[home] [Personal Program] [Help]

---

Session: Classical and Machine learning methods in flow control II
Session starts: Tuesday 04 November, 11:40
Presentation starts: 12:00
Room: Lecture room B

---

Piergiorgio Scavella (University of Naples Federico II)
Gerardo Paolillo (University of Naples Federico II)
Carlo Salvatore Greco (University of Naples Federico II)

Abstract:
Aerodynamic shape optimization and active flow control have long been studied as complementary strategies to improve airfoil performance across diverse flight regimes. Traditional optimization methods—whether gradient-based or gradient-free—often struggle with the complexity and high dimensionality of coupled shape-control problems, especially in the presence of nonlinear flow features such as separation and transition. Deep Reinforcement Learning (DRL), known for its ability to operate in complex, dynamic environments, offers a powerful alternative. This study presents a DRL-based framework that performs joint optimization of airfoil geometry and continuous tangential blowing, allowing the learning agent to simultaneously adapt shape and flow control parameters. By embedding active control into the design space, the algorithm autonomously identifies optimal actuation strategies and geometric configurations to improve aerodynamic performance. Experimental investigations are performed on the optimized geometries to validate the proposed optimization framework. The results demonstrate the potential of DRL for integrated aerodynamic design and control.