Shape optimization for blended-wing–body underwater glider using an advanced multi-surrogate-based high-dimensional model representation method

To deal with shape optimization for the blended-wing-body underwater glider (BWBUG), a multi-surrogate-based optimization method using high-dimensional model representation with a score-based infill criterion (MSIC-HDMR) is presented. In this algorithm, multiple surrogate models are constructed to alleviate the prediction uncertainty. A score-based infill criterion is proposed to obtain new samples and a reduced space is used to improve accuracy of the optimization results. Simultaneously, mean square errors of the individual surrogate models for infill points are calculated to determine which surrogate is suitable for the component terms. 20 numerical examples are used to verify the practicability of the proposed MSIC-HDMR, and the results show that the proposed algorithm has remarkable performance on all the test problems. Finally, the optimization method based on MSIC-HDMR is applied to shape optimization of the BWBUG, and the lift-to-drag ratio of the BWBUG is improved by 3.3009% with the proposed MSIC-HDMR.