From Dynamic to Evolvable Knowledge Graphs in Manufacturing: Systematic Literature Review on Learning Approaches

This systematic literature review investigates how evolvable KGs enhance manufacturing under Industry 4.0 and 5.0, identifying key technologies and gaps. Evolvable KGs adapt to changing knowledge by leveraging machine learning algorithms and human expertise to enhance decision-making, operational efficiency, and predictive maintenance capabilities beyond the capabilities of dynamic KGs. Despite the advancements, challenges persist in quality assurance, process planning, and the integration of human expertise. The findings advocate for addressing these issues to foster wider adoption and optimization of KG technologies in manufacturing. This review maps existing literature based on the KG construction process stages. The main results are the state-of-the-art tasks in creating evolvable KGs in manufacturing and categories of learning approaches in evolvable KGs. The results contribute by updating the KG construction process and widening the understanding of evolvable KGs that utilize learning. By deepening the understanding of how KGs can evolve, this review sets the base for future research to develop more dynamic and intelligent systems tailored to the emerging demands of Industry 5.0.