Developing a calibrated low fidelity model and an optimized sensor network using LIVE Digital Twin for pipelines in oil and gas industries

Abstract

Digital Twin (DT) solutions are at the forefront of intelligent prognostics and diagnostics of physical systems. The DT is the bidirectional communication between the physical and digital environments for better scheduling, manufacturing processes, health monitoring, etc. This communication is established with an optimized sensor network. LIVE Digital Twin (LIVE DT) is a novel methodology which addresses the lack of standardised DT solutions. This thesis employs LIVE DT to develop a calibrated Low Fidelity (LF) pipeline model. Three fault cases are rapidly simulated using the LF model to circumvent the need of expensive and dangerous physical experimentation. The developed data is used to develop an optimized sensor network for intelligent vibration monitoring of the pipeline. A machine learning algorithm is trained to detect the current fault experienced by the LF model. Furthermore, the presented methods and results can be scaled and customized to produce sensor networks for any physical system.