Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
Research output: Journal contributions › Conference article in journal › Research › peer-review
Standard
Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System. / Voß, Thomas; Heger, Jens; Zein El Abdine, Mazhar.
In: Simulation Notes Europe, Vol. 32, No. 3, 09.2022, p. 169-175.Research output: Journal contributions › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
AU - Voß, Thomas
AU - Heger, Jens
AU - Zein El Abdine, Mazhar
N1 - Conference code: 19
PY - 2022/9
Y1 - 2022/9
N2 - Integrating machine learning methods into the scheduling process to adjust priority rules dynamically can improve the performance of manufacturing systems. In this paper, three methods for adjusting the k-values of the ATCS sequencing rule are analyzed: neural networks, decision trees and reinforcement learning. They are evaluated in a static and a dynamic scenario. The required dataset was synthetically generated using a discrete event simulation of a flow shop environment, where product mix and system utilization were varied systematically. Across all scenarios, it is shown that all three methods can improve the performance. On par, RL and NN can reduce the mean tardiness by up to 15% and compensate for unplanned product mix changes
AB - Integrating machine learning methods into the scheduling process to adjust priority rules dynamically can improve the performance of manufacturing systems. In this paper, three methods for adjusting the k-values of the ATCS sequencing rule are analyzed: neural networks, decision trees and reinforcement learning. They are evaluated in a static and a dynamic scenario. The required dataset was synthetically generated using a discrete event simulation of a flow shop environment, where product mix and system utilization were varied systematically. Across all scenarios, it is shown that all three methods can improve the performance. On par, RL and NN can reduce the mean tardiness by up to 15% and compensate for unplanned product mix changes
KW - Engineering
UR - https://www.sne-journal.org/sne-volumes/volume-32/sne-323-september-2022
UR - https://www.mendeley.com/catalogue/09fba1e1-531d-3cdb-99ab-544f873ade10/
U2 - 10.11128/sne.32.tn.10617
DO - 10.11128/sne.32.tn.10617
M3 - Conference article in journal
VL - 32
SP - 169
EP - 175
JO - Simulation Notes Europe
JF - Simulation Notes Europe
SN - 2305-9974
IS - 3
Y2 - 15 September 2021 through 17 September 2021
ER -