Enhancing surrogate model accuracy in ship design optimization through intelligent constraint-aware sample selection

Abstract

For the hull form optimization design problem based on numerical simulation, constructing a surrogate model is usually required to reduce computational cost and time. However, since the existing sample point selection methods do not consider the influence of constraint conditions on the sampling space, the effectiveness of their sample point selection is not high, which is also one of the main reasons for the high cost of constructing a high-precision surrogate model. Therefore, this paper proposes an improved sampling method to achieve effective selection of sample points in the feasible region and improve the efficiency of the surrogate model development. The proposed method uses data mining to identify the potential mapping relationship between optimization variables and constraint conditions, realizes the selection of sample points in the space satisfying constraints, and then constructs an surrogate model in the feasible region to achieve efficient hull form optimization. Applying this method to the actual hull form optimization process of a 7500 Deadweight Tonnage (DWT) bulk carrier shows that under the same sample size, the prediction accuracy of the surrogate model is significantly improved, and the optimization result similar to that of the traditional method is obtained, verifying the engineering applicability of the intelligent sampling process proposed in this paper. This paper proposes an intelligent sampling framework integrating data mining, innovatively embeds data mining technology into the sampling process, realizes the reduction of sampling space and optimization space from the full space to the constraint subspace, leading to ship intelligent optimization.