Lines optimisation of an underwater vehicle using SMOTE and adaptive minimise LCB based dynamic surrogate models

Abstract

ABSTRACT The lines optimisation of an underwater vehicle based on a dynamic surrogate model is studied. Four performances including rapidity, manoeuverability, energy consumption and structure of the underwater vehicle are considered in the optimisation framework constructed by a generalised collaborative optimisation method. Expert knowledge based analytic hierarchy process is conducted to obtain the optimisation object that involves the four performances. Numerical simulation is performed to accurately analyze the rapidity, manoeuverability and structure performances of the underwater vehicle. To reduce the calculation burden, dynamic surrogate models are proposed to replace numerical simulation in the optimisation framework. To guarantee the optimisation efficiency and accuracy, a synthetic minority oversampling technique (SMOTE) and adaptive minimise lower confidence bound (LCB) are combined in constructing the dynamic surrogate models. The proposed optimisation strategy is applied to the SUBOFF model and compared with other dynamic surrogate models. Comparison results prove the advantages of the proposed dynamic surrogate model.