School of Computing, Engineering and Technology

AI-Enhanced Wake Control and Recovery in Floating Offshore Wind Farms

This research project will pioneer AI-enhanced aerodynamic strategies to control and recover wakes in floating offshore wind farms. Combining high-fidelity computational fluid dynamics with physics informed neural networks, the project aims to reduce wake losses, boost array efficiency, and deliver innovative design solutions for sustainable, high-performance offshore wind energy systems.

Award

MRes | MPhil | PhD | MSc by Research

Start Date

Usually February and October - at individual School's discretion

Research Opportunities

Summary

Wake interactions remain one of the most significant limitations on offshore wind farm efficiency, with downstream turbines experiencing substantial power losses and increased fatigue loading. In floating offshore wind farms, wake behaviour becomes even more complex due to platform motion, atmospheric variability, and dynamic inflow conditions. This PhD aims to develop innovative aerodynamic strategies to actively control and accelerate wake recovery using a combination of high-fidelity Computational Fluid Dynamics (CFD) and advanced Artificial Intelligence techniques.

The research will investigate novel turbine and nacelle design concepts capable of reshaping near-wake structures to enhance downstream energy capture. High-resolution numerical simulations (LES modelling) will be used to characterise wake evolution under realistic offshore conditions. Floating platform motion will be incorporated to quantify its impact on wake stability and recovery.

A key innovation of the project is the integration of Physics-Informed Neural Networks (PINNs) and hybrid CFD–machine learning models to develop reduced-order predictive tools for rapid wake optimisation. These AI-driven models will embed governing flow physics while significantly reducing computational cost, enabling large-scale wind farm optimisation studies.

The student will gain expertise in advanced turbulence modelling, offshore wind aerodynamics, GPU accelerated computing, and physics-based machine learning. Expected outcomes include high-impact journal publications, development of novel wake-control concepts, and potential collaboration with offshore wind industry stakeholders.

This project is suitable for applicants with a strong background in mechanical, aerospace, renewable energy, or computational engineering. Experience with CFD software, programming (Python/MATLAB), and fluid dynamics is desirable. Candidates with interest in AI for engineering applications are particularly encouraged to apply.