Projects
Prediction of roughness induced transition using AI
This project aims to develop a large database of high-fidelity simulations of transitional flows over rough surfaces. These types of flows play a key role in the drag reduction in aeronautical applications. From these large dataset, Advanced AI and Machine Learning techniques will be used to extract informed and predictive models of the underlying physical process that can be used in commercial Computational Fluid Dynamics (CFD) simulations.
Artificial Neural Networks for unsteady wind turbine loads
The drive to increase the size of wind turbines and wind farms requires the development of new methodologies able to model the increased complex physics such as the effects of atmospheric boundary layer, wakes and structural deflection. These surrogate models will be developed using artificial neural networks to predict the aerodynamics loads based on numerical and experimental data.
AI-based Flow Control for Transition Delay
The development of robust and sophisticated flow control strategies will be developed in this project. These can enable a drastic reduction in aerodynamics drag for the next generation of aircraft. These strategies will be developed using recent advances in reinforcement learning to explore innovative flow control strategies. Once developed from simulation, these will be implemented and tested in an experiment in the FPT wind tunnel.
AI for Control of Airfoil Acoustic Emissions
The prediction of aeroacoustics emission is a complex phenomenon that lies at the interaction of several physical systems. An AI-based framework will be developed that can extract the relevant physical interactions between these and that can predict the acoustics emission from specific sensing available. From this, efficient acoustic emission control strategies will be developed.