Deep neural network-based intelligent health monitoring system for oil and gas pipelines

Abstract

Oil and gas pipelines are critical infrastructures that require continuous monitoring to ensure public safety and prevent economic losses. This paper addresses the challenges associated with pipeline failures by proposing a Deep Neural Network (DNN)-based Structural Health Monitoring (SHM) system for real-time monitoring of oil and gas pipelines. The system utilizes installed transducers and ultrasound guided waves to collect data about the structural health without the need for pipeline shutdown. The DNN-based SHM system predicts three crucial crack parameters: crack location, width, and depth. The performance of the proposed system is compared with five commonly used Machine Learning (ML) approaches. The results demonstrate that the DNN-based SHM system outperforms the other ML-based systems, achieving 18 % less prediction error than the most accurate of the other ML approaches. Moreover, the average prediction accuracy with the proposed DNN approach for crack location, width, and depth were 97 %, 93 % and 96 %, respectively. The findings highlight the potential of DNNs for accurate and efficient pipeline health monitoring, contributing to improved decision-making and safe pipeline operations.