Implementation of Deep Learning in Teaching Factory as a Strategy for Enhancing Industrial Competencies: A Systematic Literature Review

The advancement of Industry 4.0 has significantly increased the demand for industrial competencies aligned with intelligent, data-driven manufacturing systems. Deep learning, as a core artificial intelligence technology, plays a critical role in smart factories, particularly in computer vision, predictive analytics, and automated decision-making. In parallel, the Teaching Factory model has emerged as a strategic educational approach to bridge the gap between vocational education and real industrial practices. This study conducts a Systematic Literature Review (SLR) on the integration of deep learning and pedagogical approaches within Teaching Factory and automated manufacturing learning environments, with a focus on industrial competency development. Using a structured and transparent review protocol, peer-reviewed journal articles were analyzed to identify instructional practices, learning theories, targeted competencies, and research methodologies. The review indicates that while Teaching Factory models emphasize production-based learning, deep learning has not yet been systematically embedded into their pedagogical frameworks. Existing studies predominantly address technical and cognitive competencies, with limited attention to transversal and employability competencies. Methodologically, the literature is largely dominated by conceptual frameworks and short-term case studies, underscoring the need for more empirical and longitudinal research. This review contributes by synthesizing current evidence, clarifying research gaps, and proposing directions for pedagogically grounded and industry-aligned Teaching Factory models that integrate deep learning to support comprehensive industrial competency development