Dynamically adjusting the k-values of the ATCS rule in a flexible flow shop scenario with reinforcement learning
Research output: Journal contributions › Journal articles › Research › peer-review
Standard
In: International Journal of Production Research, Vol. 61, No. 1, 2023, p. 147-161.
Research output: Journal contributions › Journal articles › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Dynamically adjusting the k-values of the ATCS rule in a flexible flow shop scenario with reinforcement learning
AU - Heger, Jens
AU - Voss, Thomas
N1 - 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
PY - 2023
Y1 - 2023
N2 - 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%.
AB - 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%.
KW - Engineering
KW - Sequencing rules
KW - dynamic adjustment
KW - simulation study
KW - reinforcement learning
KW - production planning and control
UR - http://www.scopus.com/inward/record.url?scp=85109310848&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/4063b450-6da4-3b5a-918f-b6cda7cf7e07/
U2 - 10.1080/00207543.2021.1943762
DO - 10.1080/00207543.2021.1943762
M3 - Journal articles
VL - 61
SP - 147
EP - 161
JO - International Journal of Production Research
JF - International Journal of Production Research
SN - 0020-7543
IS - 1
ER -