigation system with high accuracy. The accuracy of the predicted voltage is very important to protect the overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.",
keywords = "Artificial neural network, Conductive interference, Corrosion, Inductive interference, Mitigation, Pipeline voltages",
author = "Al-Badi, {A. H.} and K. Ellithy and S. Al-Alawi",
year = "2010",
month = "3",
day = "4",
doi = "10.2316/Journal.202.2010.1.202-2327",
language = "English",
volume = "32",
pages = "15--22",
journal = "International Journal of Computers and Applications",
issn = "1206-212X",
publisher = "ACTA Press",
number = "1",

}

TY - JOUR

T1 - Prediction of voltages on mitigated pipelines paralleling electric transmission lines using ANN

AU - Al-Badi, A. H.

AU - Ellithy, K.

AU - Al-Alawi, S.

PY - 2010/3/4

Y1 - 2010/3/4

N2 - This paper describes an artificial neural network (ANN) model developed to predict the total voltage on mitigated pipelines due to the effect of the inductive and conductive AC interference under fault conditions. The pipeline shared right-of-way with high voltage power lines and it is mitigated by gradient control wires. In particular, the developed ANN predicts the mitigated pipeline voltage under different soil resistivities, fault currents and separation distances. The results showed that the R2 value for the training and testing sets were 0.9978 and 0.996, respectively. This indicates that results from the ANN model compared well with the calculated values demonstrating the capability of the ANN simulation techniques. The results also demonstrate that the ANN-based model developed in this work can predict the voltage after applying mitigation system with high accuracy. The accuracy of the predicted voltage is very important to protect the overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.

AB - This paper describes an artificial neural network (ANN) model developed to predict the total voltage on mitigated pipelines due to the effect of the inductive and conductive AC interference under fault conditions. The pipeline shared right-of-way with high voltage power lines and it is mitigated by gradient control wires. In particular, the developed ANN predicts the mitigated pipeline voltage under different soil resistivities, fault currents and separation distances. The results showed that the R2 value for the training and testing sets were 0.9978 and 0.996, respectively. This indicates that results from the ANN model compared well with the calculated values demonstrating the capability of the ANN simulation techniques. The results also demonstrate that the ANN-based model developed in this work can predict the voltage after applying mitigation system with high accuracy. The accuracy of the predicted voltage is very important to protect the overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.

KW - Artificial neural network

KW - Conductive interference

KW - Corrosion

KW - Inductive interference

KW - Mitigation

KW - Pipeline voltages

UR - http://www.scopus.com/inward/record.url?scp=77951263276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951263276&partnerID=8YFLogxK

U2 - 10.2316/Journal.202.2010.1.202-2327

DO - 10.2316/Journal.202.2010.1.202-2327

M3 - Article

VL - 32

SP - 15

EP - 22

JO - International Journal of Computers and Applications

JF - International Journal of Computers and Applications

SN - 1206-212X

IS - 1

ER -