摘要
为满足西非—中国航线的原油远洋运输方案的时效性要求,以油船运费、滞期费和靠港费之和最低为目标函数,以供需平衡、港口水深和装卸时间为约束条件,求解一个包含船型组合、装/卸港航线组合、油种替换、批次拆分等多决策变量的大规模NP(Non-deterministic Polynomial)难问题.采用差分进化算法进行求解.为提高求解速度,采用双染色体编码、基因组压缩编码、船型与拼装变量隐式联锁、配送油种比对解码等方法,进行供需平衡约束,降低问题规模,并缩减问题的"劣质解空间",提高差分进化算法的搜索时效.利用提出的算法对中国石化某月度西非—中国航线实际原油远洋运输方案进行优化,得到优化方案平均用时约5 min,可节约运费50余万美元.
To meet the timeliness and effectiveness of the crude oil shipping scheme of West Africa-China shipping line, a large scale NP （Non-deterministic Polynomial） hard problem with multiple decision vari-ables including ship-type combination, loading/unloading port route combination, crude oil-type replace-ment and batch split is solved, where the objective is to minimize the sum of freight, demurrage and bert-hing fees, and the condition constraints are supply-demand balance, water depth of ports and loading/un-loading time. The differential evolution algorithm is adopted to solve the problem. In order to improve the solving speed, the methods of the double chromosome coding, the genome compression coding, the im-plicit interlocking of ship-type and assembly variables, and the comparison and decoding of distributed oil types are adopted to realize the supply-demand balance constraint, reduce the scale and the inferior solutions of the problem, and improve the efficiency of the differential evolution algorithm. The proposed al-gorithm is used to optimize the actual ocean crude oil shipping scheme of West Africa-China shipping line of SINOPEC in a month, and the optimized scheme can be obtained in about 5 min at average and save a-bout 500 000 USD.
出处
《上海海事大学学报》
北大核心
2017年第1期31-36,51,共7页
Journal of Shanghai Maritime University
基金
国家自然科学基金(71303258)
关键词
原油远洋运输
NP难问题
差分进化算法
数据降维
ocean crude oil shipping
non-deterministic polynomial hard problem
differential evolution algorithm
data dimension reduction
