ABSTRACT
Sustainable digital twins (DTs) are becoming crucial in civil engineering to manage the lifecycle of offshore wind turbines (OWTs), which are essential for harnessing wind energy but are susceptible to deterioration, particularly corrosion fatigue (C-F) in welded joints. Maintaining the long-term structural integrity of OWTs under site-specific conditions is essential for their sustainable operation. Advanced monitoring systems, such as supervisory control and data acquisition (SCADA) and structural health monitoring (SHM), generate vast amounts of data during an OWT’s operational life. However, this data is often sparse and does not cover all critical connections within a wind farm. This study proposes a sustainable digital twin methodology for managing deteriorating OWT structures, focusing on welded connections. The approach integrates SCADA and SHM data to augment the physical OWTs with predictive capabilities, supporting sustainable lifecycle management. A case study conducted on a typical offshore wind farm in China involves both a specially monitored OWT and additional turbines with fewer monitoring devices. The methodology begins with preprocessing SCADA and SHM data, followed by multi-physics simulations tailored to the monitored OWT conditions. These simulations train a correlation model that links structural responses to loading histories, enabling virtual sensing. Additionally, a correlation model based on these simulations and spatial relationships across the wind farm predicts loading histories for turbines with limited SHM data. By combining the reproduced loadings with climate data, the sustainable digital twin can predict corrosion fatigue deterioration in welded connections, aiding intelligent management throughout the lifecycle. This research highlights the promise of sustainable digital twins to enhance structural condition assessments and operational strategies, contributing to the extended lifespan and operational sustainability of OWT structures.
