Simone Mancini

Thomas Wagenaar, Simone Mancini, Andrés Mateo-Gabín

The optimization of geometries for aerodynamic design often relies on a large number of expensive simulations to evaluate and iteratively improve the geometries. It is possible to reduce the number of simulations by providing a starting geometry that has properties close to the desired requirements, often in terms of lift and drag, aerodynamic moments and surface areas. We show that generative models have the potential to provide such starting geometries by generalizing geometries over a large dataset of simulations. In particular, we leverage diffusion probabilistic models trained on XFOIL simulations to synthesize two-dimensional airfoil geometries conditioned on given aerodynamic features and constraints. The airfoils are parameterized with Bernstein polynomials, ensuring smoothness of the generated designs. We show that the models are able to generate diverse candidate designs for identical requirements and constraints, effectively exploring the design space to provide multiple starting points to optimization procedures. However, the quality of the candidate designs depends on the distribution of the simulated designs in the dataset. Importantly, the geometries in this dataset must satisfy other requirements and constraints that are not used in conditioning of the diffusion model, to ensure that the generated geometries are physical.

Stefano Riverso, Simone Mancini, Fabio Sarzo et al.

We consider the problem of dispatching WindFarm (WF) power demand to individual Wind Turbines (WT) with the goal of minimizing mechanical stresses. We assume wind is strong enough to let each WTs to produce the required power and propose different closed-loop Model Predictive Control (MPC) dispatching algorithms. Similarly to existing approaches based on MPC, our methods do not require changes in WT hardware but only software changes in the SCADA system of the WF. However, differently from previous MPC schemes, we augment the model of a WT with an ARMA predictor of the wind turbulence, which reduces uncertainty in wind predictions over the MPC control horizon. This allows us to develop both stochastic and deterministic MPC algorithms. In order to compare different MPC schemes and demonstrate improvements with respect to classic open-loop schedulers, we performed simulations using the SimWindFarm toolbox for MatLab. We demonstrate that MPC controllers allow to achieve reduction of stresses even in the case of large installations such as the 100-WTs Thanet offshore WF.