改进高效全局优化算法在船型优化中的应用  

Application of improved efficient global optimization algorithm

作　　者：朱雨辰 ZHU Yu-chen(Shanghai Maritime University,Shanghai 201306,China)

机构地区：[1]上海海事大学,上海201306

出　　处：《舰船科学技术》2024年第1期88-93,共6页Ship Science and Technology

摘　　要：船型优化问题的复杂度越来越大,导致昂贵数值计算量越来越大,进而优化成本越来越高,对优化技术提出了更高的要求:精简计算量,降低优化成本。本文针对高效全局优化算法进行研究和开发,对其初始样本点、加点法则以及收敛条件等进行了探讨,采用多种初始样本点数启动优化,采用“期望函数”作为单目标加点法则以及欧氏距离EIM函数作为多目标加点法则,使用遗传算法对加点函数进行寻优精确定位最佳新增样本点,并通过标准优化测试函数进行了验证。为船型优化问题提供了新的思路。The ship hull optimization problem is becoming more and more complex, resulting in an increasing amount of expensive numerical calculations, which in turn makes the optimization cost higher and higher. This puts forward higher requirements for optimization technology, to streamline the calculation amount and reduce the optimization cost. This paper conducts research and development on efficient global optimization algorithms, discusses its initial sample points, sample point adding rules and convergence conditions, using a variety of initial sample points to start optimization. Expected Improvement as the single-objective sample adding rule and euclidean. The distance EIM function is used as a multi-objective sample adding rule, and a genetic algorithm is used to optimize the sample adding function to accurately locate the best new sample points, and is verified through a standard optimization test function. It provides new ideas for ship type optimization problems.

关 键 词：船型优化 精简计算量 高效全局优化算法 加点法则 

分 类 号：U661.31[交通运输工程—船舶及航道工程]