Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Sequencing operations can be difficult, especially under uncertain conditions. Applying decentral sequencing rules has been a viable option; however, no rule exists that can outperform all other rules under varying system performance. For this reason, reinforcement learning (RL) is used as a hyper heuristic to select a sequencing rule based on the system status. Based on multiple training scenarios considering stochastic influences, such as varying inter arrival time or customers changing the product mix, the advantages of RL are presented. For evaluation, the trained agents are exploited in a generic manufacturing system. The best agent trained is able to dynamically adjust sequencing rules based on system performance, thereby matching and outperforming the presumed best static sequencing rules by ~ 3%. Using the trained policy in an unknown scenario, the RL heuristic is still able to change the sequencing rule according to the system status, thereby providing a robust performance.
Translated title of the contributionDynamische Auswahl von Reihenfolgeregeln mit bestärkendem Lernen in einer Werkstattfertigung mit stochastischen Einflüssen
Original languageEnglish
Title of host publicationProceedings of the 2020 Winter Simulation Conference, WSC 2020
EditorsK.-H. Bae, B. Feng, S. Kim, S. Lazarova-Molnar, Z. Zheng, T. Roeder, R. Thiesing
Number of pages11
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date14.12.2020
Pages1608 - 1618
Article number9383903
ISBN (electronic)978-1-7281-9499-8
DOIs
Publication statusPublished - 14.12.2020
EventWinter Simulation Conference - WSC 2020: Simulation Drives Innovation - Orlando, United States
Duration: 14.12.202018.12.2020
http://meetings2.informs.org/wordpress/wsc2020/

Recently viewed

Publications

  1. Analysis of PI controllers with anti-windup techniques on level systems
  2. Structure and dynamics laboratory testing of an indirectly controlled full variable valve train for camless engines
  3. Facing complexity through informed simplifications
  4. Global Finite-Time Stabilization of Planar Linear Systems With Actuator Saturation
  5. Wavelet functions for rejecting spurious values
  6. Grounding Space
  7. Implementing ERP systems in multinational projects
  8. Scaling-based Least Squares Methods with Implemented Kalman filter Approach for Nano-Parameters Identification
  9. An Optimal and Stabilising PI Controller with an Anti-windup Scheme for a Purification Process of Potable Water
  10. Modeling of lateness distributions depending on the sequencing method with respect to productivity effects
  11. Passive Rotation Compensation in Parallel Kinematics Using Quaternions
  12. Combining a PI Controller with an Adaptive Feedforward Control in PMSM
  13. Automatic three-dimensional geometry and mesh generation of periodic representative volume elements for matrix-inclusion composites
  14. Proceedings of the 7th Natural Language Interfaces for the Web of Data (NLIWoD)
  15. archiDART: an R package for the automated computation of plant root architectural traits
  16. A dialectical perspective on innovation: Conflicting demands, multiple pathways, and ambidexterity
  17. Model and Validation of the Electromagnetic Interference Produced by Power Transmission Lines in Robotic Systems
  18. The role of task complexity, modality and aptitude in narrative task performance
  19. Parametric finite element model and mechanical characterisation of electrospun materials for biomedical applications
  20. Soft Optimal Computing to Identify Surface Roughness in Manufacturing Using a Gaussian and a Trigonometric Regressor
  21. Project and Design of a Catamaran Prototype with Aerial Propulsion System
  22. Desynchronization of the Public and the Private
  23. An Adaptive Resonance Regulator for an Actuator using Periodic Signals in Camless Engine Systems
  24. Datenstrukturen & Algorithmen
  25. A Robust Approximated Derivative Action of a PID Regulator to be Applied in a Permanent Magnet Synchronous Motor Control
  26. Perfectly nested or significantly nested - an important difference for conservation management
  27. The role of plant biodiversity in modifying the structure and functioning of higher tropic Levels in species-rich forests
  28. The polarity field concept
  29. Tree diversity promotes functional dissimilarity and maintains functional richness despite species loss in predator assemblages
  30. Collaborative business in supply chains - a system dynamics approach
  31. Challenges in political interviews
  32. Digital Business Transformation and the Changing Role of the IT Function
  33. A Model Based Feedforward Regulator Improving PI Control of an Ice-Clamping Device Activated by Thermoelectric Cooler
  34. Доля на внутрішньому ринку“ для України в рамках Угоди про асоціацію між Україною та ЄС