<div class="csl-bib-body">
<div class="csl-entry">Halbwidl, C., Sobottka, T., Gaal, A., & Sihn, W. (2021). Deep Reinforcement Learning as an Optimization Method for the Configuration of Adaptable, Cell-Oriented Assembly Systems. In D. Mourtzis (Ed.), <i>54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0</i> (pp. 1221–1226). Elsevier BV. https://doi.org/10.1016/j.procir.2021.11.205</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/138180
-
dc.description.abstract
This paper investigates the feasibility and performance of Deep Reinforcement Learning (RL) as a method for optimizing assembly cell configurations in adaptable cell-oriented assembly systems (ACAS). ACAS can be as productive as conventional assembly lines, while offering greater flexibility and resilience. However, optimizing their layout configuration and resource assignment poses a complex challenge for conventional optimization methods. A RL and simulation-based method is evaluated in an ACAS use-case setting, including a benchmark with metaheuristics. The findings show the limitations of RL for static aspects of the optimization problem, but also indicate RL's considerable benefits for dynamic optimization tasks in ACAS.
en
dc.relation.ispartofseries
Procedia CIRP
-
dc.subject
General Materials Science
-
dc.subject
Configuration
-
dc.subject
Reinforcement Learning
-
dc.subject
Modular Assembly System
-
dc.subject
Simulation-based Optimization
-
dc.title
Deep Reinforcement Learning as an Optimization Method for the Configuration of Adaptable, Cell-Oriented Assembly Systems
-
dc.type
Konferenzbeitrag
de
dc.type
Inproceedings
en
dc.relation.publication
54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0
-
dc.relation.issn
2212-8271
-
dc.description.startpage
1221
-
dc.description.endpage
1226
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
54th CIRP CMS 2021 - Towards Digitalized Manufacturing 4.0
-
tuw.container.volume
104
-
tuw.peerreviewed
true
-
tuw.book.ispartofseries
Procedia CIRP
-
tuw.relation.publisher
Elsevier BV
-
tuw.publication.invited
invited
-
tuw.researchTopic.id
X1
-
tuw.researchTopic.name
außerhalb der gesamtuniversitären Forschungsschwerpunkte
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E330-02 - Forschungsbereich Betriebstechnik, Systemplanung und Facility Management
-
tuw.publisher.doi
10.1016/j.procir.2021.11.205
-
dc.description.numberOfPages
6
-
tuw.event.name
CIRP CMS 2021 - 54th CIRP Conference on Manufacturing Systems 2021
-
tuw.event.startdate
22-09-2021
-
tuw.event.enddate
24-09-2021
-
tuw.event.online
Online
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Athens, Greece
-
tuw.event.country
GR
-
tuw.event.presenter
Halbwidl, Christoph
-
tuw.presentation.online
Online
-
wb.sciencebranch
Wirtschaftswissenschaften
-
wb.sciencebranch.oefos
5020
-
wb.facultyfocus
Außerhalb der primären Forschungsgebiete der Fakultät
de
wb.facultyfocus
Outside the Faculty's primary research activities
en
item.fulltext
no Fulltext
-
item.grantfulltext
none
-
item.openairetype
conference paper
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.cerifentitytype
Publications
-
crisitem.author.dept
E330 - Institut für Managementwissenschaften
-
crisitem.author.dept
E330 - Institut für Managementwissenschaften
-
crisitem.author.parentorg
E300 - Fakultät für Maschinenwesen und Betriebswissenschaften
-
crisitem.author.parentorg
E300 - Fakultät für Maschinenwesen und Betriebswissenschaften