多维数据驱动贝叶斯网络的隧道岩体强度预测方法研究

doi:10.3724/1000-6915.jrme.2025.0353

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (3929 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Accurate prediction of tunnel rock mass strength is essential for ensuring construction safety. This study introduces a Bayesian network (BN)-based method that leverages multidimensional data. First, an enhanced Swin-Transformer, integrated with UNets capability for small-scale feature extraction, achieves high-precision segmentation of apparent rock mass features (e.g., leakage and fractures), attaining an average accuracy of 89.3%, which surpasses conventional models. Subsequently, a multidimensional dataset is constructed by integrating apparent features, internal parameters, physical-mechanical properties, and design parameters. Test results indicate that the constructed Bayesian network achieves an accuracy of 89.6%, outperforming traditional machine learning, deep learning, and experience-driven Bayesian network methods. It maintains an accuracy of 82.3% on untrained samples, demonstrating exceptional generalization capabilities. Sensitivity analysis reveals that fracture and weathering parameters are the dominant factors influencing rock strength. The proposed framework facilitates interactive operation and allows for partial parameter input, thereby providing a practical tool for intelligent tunnel engineering.

Key words： rock mechanics rock strength multidimensional data-driven Bayesian network improved vision model drilling parameters SHAP sensitivity

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WU Chen1
	2
	HUANG Hongwei1*
	NI Yiqing2
	ZHOU Mingliang1

Cite this article:

WU Chen1,2,HUANG Hongwei1*, et al. A multidimensional data-driven Bayesian network approach for predicting tunnel rock mass strength[J]. , 2026, 45(5): 1321-1335.

URL:

https://rockmech.whrsm.ac.cn/EN/10.3724/1000-6915.jrme.2025.0353 OR https://rockmech.whrsm.ac.cn/EN/Y2026/V45/I5/1321

[1] ZHANG G H，YU J C，HAN Z Y，et al. A rock strength prediction model utilizing real-time data from percussion-rotary drilling measurements[J]. Rock Mechanics and Rock Engineering，2025，58(7)：7 783-7 803.
[2] XUE Y G，MA X M，QIU D H，et al. Analysis of the factors influencing the nonuniform deformation and a deformation prediction model of soft rock tunnels by data mining[J]. Tunnelling and Underground Space Technology，2021，109：103769.
[3] 孙欢，刘晓丽，王恩志，等. 基于X射线断层扫描预测岩石单轴抗压强度[J]. 岩石力学与工程学报，2019，38(增2)：3 575-3 582. (SUN Huan，LIU Xiaoli，WANG Enzhi，et al. Prediction of rock uniaxial compressive strength based on X-ray computed tomography[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(Supp.2) ：3 575-3 582.(in Chinese))
[4] FUKUI，K，OKUBO S，Some attempts for estimating rock strength and rock mass classification from cutting force and investigation of optimum operation of tunnel boring machines[J]. Rock Mechanics and Rock Engineering，2006，39(1)：25-44.
[5] 江桁，刘学增，朱合华. 基于隧道快速检测车数据的公路隧道衬砌开裂识别模型研究[J]. 现代隧道技术，2020，57(5)：61-65. (JIANG Heng，LIU Xuezeng，ZHU Hehua. Lining crack identification model for highway tunnels based on data from rapid inspection vehicles[J]. Modern Tunnelling Technology，2020，57(5)：61-65.(in Chinese))
[6] 陈湘生，曾仕琪，韩文龙，等. 机器学习方法在盾构隧道工程中的应用研究现状与展望[J]. 土木与环境工程学报，2024，46(1)：1-13. (CHEN Xiangsheng，ZENG Shiqi，HAN Wenlong，et al. Research status and prospects of machine learning applications in shield tunneling engineering[J]. Journal of Civil and Environmental Engineering，2024，46(1)：1-13.(in Chinese))
[7] 黄宏伟，李庆桐. 基于深度学习的盾构隧道渗漏水病害图像识   别[J]. 岩石力学与工程学报，2017，36(12)：2 897-2 906.(HUANG Hongwei，LI Qingtong. Image recognition of water leakage disease in shield tunnels based on deep learning[J]. Chinese Journal of Rock Mechanics and Engineering，2017，36(12)：2 897-2 906.(in Chinese))
[8] WU C，HUANG H W，ZHANG L，et al. Towards automated 3D evaluation of water leakage on a tunnel face via improved GAN and self-attention DL model[J]. Tunnelling and Underground Space Technology，2023，142：105432.
[9] 黄宏伟，陈佳耀. 基于机器视觉的隧道围岩智能识别分级与开挖安全风险研究[J]. 应用基础与工程科学学报，2023，31(6)：1 382- 1 409.(HUANG Hongwei，CHEN Jiayao. Research on intelligent recognition and classification of tunnel surrounding rock and excavation safety risk based on machine vision[J]. Journal of Basic Science and Engineering，2023，31(6)：1 382-1 409.(in Chinese))
[10] CHEN I H，HO S C，SU M B. Computer vision application programming for settlement monitoring in a drainage tunnel[J]. Automation in Construction，2020，110：103011.
[11] 周鸣亮，汪长松，黄宏伟，等. 融合机器视觉与性能分析的运营盾构隧道结构安全状态评价[J]. 应用基础与工程科学学报，2023， 31(6)：1 461-1 476.(ZHOU Mingliang，WANG Changsong，HUANG Hongwei，et al. Evaluation of structural safety state of operational shield tunnels integrating machine vision and performance analysis[J]. Journal of Basic Science and Engineering，2023，31(6)：1 461-1 476. (in Chinese))
[12] 何满潮，任富强，宫伟力，等. 基于双目立体视觉技术的岩爆碎屑弹射速度理论修正模型[J]. 岩石力学与工程学报，2017，36(10)：2 341-2 349.(HE Manchao，REN Fuqiang，GONG Weili，et al. Theoretical correction model for the ejection velocity of rockburst fragments based on binocular stereo vision technology[J]. Chinese Journal of Rock Mechanics and Engineering，2017，36(10)：2 341- 2 349.(in Chinese))
[13] HUANG H W，WU C，ZHOU M L，et al. Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network[J]. International Journal of Mining Science and Technology，2024，34(3)：323-337.
[14] WU C，HUANG H W，CHEN J Y，et al. A novel Tree-augmented Bayesian network for predicting rock weathering degree using incomplete dataset[J]. International Journal of Rock Mechanics and Mining Sciences，2024，183：105933.
[15] 吕擎峰，李钰，牛荣，等. 基于深度学习的特殊岩土隧道围岩变形预测研究[J]. 应用基础与工程科学学报，2023，31(6)：1 590-   1 600.(LV Qingfeng，LI Yu，NIU Rong，et al. Research on deformation prediction of surrounding rock in special rock and soil tunnels based on deep learning[J]. Journal of Basic Science and Engineering，2023，31(6)：1 590-1 600.(in Chinese))
[16] 周轮，李术才，许振浩，等. 隧道综合超前地质预报技术及其工程应用[J]. 山东大学学报：工学版，2017，47(2)：55-62.(ZHOU Lun，LI Shucai，XU Zhenhao，et al. Comprehensive advanced geological prediction technology for tunnels and its engineering applications[J]. Journal of Shandong University：Engineering Science，2017，47(2)：55-62.(in Chinese))
[17] 汪进超，韩增强，王益腾，等. 基于像素空间信息的孔内低照度图像孔隙结构量化方法研究[J]. 岩石力学与工程学报，2024，43(增1)： 175-186.(WANG Jinchao，HAN Zengqiang，WANG Yiteng，et al. Research on a quantitative method for pore structure in low-illumination images within boreholes based on pixel spatial information[J]. Chinese Journal of Rock Mechanics and Engineering，2024，43(Supp.1)：175-186.(in Chinese))
[18] 宋宇飞，曹琰波，范文，等. 基于贝叶斯方法的降雨诱发滑坡概率型预警模型研究[J]. 岩石力学与工程学报，2023，42(3)：558-574.(SONG Yufei，CAO Yanbo，FAN Wen，et al. Research on a probabilistic early warning model for rainfall-induced landslides based on the Bayesian method[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(3)：558-574.(in Chinese))
[19] 卢鑫月，许成顺，侯本伟，等. 基于动态贝叶斯网络的地铁隧道施工风险评估[J]. 岩土工程学报，2022，44(3)：492-501.(LU Xinyue，XU Chengshun，HOU Benwei，et al. Risk assessment of subway tunnel construction based on dynamic Bayesian network[J]. Chinese Journal of Geotechnical Engineering，2022，44(3)：492-501.(in Chinese))
[20] ZHOU Z，RAHMAN M M，TAJBAKHSH N，et al. Unet++：A nested u-net architecture for medical image segmentation[C]// International workshop on deep learning in medical image analysis. Cham：Springer International Publishing，2018：3-11.
[21] LIU Z，LIN Y，CAO Y，et al. Swin transformer：hierarchical vision transformer using shifted windows[C]// IEEE/CVF// International Conference on Computer Vision (ICCV). [S. l.]：[s. n.]，2021：9 992-10 002.
[22] MENG Z，ZHANG Z，GUO D，et al. Defocused calibration for large field-of-view binocular cameras[J]. Automation in Construction，2023，147：104737.
[23] ZHOU Z，ZHANG J，GONG C，Hybrid semantic segmentation for tunnel lining cracks based on Swin Transformer and convolutional neural network[J]. Computer‐Aided Civil and Infrastructure Engineering，2023，38(17)： 2 491-2 510.
[24] CHEN J Y，YANG T J，ZHANG D M，et al. Deep learning based classification of rock structure of tunnel face[J]. Geoscience Frontiers，2021，12(1)：395-404.
[25] DONG R，PAN X，LI F，DenseU-Net-Based semantic segmentation of small objects in urban remote sensing images[J]. IEEE Access，2019，7：65 347-65 356.
[26] HE X，ZHOU Y，ZHAO J，et al. Swin transformer embedding UNet for remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing，2022，60：1-15.
[27] 陈贺，付有旺. 贡山县进藏通道群发性滑坡地质特征与降雨阈值[J]. 岩石力学与工程学报，2025，43(增2)：3 861-3 871.(CHEN He，FU Youwang. Geological characteristics and rainfall thresholds of group-occurring landslides along the passage to Xizang in Gongshan County[J]. Chinese Journal of Rock Mechanics and Engineering，2025，43(Supp.2)：3 861-3 871.(in Chinese))
[28] WU C，HUANG H W，ZHANG L，et al. Towards automated 3D evaluation of water leakage on a tunnel face via improved GAN and self-attention DL model[J]. Tunnelling and Underground Space Technology，2023，142：105432.
[29] 马聪，李彦峰，王国辉，等. 基于贝叶斯网络的隧道围岩质量概率预测方法[J]. 自然科学报告，2022，12(1)：15 188.(MA Cong，LI Yanfeng，WANG Guohui，et al. A probability prediction method for classification of surrounding rock quality based on Bayesian network[J]. Scientific Reports，2022，12(1)：15 188.(in Chinese))
[30] 魏建新，王国荣，张良，等. 随机裂隙组合条件下岩体强度参数的研究[J]. 机械工程进展，2018，10(6)：1-13.(WEI Jianxin，WANG Guorong，ZHANG Liang，et al. Study on rock strength parameters with stochastic combination discontinuities[J]. Advances in Mechanical Engineering，2018，10(6)：1-13.(in Chinese))
[31] COOPER G F，HERSKOVITS E，A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning，1992，9(4)：309-347.
[32] MA J J，LI T B，LI X，et al. A probability prediction method for the classification of surrounding rock quality of tunnels with incomplete data using Bayesian networks[J]. Tunnelling and Underground Space Technology，2021，112：103893.
[33] WU C，HUANG H W，CHEN J Y，et al. A novel Tree-augmented Bayesian network for predicting rock weathering degree using incomplete dataset[J]. Engineering Geology，2023，325：107278.
[34] 吴亮，李健，马丹，等. 基于集成学习与贝叶斯优化的岩石抗压强度预测[J]. 地球科学，2023，48(5)：1 686-1 695.(WU Liang，LI Jian，MA Dan，et al. Prediction for rock compressive strength based on ensemble learning and Bayesian optimization[J]. Earth Science：Journal of China University of Geosciences，2023，48(5)：1 686- 1 695. (in Chinese))
[35] 姜鹏飞，张炜，陈志良，等. 钻锚一体化锚杆随钻测量岩石强度试验研究[J]. 采矿与岩层控制工程学报，2025，7(1)：013041. (JIANG Pengfei，ZHANG Wei，CHEN Zhiliang，et al. Experimental study on in-drill measurement of rock strength using integrated drilling-bolt system[J]. Journal of Mining and Strata Control Engineering，2025，7(1)：013041.(in Chinese))
[36] 赵志强，王箫鹤，武璟. 基于随钻数据的岩体强度预测模型及其适配性评价[J]. 煤炭学报，2025，50(10)：4 743-4 758.(ZHAO Zhiqiang，WANG Xiaohe，WU Jing. Rock mass strength prediction model and its adaptability evaluation based on while-drilling data[J]. Journal of China Coal Society，2025，50(10)：4 743-4 758.(in Chinese))
[37] 赵杰，王强，杨帆，等. 基于岩屑升尺度理论的岩石强度预测方法研究[J]. 岩石力学与工程学报，2025，44(6)：1 527-1 538. (ZHAO Jie，WANG Qiang，YANG Fan，et al. A rock strength prediction method based on rock-cuttings upscaling theory[J]. Chinese Journal of Rock Mechanics and Engineering，2025，44(6)：1 527-   1 538.(in Chinese))