Geological Feature-Guided Fusion of Multi-Source Probing Information for Rock-Mass Integrity Prediction
-
摘要: 在深部地质工程中，准确预报岩体完整性，感知前方地质环境，对于保障施工过程的安全与效率具有重要的指导意义，多源探测手段获取的结论因机理差异、噪声干扰等多种原因，容易出现冲突矛盾，难以有效进行融合. 提出基于地质特征引导多源探测信息融合的岩体完整性预报方法，以地质特征作为引导，引入交叉注意力机制，依据实际地质环境自适应调整各探测结论贡献度，实现多源探测结论的冲突消解，获取岩体完整性融合预报结论. 并将此融合预报方法应用于实际深部隧道工程中，与其他几种常用方法相比，能够实现对前方岩体完整性准确的预报，且所得结果具有较强的可解释性.Abstract: In deep geological engineering, accurate prediction of rock-mass integrity and sensing of geological conditions ahead are important for construction safety and efficiency. However, conclusions from multiple probing methods often conflict due to differences in sensing mechanisms, noise interference, and other factors, making effective fusion difficult. This paper proposes a geology-guided fusion method for rock-mass integrity prediction using multi-source probing information. Geological features serve as guidance, and a cross-attention mechanism adaptively adjusts the contribution of each probing conclusion under actual geological conditions, thereby resolving conflicts among multi-source results and generating a fused integrity prediction. Applied to a real deep tunnel project, the proposed method outperforms several commonly used methods in prediction accuracy and yields highly interpretable results.
-
图 2 岩体完整性融合预报结果对比图
Fig. 2. Comparative results of rock mass integrity fusion prediction
图 3 不同方法的混淆矩阵对比
a. 所提方法；b. 层次分析；c. 随机森林；d. 支持向量回归；e. 极限学习机
Fig. 3. Comparison of confusion matrices for different methods
表 1 各方法的性能指标对比
Table 1. Performance metrics comparison for the methods
方法 准确率 精确度 召回率 F1值 所提方法 0.757 0.741 0.792 0.740 层次分析 0.730 0.674 0.680 0.677 随机森林 0.667 0.620 0.636 0.622 支持向量回归 0.667 0.620 0.636 0.622 极限学习机 0.640 0.529 0.524 0.522 
下载: 导出CSV
-
Cai, W., Dou, L. M., Zhang, M., et al., 2018. A Fuzzy Comprehensive Evaluation Methodology for Rock Burst Forecasting Using Microseismic Monitoring. Tunnelling and Underground Space Technology, 80: 232-245. https://doi.org/10.1016/j.tust.2018.06.029 Cao, W. H., Xu, J. P., Liu, Z. T., 2017. Speaker-Independent Speech Emotion Recognition Based on Random Forest FeatureSelection Algorithm, Proceedings of the 36th Chinese Control Conference (CCC), 10995-10998. doi: 10.23919/ChiCC.2017.8029112 Chang, X. Y., Fan, H. Y., Fu, Y. G., et al., 2026. A Transformer-Based Surrogate Modeling Strategy for Tunnel Digital Twin in Full-Field Displacement Prediction under Adjacent Tunnel Construction. Advanced Engineering Informatics, 69: 104045. https://doi.org/10.1016/j.aei.2025.104045 Dong, F. R., Wang, S. H., Yang, Y., et al., 2025. Research on Dynamic Fuzzy Prediction Method for Surrounding Rock Stability of Mountain Tunnels Throughout the Construction Period. Tunnelling and Underground Space Technology, 158: 106390. https://doi.org/10.1016/j.tust.2025.106390 Esmailzadeh, A., Mikaeil, R., Shafei, E. F., et al., 2018. Prediction of Rock Mass Rating Using TSP Method and Statistical Analysis in Semnan Rooziyeh Spring Conveyance Tunnel. Tunnelling and Underground Space Technology, 79: 224-230. https://doi.org/10.1016/j.tust.2018.05.001 Ghosh, N., Santoni, D., Saha, I., et al., 2025. A Review on the Applications of Transformer-Based Language Models for Nucleotide Sequence Analysis. Computational and Structural Biotechnology Journal, 27: 1244-1254. https://doi.org/10.1016/j.csbj.2025.03.024 Guo, K., Zhang, L. M., 2021. Multi-Source Information Fusion for Safety Risk Assessment in Underground Tunnels. Knowledge-Based Systems, 227: 107210. https://doi.org/10.1016/j.knosys.2021.107210 Han, S. C., Li, Z. L., Zhou, Z. L., et al., 2025. Research on Real-Time Prediction Method of Surrounding Rock Classification of TBM Tunnel Based on Stacked Ensemble Classifier. Tunnelling and Underground Space Technology, 166: 107025. https://doi.org/10.1016/j.tust.2025.107025 Huang, Z. Q., Huang, Z., An, P. T., et al., 2024. Reconstruction and Prediction of Tunnel Surrounding Rock Deformation Data Based on PSO Optimized LSSVR and GPR Models. Results in Engineering, 24: 103445. https://doi.org/10.1016/j.rineng.2024.103445 Islam, S., Elmekki, H., Elsebai, A., et al., 2024. A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks. Expert Systems with Applications, 241: 122666. https://doi.org/10.1016/j.eswa.2023.122666 Jiang, J. L., Hu, G., Sheng, G. L., et al., 2026. PSG-MCANet: Multi-Order Cross-Attention Modeling for Multimodal Fusion Based on Punning Semantic Guidance. Pattern Recognition, 172: 112723. https://doi.org/10.1016/j.patcog.2025.112723 Li, R., Yan, J. L., He, Y. J., et al., 2025. Real-Time and Explainable Rock Mass Classification under Imbalanced Tunnel Boring Machine Data Using Hybrid Resampling and Ensemble Learning. Engineering Applications of Artificial Intelligence, 162: 112641. https://doi.org/10.1016/j.engappai.2025.112641 Li, S. C., Liu, B., Xu, X. J., et al., 2017. An Overview of Ahead Geological Prospecting in Tunneling. Tunnelling and Underground Space Technology, 63: 69-94. https://doi.org/10.1016/j.tust.2016.12.011 Li, S. C., Liu, C., Zhou, Z. Q., et al., 2021. Multi-Sources Information Fusion Analysis of Water Inrush Disaster in Tunnels Based on Improved Theory of Evidence. Tunnelling and Underground Space Technology, 113: 103948. https://doi.org/10.1016/j.tust.2021.103948 Li, S. C., Zhou, Z. Q., Ye, Z. H., et al., 2015. Comprehensive Geophysical Prediction and Treatment Measures of Karst Caves in Deep Buried Tunnel. Journal of Applied Geophysics, 116: 247-257. https://doi.org/10.1016/j.jappgeo.2015.03.019 Li, S. C., Liu, B., Sun, H. F., et al., 2014. State of Art and Trends of Advanced Geological Prediction in Tunnel Construction. Chinese Journal of Rock Mechanics and Engineering, 33(6): 1090-1113(in Chinese with English abstract). Liu, Z. B., Li, L., Fang, X. L., et al., 2021. Hard-Rock Tunnel Lithology Prediction with TBM Construction Big Data Using a Global-Attention-Mechanism-Based LSTM Network. Automation in Construction, 125: 103647. https://doi.org/10.1016/j.autcon.2021.103647 Ma, J. J., Ma, C. C., Li, T. B., et al., 2024. Real-Time Classification Model for Tunnel Surrounding Rocks Based on High-Resolution Neural Network and Structure-Optimizer Hyperparameter Optimization. Computers and Geotechnics, 168: 106155. https://doi.org/10.1016/j.compgeo.2024.106155 Mahmoodzadeh, A., Mohammadi, M., Daraei, A., et al., 2020. Decision-Making in Tunneling Using Artificial Intelligence Tools. Tunnelling and Underground Space Technology, 103: 103514. https://doi.org/10.1016/j.tust.2020.103514 Pereira, T. O., Abbasi, M., Arrais, J. P., 2025. ABIET: an Explainable Transformer for Identifying Functional Groups in Biological Active Molecules. Computers in Biology and Medicine, 187: 109740. https://doi.org/10.1016/j.compbiomed.2025.109740 Qiu, W. X., Xu, S. X., Cai, J. H., et al., 2024. A Method for Assessing Probability of Tunnel Collapse Based on Artificial Intelligence Deformation Prediction. Earth Science, 49(11): 4204-4215(in Chinese with English abstract). Shi, S. S., Li, S. C., Li, L. P., et al., 2014. Advance Optimized Classification and Application of Surrounding Rock Based on Fuzzy Analytic Hierarchy Process and Tunnel Seismic Prediction. Automation in Construction, 37: 217-222. https://doi.org/10.1016/j.autcon.2013.08.019 Sun, H. Y., Sheng, L. Y., Dai, Y. M., et al., 2025.3D Geological Modeling of Tunnel Alignment in the Complex Mountainous Region of Yongshan, China, Based on Multisource Data Fusion. Engineering Geology, 354: 108209. https://doi.org/10.1016/j.enggeo.2025.108209 Wang, J., Fang, Q., Wang, G., et al., 2024. Semi-Supervised Recognition of Tunnel Surrounding Rock Discontinuities Using Drilling Jumbo Data. Automation in Construction, 166: 105623. https://doi.org/10.1016/j.autcon.2024.105623 Wu, X. G., Feng, Z. B., Yang, S., et al., 2024. Safety Risk Perception and Control of Water Inrush during Tunnel Excavation in Karst Areas: an Improved Uncertain Information Fusion Method. Automation in Construction, 163: 105421. https://doi.org/10.1016/j.autcon.2024.105421 Yadav, V., Kainthola, A., 2025. Comparative Study of Predicted and Actual Rock Mass Condition in Himalayan Railway Tunnels. Physics and Chemistry of the Earth, Parts A/B/C, 140: 104026. https://doi.org/10.1016/j.pce.2025.104026. Yan, X. H., Guo, C. B., Liu, Z. B., et al., 2022. Physical Simulation Experiment of Granite Rockburst in a Deep-Buried Tunnel in Kangding County, Sichuan Province, China. Earth Science, 47(6): 2081-2093(in Chinese with English abstract). Yin, X., Cheng, S. Y., Yu, H. G., et al., 2024. Probabilistic Assessment of Rockburst Risk in TBM-Excavated Tunnels with Multi-Source Data Fusion. Tunnelling and Underground Space Technology, 152: 105915. https://doi.org/10.1016/j.tust.2024.105915 Zheng, X. Q., Peng, B., Xue, A. K., et al., 2025. Self-Attention Based Difference Long Short-Term Memory Network for Industrial Data-Driven Modeling. Chemometrics and Intelligent Laboratory Systems, 267: 105535. https://doi.org/10.1016/j.chemolab.2025.105535 李术才, 刘斌, 孙怀凤, 等, 2014. 隧道施工超前地质预报研究现状及发展趋势. 岩石力学与工程学报, 33(6): 1090-1113. 吴波, 丘伟兴, 徐世祥, 等, 2024. 基于人工智能变形预测隧道坍塌失效概率评估方法. 地球科学, 49(11): 4204-4215. doi: 10.3799/dqkx.2022.147 严孝海, 郭长宝, 刘造保, 等, 2022. 四川康定某深埋隧道花岗岩岩爆物理模拟实验研究. 地球科学, 47(6): 2081-2093. -
点击查看大图
图(3) / 表(1)
计量
- 文章访问数: 197
- HTML全文浏览量: 34
- PDF下载量: 26
- 被引次数: 0
