Abstract
Learning Factories (LFs) have become increasingly important in engineering education, offering environments where students can engage in experiential learning and connect theoretical knowledge with industrial practice. In 2016, LIUC University established the i-FAB LF, a foosball assembly line where students experience real factory scenarios, as part of educational formats designed to develop skills in lean manufacturing and Industry 4.0. In this context, a variety of activities devoted to industrial engineering students has been developed. Among these, a learning activity centered on the integration of Artificial Intelligence (AI) into quality management stands out as a representative example, fostering the development of the skills required by the new workforce in the context of Industry 5.0 (I5.0). This activity offers a hands-on, team-based learning experience, with its pedagogical foundation rooted in the A3 problem-solving framework, which guides students in systemat ically identifying quality issues, collecting relevant data, and analyzing root causes in the production process. Following this structured analysis, students apply their insights to develop an AI tool leveraging convolutional neural networks to automati cally detect and classify assembly defects. In this way, the A3 process provides both the diagnostic foundation and the data driven roadmap for AI implementation, connecting structured problem solving with innovative technological countermeasures. Taken together, these elements foster skills in creative and innovative thinking, collaboration, data analytics and problem solving – considered as key competencies in the I5.0 paradigm. The contribution of this study is to present the LF-based educational activity and to report students’ perceptions collected through a structured questionnaire on three dimensions: learn ing experience and pedagogical design, collaboration and motivation, and quality of the learning environment.