An artificial neural network model for predicting electromagnetic interference effects on gas pipelines built in power lines row

Electromagnetic interference effects of transmission lines upon nearby gas pipelines are a real problem, which can place both operator safety and pipeline integrity at risk. This paper presents a technique based on an artificial neural network (ANN) for predicting the electromagnetic inference effects on gas pipelines shared right-of-way (ROW) with high voltage transmission lines. The developed ANN-based technique uses pre-determined system parameters (transmission voltage, load current, soil resistivity, and separation distance) as continuous inputs. Based on such information the ANN can predict the pipelines induced voltage due to the electromagnetic interference. The proposed ANN technique has been applied to predict the induced voltage on the gas pipelines built in a typical power line ROW in Sultanate of Oman. The results demonstrate that the ANN-based model developed in this work 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 the overall pipeline integrity and make the pipeline and appurtenances safe for operating personnel.