Multi-Dimensional Digital Twin Models with Dynamic Updating Scheme for Enhanced Wind Turbine O&M Decision-Making

Wind energy, as a critical renewable energy source in the global energy transition, requires efficient operation, reliability, and maintenance (O&M). While digital twin technology enables intelligent O&M of wind turbines by creating virtual replicas of physical systems, existing models predominantly remain static or rely on periodic updates, lacking real-time feedback capabilities regarding equipment performance degradation and maintenance-induced perturbations, thus limiting decision-making accuracy. To address this limitation, this paper proposes a digital twindriven O&M optimization method. Multi-dimensional digital twin models including a physics-based model, a data-driven model, and an O&M knowledge model are constructed. Considering the impacts of equipment degradation and maintenance activities on the physical entity, a dynamic model update scheme is proposed to ensure the consistency between the digital twin models and the state of the physical system. A case study on a 5 MW benchmark wind turbine demonstrates the effectiveness of the approach in enhancing the intelligence of wind turbine O&M decision-making, thereby supporting the practical application of digital twin technology in the wind power sector.