An integrated knowledge graph and digital twin framework for data intelligent industry education in the nylon chemical industry

The nylon chemical industry chain is characterized by long processes, complex positions, high safety risks, and strong demand for digital transformation. Traditional industry-education integration models struggle to dynamically respond to changes in enterprise job capabilities, lack access to real-world production scenarios, and suffer from low efficiency in multi-entity collaboration. To address these challenges, this paper proposes a data-intelligent-driven model for constructing and collaboratively governing an industry-education integration community in the nylon chemical industry (NylonChem-IEKG). This model uses a knowledge graph of the industry chain as its semantic organization core, integrating multi-source data such as enterprises, processes, positions, skills, courses, training tasks, and governance indicators. It utilizes a digital twin training platform as its practical carrier, supporting virtual training in key scenarios such as polymerization, spinning, quality inspection, and safety management. Furthermore, it achieves a closed-loop linkage between industry demand, educational supply, and governance feedback through knowledge graph reasoning, course-position mapping, a recommendation engine, and a collaborative governance module. Experimental results demonstrate that NylonChem-IEKG outperforms traditional industry-education integration systems and single-function platforms in terms of response efficiency, relationship support, data integration, enterprise participation, and governance performance. Research indicates that data sharing, deep enterprise involvement, digital twin training, and knowledge graph reasoning are key pathways to improving the operational quality of the nylon chemical industry-education integration community.