Integration of Hand Tracking and Process Mining to Improve Knowledge Transfer on the Shoopfloor
International Conference on Control, Automation and Robotics (ICCAR), pp. 16–20
Abstract
For many small and medium-sized companies in Germany, maintaining best practices on the shopfloor is essential for competitiveness. Due to the impending wave of retirements and the changing employment patterns of the younger generations, there is a risk that knowledge will be lost when employees leave. This calls for innovative solutions for the digital capture, storage and provision of knowledge. This article presents a method that uses machine learning to capture hand movements and thus generate event logs for evaluation based on process mining. Using an example from manual assembly, it is shown how this system can be used to record the actions of different employees and analyze them from an efficiency and ergonomic point of view in order to gain an insight into the individual strategies, routines and tricks of the employees during assembly and make them usable for everyone.
Authors 4
-
Yannick Dassen Aachen Laboratory for Machine Tools and Production Engineering (WZL) Department Automation and Control
RWTH Aachen University · FH Aachen
Affiliation as printed
Laboratory for Machine Tools and Production Engineering,Department Automation and Control,Aachen,Germany
-
Yan Ke Zhao Aachen Laboratory for Machine Tools and Production Engineering (WZL) Department Automation and Control
RWTH Aachen University · FH Aachen
Affiliation as printed
Laboratory for Machine Tools and Production Engineering,Department Automation and Control,Aachen,Germany
-
Oliver Petrović Aachen Laboratory for Machine Tools and Production Engineering (WZL) Department Automation and Control
RWTH Aachen University · FH Aachen
Affiliation as printed
Laboratory for Machine Tools and Production Engineering,Department Automation and Control,Aachen,Germany
-
Affiliation as printed
Chair of Machine Tools Laboratory for Machine Tools and Production Engineering,Aachen,Germany
Cited by 0 stored of 0
No patents citing this paper on Lens.org (checked 2026-10-06).
References 14
-
W6779442434details pending0citations
14 results