期刊
COMPUTERS & INDUSTRIAL ENGINEERING
卷 162, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cie.2021.107704
关键词
Scheduling; Mixed model sequencing; Reinforcement learning; Metaheuristics; Mixed-integer linear programming
This study introduces a reinforcement learning approach to minimize work overload situations in the mixed model sequencing problem. By generating sequences in a constructive way and using metaheuristics, the trained policy can quickly create an initial sequence to improve solution quality. Numerical evaluation on benchmark datasets shows superior performance to established methods when demand plan distribution aligns with learning process expectations.
This study presents a reinforcement learning (RL) approach for the mixed model sequencing (MMS) problem with a minimization of work overload situations. The proposed approach generates the sequence in a constructive way, so that an action denotes the model to be sequenced next. The trained policy quickly creates an initial sequence, which allows us to use the cutoff time to further improve the solution quality with a metaheuristic. Our numerical evaluation based on an existing benchmark dataset shows that our approach is superior to established methods if the demand plan follows its expected distribution from the learning process.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据