Multi-scale Dynamic Wake Modeling and Prediction of Floating Offshore Wind Turbines via Physics-Informed Neural Networks and Fourier Neural Operators
arXiv:2604.23937v2 Announce Type: replace-cross Abstract: Multi-scale dynamic wake modeling and prediction are essential for the real-time control and optimization of floating offshore wind turbines (FOWTs). In this study, wakes of FOWTs under coupled surge and pitch motions across a range of Strouhal numbers (St), which can induce wake meandering, are modeled via two novel deep-learning frameworks: physics-informed neural networks (PINNs) and Fourier neural operators (FNOs). The high-fidelity dataset is obtained from large-eddy simulations with the actuator line model (LES-AL). The results de
The increasing scale and complexity of offshore wind energy, coupled with advancements in deep learning, create a critical need and opportunity for more sophisticated modeling and prediction tools.
Improved wake modeling for floating offshore wind turbines (FOWTs) is crucial for optimizing energy capture, reducing operational costs, and accelerating the deployment of this clean energy technology, which is a key component of the future energy mix.
The ability to accurately model and predict dynamic wake effects in real-time will enable more efficient FOWT designs, better array layouts, and proactive control strategies, leading to higher energy output and increased grid stability.
- · Offshore wind developers
- · Renewable energy sector
- · AI/ML solution providers
- · Turbine manufacturers
- · Traditional CFD modeling approaches
- · Inefficient energy producers
More cost-effective and reliable floating offshore wind farms become feasible, accelerating their global adoption.
Increased grid penetration of offshore wind power could reduce reliance on fossil fuels, contributing to decarbonization goals.
The success of physics-informed AI in this domain could accelerate its application to other complex engineering and environmental challenges, driving further innovation in predictive modeling across various industries.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG