Smart use case picking with DUCAR: A hands-on approach for a successful integration of machine learning in production processes

Schäfer F, Mayr A, Schwulera E, Franke J (2020)


Publication Type: Conference contribution

Publication year: 2020

Journal

Publisher: Elsevier B.V.

Book Volume: 51

Pages Range: 1311-1318

Conference Proceedings Title: Procedia Manufacturing

Event location: Athens GR

DOI: 10.1016/j.promfg.2020.10.183

Abstract

The increasing data availability in production processes combined with open source software tools in the field of machine learning (ML) lead to a new level of process improvement possibilities. For many companies, the challenge is now to identify potential use cases with considerable business impact by integrating ML techniques in production processes. Especially hands-on approaches, which provide a structured guideline through the process with concrete tools, are missing. Therefore, this paper presents the smart use case picking approach DUCAR, which consists of five phases. The first phase is the definition of the ML use case domain followed by the understanding of potential processes and process steps in the second phase. In the third phase, use case ideas are collected based on the gained knowledge. After the analysis and selection of the most promising use cases in the fourth phase, the final fifth phase focuses the realization of these use cases to successfully integrate ML in production processes. To validate the DUCAR approach, the field of electronics production is used as an example.

Authors with CRIS profile

How to cite

APA:

Schäfer, F., Mayr, A., Schwulera, E., & Franke, J. (2020). Smart use case picking with DUCAR: A hands-on approach for a successful integration of machine learning in production processes. In George-Christopher Vosniakos, Marcello Pellicciari, Panorios Benardos, Angelos Markopoulos (Eds.), Procedia Manufacturing (pp. 1311-1318). Athens, GR: Elsevier B.V..

MLA:

Schäfer, Franziska, et al. "Smart use case picking with DUCAR: A hands-on approach for a successful integration of machine learning in production processes." Proceedings of the 30th International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2021, Athens Ed. George-Christopher Vosniakos, Marcello Pellicciari, Panorios Benardos, Angelos Markopoulos, Elsevier B.V., 2020. 1311-1318.

BibTeX: Download