Dynamically adjusting the k-values of the ATCS rule in a flexible flow shop scenario with reinforcement learning

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

Given the fact that finding the optimal sequence in a flexible flow shop is usually an NP-hard problem, priority-based sequencing rules are applied in many real-world scenarios. In this contribution, an innovative reinforcement learning approach is used as a hyper-heuristic to dynamically adjust the k-values of the ATCS sequencing rule in a complex manufacturing scenario. For different product mixes as well as different utilisation levels, the reinforcement learning approach is trained and compared to the k-values found with an extensive simulation study. This contribution presents a human comprehensible hyper-heuristic, which is able to adjust the k-values to internal and external stimuli and can reduce the mean tardiness up to 5%.
Original languageEnglish
JournalInternational Journal of Production Research
Volume61
Issue number1
Pages (from-to)147-161
Number of pages15
ISSN0020-7543
DOIs
Publication statusPublished - 2023

Bibliographical note

Publisher Copyright:
© 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Titel der Ausgabe: Analytics and Machine Learning in Scheduling and Routing Optimization

    Research areas

  • Engineering - Sequencing rules, dynamic adjustment, simulation study, reinforcement learning, production planning and control

Recently viewed

Publications

  1. Parameters Estimation of a Lotka-Volterra Model in an Application for Market Graphics Processing Units
  2. Trait correlation network analysis identifies biomass allocation traits and stem specific length as hub traits in herbaceous perennial plants
  3. Modeling and simulation of size effects in metallic glasses with non-local continuum mechanics theory
  4. Interaction-Dominant Causation in Mind and Brain, and Its Implication for Questions of Generalization and Replication
  5. Entry, exit and productivity
  6. Learning from partially annotated sequences
  7. Self-regulation in error management training: emotion control and metacognition as mediators of performance effects
  8. Neural correlates of the enactment effect in the brain
  9. From Knowledge to Application
  10. Cross-case knowledge transfer in transformative research: enabling learning in and across sustainability-oriented labs through case reporting
  11. Constructing strangeness
  12. The Network Dynamics of Movements
  13. Introduction to Felipe Ehrenberg's "In Search of a Model for Life"
  14. Modeling a modular omnidirectional AGV developmental platform with integrated suspension and power-plant
  15. Automatic generation of periodic representative volume elements for matrix-inclusion composites and their efficiency in multiscaling
  16. Influence of Dy in solid solution on the degradation behavior of binary Mg-Dy alloys in cell culture medium
  17. The Crowd in Flux
  18. Choice and quantity demand for improved and unimproved public water sources in rural areas
  19. A Person-Centered Approach for Analyzing Multidimensional Integration in Collaboration Between Educational Researchers and Practitioners
  20. A Smart Sensing Architecture for Misalignment Measurements
  21. Self-Compassion as a Facet of Neuroticism? A Reply to the Comments of Neff, Tóth-Király, and Colosimo (2018)
  22. Microeconometric Studies on Firm Behavior and Performance
  23. Unsichtbare Gewalt
  24. The Role of Formalisation, Participation and Context in the Success of Public Involvement Mechanisms in Resource Management
  25. How to Curate Diversity and Otherness in Global Performance Art
  26. Systematic learning in water governance: insights from five local adaptive management projects for water quality innovation
  27. Benno Reifenberg (1892-1970)