Simulation optimisation for improving the efficiency of a production line
Simulation optimisation for improving the efficiency of a production line
Finding the best set up for a production line is a traditional simulation problem. Here, we apply and adapt Optimal Computing Budget Allocation (OCBA), a well-known method for optimisation via simulation to find the best design for a production line. Typically OCBA is implemented in a sequential fashion with the results of one (or a small number) of replications being used to adapt suggest how the sampling should be allocated in the next step. In this paper we change that format to fit in with the typical experimental set up at Ford and instead work in five main stages. Each stage is allocated a set amount of simulation time and we use OCBA to determine how long to run the simulation for with each system configuration. The results show that using OCBA can substantially increase the efficiency of selecting the best out of a number of designs.
Optimisation via simulation, Production line, Simulation
137-144
Operational Research Society
Calverley, Joseph
abb2f241-1495-44ab-8e9f-2525d1e9be3e
Currie, Christine
dcfd0972-1b42-4fac-8a67-0258cfdeb55a
Stephan, Bhakti
8e9a2ea5-140a-44c0-9c17-e9cf93662f80
Higgins, Michael
335b05bf-6883-47a7-9566-116ea70d52a5
Monks, Thomas
fece343c-106d-461d-a1dd-71c1772627ca
2021
Calverley, Joseph
abb2f241-1495-44ab-8e9f-2525d1e9be3e
Currie, Christine
dcfd0972-1b42-4fac-8a67-0258cfdeb55a
Stephan, Bhakti
8e9a2ea5-140a-44c0-9c17-e9cf93662f80
Higgins, Michael
335b05bf-6883-47a7-9566-116ea70d52a5
Monks, Thomas
fece343c-106d-461d-a1dd-71c1772627ca
Calverley, Joseph, Currie, Christine, Stephan, Bhakti, Higgins, Michael and Monks, Thomas
(2021)
Simulation optimisation for improving the efficiency of a production line.
Fakhimi, Masoud, Boness, Tom and Robertson, Duncan
(eds.)
In Operational Research Society 10th Simulation Workshop, SW 2021 - Proceedings.
Operational Research Society.
.
(doi:10.36819/SW21.014).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Finding the best set up for a production line is a traditional simulation problem. Here, we apply and adapt Optimal Computing Budget Allocation (OCBA), a well-known method for optimisation via simulation to find the best design for a production line. Typically OCBA is implemented in a sequential fashion with the results of one (or a small number) of replications being used to adapt suggest how the sampling should be allocated in the next step. In this paper we change that format to fit in with the typical experimental set up at Ford and instead work in five main stages. Each stage is allocated a set amount of simulation time and we use OCBA to determine how long to run the simulation for with each system configuration. The results show that using OCBA can substantially increase the efficiency of selecting the best out of a number of designs.
Text
SW20_Ford_and_UoS_Paper__Copy_ (2)
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 27 February 2021
Published date: 2021
Additional Information:
Funding Information:
Joseph Calverley was funded by an EPSRC vacation grant at the University of Southampton (EP/R513325/1).
Publisher Copyright:
© 2021 SW 2021. All rights reserved.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
Venue - Dates:
10th Operational Research Society Simulation Workshop, SW 2021, , Virtual, Online, 2021-03-22 - 2021-03-26
Keywords:
Optimisation via simulation, Production line, Simulation
Identifiers
Local EPrints ID: 449818
URI: http://eprints.soton.ac.uk/id/eprint/449818
PURE UUID: 1d28a2cb-7145-46f5-8cba-567ba3b34a92
Catalogue record
Date deposited: 18 Jun 2021 16:31
Last modified: 18 Mar 2024 03:50
Export record
Altmetrics
Contributors
Author:
Joseph Calverley
Author:
Michael Higgins
Author:
Thomas Monks
Editor:
Masoud Fakhimi
Editor:
Tom Boness
Editor:
Duncan Robertson
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics