Floating Offshore Wind Turbine Structures: A Digital Twins-Informed Intelligent Operation and Maintenance

Floating offshore wind turbines (FOWTs) are essential for exploiting deep-water renewable wind resources. However, they face significant structural risks due to corrosion-fatigue (C-F) coupled degradation, particularly in the harsh marine environment. This study introduces a Digital Twinning framework aimed at improving the intelligent operation and maintenance (O&M) of FOWT structures, focusing on the resilience and sustainability of these assets. A Digital Twin is a real-time virtual replica of a physical asset, continuously updated with operational data, enabling advanced monitoring and predictive analytics. This framework integrates Supervisory Control and Data Acquisition (SCADA) system data with Structural Health Monitoring (SHM) inputs, creating a comprehensive model of the turbine’s operational state and structural health. By utilising tailored multi-physics simulations, a correlation model is developed to link structural responses to loading histories, improving virtual sensing and fatigue damage prediction. The methodology follows key steps: i) preprocessing SCADA and SHM data for accuracy; ii) conducting multi-physics simulations to inform the correlation model; iii) predicting load histories for turbines with limited monitoring using spatial relationships within the wind farm. By combining these predicted loads with environmental data, the Digital Twin can forecast corrosion-fatigue progression, enabling proactive maintenance strategies. The results show that this approach significantly enhances structural condition assessments and informs O&M decisions that extend the operational lifespan of FOWTs. This study highlights the transformative potential of data-driven methodologies in advancing offshore renewable energy infrastructure, offering a pathway for more reliable and sustainable energy production in challenging marine environments.