Design and Verification of Process Discovery Based on NLP Approach and Visualization for Manufacturing Industry

Junhyung Moon, Gyuyoung Park, Minyeol Yang and Jongpil Jeong
Additional contact information
Junhyung Moon: Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, Korea
Gyuyoung Park: Department of Systems Management Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, Korea
Minyeol Yang: Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, Korea
Jongpil Jeong: Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, Korea

Sustainability, 2022, vol. 14, issue 3, 1-27

Abstract: When a consultant of a company that provides a smart factory solution consults with a customer, it is difficult to define the outline of the manufacturing process and create all activities within the process by case. It requires a large amount of resources from the company to perform a task. In this study, we propose a process discovery automation system that helps consultants define manufacturing processes. In addition, for process discovery, a fully attention-based transformer model, which has recently shown a strong performance, was applied. To be useful to consultants, we solved the black box characteristics of the deep learning model applied to process discovery and proposed a visualization method that can be used in the monitoring system when explaining the discovery process. In this study, we used the event log of the metal fabrication process to perform the modeling, visualization, and evaluation.

Keywords: process mining; process discovery; manufacturing industry; transformer; process visualization (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/3/1103/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/3/1103/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:3:p:1103-:d:727969

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().