An artificial neural network model for predicting gas pipeline induced voltage caused by power lines under fault conditions

Abstract

Purpose Presents a technique based on the development of an artificial neural network (ANN) model for predicting the electromagnetic inference effects on gas pipelines shared right-of-way (ROW) with high voltage transmission lines. Design/methodology/approach Examines the induced pipeline voltage under different soil resistivity, fault current and separation distance. Findings The results indicate strong agreement between model prediction and observed values. Originality/value Demonstrates that the ANN-based model developed can predict the induced voltage with high accuracy. The accuracy of the predicted induced voltage is very important for designing mitigation systems that will increase overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.