[Zurück]

S. Nixdorf, T. Madreiter, S. Hofer:
"A Work-based Learning Approach for Developing Robotics Skills of Maintenance Professionals";
Vortrag: 12th Conference on Learning Factories (CLF), Singapore; 11.04.2022 - 13.04.2022; in: "SSRN Tomorrow's Research Today", (2022).

Industry 4.0 and implementation of intelligent solutions into manufacturing practice pose skill mismatches of industrial workforce. Factory maintenance is particularly impacted due to the implementation of AI-enhanced and IoT-based technologies. Job profiles of maintenance staff are transforming accordingly, resulting in imminent skill mismatches. Maintenance practice of the future comprises of i) manual and cognitive tasks for inspecting, repairing, and overhauling industrial machines on the shop floor supported by cognitive and physical assistance systems, and ii) cognitive management tasks including planning, monitoring, and controlling, based on data-driven predictions and AI-enhanced recommendations. Optimizing person-job-fit and closing associated skill gaps in smart manufacturing are the subjects of research inter alia in work-based learning, especially focusing on design and development of tailor-made upskilling programs. To pursue this line of research, this paper provides a methodology for design and development of a training program dedicated to the emerging robotics skill requirements of maintenance professionals. Based on analysis of a typical maintenance process divided by cognitive and manual tasks, competence needs of (future) maintenance workforce are derived, and matching learning outcomes are defined to develop a learning path. The methodology is applied to a corrective maintenance task for a pneumatic cylinder, resulting in a training program for obtaining needed skills. It is facilitated by a blended learning approach, comprising of E-learning and hands-on learning materials. Of particular interest is the acquisition of manual robotics skills through performing manual maintenance tasks in a human-robot collaboration. Initial pilot evaluations suggest high quality of the training program. Potential impact of the adoption of collaborative robots in maintenance as well as limitations and extensions are discussed.

Maintenance, Cobots, Learning factories, Work based learning, Blended Learning, Industry 4.0

http://dx.doi.org/10.2139/ssrn.4074528