大规模集装箱装载问题  

Large-scale container loading problem

作　　者：吴楚楠[1] 刘科峰[2] 彭斯俊[2] 黄樟灿[2] 

机构地区：[1]武汉理工大学计算机学院,武汉430070 [2]武汉理工大学数学系,武汉430070

出　　处：《计算机工程与应用》2013年第1期231-233,257,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(No.30570611)

摘　　要：对于大规模三维装箱问题,利用区域分裂法的基本思想,将复杂的大规模装箱问题通过货物的重组分解为若干个小区域上的问题,然后通过合并小区域之间的解得到整个区域的解。该方法能分解大型问题为小型问题,复杂区域问题为简单区域问题。在传统演化算法的基础上,引入了模拟退火产生新个体思想对其进行改进,提高了算法的运行效率和解的有效性。通过对某港口案例进行测试,结果证实该算法能满足实际装载需求。For large-scale three-dimensional packing problem, in use of the basic idea of＇domain decomposition method, the huge complex problems by packing the goods are re-divided into a number of small regional issues, and then merge those together, the whole region solution will come out. This method can decompose large problems into small issues, complex regional problems into simple regional issues. In base of traditional evolutionary algorithm, simulated annealing generating new individual ideas is introduced to improve it, raising the efficiency of the algorithm and the effectiveness of solution. Through the test of a number of cases of a certain port, the results prove that this method can meet the actual load demand.

关 键 词：区域分裂法 货物重组 演化算法 

分 类 号：O223[理学—运筹学与控制论] TP391[理学—数学]