权重搜索遗传算法在液货船装卸计划生成中的应用  

Application of weight coefficient searching genetic algorithm in the plan generation of cargo loading and unloading for liquid cargo carrier

作　　者：齐鸣[1] 林嘉昊[1] 孙淼[1] 张勇[1] QI Ming;LIN Jiahao;SUN Miao;ZHANG Yong(Marine Design and Research Institute of China,Shanghai 200011,China)

机构地区：[1]中国船舶及海洋工程设计研究院,上海200011

出　　处：《中国舰船研究》2022年第S01期28-36,共9页Chinese Journal of Ship Research

摘　　要：[目的]液货船装卸计划的生成时间和安全评价极大程度上影响着船舶在港装卸效率,故提出采用权重搜索遗传算法制定液货船装卸计划。[方法]通过梳理液货船装载状态的安全校核指标,围绕浮态限制、完整稳性校核、静水强度校核、装卸计划与船员预设流程匹配度,建立液货船装卸计划校核问题的非确定多项式及相应的优化目标函数。通过改变其中各影响因子的权重,形成优化目标函数簇,再使用精英保留的遗传算法,得到目标函数簇中每个成员的最优解,形成某超大型油轮装卸计划最优解集合,并与基于传统线型拟合生成的装卸计划进行对比。[结果]结果显示,在应用权重搜索遗传算法生成装卸计划的各个阶段,船舶浮态更符合目标浮态,稳性状态明显优于用户预设方案。[结论]研究表明,基于精英保留策略的权重搜索遗传算法可以有效提升液货船装卸计划制定的准确性与可靠性。[Objective]Cargo loading and unloading plan generation time and safety evaluation have a great influence on the handling efficiency. To this end, this paper introduce weight coefficient searching genetic algorithm into the plan generation. [Methods]Loading safety status mainly involves draft limitation, intact stability checking, hyrostatic strength checking and compatibility between the generated loading and unloading plan and preset process. In this study, a non-deterministic polynomial and corresponding optimization objective functions are established to solve the loading and unloading scheme generation problem of liquid cargo carriers. The weight of each influence factor in the objective function is changed and recorded in sequence to form an optimal objective function cluster. The optimal solution of each member in the cluster is then carried out through an elitist preservation genetic algorithm in order to provide an optimal solution set. On this basis, a comparison is made with the loading and unloading plan of a very large crude oil carrier(VLCC) generated by the linear fitting method[Results]The ship draft status is more consistent with the target, and the stability state is obviously better than that of the user preset plan in each loading/unloading step generated by this algorithm. [Conclusion]The weight coefficient searching genetic algorithm based on elitist preservation proposed in this paper can improve the accuracy and reliability of the liquid cargo carrier loading sequence.

关 键 词：液货船 装卸计划 权重搜索 精英保留 遗传算法 

分 类 号：U674.133[交通运输工程—船舶及航道工程]