Tidal turbine blade design optimization based on coupled deep learning and blade element momentum theory

The practical design optimization of blade structures is crucial for enhancing the power capture capability of tidal turbines. However, the significant computational costs required for directly optimizing turbine blades through numerical simulations limit the practical application of blade structure optimization. This paper proposes a framework for tidal turbine blade design optimization based on deep learning (DL) and blade element momentum (BEM). This framework employs control points to parameterize the three-dimensional geometric shape of the blades, uses convolutional neural networks to predict the hydrodynamic performance of each hydrofoil section, and couples BEM to forecast the performance of tidal turbine blades. The multi-objective non-dominated sorting genetic algorithm II is employed to optimize the geometric parameters of turbine blades to maximize the power coefficient and minimize the thrust coefficient, aiming to obtain the optimal trade-off solution. The results indicate that the prediction of the DL-BEM model agrees well with experimental data, significantly improving optimization efficiency. The optimized tidal turbine blades exhibit excellent power coefficients and reduced thrust coefficients, achieving a more balanced structural solution. The proposed optimization framework based on DL accurately and rapidly predicts the performance of tidal turbines, facilitating the design optimization of high-performance tidal turbine blades.