Show simple item record

dc.contributor.authorSabuncuoğlu, İ.en_US
dc.contributor.authorTouhami, S.en_US
dc.date.accessioned2016-02-08T10:32:40Z
dc.date.available2016-02-08T10:32:40Z
dc.date.issued2002en_US
dc.identifier.issn0020-7543
dc.identifier.urihttp://hdl.handle.net/11693/24672
dc.description.abstractArtificial neural networks are often proposed as an alternative approach for formalizing various quantitative and qualitative aspects of complex systems. This paper examines the robustness of using neural networks as a simulation metamodel to estimate manufacturing system performances. Simulation models of a job shop system are developed for various configurations to train neural network metamodels. Extensive computational tests are carried out with the proposed models at various factor levels (study horizon, system load, initial system status, stochasticity, system size and error assessment methods) to see the metamodel accuracy. The results indicate that simulation metamodels with neural networks can be effectively used to estimate the system performances.en_US
dc.language.isoEnglishen_US
dc.source.titleInternational Journal of Production Researchen_US
dc.relation.isversionofhttp://dx.doi.org/10.1080/00207540210135596en_US
dc.subjectComputer simulationen_US
dc.subjectLarge scale systemsen_US
dc.subjectMathematical modelsen_US
dc.subjectNeural networksen_US
dc.subjectProblem solvingen_US
dc.subjectRobustness (control systems)en_US
dc.subjectJob-shop systemsen_US
dc.subjectProduction engineeringen_US
dc.titleSimulation metamodelling with neural networks: an experimental investigationen_US
dc.typeArticleen_US
dc.departmentDepartment of Industrial Engineeringen_US
dc.citation.spage2483en_US
dc.citation.epage2505en_US
dc.citation.volumeNumber40en_US
dc.citation.issueNumber11en_US
dc.identifier.doi10.1080/00207540210135596en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record