Digital twin approach with minimal sensors for Riser's fatigue-damage estimation

Abstract

This study proposes riser fatigue monitoring based on digital twin models with a motion sensor attached to the platform and riser. The reference model was a spread-moored Floating Production Storage and Offloading (FPSO) with Steel Lazy-Wave Risers (SLWR). Coupled dynamics simulations under given environmental conditions were performed to generate synthetic sensor signals for digital twin models. Finite-element-based riser digital twin models were then constructed to run with the synthetic sensor inputs. A machine learning algorithm that estimates the 3D current profile along the water column was employed to improve the digital twin models by inputting the estimated current profile as additional loads. The digital twin models with or without the estimated current produce the time histories of behaviors and stresses along the riser, and the corresponding fatigue damage and life were estimated by the rainflow-counting method. The fatigue assessment results demonstrate its feasibility through small errors in fatigue damage.