The cabin-skeleton coupling structure of a blended-wing-body underwater glider is optimized using a data-driven discrete optimization concept.

First, a Kriging-assisted discrete global optimization algorithm (KDGO) is proposed for computationally expensive black-box problems. The KDGO uses a novel infill-sampling strategy to capture discrete sample points with better performance, and introduces a multi-start method with a data mining strategy, including multi-start optimization, projection, sampling and selection. Second, a parametric cabin-skeleton coupling structure model is established using the finite element analysis method under lifting deformation and deep-water pressure conditions. The float-to-weight ratio and strength and stability of the cabin-skeleton structure are taken as the goal and constraints respectively. Considering the interference between shape and cabin, and the coupling relationship between cabin and skeleton, a discrete optimization mathematical model of the overall coupling structure is established. Finally, the discrete optimization algorithm and coupling structure simulation are combined to build an overall optimization framework.

By using KDGO to conduct 200 function evaluations and comparing the optimal feasible points in design of experiments (DoE) with the global optimal feasible points after optimization, it is found that the optimized float-to-weight ratio of the coupling structure is increased by nearly 40%, representing satisfactory results.

The results of this study can provide valuable references for the cabin-skeleton coupling structure design of blended-wing-body underwater gliders.