基于遗传算法的缓波型立管多目标集成优化

缓波型立管由于设计参数较多且优化目标之间相互影响，设计结果具有很大的不确定性。随着代理模型和智能优化算法的发展，针对缓波型立管的优化可以提出更好的解决方案。以提高力学性能和经济效益为优化目标，采用基于Kriging插值模型和NSGA-II算法的多目标优化策略，对考虑顶部浮体影响的深水缓波型立管进行动力响应分析，并开展线型—截面双目标优化集成设计和线型—浮筒三目标优化集成设计。将处于不同几何尺度的设计变量进行集成，旨在各目标存在相互竞争的情况下，与截面、浮筒设计形成有效互动以提高线型设计的总体性能。结果表明，Pareto最优解集可提供多个选择方案，以满足工程实际需要。将所选最优方案与初始设计进行对比，并以疲劳性能和成本估算作为优化的校核指标，取得了理想的优化效果。

Multi-objective integrated optimization of steel lazy wave riser based on genetic algorithm

The design of steel lazy wave riser has great uncertainty due to the large number of design parameters and the interplay between optimization objectives. With the development of approximate model and intelligent optimization algorithm, a better solution can be proposed for the optimization of steel lazy wave riser. In order to improve the dynamic behavior and economic performance, a multi-objective optimization strategy based on Kriging interpolation and NSGA-II algorithm is adopted to analyze the dynamic response of deepwater steel lazy wave riser considering the influence of floating platform. In the case of competing objectives, the dual-objective optimization configuration-section integrated design and three-objective optimization configuration-buoyancy module integrated design are carried out, aiming to achieve effective interaction to improve the overall performance of the configuration. It is observed that Pareto optimal solution set can provide multiple alternatives to satisfy the engineering requirement. The optimal scheme is compared with the initial design, and the fatigue performance and cost estimation are taken as the validation, indicating that this multi-objective integrated optimization strategy obtains desired results.