ZHU Qing,YU Jun,WU Tingchen,et al.A Knowledge-Graph Construction Method for TBM Tunnel Collapse Risk Based on the Synergy Between Construction Data and Expert Knowledge[J].Journal of Geomatics,2026,51(5):1-8
ZHU Qing,YU Jun,WU Tingchen,et al.A Knowledge-Graph Construction Method for TBM Tunnel Collapse Risk Based on the Synergy Between Construction Data and Expert Knowledge[J].Journal of Geomatics,2026,51(5):1-8DOI: 10.14188/j.2095-6045.20260062.
A Knowledge-Graph Construction Method for TBM Tunnel Collapse Risk Based on the Synergy Between Construction Data and Expert Knowledge
During TBM tunnel construction, collapse risk continuously evolves as a result of interactions between surrounding rock conditions and tunneling behaviors. Existing knowledge modeling approaches mainly rely on static textual semantics or empirical rules, making it difficult to capture the dynamic risk variations revealed by construction monitoring data, which in turn limits the timeliness and accuracy of risk assessment. To address this issue, this study proposes a TBM surrounding-rock collapse risk knowledge graph construction method that integrates expert knowledge with construction monitoring data. First, an ontology of collapse-risk elements is developed based on literature review and engineering expertise, providing a unified semantic model for geological conditions, TBM tunneling response states, risk events, and their relationships. Second, using tunneling segments as the fundamental spatiotemporal unit, segment-level statistical features are extracted from monitoring data such as advance rate, cutterhead torque, and thrust. An interpretable decision tree model is then employed to learn high-risk split thresholds, semantically mapping continuous numerical features into instances of TBM tunneling response states, thereby enabling an explainable transformation from monitoring data to graph semantics. Finally, under the constraints of the ontology, segment-wise knowledge triples of “geological condition-TBM response state-risk event” are organized and stored in a graph database to form the collapse risk knowledge graph. A typical TBM tunnel case demonstrates that the constructed knowledge graph can systematically organize the associations between adverse geological conditions (e.g., fault-fractured zones and water inrush) and abnormal TBM response states, enabling structured representation of the collapse-risk evolution process and supporting segment-scale risk assessment as well as retrospective analysis of risk evolution.
Yang Jun , Qiao Linke , Li Changjiang , et al . Risk Assessment of Shield Tunnel Collapse Accident Based on Fuzzy Analytic Hierarchy Process [J]. Sādhanā , 2024 , 49 ( 2 ): 174
Li Li , Ni Bo , Zhang Shixin , et al . Tunnel Collapse Risk Assessment Based on Improved Quantitative Theory III and EW-AHP Coupling Weight [J]. Scientific Reports , 2022 , 12 : 16054
Li Jinhui , Guo Dong , Chen Zuyu , et al . Transfer Learning for Collapse Warning in TBM Tunneling Using Databases in China [J]. Computers and Geotechnics , 2024 , 166 : 105968
Wu Zhijun , Wei Rulei , Chu Zhaofei , et al . Real-Time Rock Mass Condition Prediction with TBM Tunneling Big Data Using a Novel Rock—Machine Mutual Feedback Perception Method [J]. Journal of Rock Mechanics and Geotechnical Engineering , 2021 , 13 ( 6 ): 1 311 - 1 325
Guo Dong , Li Jinhui , Li Xu , et al . Advance Prediction of Collapse for TBM Tunneling Using Deep Learning Method [J]. Engineering Geology , 2022 , 299 : 106556
Wang Shuangjing , Wang Lechen , Wu Leijie , et al . A Jamming Risk Warning Model for TBM Tunnelling Based on Bayesian Statistical Methods [J]. Scientific Reports , 2025 , 15 : 35452
Ji Shaoxiong , Pan Shirui , Cambria E , et al . A Survey on Knowledge Graphs: Representation, Acquisition, and Applications [J]. IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 2 ): 494 - 514
Isah M A , Kim B S . Question-Answering System Powered by Knowledge Graph and Generative Pretrained Transformer to Support Risk Identification in Tunnel Projects [J]. Journal of Construction Engineering and Management , 2025 , 151 : 04024193
Mequanenit A M , Nibret E A , Herrero-Martín P , et al . A Deep Reinforcement Learning-Enhanced Multi-agent System for Ontology—Based Health Management in Nanotechnology [J]. Electronics , 2025 , 14 ( 23 ): 4580
Li Xuewei , Li Shuchen , Yuan Jingfeng , et al . A Data-Driven and Knowledge Graph-Based Research on Safety Risk-Coupled Evolution Analysis and Assessment in Shield Tunneling [J]. Tunnelling and Underground Space Technology , 2025 , 162 : 106657
Xie Weiqiang , Liu Xiaoli , Qian Ruipeng , et al . Development of a Novel TBM Tunnelling Test Platform and Its Application in Rock-Machine Interaction Analysis [J]. Rock Mechanics and Rock Engineering , 2025 , 58 ( 1 ): 867 - 885
Xue Y D , Hou Y C . An Ontology of Risk Management for Tunnel Construction [C]. The 58th U.S. Rock Mechanics/Geomechanics Symposium , Golden, Colorado, USA , 2024
Liu Ping , Jin Xueqiang , Shang Yongtao . Ontology-Based Automated Knowledge Identification of Safety Risks in Metro Shield Construction [J]. Journal of Asian Architecture and Building Engineering , 2026 , 25 ( 2 ): 1 295 - 1 324
Zheng Lifeng , Xiao Haohan , Nie Ding . Data Preprocessing and Excavation Process Analysis Based on Multi TBM Tunnel Project [C]// The 2024 International Conference on Smart City and Information System , Kuala Lumpur Malaysia : ACM , 2024 : 367 - 370
Chen Chao , Lu Yanyun , Wu Bo , et al . Digital Twin-Based and Knowledge Graph-Enhanced Emergency Response in Urban Infrastructure Construction [J]. Applied Sciences , 2025 , 15 ( 11 ): 6009
Xu Zhenhao , Wang Zhaoyang , Li Shucai , et al . GeoPredict-LLM: Intelligent Tunnel Advanced Geological Prediction by Reprogramming Large Language Models [J]. Intelligent Geoengineering , 2024 , 1 ( 1 ): 49 - 57
Salimi A , Faradonbeh R S , Monjezi M , et al . TBM Performance Estimation Using a Classification and Regression Tree (CART) Technique [J]. Bulletin of Engineering Geology and the Environment , 2018 , 77 ( 1 ): 429 - 440
Yang Y , Choi H , Yeom Y , et al . Data-Augmented Machine Learning for Risk Management of Tunnel Boring Machine Jamming Considering Coupled Geological Factors [J]. Computer-Aided Civil and Infrastructure Engineering , 2025 , 40 ( 27 ): 5 010 - 5 026
Gan Binlin , Zhang Dongmei , Huang Zhongkai , et al . Ontology-Driven Knowledge Graph for Decision-Making in Resilience Enhancement of Underground Structures: Framework and Application [J]. Tunnelling and Underground Space Technology , 2025 , 163 : 106739
Pan Shirui , Luo Linhao , Wang Yufei , et al . Unifying Large Language Models and Knowledge Graphs: A Roadmap [J]. IEEE Transactions on Knowledge and Data Engineering , 2024 , 36 ( 7 ): 3 580 - 3 599
Lin L S , Hu J R , Zhong Z , et al . A Hybrid Data Mining Method for Tunnel Engineering Based on Real-Time Monitoring Data From Tunnel Boring Machines [J]. IEEE Access , 2020 , 8 : 90 430 - 90 449
Ling Jiaxin , Li Xiaojun , Li Haijiang , et al . Hybrid NLP-Based Extraction Method to Develop a Knowledge graph for Rock Tunnel Support Design [J]. Advanced Engineering Informatics , 2024 , 62 ( Part B ): 102725