机组复原问题研究  

Research on airline crew recovery

作　　者：李艳艳[1] 乐美龙[2] 韩晓龙[1] 

机构地区：[1]上海海事大学物流研究中心,上海201306 [2]上海交通大学海洋航运研究所,上海200240

出　　处：《广西大学学报（自然科学版）》2015年第3期736-743,共8页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(71171129);上海市科委科研计划项目(111510501900;12dz1124802);上海市教委科研项目(11YZ137)

摘　　要：精细的运筹规划研究为航空公司提供了越来越高效的运营计划,使得飞机和机组的利用率非常之高,这导致即使是小小的意外发生,都将影响计划的实施,甚至是整个航班计划的中断。所以,不正常运营规划显得愈发重要,而机组复原又是其中重要的环节。针对该问题,提出了能充分描述该问题的关系网络图,建立了多商品网络模型。对于该大规模整数规划问题,设计了适用的对偶单纯形法,从而大大减少了问题求解的时间。算例分析表明,算法满足航空公司不正常运行期的实时控制要求。和cplex线性规划求解方法做性能比较证明了算法具有较高的求解效率。Fine management planning provides an airline with an efficient plan,which usually has high utilization of resources and very tight aircraft and crew assignment. But in many cases, a small perturbation in the plan will result in major disruption to the scheduled flight. Thus, irregular flight management becomes more important to airlines, and crew recovery is one of the important steps. Aiming at solving this problem, a connection network and a multi-commodity flow model are presen-ted. For this large integer programming problems, a suitable dual simplex method is designed, which greatly reduces the time for problem solving. Experimental results show that the method fulfill the airline＆#39;s real-time control demand during abnormal operation period. Compared with the cplex linear programming method, the presented algorithm has higher efficiency.

关 键 词：机组复原 关系网络图 多商品流 实时控制 对偶单纯形法 

分 类 号：N945.15[自然科学总论—系统科学]