摘要
针对多项目船台搭载调度问题,提出一种改进的多种群遗传算法。考虑实际船台搭载过程同时受机器能力约束和节拍约束,建立了受机器能力约束和节拍约束的资源受限多项目调度的数学模型,对船台周期进行优化。结合了多种优先规则生成初始种群,保证初始个体的质量和均匀分布性;交叉算子和变异算子能确保产生合法的新个体,迁移算子能协同多种群进化减小遗传参数对结果的影响。最后通过船厂数据进行验证和与其他算法的比较,结果证明该算法能合理分配资源,明显缩短船台周期,很好地解决带机器能力约束的多项目船台吊装调度问题。
A modified multi-population genetic algorithm was proposed for solving multi-project block erection scheduling problem. Considering shipyard actually confines to machine eligibility and work hour constraint at the same time, a mathematical model of the multi-project scheduling problem considering machine eligibility and work hour constraints was established, to minimize the makespan. The adapted multi-population genetic algorithm, combined with priority rules was used to generate the original population so as to ensure the high quality of original individuals and the uniformity of solution space. Crossover and mutation operators guaranteed the offspring were always feasible, immigrant operator coordinated the evolution among multi-population thus to weaken the influence of genetic parameter to the result. Finally, the experiment was performed on data from some shipbuilding company and compared with other scheduling schemes, and the result shows the effectiveness of this proposed algorithm. The proposed algorithm can do well in solving the multi- project block erection scheduling problem with machine eligibility constraint.
出处
《计算机应用》
CSCD
北大核心
2016年第A02期77-81,共5页
journal of Computer Applications
关键词
多船
搭载
机器能力约束
紧前约束
节拍约束
multi-vessel
block erection
machine eligibility constraint
precedence constraint
work hour constraint
