Abstract: To enhance the stability and safety of the underwater structure of the submersible pressure hull, this study focuses on its multi-objective optimization design, aiming to achieve a synergetic improvement of quality, strength and stability. The parametric analysis process is used to analyze the initial ring-stiffened pressure shell scheme, using the optimal Latin hypercube sampling method to explore the influence of design variables on target responses. A high-precision response surface model and a multi-objective optimization model are also established, thereby enabling the multi-objective optimization of the pressure hull using the NSGA-II genetic algorithm. The results show that among the four optimized schemes, the weight of scheme A and scheme C is reduced by 7.3 kg and 6.6 kg, respectively, while the ultimate strength of scheme B and scheme D is increased by 0.177 MPa and 0.031 MPa, respectively. It is confirmed that the multi-objective optimization method integrating response surface models and genetic algorithm can effectively improve the performance of submersible pressure hull. It can provide a valuable reference for the design of deep-sea exploration equipment.

Key words: ring-stiffened pressure hull, response surface model, multi-objective optimization, non-dominated sorting genetic algorithm II（NSGA-II）

摘要： 为提升潜水器耐压壳水下结构的综合性能,需聚焦于多目标优化设计研究,从而实现质量、强度和稳定性的协同提升。该文采用参数化分析流程对初始环肋耐压壳方案展开研究,通过最优拉丁超立方设计法进行采样,探讨设计变量对目标响应的影响;建立了高精度响应面模型及相应的多目标优化模型,进而通过第二代非支配排序遗传算法（non-dominated sorting genetic algorithm II,NSGA-II）对耐压壳多目标优化求解。研究表明：4组优化方案中,A、C方案分别减重7.3 kg和6.6 kg,B、D方案的极限强度分别提高0.177 MPa和0.031 MPa,由此证明结合响应面模型和遗传算法的多目标优化方法能有效提升潜水器耐压壳的性能,为深海探测装备的设计提供参考。

关键词: 环肋耐压壳, 响应面模型, 多目标优化, 第二代非支配排序遗传算法