Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems)
Production system simulation is a powerful tool to achieve efficient operations in complicated production systems such as high-mix and low-volume production. However, it takes significant efforts and expertise to construct accurate simulation models. In this article, a novel modeling approach called...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2023-12-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/89/928/89_23-00205/_pdf/-char/en |
| _version_ | 1797376270342815744 |
|---|---|
| author | Satoshi NAGAHARA Toshiya KAIHARA Nobutada FUJII Daisuke KOKURYO |
| author_facet | Satoshi NAGAHARA Toshiya KAIHARA Nobutada FUJII Daisuke KOKURYO |
| author_sort | Satoshi NAGAHARA |
| collection | DOAJ |
| description | Production system simulation is a powerful tool to achieve efficient operations in complicated production systems such as high-mix and low-volume production. However, it takes significant efforts and expertise to construct accurate simulation models. In this article, a novel modeling approach called as data-driven and multi-scale modeling is proposed. The proposed approach combines various modeling methods to maximize the simulation accuracy. In order to verify the usefulness of the proposed approach, computational experiments for simple production systems to compare modeling methods are conducted. The experimental results show that the superiority of modeling methods depends on the background knowledge and available information about target production system and the proper use of modeling methods is important to achieve high accuracy. |
| first_indexed | 2024-03-08T19:36:07Z |
| format | Article |
| id | doaj.art-24ff0712f93745f584762c7d34edf354 |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-03-08T19:36:07Z |
| publishDate | 2023-12-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-24ff0712f93745f584762c7d34edf3542023-12-26T00:20:42ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612023-12-018992823-0020523-0020510.1299/transjsme.23-00205transjsmeData-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems)Satoshi NAGAHARA0Toshiya KAIHARA1Nobutada FUJII2Daisuke KOKURYO3Center for Technology Innovation – Connective Automation., Research and Development Group, Hitachi, Ltd.Graduate School of System Informatics, Kobe UniversityGraduate School of System Informatics, Kobe UniversityGraduate School of System Informatics, Kobe UniversityProduction system simulation is a powerful tool to achieve efficient operations in complicated production systems such as high-mix and low-volume production. However, it takes significant efforts and expertise to construct accurate simulation models. In this article, a novel modeling approach called as data-driven and multi-scale modeling is proposed. The proposed approach combines various modeling methods to maximize the simulation accuracy. In order to verify the usefulness of the proposed approach, computational experiments for simple production systems to compare modeling methods are conducted. The experimental results show that the superiority of modeling methods depends on the background knowledge and available information about target production system and the proper use of modeling methods is important to achieve high accuracy.https://www.jstage.jst.go.jp/article/transjsme/89/928/89_23-00205/_pdf/-char/enproduction system simulationproduction systemsystem identificationmachine learning |
| spellingShingle | Satoshi NAGAHARA Toshiya KAIHARA Nobutada FUJII Daisuke KOKURYO Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) Nihon Kikai Gakkai ronbunshu production system simulation production system system identification machine learning |
| title | Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) |
| title_full | Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) |
| title_fullStr | Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) |
| title_full_unstemmed | Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) |
| title_short | Data-driven and multi-scale modeling approach for production system simulation (Fundamental study on model identification for single process systems) |
| title_sort | data driven and multi scale modeling approach for production system simulation fundamental study on model identification for single process systems |
| topic | production system simulation production system system identification machine learning |
| url | https://www.jstage.jst.go.jp/article/transjsme/89/928/89_23-00205/_pdf/-char/en |
| work_keys_str_mv | AT satoshinagahara datadrivenandmultiscalemodelingapproachforproductionsystemsimulationfundamentalstudyonmodelidentificationforsingleprocesssystems AT toshiyakaihara datadrivenandmultiscalemodelingapproachforproductionsystemsimulationfundamentalstudyonmodelidentificationforsingleprocesssystems AT nobutadafujii datadrivenandmultiscalemodelingapproachforproductionsystemsimulationfundamentalstudyonmodelidentificationforsingleprocesssystems AT daisukekokuryo datadrivenandmultiscalemodelingapproachforproductionsystemsimulationfundamentalstudyonmodelidentificationforsingleprocesssystems |