Driven by China’s national “Smart Reform and Digital Transformation (SRDT)” strategy and the imperative of industry-education integration, the architectural design program in vocational undergraduate education urgently needs to transcend traditional pedagogical limitations in ancient building conservation. This study takes Huadu Gangtou Ancient Village and Conghua Qiangang Ancient Village in Guangzhou as real-world data collection bases to construct a “digital twin + AI + industry-education integration” teaching model. Through a four-stage instructional process – point cloud acquisition, AI-driven semantic segmentation, damage diagnosis, and generative design – students advance from technical cognition to innovative application. Quantitative results show that student proficiency scores increased from a pre-test average of 60.2 to 79.5, and the proportion of students able to independently operate AI tools rose from 12% to 67%. The model effectively enhances digital skills and professional competence, providing a replicable pathway for Lingnan vernacular dwellings renewal. Challenges including technical thresholds and enterprise participation sustainability are analyzed, with corresponding improvement strategies proposed.
References
[1] Blagonić, B., Markovinović, D., Matijević, H., Redovniković, L. (2025) Integration of digital twin technologies in urban regeneration of a small historic town in Europe. Sustainability, 17(23), 10740.
[2] Jang, D. H., Roh, G. T., Jeon, C. H., Shim, C. S. (2025) Simulation-based optimization of crane lifting position and capacity using a construction digital twin for prefabricated bridge deck assembly. Buildings, 15(3), 475.
[3] Ruiz-Díaz, C., Triviño-Tarradas, P., Guerrero-Vacas, G., Rodríguez-Alabanda, Ó., Medina-Triviño, P., Serrano-Baena, M. M. (2026) From laboratory to building scale: a digital-twin methodology for resilience-oriented assessment of RC infrastructure using waste wool-fibre cementitious materials. Sustainability, 18(8), 3942.
[4] Lee, S. J., Kim, T. Y., Kim, J., Yun, H. S. (2026) Digital twin-based wildfire simulation on a 1 m DEM and adaptive water-mist optimization for heritage protection: Bogwangsa Temple, South Korea. Sustainability, 18(8), 3835.
[5] Nie, Y., Wu, Z., Xing, Z., Luo, M. (2026) Digital twin for architectural heritage: a comprehensive conceptual framework integrating structural health, microclimate, and energy performance. Sustainability, 18(6), 3080.
[6] Ehtsham, M., Parisi, G., Pedone, F., Rossi, F., Zincani, M., Congiu, E., Marchionni, C. (2025) AI-powered advanced technologies for a sustainable built environment: a systematic review on emerging challenges. Sustainability, 17(17), 8005.
[7] Kaewunruen, S., Zhaochen, Z., Khongsomchit, L., Lin, Y. H., Ndlovu, N. T. (2026) BIM-driven digital twin for climate change adaptation and resilience of railway overhead line system. Sustainability, 18(4), 1909.
[8] Jiang, F., Xie, H., Gandla, S. R., Fei, S. (2025) Transforming hospital HVAC design with BIM and digital twins: Addressing real-time use changes. Sustainability, 17(8), 3312.
[9] Guo, H., Liu, X., Wang, C., Wang, F., Hui, C. (2026) A merging-assembly strategy for complex scenario-oriented digital twin modeling. Digital Engineering, 100117.
[10] Mansuri, L. E., Patel, D. A., Udeaja, C., Makore, B. C. N., Trillo, C., Awuah, K. G. B., Jha, K. N. (2022) A systematic mapping of BIM and digital technologies for architectural heritage. Smart and Sustainable Built Environment, 11(4), 1060-1080.
[11] Pan, X., Lin, Q., Ye, S., Li, L., Guo, L., Harmon, B. (2024) Deep learning based approaches from semantic point clouds to semantic BIM models for heritage digital twin. Heritage Science, 12(1), 1-17.
[12] Liu, Z., Brigham, R., Long, E. R., Wilson, L., Frost, A., Orr, S. A., Grau-Bové, J. (2022) Semantic segmentation and photogrammetry of crowdsourced images to monitor historic facades. Heritage Science, 10(1), 27.
[13] Hou, H., Lai, J. H., Wu, H., Wang, T. (2024) Digital twin application in heritage facilities management: systematic literature review and future development directions. Engineering, Construction and Architectural Management, 31(8), 3193-3221.
[14] Mazzetto, S. (2024) Integrating emerging technologies with digital twins for heritage building conservation: an interdisciplinary approach with expert insights and bibliometric analysis. Heritage, 7(11), 6432-6479.
[15] Li, Y., Cheng, H., Qin, Q. (2025) Evaluations and improvement methods of deep learning ability in blended learning. International Journal of e-Collaboration (IJeC), 21(1), 1-17.
Share and Cite
Li, W. (2026) Digital Twin and AI-driven Teaching Innovation for Lingnan Vernacular Dwellings Renewal: The “Smart Reform and Digital Transformation” Path of Industry-education Integration. Global Education Bulletin, 3(2), 10-22. https://doi.org/10.71052/grb2025/CCHX9285