船舶平面分段流水线多目标模糊调度的改进粒子群算法  

An improved PSO algorithm for multi-objective fuzzy scheduling problem of flow line for panel block construction

作　　者：杨志[1,2] 柳存根 YANG Zhi;LIU Cun-gen(State Key Laboratory of Ocean Engineering, Shanghai Jiaotong University, Shanghai 200240, China;Collaborative Innovation Center for Advanced Ship and Deep-sea Exploration, Shanghai 200240, China)

机构地区：[1]上海交通大学船舶与海洋工程国家重点实验室,上海200240 [2]高新船舶与深海开发装备协同创新中心,上海200240

出　　处：《舰船科学技术》2018年第5期46-51,共6页Ship Science and Technology

基　　金：国家重点基础研究发展计划资助项目(2013CB036103)

摘　　要：针对船舶平面分段建造过程中广泛存在的不确定性问题,考虑在平面分段流水线调度中引入更贴近实际的模糊调度。以模糊数表示加工时间和交货期,以最小化最大完工时间、最大化平均满意度为调度目标,建立平面分段流水线多目标模糊调度问题的数学模型,设计了求解该问题的改进多目标粒子群算法。提出一种按反Logistic曲线规律动态变化的惯性权重,从而在一定程度上平衡算法的全局和局部搜索能力;嵌入由3种邻域结构随机排列构造的变邻域搜索算子以增强算法的局部改良性搜索能力;采用一种基于拥挤距离的非支配解动态维护策略以提高解的分布性。结合实例数据,通过对算法进行比较,证实了各项改进措施的有效性,以及所设计算法求解平面分段流水线多目标模糊调度问题的优越性。Considering that uncertainty is common in ship construction, the concept of fuzzy scheduling is introduced in the scheduling problem of panel block construction. It is formulated as a multi-objective fuzzy blocking flow shop scheduling problem with a fuzzy processing time and fuzzy due date, and not only minimizes the fuzzy makespan but also maximizes the average agreement index. An improved multi-objective particle swarm optimization is developed to solve the scheduling problem. Dynamic inertia weight changed in an inverse Logistic curve is employed to balance the global and local search ability to some extent. A variable neighborhood search operator with three randomly ranked neighborhood structures is embedded to enhance the evolutionary search ability. Furthermore, a dynamic crowding distance based maintenance strategy for non-dominated solutions is adopted to improve the distribution of the ones. Computational comparisons demonstrate the feasibility and effectiveness of the proposed algorithm.

关 键 词：平面分段 流水线 模糊调度 多目标 粒子群算法 

分 类 号：U673.2[交通运输工程—船舶及航道工程]