Enhanced digital twin framework for real-time prediction of fatigue damage on semi-submersible platforms under long-term multi-sea conditions

Abstract

As the development of offshore oil and gas resources progresses into deeper waters, the impact on marine structures becomes increasingly severe, resulting in significant structural damage. This highlights the importance of health monitoring for marine structures. The emergence of digital twin technology in ocean engineering has greatly advanced the development of marine structure monitoring technologies, improving the intelligence and real-time capabilities of structural health monitoring. This paper proposes an innovative data-driven digital twin framework, applied to the real-time fatigue damage prediction of the semi-submersible platform under long-term multi-sea conditions. Notably, this study introduces a novel stress twinning method along with a high-precision post-processing module that combines field monitoring data with high-fidelity simulation model results. This integration establishes a bidirectional connection between the physical structure and its digital counterpart, enabling real-time mapping of structural hotspot stresses and more accurate fatigue damage predictions. The proposed framework was validated on the semi-submersible platform in the South China Sea, and the results proved its practicality and transformative potential in offshore structure management.