Predicting the total pipeline voltage installed in high voltage Ac corridors by using an artificial neural network

Pipelines and power lines often use the same way to minimize land use, to reduce installed cost and reduce damage to the environment. Induced ac voltage & current on the pipeline during steady-state and fault conditions can develop due to proximity of the pipelines to the power lines. This induced voltage is hazardous to personnel who may come in contact with the exposed structures connected with the pipelines. It also can create sever corrosions to the pipelines as well as pipeline failure.

This paper presents a technique based on the development of an artificial neural network (ANN) model for predicting the total pipeline voltages shared right-of-way (ROW) with high voltage power lines before and after applying mitigation system. In particular, the ANN predicts the pipeline voltage under different soil resistivity, fault currents and separation distances before and after applying mitigation system. The results indicate good agreement between model prediction and the calculated values. This high generalization capability indicates that the ANN model predicted with 99.3% accuracy; these results demonstrate that the ANN-based model developed in this work can predict the total voltage, before and after applying mitigation system, with high accuracy