A mechanism-informed reinforcement learning framework for shape optimization of airfoils

arXiv:2403.04329v1 Announce Type: cross
Abstract: In this study, we present the mechanism-informed reinforcement learning framework for airfoil shape optimization. By leveraging the twin delayed deep deterministic policy gradient algorithm for its notable stability, our approach addresses the complexities of optimizing shapes governed by fluid dynamics. The PDEs-based solver is adopted for its accuracy even when the configurations and geometries are extraordinarily changed during the exploration. Dual-weighted residual-based mesh refinement strategy is applied to ensure the accurate calculation of target functionals. …

abstract algorithm arxiv complexities cs.ce cs.lg cs.na dynamics fluid dynamics framework gradient math.na optimization policy reinforcement reinforcement learning solver stability study twin type