HYDROFOIL OPTIMIZATION DESIGN OF TIDAL ENERGY TURBINE BASED ON GENERATIVE ADVERSARIAL NETWORK

To address the issue that global optimization of hydrofoils requires extensive computational fluid dynamics (CFD) simulations, leading to increased computational costs, the hydrofoil optimization design framework based on generative adversarial networks (GAN) and CFD is proposed. GAN is utilized to parameterize hydrofoil designs based on the existing airfoil library. Due to the high-dimensional generation capability of GAN，this parameterization method can generate a large number of smooth and realistic hydrofoils using only a small number of parameters，thereby reducing the dimensions of the hydrofoil parameterization. This optimization framework combines Python scripts and OpenFOAM to automatically complete the mesh generation and fluid simulation of the hydrofoil，resulting in a hydrofoil with a higher lift-to-drag ratio. The total optimization time cost is 69.8 hours，which improves optimization efficiency and accuracy. Furthermore，the optimized hydrofoils are applied to the design of tidal turbine blades. The results indicate that the optimal power coefficient of the tidal turbine blades modeled using the optimized hydrofoil Optc increases by 15.56%，enhancing the energy capture performance of the turbine. © 2024 Science Press. All rights reserved.