Real-time intelligent evaluation and advanced prediction of surrounding rock integrity during mechanized drill-and-blast tunneling based on drilling parameters
CHEN Ziquan1, 2, WEI Fangming1, 2, HE Chuan1, 2*, LIN Nengduo1, 2, WANG Bo1, 2, YAO Renjie1, 2
(1. State Key Laboratory of Intelligent Geotechnics and Tunnelling, Southwest Jiaotong University, Chengdu, Sichuan 610031, China;
2. Key Laboratory of Transportation Tunnel Engineering of Ministry of Education, Southwest Jiaotong University,
Chengdu, Sichuan 610031, China)
Abstract：To address the challenges associated with accurately identifying the integrity of tunnel surrounding rock in complex geological environments—specifically issues of high difficulty, insufficient refinement, poor timeliness, and low accuracy of advanced predictions—a three-dimensional refined intelligent identification and dynamic advanced prediction method for assessing the fragmentation degree of tunnel surrounding rock in mechanized drilling and blasting construction has been developed. This method integrates drilling parameters collected by the rock drilling trolley with a deep learning algorithm model, focusing on the construction process：(1) The research findings indicate a significant correlation between drilling parameters and rock mass integrity. Utilizing this relationship, the proposed method for extracting the fluctuation features of drilling parameter data can effectively characterize the development of joints and fissures within the rock mass. Unlike traditional surface observation methods at the tunnel face, this approach employs a spatial interpolation technique for discrete borehole data, enabling a non-uniform, high-density characterization of the surrounding rock’s integrity within the three-dimensional spatial range of the excavation face. (2) Taking into account the spatial distribution characteristics and temporal variation features of the drilling parameters, an intelligent recognition method for the integrity of tunnel surrounding rock using the drilling and blasting technique was constructed based on an attention spatial-temporal fusion network model, achieving an accuracy rate of 91.38%. This represents an improvement of 19.58% compared to the LSTM model, transforming the recognition of rock mass integrity at the tunnel face from a superficial understanding to a “three-dimensional refined dynamic intelligent evaluation.” (3) Based on the spatial continuity and gradual change characteristics of the lithology through which long tunnels pass, an advanced prediction model for the integrity of surrounding rock is proposed, utilizing a bidirectional long short-term memory neural network (Bi-LSTM). This model dynamically predicts the integrity of surrounding rock in the next unexcavated cycle based on the variation patterns of surrounding rock information from the excavated section, achieving an accuracy rate of 88.75%. It provides effective support for evaluating surrounding rock quality, identifying stability, and making dynamic decisions regarding excavation and support in mechanized tunnel construction using the drilling and blasting method.
陈子全1，2，魏方铭1，2，何 川1，2*，林能多1，2，汪 波1，2，姚人杰1，2. 基于随钻参数的钻爆法隧道围岩完整程度智能判识与超前预测方法研究[J]. 岩石力学与工程学报, 2026, 45(8): 2437-2453.
CHEN Ziquan1, 2, WEI Fangming1, 2, HE Chuan1, 2*, LIN Nengduo1, 2, WANG Bo1, 2, YAO Renjie1, 2. Real-time intelligent evaluation and advanced prediction of surrounding rock integrity during mechanized drill-and-blast tunneling based on drilling parameters. , 2026, 45(8): 2437-2453.
[1] 白松松，周宗青，高成路，等. 钻爆法海底隧道穿越断层破碎带围岩稳定性综合分析与控制方法研究[J]. 岩石力学与工程学报，2025，44(3)：691–704.(BAI Songsong，ZHOU Zongqing，GAO Chenglu，et al. Research on comprehensive analysis and control method of surrounding rock stability in submarine tunnel crossing fault fracture zone by drilling and blasting method[J]. Chinese Journal of Rock Mechanics and Engineering，2025，44(3)：691–704.(in Chinese))
[2] 谢良涛，严 鹏，范 勇，等. 钻爆法与TBM开挖深部洞室诱发围岩应变能释放规律[J]. 岩石力学与工程学报，2015，34(9)：1 786– 1 795.(XIE Liangtao，YAN Peng，FAN Yong，et al. Releasing of strain energy induced by excavation using drilling and blasting method and TBM in deep tunnel[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(9)：1 786–1 795.(in Chinese))
[3] 查 浩，魏玉峰，李树武，等. 考虑轴向裂隙影响的岩体完整性计算模型[J]. 岩石力学与工程学报，2024，43(增2)：3 972–3 980. (ZHA Hao，WEI Yufeng，LI Shuwu，et al. A rock mass integrity calculation model considering the influence of axial cracks[J]. Chinese Journal of Rock Mechanics and Engineering，2024，43(Supp.2)：3 972–3 980.(in Chinese))
[4] 姬付全，梁晓腾，邱 敏，等. 利用随钻测量技术评估岩体结构形态[J]. 公路交通科技，2023，40(1)：144–151.(JI Fuquan,，LIANG Xiaoteng，QIU Min，et al. Evaluation on rock mass structure using MWD technology[J]. Journal of Highway and Transportation Research and Development，2023，40(1)：144–151.(in Chinese))
[5] 董家兴，刘梦飞，米 健，等. 砂化白云岩隧洞围岩结构面几何参数精准表征及工程地质特性评价[J]. 岩石力学与工程学报，2025，44(9)：2 292–2 304.(DONG Jiaxing，LIU Mengfei，MI Jian，et al. Precise characterization of geometric parameters of structural planes and engineering geological evaluation of surrounding rock in sandy dolomite tunnel[J]. Chinese Journal of Rock Mechanics and Engineering，2025，44(9)：2 292–2 304.(in Chinese))
[6] 葛云峰，夏 丁，唐辉明，等. 基于三维激光扫描技术的岩体结构面智能识别与信息提取[J]. 岩石力学与工程学报，2017，36(12)：3 050–3 061.(GE Yunfeng，XIA Ding，TANG Huiming，et al. Intelligent identification and extraction of geometric properties of rock discontinuities based on terrestrial laser scanning[J]. Chinese Journal of Rock Mechanics and Engineering，2017，36(12)：3 050–3 061.(in Chinese))
[7] 薛东杰，唐麒淳，王 傲，等. 基于FCN的岩石混凝土裂隙几何智能识别[J]. 岩石力学与工程学报，2019，38(增2)：3 393–3 403. (XUE Dongjie，TANG Qichun，WANG Ao，et al. FCN-based intelligent identification of crack geometry in rock or concrete[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(Supp.2)：3 393– 3 403.(in Chinese))
[8] 张运波，雷明锋，肖勇卓，等. 隧道掌子面节理卷积神经网络智能识别方法[J]. 中国公路学报，2024，37(7)：35–45.(ZHANG Yunbo，LEI Mingfeng，XIAO Yongzhuo，et al. Intelligent recognition method of tunnel face joints and fissures using convolutional neural network[J]. China Journal of Highway and Transport，2024，37(7)：35–45.(in Chinese))
[9] SANTOS AEM，LANA M S，PEREIRA T M. Evaluation of machine learning methods for rock mass classification[J]. Neural Computing and Application，2022，34(6)：4 633–4 642.
[10] MA J J，LI T B，MENG L B. A real-time intelligent classification model using machine learning for tunnel surrounding rock and its application[J]. Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards，2023，17(1)：146–168.
[11] ZHANG C H，WANG Y，WU L J，et al. Physics-informed and data-driven machine learning of rock mass classification using prior geological knowledge and TBM operational data[J]. Tunnelling and Underground Space Technology，2024，152：105923.
[12] 岳中琦. 钻孔过程监测(DPM)对工程岩体质量评价方法的完善与提升[J]. 岩石力学与工程学报，2014，33(10)：1 977–1 996.(YUE Zhongqi. Drilling process monitoring for refining and upgrading rock mass quality classification methods[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(10)：1 977–1 996.(in Chinese))
[13] 贾朝军，陈范雷，雷明锋，等. 基于数字钻进参数的岩石强度确定方法[J]. 西南交通大学学报，2025，60(3)：589–598.(JIA Chaojun，CHEN Fanlei，LEI Mingfeng，et al. Determination method of rock strength based on digital drilling parameters[J]. Journal of Southwest Jiaotong University，2025，60(3)：589–598.(in Chinese))
[14] WANG J，FANG Q，WANG G，et al. Attention-guided cascaded network for predicting tunnel surrounding rock properties using measurement-while-drilling data[J]. Automation in Construction，2025，177：106310.
[15] WANG J，FANG Q，WANG G，et al. Semi-supervised recognition of tunnel surrounding rock discontinuities using drilling jumbo data[J]. Automation in Construction，2024，166：105623.
[16] YI W H，WANG M N，XIA Q Y，et al. Rockburst prediction based on multi-featured drilling parameters and extreme tree algorithm for full-section excavated tunnel faces[J]. Journal of Rock Mechanics and Geotechnical Engineering，2025，17(1)：258–274.
[17] 亢金涛，许振浩，谢辉辉，等. 基于钻进数据定量解译的隧道围岩完整性评价[J]. 中南大学学报：自然科学版，2025，56(9)：3 820– 3 834.(KANG Jintao，XU Zhenhao，XIE Huihui，et al. Integrity evaluation of tunnel surrounding rock based on quantitative interpretation of drilling data[J]. Journal of Central South University：Science and Technology，2025，56(9)：3 820–3 834.(in Chinese))
[18] 梁 铭，彭 浩，解威威，等. 基于数字钻探与多尺度模型融合的隧道岩体完整性自动解译技术研究及应用[J]. 岩土工程学报，2024，46(2)：396–405.(LIANG Ming，PENG Hao，XIE Weiwei，et al. Application of automatic interpretation technology of tunnel rock mass integrity based on digital drilling and multi-scale model fusion[J]. Chinese Journal of Geotechnical Engineering，2024，46(2)：396–405.(in Chinese))
[19] 张幼振，张 宁，邵俊杰，等. 基于钻进参数聚类的含煤地层岩性模糊识别[J]. 煤炭学报，2019，44(8)：2 328–2 335.(ZHANG Youzhen，ZHANG Ning，SHAO Junjie，et al. Fuzzy identification of coal-bearing strata lithology based on drilling parameter clustering[J]. Journal of China Coal Society，2019，44(8)：2 328–2 335.(in Chinese))
[20] 陈万志，尹明悦，王天元. 基于生成对抗网络的流量异常检测方法[J]. 电子测量与仪器学报，2025，39(10)：165–175.(CHEN Wanzhi，YIN Mingyue，WANG Tianyuan. Traffic anomaly detection method based on generative adversarial networks[J]. Journal of Electronic Measurement and Instrumentation，2025，39(10)：165–175.(in Chinese))
[21] 李明超，符家科，张 野，等. 耦合岩石图像与锤击音频的岩性分类智能识别分析方法[J]. 岩石力学与工程学报，2020，39(5)：996–1 004.(LI Mingchao，FU Jiake，ZHANG Ye，et al. Intelligent recognition and analysis method of rock lithology classification based on coupled rock images and hammering audios[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(5)：996–1 004.(in Chinese))
[22] 曲麒霖，秘金钟，徐彦田，等. 基于监督聚类法的板块格网速度场构建方法研究[J]. 测绘科学，2024，49(12)：20–27.(QU Qilin，MI Jinzhong，XU Yantian，et al. Research on the construction method of plate grid velocity field based on supervised clustering method[J]. Science of Surveying and Mapping，2024，49(12)：20–27.(in Chinese))
[23] 易文豪，夏覃永，孙鸿强，等. 基于岩石可钻性指标的钻爆法隧道掌子面岩石坚硬程度智能判识[J]. 中国铁道科学，2025，46(2)：128–139.(YI Wenhao，XIA Qinyong，SUN Hongqiang，et al. Intelligent identification of rock hardness drillability index for drill-and-blast tunnel faces[J]. China Railway Science，2025，46(2)：128–139.(in Chinese))
[24] 邢保印，张炜怡，章广成，等. 基于变形速率分解的阶跃型滑坡预测——以呷爬滑坡为例[J]. 岩石力学与工程学报，2023，42(3)：685–697.(XING Baoyin，ZHANG Weiyi，ZHANG Guangcheng，et al. Prediction of step-type landslides based on deformation rate decomposition——A case study of Gapa landslide[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(3)：685–697.(in Chinese))
[25] 陈进帆，尚德磊，赵志宏，等. 基于机器学习的含充填裂隙岩样断裂行为预测方法[J]. 岩石力学与工程学报，2023，42(增1)：3 458–3 472.(CHEN Jinfan，SHANG Delei，ZHAO Zhihong，et al. Prediction method of fracture behaviors of rock samples with an infilled fracture based on machine learning[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(Supp.1)：3 458–3 472.(in Chinese))
[26] 张世殊，王 鹏，张 开，等. 基于全过程信息的多源数据融合隧道超前地质预报方法[J]. 岩石力学与工程学报，2025，44(4)：838–849.(ZHANG Shishu，WANG Peng，ZHANG Kai，et al. An advanced geological forecast method of tunnels based on multi-source data fusion of full-process information[J]. Chinese Journal of Rock Mechanics and Engineering，2025，44(4)：838–849.(in Chinese))
[27] 周 中，张俊杰，丁昊晖，等. 基于GA-Bi-LSTM的盾构隧道下穿既有隧道沉降预测模型[J]. 岩石力学与工程学报，2023，42(1)：224–234.(ZHOU Zhong，ZHANG Junjie，DING Haohui，et al. Settlement prediction model of shield tunnel under-crossing existing tunnel based on GA-Bi-LSTM[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(1)：224–234.(in Chinese))
2026, Vol. 45 
