Time-series prediction and application of surrounding rock deformation during TBM excavation in hard rock tunnels
SHAO Zeyu1, ZHANG Dengke1, MA Hongsu2, WANG Bo1, LU Hui3, ZHOU Yuansheng1, ZHOU Zheng1, PU Shikun1, LI Erbing1*
(1. State Key Laboratory of Disaster Prevention and Mitigation of Explosion and Impact, Army Engineering University of PLA, Nanjing, Jiangsu 210007, China; 2. Beijing Research Institute of Uranium Geology, Beijing 100029, China; 3. College of Field Engineering, Army Engineering University of PLA, Nanjing, Jiangsu 210007, China)
Abstract：To evaluate the stability and long-term structural safety of hard rock roadways, this study analyzes the long-term deformation characteristics of surrounding rock induced by TBM excavation and performs high-precision trend predictions. However, traditional prediction methods are often impeded by idealized assumptions and the limitations inherent in single-model frameworks, thereby failing to achieve the high-precision predictions required for surrounding rock deformation under hard rock field conditions. Using the TBM excavation project at the －280 m experimental level of the Beishan underground research laboratory in China as a case study, this research employed real-time in-situ deformation data captured by an embedded multipoint displacement meter system to construct a hybrid prediction model, termed CPO-CLA. This model integrates the crested porcupine optimizer (CPO), convolutional neural network (CNN), long short-term memory (LSTM), and Attention mechanism, utilizing the monitoring data to conduct precise predictions of the long-term deformation of tunnel surrounding rock. The results indicate that during TBM excavation, the internal displacement of the surrounding rock undergoes two distinct phases: an excavation phase and a stable convergence phase, with the maximum cumulative displacement reaching 0.359 8 mm. The CPO-CLA model exhibited superior predictive performance in TBM hard rock tunnel engineering, achieving a mean coefficient of determination R2 of 0.953 on the test set, thereby validating its effectiveness. Comparative analysis against various mainstream meta-heuristic algorithms reveals that the CPO algorithm significantly outperforms them in terms of convergence speed, computational efficiency, and optimization accuracy.
邵泽宇1，张登科1，马洪素2，王 波1，卢 辉3，周元胜1，周 政1，濮仕坤1，李二兵1*. 硬岩巷道TBM开挖围岩时序变形预测与应用研究[J]. 岩石力学与工程学报, 2026, 45(9): 2717-2730.
SHAO Zeyu1, ZHANG Dengke1, MA Hongsu2, WANG Bo1, LU Hui3, ZHOU Yuansheng1, ZHOU Zheng1, PU Shikun1, LI Erbing1*. Time-series prediction and application of surrounding rock deformation during TBM excavation in hard rock tunnels. , 2026, 45(9): 2717-2730.
[1] 赵宇飞，张云旆，杨建喜，等. TBM在水利工程中的应用进展及发展方向[J]. 中国水利，2025，(21)：56–64 (ZHAO Yufei，ZHANG Yunpei，YANG Jianxi，et al. Application and future development of TBM in water project construction[J]. China Water Resources，2025，(21)：56–64.(in Chinese))
[2] 李文庆，刘永胜，洪开荣，等. TBM隧道掘进参数与围岩等级的映射关系[J]. 隧道建设(中英文)，2026，46(2)：336–347.(LI Wenqing，LIU Yongsheng，HONG Kairong，et al. Mapping relationships between TBM tunneling parameters and surrounding rock grades[J]. Tunnel Construction，2026，46(2)：336–347.(in Chinese))
[3] LUO W，XUE Y D，SUN Y L，et al. A knowledge-data dual-driven framework for predicting surrounding rock classification in TBM tunneling and generalization analysis[J]. Tunnelling and Underground Space Technology，2026，170：107378.
[4] 张登科，孟 涛，韩 阳，等. 不同裂缝扩展速率下北山花岗岩断裂特征及其演化机制研究[J]. 岩石力学与工程学报，2024，43(11)：2 712–2 724.(ZHANG Dengke，MENG Tao，HAN Yang，et al. Study on the fracture characteristics and evolution mechanisms of Beishan granite under different crack propagation rates[J]. Chinese Journal of Rock Mechanics and Engineering，2024，43(11)：2 712–2 724.(in Chinese))
[5] 丁秀丽，张雨霆，黄书岭，等. 隧洞围岩大变形机制、挤压大变形预测及应用[J]. 岩石力学与工程学报，2023，42(3)：521–544.(DING Xiuli，ZHANG Yuting，HUANG Shuling，et al. Large deformation mechanism of surrounding rock masses of tunnels，prediction method of squeezing large deformation and its application[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(3)：521–544.(in Chinese))
[6] 汪洪星，李珂瑶，张 超，等. 基于贝叶斯网络的隧道围岩变形动态预测模型[J]. 岩石力学与工程学报，2026，45(2)：553–577.(WANG Hongxing，LI Keyao，ZHANG Chao，et al. Dynamic prediction model of tunnel surrounding rock deformation based on Bayesian network[J]. Chinese Journal of Rock Mechanics and Engineering，2026，45(2)：553–577.(in Chinese))
[7] WANG Y，LIU Y，WANG Z F，et al. Investigation on progressive failure process of tunnel lining induced by creep effect of surrounding rock：A case study[J]. Engineering Failure Analysis，2023，144：106946.
[8] ZHANG D，HAN Y，WANG C，et al. Time series prediction of tunnel surrounding rock deformation using CPO-CLA integrated model[J]. Journal of Rock Mechanics and Geotechnical Engineering，2025，18(12)：7 915–7 930.
[9] MASINI R P，MEDEIROS M C，MENDES E F. Machine learning advances for time series forecasting[J]. Journal of Economic Surveys，2023，37(1)：76–111.
[10] CERQUEIRA V，TORGO L，MOZETI? I. Evaluating time series forecasting models：An empirical study on performance estimation methods[J]. Machine Learning，2020，109(11)：1 997–2 028.
[11] YU Y，SI X，HU C，et al. A review of recurrent neural networks：LSTM cells and network architectures[J]. Neural Computation，2019，31(7)：1 235–1 270.
[12] CUI K，JING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing and Applications，2019，31(12)：8 205–8 215.
[13] HE W，WANG Z，JIANG H. Model optimizing and feature selecting for support vector regression in time series forecasting[J]. Neurocomputing，2008，72(1/3)：600–611.
[14] CUI J，WU S，CHENG H，et al. Time series prediction of the surrounding rock displacement of a soft rock tunnel in the Central Yunnan Water Diversion Project[J]. Journal of Tsinghua University：Science and Technology，2024，64(7)：1 215–1 225.
[15] 王述红，董福瑞. 基于变形预测和参数反演的山岭隧道围岩稳定性分析[J]. 岩土工程学报，2023，45(5)：1 024–1 035.(WANG Shuhong，DONG Furui. Stability analysis of surrounding rock of mountain tunnels based on deformation prediction and parameter inversion[J]. Chinese Journal of Geotechnical Engineering，2023，45(5)：1 024–1 035.(in Chinese))
[16] FANG Q，CHEN S，LIU X Z，et al. Application of the variational mode decomposition-based CNN-LSTM model in predicting excavation deformation[J]. Mechanics in Engineering，2024，46(5)：1 015–1 022.
[17] MAY R，DANDY G，MAIER H. Review of input variable selection methods for artificial neural networks[J]. Artificial Neural Networks-Methodological Advances and Biomedical Applications，2011，10(1)：19–45.
[18] WANG L，WANG Z，QU H，et al. Optimal forecast combination based on neural networks for time series forecasting[J]. Applied Soft Computing，2018，66：1–17.
[19] PAN Y，CHEN L，WANG J，et al. Research on deformation prediction of tunnel surrounding rock using the model combining firefly algorithm and nonlinear auto-regressive dynamic neural network[J]. Engineering with Computers，2021，37(2)：1 443–1 453.
[20] 肖时辉，王 峰，何柏延，等. 基于LHS-WOA-ELM的隧道围岩参数反演分析[J]. 矿业研究与开发，2025，45(3)：91–100.(XIAO Shihui，WANG Feng，HE Baiyan，et al. Inversion analysis on surrounding rock parameters of tunnel based on LHS-WOA-ELM[J]. Mining Research and Development，2025，45(3)：91–100.(in Chinese))
[21] 姜 岚，张荣添，唐 波，等. 基于PSO-GWO-BP的抽水蓄能电站地下厂房围岩参数反演与稳定性预测[J]. 水力发电，2025，51(11)：24–30.(JIANG Lan，ZHANG Rongtian，TANG Bo，et al. Inversion of surrounding rock parameters and stability prediction of underground powerhouse of pumped-storage power station based on PSO-GWO-BP algorithm[J]. Water Power，2025，51(11)：24–30.(in Chinese))
[22] BAHDANAU D，CHO K，BENGIO Y. Neural machine translation by jointly learning to align and translate[C]// The 3rd International Conference on Learning Representations，ICLR 2015：Conference Track Proceedings. San Diego，CA：ICLR，2015.
[23] ABDEL-BASSET M，MOHAMED R，ABOUHAWWASH M. Crested porcupine optimizer：A new nature-inspired metaheuristic[J]. Knowledge-Based Systems，2024，284：111257.
[24] 郑益武，张海洋，赵星光，等. 中国高放废物地质处置地下实验室稳定性预测[J]. 工业建筑，2022，52(增1)：803–808.(ZHENG Yiwu，ZHANG Haiyang，ZHAO Xingguang，et al. Stability prediction on surrounding rocks of China?s underground research laboratory for high-level radioactive waste disposal[J]. Industrial Construction，2022，52(Supp.1)：803–808.(in Chinese))
[25] 王 驹，陈 亮，苏 锐，等. 中国高放废物地质处置北山地下实验室重大进展[J]. 世界核地质科学，2023，40(增1)：473–490.(WANG Ju，CHEN Liang，SU Rui，et al. Beishan underground research laboratory for geological disposal of high level radioactive waste in China[J]. World Nuclear Geoscience，2023，40(Supp.1)：473–490.(in Chinese))
[26] 郑益武，吴世兵，陈 亮，等. 北山花岗岩爆破损伤及力学特性劣化研究[J]. 世界核地质科学，2025，42(6)：1 322–1 332.(ZHENG Yiwu，WU Shibing，CHEN Liang，et al. Study on blasting damage and mechanical property degradation of Beishan granite[J]. World Nuclear Geoscience，2025，42(6)：1 322–1 332.(in Chinese))
[27] 徐 凯，袁蒋鹏. 粗泛化箱型图法在大中跨径桥梁监测异常值剔除的应用[J]. 广东公路交通，2024，50(1)：66–71.(XU Kai，YUAN Jiangpeng. Application of rough generalization box plot in eliminating outlier of bridge monitoring[J]. Guangdong Highway Communications，2024，50(1)：66–71.(in Chinese))
[28] 李洁松，刘 韬，伍 星. 基于皮尔逊相关系数统计特征滚动轴承RUL预测[J]. 航空动力学报，2025，40(7)：85–94.(LI Jiesong，LIU Tao，WU Xing. Prediction of rolling bearing RUL based on statistical characteristics of Pearson correlation coefficient[J]. Journal of Aerospace Power，2025，40(7)：85–94.(in Chinese))
[29] 尚 敏，廖 芬，马 锐，等. 白家包滑坡变形与库水位、降雨相关性定量化分析研究[J]. 工程地质学报，2021，29(3)：742–750.(SHANG Min，LIAO Fen，MA Rui，et al. Quantitative analysis of the correlation between deformation of Baijiabao landslide and reservoir water level and rainfall[J]. Journal of Engineering Geology，2021，29(3)：742–750.(in Chinese))
[30] HUO J Q，ZHAO Y，ZHANG Z S，et al. More sensitive to drought of young tissues with weak water potential adjustment capacity in two desert shrubs[J]. Science of the Total Environment，2021，789：147923.
[31] 李洪超，王富旗，张 继，等. 岩石RHT模型部分参数的敏感性分析及确定[J]. 高压物理学报，2025，39(6)：66–76.(LI Hongchao，WANG Fuqi，ZHANG Ji，et al. Sensitivity analysis and determination of some parameters of the rock RHT model[J]. Chinese Journal of High Pressure Physics，2025，39(6)：66–76.(in Chinese))
2026, Vol. 45 
