Dr. Zijian Wang
PhD, MSc, MEng, BEng
Independent Postdoctoral Researcher
zijian.wang(at)tum.de
About Zijian:
Dr. Zijian Wang is an independent postdoctoral researcher at the TUM Georg Nemetschek Institute (TUM GNI). He obtained his PhD from Technion – Israel Institute of Technology as a Marie Curie Early-Stage Researcher in the Cloud BIM (CBIM) project, funded by the EU Horizon 2020 program (November 2020 – January 2024). He worked under the supervision of Prof. Rafael Sacks. Before that, he completed a master’s degree in Computer and Machine Vision at Cranfield University (2019–2020) and a second master’s in Civil Engineering at Central South University. He received his bachelor’s degree in Civil Engineering from Chongqing Jiaotong University (2014–2018). He has also visited the University of Cambridge as a researcher (2022) and worked at Trimble Finland (2023).
As an interdisciplinary researcher with expertise in both civil engineering and machine learning, he is dedicated to advancing digitalization in the construction industry through the application of advanced computer science techniques. He has participated in and conducted several research projects related to AI in construction, such as detecting personal protective equipment by deep learning, tunnel temperature data mining, BIM semantic enrichment by graph neural networks, and more.
At TUM GNI, Dr. Wang is focused on the proposed research: Building Information Graphs (BIGs). This aims to adopt graphs as an alternative information modeling method to support graph learning and graph applications. Graphs inherently capture relationships explicitly between objects, enabling a more detailed, object-level data representation. Graphs are also flexible in representing and embedding multi-modal data in a machine-accessible format, enabling computational learning. By transforming design information into graphs, BIGs could enable a variety of innovative graph applications that current BIM technologies struggle to support, such as multidisciplinary change propagation, automated consistency maintenance, object-based version control, and more. This approach has the potential to foster a more collaborative, intelligent, and generative future in design.
Selected Journal Articles
Wang, Z.*, Ouyang, B. and Sacks, R., 2023. Graph-based inter-domain consistency maintenance for BIM models. Automation in Construction, 154, p.104979. https://doi.org/10.1016/j.autcon.2023.104979
Sacks, R.*, Wang Z., Ouyang, B., Utkucu D. and Chen S., 2022. Toward artificially intelligent cloud-based building information modeling for collaborative multidisciplinary design. Advanced Engineering Informatics, 53, p.101711. https://doi.org/10.1016/j.aei.2022.101711
Wang, Z.*, Sacks, R. and Yeung, T., 2021. Exploring graph neural networks for semantic enrichment: Room type classification. Automation in Construction, 134, p.104039. https://doi.org/10.1016/j.autcon.2021.104039
Wang, Z.*, Sacks, R., Ouyang, B., Ying, H. and Borrmann, A., 2024. A Framework for Generic Semantic Enrichment of BIM Models. Journal of Computing in Civil Engineering, 38(1), p.04023038. https://doi.org/10.1061/JCCEE5.CPENG-5487
Wang, Z., Cai, Z. and Wu, Y.*, 2023. An improved YOLOX approach for low-light and small object detection: PPE on tunnel construction sites. Journal of Computational Design and Engineering, 10(3), pp.1158-1175. https://doi.org/10.1093/jcde/qwad042
Wang, Z., Wu, Y., Yang, L., Thirunavukarasu, A., Evison, C. and Zhao, Y.*, 2021. Fast personal protective equipment detection for real construction sites using deep learning approaches. Sensors, 21(10), p.3478. https://doi.org/10.3390/s21103478
Utkucu, D., Ying, H., Wang, Z. and Sacks, R., 2024. Classification of architectural and MEP BIM objects for building performance evaluation. Advanced Engineering Informatics, 61, p.102503. https://doi.org/10.1016/j.aei.2024.102503
Conference Articles
Wang, Z.*, Ying, H. and Sacks, R., Two Fundamental Questions Concerning BIM Data Representation for Machine Learning. In CIB W78 2024. https://itc.scix.net/pdfs/w78-2024-paper_25.pdf
Wang, Z.*, Ying, H., Sacks, R. and Borrmann, A., 2023. CBIM: A graph-based approach to enhance interoperability using semantic enrichment. In EG-ICE 2023. https://www.ucl.ac.uk/bartlett/construction/sites/bartlett_construction/files/1339.pdf
Wang, Z.*, Ouyang, B. and Sacks, R., 2023. CBIM: object-level cloud collaboration platform for supporting across-domain asynchronous design. In EC3 Conference 2023 (pp. 117-124). 10.35490/EC3.2023.189
Ouyang, B., Wang Z.* and Sacks, R., 2022. Semantic enrichment of object associations across federated BIM semantic graphs in a common data environment. In ECPPM 2022 (pp. 591-598). https://doi.org/10.1201/9781003354222
Wang, Z., Yeung, T., Sacks, R.* and Su, Z., 2021. Room type classification for semantic enrichment of building information modeling using graph neural networks. In Proc. of the Conference CIB W78 (Vol. 2021, pp. 11-15) https://cbim2020.net.technion.ac.il/files/2021/10/w78-2021-paper-077.pdf
Awards
- Thorpe Medal, European Council on Computing in Construction (EC3) (2023)
- Eastman Best Ph.D. Paper, Int Joint Conference CIB W78 - LDAC (2021)