Technology-enhanced data-driven approach for additive manufacturing education

RWTH Publications (RWTH Aachen)

Abstract

This dissertation presents a comprehensive and future-oriented methodology for additive manufacturing (AM) education that addresses the rapidly evolving skill requirements of Industry 4.0. The proposed methodology is built around a four-step framework consisting of: (1) analysis of industrial needs, (2) curriculum design, (3) technology-enhanced learning, and (4) data-driven monitoring. In the first phase, expert interviews, content analyses, and focus groups are employed to identify key competencies, job profiles, and learning challenges within the AM sector. Based on these insights, a flexible and modular AM education program is designed, covering awareness, basic, and advanced levels. The curriculum is aligned with industry roles and learning outcomes and emphasizes the integration of theoretical and practical knowledge across disciplines. The third phase enhances the educational experience through immersive technologies. Two applications – AR DfAM Explorer and VR 4 AM – are developed and implemented to increase learner engagement, accessibility, and comprehension of complex topics such as design for additive manufacturing (DfAM) and powder bed fusion (PBF) processes. These applications are evaluated through user feedback and pilot studies involving students and professionals. In the final phase, a data-driven monitoring approach is introduced to ensure continuous curriculum relevance. Over 11,000 AM job postings are collected and analyzed using natural language processing (NLP) techniques – Word2Vec, LSTM, and BERT – to identify current and emerging skill demands across regions and industries. This enables feedback loops for updating learning content in alignment with labor market trends. The results demonstrate improved learning outcomes and adaptability of AM education. The methodology offers a transferable model for other advanced manufacturing fields such as robotics. By combining structured pedagogical design with digital innovation and market intelligence, this research contributes to the development of responsive, lifelong learning systems for the workforce of tomorrow.

Authors 1

1. Gustavo Melo corresponding Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen