Digital Twin is a new paradigm combining multiphysics modelling together with data-driven analytics. In recent years, it draws considerable interest from the oil and gas field operators due to lower oil prices to reduce the downtime due to planned or unplanned preventive maintenance in production field which cost several million in the operational cost (OPEX). The digital twin is an integrated system with low-cost IoT sensors to gather system data, advanced data analytics to draw meaningful insights and predictive maintenance strategy based on the machine learning algorithm to reduce preventive maintenance cost. Overall the digital twin act as a digital replica of the field asset which is monitored and maintained based on actual sensor data from the physical field using machine learning.
This paper will demonstrate the conceptual design of a digital twin of subsea pipeline system integrating the computational model, field sensor data analytics and predictive maintenance based on the machine learning algorithm. The computational model is first developed in the finite element (FE) model and calibrated by the field sensor data installed on the physical system.
The computational model will be used to predict any change of pipe behaviour due to sudden changes in loading due to high pressure, slugging or leak etc. The proposed digital twin model will assist the oil and gas field operators in minimizing the OPEX with predictive maintenance schedule when it's needed to avoid failure in the pipeline system.