A reduced order data-driven method for resistance prediction and shape optimization of hull vane

Hull Vane (HV) is an energy-saving appendage introduced by Hull Vane BV company to reduce total ship resistance. Shapewise, HV is a hydrofoil wing transversely fixed at the transom bottom of the hull. In this paper, a data-driven shape optimization method is proposed for HV. To avoid the time-consuming resistance evaluation of designs via a viscous flow solver, we develop a Machine-Learning (ML) based model that predicts the hull's total resistance in the presence of an HV. For this purpose, Principal-Component Analysis (PCA) is first implemented to reduce the dimensionality of the problem, and then the prediction model is trained with the most influential of the Principal Components (PCs). Given that these PCs capture the maximum geometric variance of the original design space, higher accuracy can be achieved at the expense of a few training samples. After the training phase, the model is integrated with an optimizer, which searches in a dimensionally-reduced design space for the optimal design of the HV. The obtained results achieved a 70% dimensionality reduction with the aid PCA and an approximately 98% accuracy for predicting total resistance. Compared with the reference HV, the optimized one reduced the total resistance by 1.2%.