Compound Rules and Reinforcement Learning Based Scheduling Method for Mixed Model Assembly Lines

被引：0

作者：

Guo J. ^{[1
,2
]}

Lyu Y. ^{[3
]}

Dai Z. ^{[1
]}

Zhang J. ^{[3
]}

Guo Y. ^{[2
]}

机构：

[1] Shanghai Spaceflight Precision Machinery Institute, Shanghai

[2] School of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing

[3] Institute of Artificial Intelligence, Donghua University, Shanghai

来源：

Zhongguo Jixie Gongcheng/China Mechanical Engineering | 2023年 / 34卷 / 21期

关键词：

balancing and sequencing; compound rule; deep reinforcement learning; integrated optimization; mixed model assembly line;

D O I：

10.3969/j.issn.1004-132X.2023.21.009

中图分类号：

学科分类号：

摘要：

A scheduling method was proposed based on compound rules and reinforcement learning for balancing and sequencing problems of mixed model assembly lines. A balancing rule set and a sequencing rule set were designed with the consideration of mathematical model, and a proximal policy optimization（P P O ） algorithm featured with Actor-Critic training procedure and preferential experience learning mechanism was employed to regulate weighted parameters of these rules, in order to generate reasonable balancing and sequencing solutions. In comparative experiments, the proposed scheduling method demonstrates the effectiveness over other methods including P P O algorithm with single rule, compound rules, and a genetic algorithm. © 2023 China Mechanical Engineering Magazine Office. All rights reserved.

引用

页码：2600 / 2606and2614

共 18 条

[11] TORTORELLI A, IMRAN M, DELLI PRISCOL I F, A ParallelDeepReinforcementLearningFrameworkforControllingIndustrialAssemblyLines[J], Electronics, 11, 4, pp. 539-548, (2022)
[12] OSTERMEIER F F., On the Trade-offs between Scheduling Objectivesfor Unpaced Mixed-model AssemblyLines[J], InternationalJournalo f ProductionResearch, 60, 3, pp. 866-893, (2022)
[13] LV Y, ZHANG J., A Genetic Regulatory Network Based Method for Multi-objective Sequencing Problem in Mixed-model Assembly Lines [J], MathematicalBiosciencesand Engineering, 16, 3, pp. 1228-1243, (2019)
[14] ZHANG Kai, JIAO Xiaogang, Researchon FlexibleJob-shopScheduling Problems withIntegratedReinforcementLearningAlgorithm, China MechanicalEngineering, 34, 2, pp. 201-207, (2023)
[15] Y U Xin, Wenjun W U, Jie L U O, Et al., Identification MethodforCollective Consensus Mechanism Basedo n InverseReinforcementLearning, Sci. Sin.Tech, 53, 2, pp. 258-267, (2023)
[16] PARK J, CHUN J, KIM S H, Et al., Learning to ScheduleJob-shop Problems: Representation and PolicyLearning Using Graph NeuralNetworkand ReinforcementLearning[J], InternationalJournal ofProductionResearch, 59, 11, pp. 3360-3377, (2021)
[17] BAUTISTA J, CANO A., Solving Mixed Model SequencingProbleminAssemblyLineswithSerial Workstations with Work Overload Minimisation andInterruption Rules[J], European Journalof OperationalResearch, 210, 3, pp. 495-513, (2011)
[18] ZHOU Yaqin, Changqi L Y U Youlong, Et al., SchedulingtheProductiono f AerospaceStructuralParts with Dual Resource Constraints, Journalof MechanicalEngineering, 54, 9, pp. 55-63, (2018)

← 1 2 →