Design of Blended-wing-body Underwater Gliders Based on Dual-layer Multi-objective Optimization

To enhance the performance and optimization efficiency of blended-wing-body underwater glider (BWBUG), this study proposes a dual-layer multi-objective optimization method for shape design of BWBUGs. A fully parameterized model of the shape of BWBUG is established, an analysis platform for shape performance is built, and a performance database and high-precision neural network mapping models are established. These mapping models are used to study the correlations among design parameters and performance metrics. Furthermore, a dual-layer constrained multi-objective optimization algorithm is constructed to optimize the BWBUG shape by taking the lift-to-drag ratio and internal capacity as objectives. The optimization process is conducted using the developed mapping models. The results demonstrate the lift-to-drag ratio and internal capacity of the optimized BWBUG are improved by 31.49 and 11.33, respectively. Additionally, the weighted score analyses under varying weight scenarios further validate the effectiveness and robustness of the proposed optimization method.