Development of a virtual metrology system for smart manufacturing: A case study of spandex fiber production

Virtual metrology (VM) is one of the most important enabling technologies in smart manufacturing. Although there is an abundance of literature on VM applications, the context of continuous production has received less attention. Fundamental challenges involved in the application of VM to a continuou...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers in industry 2023-02, Vol.145, p.103825, Article 103825
Hauptverfasser: Lim, Dong-Joon, Kim, Sangjin, Hwang, Uijong, Jeong, Sanghun, Kim, Dongwook, Kim, Yeolib
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Virtual metrology (VM) is one of the most important enabling technologies in smart manufacturing. Although there is an abundance of literature on VM applications, the context of continuous production has received less attention. Fundamental challenges involved in the application of VM to a continuous process have been overlooked in comparison with intermittent (or batch) processes. Here, we described a real-world VM system for the manufacturing of spandex fiber, focusing on how practical challenges associated with a continuous process, including time synchronization, recirculation process, and autocorrelated features, can be addressed using data analytics. A model refresh strategy is discussed for the deployed VM system to ensure continuous usability and high-quality predictions. The virtual-physical connection established by the VM system creates a virtuous cycle in which constantly updated data render the system realistic, and valuable insights generated by the system can be applied to the physical production environment. •A real-world development case of a virtual metrology system for smart manufacturing is presented.•The role and aim of expert systems for spandex fiber production are discussed.•Practical challenges associated with continuous production process are addressed.•A model refresh strategy to ensure continuous usability with high-quality prediction is established.•A virtual-physical connection enabled by the deployed system has been demonstrated
ISSN:0166-3615
1872-6194
DOI:10.1016/j.compind.2022.103825