AI-driven digital twins for resilient wind turbines under extreme conditions

The increasing deployment of wind turbines in extreme environmental conditions, like high-altitude icing plateaus, introduces significant structural and operational challenges. Harsh conditions, including corrosion fatigue, ice-induced dynamic loads, and fluctuating wind forces, accelerate component degradation and increase maintenance demands. Traditional operation and maintenance (O&M) strategies struggle to adapt to these conditions, demanding a shift towards more proactive, adaptive and intelligent solutions. AI-driven digital twins (DTs) offer a transformative approach by integrating real-time monitoring, predictive analytics, and adaptive control to enhance turbine resilience. This study focuses on enhancing the resilience of onshore wind turbine towers in challenging environments using a digital twin (DT) framework. The case study investigates a 5 MW onshore wind turbine with a lattice-tubular hybrid (LTH) tower, subjected to highly variable wind and environmental loads. Through a DT framework integrating OpenFAST and OpenSees, the study combines multi-physics simulations with supervisory control and data acquisition (SCADA) and structural health monitoring (SHM) data to reconstruct wind-induced loads and predict fatigue deterioration in critical components, such as bolted ring-flange connections. The results demonstrate that the DT-enabled model updating significantly reduces estimated fatigue damage, improving structural reliability and enabling proactive maintenance under fluctuating conditions. Beyond the advances, challenges still remain, including data integration, real-time processing, and cost-effective deployment. Future works are highly advised to focus on refining AI models, enhancing sensor data accuracy, and developing standardized frameworks for DT applications in renewable energy. By addressing these challenges, AI-driven DTs can play a crucial role in the long-term sustainability and resilience of wind energy systems under extreme conditions.