Stability analysis of surrounding rock of mountain tunnels based on deformation prediction and parameter inversion
-
摘要: 隧道围岩变形与岩体力学参数之间存在复杂的非线性关系,是围岩状态改变最直观的表现,也是围岩稳定性综合判别的重要指标。提出一种基于变形时序预测和力学参数反演的山岭隧道围岩稳定性分析方法。首先引入Tent混沌扰动和自适应警戒调整机制,构建基于自适应混沌麻雀搜索算法优化极限学习机(ACSSA-ELM)的变形时序预测模型和力学参数反演模型,进一步采用三次样条插值和变分模态分解(VMD)对已开挖断面围岩实测变形预处理,利用变形时序预测模型采取窗口滚动单步预测的方式对已开挖断面围岩最终变形值进行预测,并用于力学参数反演模型中获取开挖段围岩的“修正”力学参数,基于数值模型正算结果和开挖段已测变形值预测开挖段围岩变形和变形速率,进而分析其稳定性。依托重庆市花阳隧道进行了方法的验证与应用,并对隧道ZK40+820断面围岩的稳定性进行了合理可靠的预测分析。最后对方法的使用条件和反演参数的准确性进行了讨论。Abstract: There is a complex nonlinear relationship between the deformation of the surrounding rock of tunnels and the mechanical parameters of rock mass, which is the most intuitive expression for change of state of the surrounding rock, and is also an important index for the comprehensive discrimination of its stability. A stability analysis method for the surrounding rock of tunnels based on the deformation prediction and the mechanical parameter inversion is proposed. Firstly, by introducing the tent chaotic disturbance and the adaptive vigilance adjustment mechanism, the deformation time series prediction model and the mechanical parameter inversion model based on the adaptive chaos sparrow algorithm optimized extreme learning machine (ACSSA-ELM) are established. Further, the cubic spline interpolation and the variational modal decomposition (VMD) are used to preprocess the measured deformation values of the surrounding rock of the excavated section, and the deformation time series prediction model is used to predict the final deformation values of the surrounding rock of the excavated section using the dynamic window rolling single-step prediction, which is used to obtain the real mechanical parameters of the surrounding rock of the excavation section in the mechanical parameter inversion model. Based on the forward calculation results of the numerical model and the measured deformation values of the excavation section, the deformation and deformation rate of the surrounding rock in the excavation section are predicted, and then its stability is analyzed. Taking the Huayang tunnel of Chongqing as an example, the proposed method is verified and applied, and the stability of the surrounding rock of ZK40+820 section of the tunnel is reliably predicted and analyzed. Finally, the application conditions of the method and the accuracy of the inversion parameters are discussed.
-
-
表 1 ZK40+800断面4种模型趋势项变形预测结果对比
Table 1 Comparison of predicted results of trend-term deformation by four models for ZK40 + 800 section
指标 监测点 ACSSA-ELM SSA-ELM GWO-ELM BP 监测点 ACSSA-ELM SSA-ELM GWO-ELM BP RMSE GCJ 0.11 0.46 0.33 1.15 SSL 0.11 0.21 0.46 0.59 ARE 0.09 0.39 0.27 0.91 0.08 0.14 0.39 0.45 SMAPE 0.46 1.97 1.34 4.36 0.49 0.84 2.26 2.60 RMSE ZSL 0.25 0.28 0.35 0.61 XSL 0.15 0.52 0.34 0.33 ARE 0.19 0.24 0.28 0.48 0.13 0.42 0.25 0.22 SMAPE 1.50 1.92 2.17 3.66 1.14 3.52 2.07 1.81 表 2 围岩力学参数反演模型训练样本集
Table 2 Training sample sets of mechanical parameter inversion model for surrounding rock
样本编号 E/GPa c/MPa μ GCJ/mm SSL/mm ZSL/mm XSL/mm 1 1.5000 0.3000 0.2500 34.5285 24.1551 19.3244 14.7527 2 1.8750 0.3000 0.2500 28.0792 19.3012 14.3012 11.3671 3 2.2500 0.3000 0.2500 23.8682 15.1129 11.4967 9.8530 ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ 25 3.0000 1.2000 0.3500 15.6302 12.9397 9.6325 8.2561 表 3 围岩力学参数反演模型测试样本集
Table 3 Test sample sets of mechanical parameter inversion model for surrounding rock
样本编号 E/GPa c/MPa μ GCJ/mm SSL/mm ZSL/mm XSL/mm 1 1.5000 0.4500 0.2625 33.3623 25.1538 19.5234 15.8074 2 1.8750 0.6500 0.2875 26.5388 20.1030 15.2248 13.2724 3 2.2500 0.8500 0.3125 21.8077 16.8328 14.2017 12.3318 4 2.6250 1.0500 0.3375 18.2687 13.9744 11.6823 10.1458 5 3.0000 1.2500 0.3625 15.3268 13.3857 9.6086 8.8342 表 4 ACSSA-ELM围岩力学参数反演模型计算结果
Table 4 Results of ACSSA-ELM mechanical parameter inversion model for surrounding rock
编号 E/GPa c/MPa μ 目标值 反演值 相对误差% 目标值 反演值 相对误差% 目标值 反演值 相对误差% 1 1.5000 1.4956 0.293 0.4500 0.4508 0.178 0.2625 0.2668 1.638 2 1.8750 1.8792 0.224 0.6500 0.6301 3.060 0.2875 0.2867 0.278 3 2.2500 2.2472 0.124 0.8500 0.8526 0.306 0.3125 0.3114 0.325 4 2.6250 2.6300 0.042 1.0500 1.0864 3.467 0.3375 0.3374 0.089 5 3.0000 3.0022 0.190 1.2500 1.2848 2.784 0.3625 0.3594 0.030 平均相对误差% 0.175 1.959 0.472 表 5 ZK40+820断面变形最佳拟合曲线
Table 5 Best fitting curves of deformation of ZK40 + 820 section
监测点位 曲线方程 SSE R-square Adjusted R-square RMSE GCJ 1.068 0.9983 0.9981 0.2668 SSL 1.568 0.9952 0.9942 0.3347 ZSL 0.9977 0.9945 0.9935 0.3012 表 6 已开挖断面实测变形值
Table 6 Measured deformation values of excavated section
监测断面 GCJ/mm SSL/mm ZSL/mm XSL/mm ZK40+775 20.270 15.274 13.578 11.022 ZK40+780 21.077 11.679 8.897 7.114 ZK40+790 19.263 12.572 10.733 8.993 ZK40+800 20.672 17.117 13.135 12.104 表 7 力学参数反演值
Table 7 Inverse values of mechanical parameters
监测断面 E/GPa c/MPa μ ZK40+775 2.5974 0.5571 0.2786 ZK40+780 2.6545 0.5780 0.2476 ZK40+790 2.6554 0.7751 0.3028 ZK40+800 2.3744 1.0083 0.3284 工程地质勘查报告实测值 2.8000 0.6200 0.3600 -
[1] 孙振宇, 张顶立, 侯艳娟, 等. 基于现场实测数据统计的隧道围岩全过程变形规律及稳定性判据确定[J]. 岩土工程学报, 2021, 43(7): 1261-1270, 1376. http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18670.shtml SUN Zhenyu, ZHANG Dingli, HOU Yanjuan, et al. Whole-process deformation laws and determination of stability criterion of surrounding rock of tunnels based on statistics of field measured data[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(7): 1261-1270, 1376. (in Chinese) http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18670.shtml
[2] 王述红, 董福瑞, 朱宝强, 等. 山岭隧道围岩参数智能反演及稳定性分析[J]. 应用基础与工程科学学报, 2021, 29(5): 1171-1185. WANG Shuhong, DONG Furu, ZHU Baoqiang, et al. Intelligent inversion and stability analysis of surrounding rock of mountain tunnel[J]. Journal of Basic Science and Engineering, 2021, 29(5): 1171-1185. (in Chinese)
[3] 田明杰, 牟智恒, 仇文革. 基于BP神经网络的隧道稳定性分析研究[J]. 土木工程学报, 2017, 50(增刊2): 260-266. doi: 10.15951/j.tmgcxb.2017.s2.041 TIAN Mingjie, MOU Zhiheng, QIU Wenge. Research of the model comprehensive judgement for tunnel stability based on BP neural network[J]. China Civil Engineering Journal, 2017, 50(S2): 260-266. (in Chinese) doi: 10.15951/j.tmgcxb.2017.s2.041
[4] 吴秋军, 王明年, 刘大刚. 基于现场位移监测数据统计分析的隧道围岩稳定性研究[J]. 岩土力学, 2012, 33(增刊2): 359-364. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2012S2057.htm WU Qiujun, WANG Mingnian, LIU Dagang. Research on stability of tunnel surrounding rocks based on statistical analysis of on-site displacement monitoring data[J]. Rock and Soil Mechanics, 2012, 33(S2): 359-364. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2012S2057.htm
[5] 孙潇昊, 缪林昌, 林海山. 不同埋深盾构隧道开挖面稳定问题数值模拟[J]. 东南大学学报(自然科学版), 2017, 47(1): 164-169. https://www.cnki.com.cn/Article/CJFDTOTAL-DNDX201701028.htm SUN Xiaohao, MIAO Linchang, LIN Haishan. Numerical simulation research on excavation face stability of different depths of shield tunnel[J]. Journal of Southeast University (Natural Science Edition), 2017, 47(1): 164-169. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DNDX201701028.htm
[6] 阮永芬, 高春钦, 刘克文, 等. 基于粒子群算法优化小波支持向量机的岩土力学参数反演[J]. 岩土力学, 2019, 40(9): 3662-3669. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201909042.htm RUAN Yongfen, GAO Chunqin, LIU Kewen, et al. Inversion of rock and soil mechanics parameters based on particle swarm optimization wavelet support vector machine[J]. Rock and Soil Mechanics, 2019, 40(9): 3662-3669. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201909042.htm
[7] 阮永芬, 余东晓, 吴龙, 等. DE-GWO算法优化SVM反演软土力学参数[J]. 岩土工程学报, 2021, 43(增刊1): 166-170. http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18739.shtml RUAN Yongfen, YU Dongxiao, WU Long, et al. DE-GWO algorithm to optimize SVM inversion mechanical parameters of soft soil[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(S1): 166-170. (in Chinese) http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18739.shtml
[8] GAO W, CHEN D L, DAI S, et al. Back analysis for mechanical parameters of surrounding rock for underground roadways based on new neural network[J]. Engineering With Computers, 2018, 34(1): 25-36.
[9] 王开禾, 罗先启, 沈辉, 等. 围岩力学参数反演的GSA-BP神经网络模型及应用[J]. 岩土力学, 2016, 37(增刊1): 631-638. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2016S1083.htm WANG Kaihe, LUO Xianqi, SHEN Hui, et al. GSA-BP neural network model for back analysis of surrounding rock mechanical parameters and its application[J]. Rock and Soil Mechanics, 2016, 37(S1): 631-638. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2016S1083.htm
[10] BERTUZZI R. Back-analysing rock mass modulus from monitoring data of two tunnels in Sydney, Australia[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2017, 9(5): 877-891.
[11] JIANG A N, LI P. Back-analysis of mechanics parameters of tunnel based on particle swarm optimization and numerical simulation[J]. Key Engineering Materials, 2011(474/475/476): 1373-1376.
[12] 刘开云, 方昱, 刘保国, 等. 隧道围岩变形预测的进化高斯过程回归模型[J]. 铁道学报, 2011, 33(12): 101-106. LIU Kaiyun, FANG Yu, LIU Baoguo, et al. Intelligent deformation prediction model of tunnel surrounding rock based on genetic-Gaussian process regression coupling algorithm[J]. Journal of the China Railway Society, 2011, 33(12): 101-106. (in Chinese)
[13] 李茂达, 樊磊, 李磊, 等. 隧道与地下工程围岩变形的灰色优化与预测[J]. 土木建筑与环境工程, 2013, 35(增刊2): 143-145. https://www.cnki.com.cn/Article/CJFDTOTAL-JIAN2013S2037.htm LI Maoda, FAN Lei, LI Lei, et al. Tunnels and underground engineering optimization and gray rock deformation prediction[J]. Journal of Civil, Architectural & Environmental Engineering, 2013, 35(S2): 143-145. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JIAN2013S2037.htm
[14] 靖洪文, 吴俊浩, 马波, 等. 基于模糊灰色系统的深部巷道围岩变形预测模型及应用[J]. 煤炭学报, 2012, 37(7): 1099-1104. JING Hongwen, WU Junhao, MA Bo, et al. Prediction model and its application of deep mine tunnel surrounding rock deformation based on fuzzy-gray system[J]. Journal of China Coal Society, 2012, 37(7): 1099-1104. (in Chinese)
[15] ZHANG L, SHI B, ZHU H H, et al. PSO-SVM-based deep displacement prediction of Majiagou landslide considering the deformation hysteresis effect[J]. Landslides, 2021, 18(1): 179-193.
[16] 朱宝强, 王述红, 张泽, 等. 基于时间序列与DEGWO-SVR模型的隧道变形预测方法[J]. 浙江大学学报(工学版), 2021, 55(12): 2275-2285. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC202112007.htm ZHU Baoqiang, WANG Shuhong, ZHANG Ze, et al. Prediction method of tunnel deformation based on time series and DEGWO-SVR model[J]. Journal of Zhejiang University (Engineering Science), 2021, 55(12): 2275-2285. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC202112007.htm
[17] YANG B B, YIN K L, LACASSE S, et al. Time series analysis and long short-term memory neural network to predict landslide displacement[J]. Landslides, 2019, 16(4): 677-694.
[18] XU S L, NIU R Q. Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China[J]. Computers and Geosciences, 2018, 111(1): 87-96. doi: 10.1016/j.cageo.2017.10.013
[19] XUE J K, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[20] 滕志军, 吕金玲, 郭力文, 等. 一种基于Tent映射的混合灰狼优化的改进算法[J]. 哈尔滨工业大学学报, 2018, 50(11): 40-49. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201811007.htm TENG Zhijun, LV Ji-ling, GUO Liwen, et al. An improved hybrid grey wolf optimization algorithm based on Tent mapping[J]. Journal of Harbin Institute of Technology, 2018, 50(11): 40-49. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX201811007.htm
[21] 王培珍, 刘曼, 王高, 等. 基于改进极限学习机的焦煤惰质组分类方法[J]. 煤炭学报, 2020, 45(9): 3262-3268. WANG Peizhen, LIU Man, WANG Gao, et al. Classification approach for inertinite of coking coal based on an improved extreme learning machine[J]. Journal of China Coal Society, 2020, 45(9): 3262-3268. (in Chinese)
[22] 罗亦泳, 黄城, 张静影. 基于变分模态分解的变形监测数据去噪方法[J]. 武汉大学学报(信息科学版), 2020, 45(5): 784-790. LUO Yiyong, HUANG Cheng, ZHANG Jingying. Denoising method of deformation monitoring data based on variational mode decomposition[J]. Geomatics and Information Science of Wuhan University, 2020, 45(5): 784-790. (in Chinese)
[23] 张霄. 基于改进极限学习机的隧道围岩位移反分析[D]. 成都: 西南交通大学, 2017. ZHANG Xiao. Displacement Back Analysis of Tunnel Surrounding Rock Based on Improved Limit Learning Machine[D]. Chengdu: Southwest Jiaotong University, 2017. (in Chinese)
[24] 公路隧道施工技术规范: JTG/T 3660—2020[S]. 北京: 人民交通出版社, 2020. Technical Specifications for Construction of Highway Tunnel: JTG/T 3660—2020[S]. Beijing: China Communications Press, 2020. (in Chinese)
[25] 王述红, 朱宝强. 山岭隧道洞口段地表沉降时序预测研究[J]. 岩土工程学报, 2021, 43(5): 813-821. http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18612.shtml WANG Shuhong, ZHU Baoqiang. Time series prediction for ground settlement in portal section of mountain tunnels[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(5): 813-821. (in Chinese) http://manu31.magtech.com.cn/Jwk_ytgcxb/CN/abstract/abstract18612.shtml