«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

卷:

第47卷

期数:

2025年第04期

页码:

634-645

栏目:

黄河流域生态保护和高质量发展专刊(下)

出版日期:

2025-07-15

文章信息/Info

Title:

Deformation Prediction of Weak Surrounding Rock of the Tunnel Based on DBO-BiLSTM

文章编号:

1672-6561(2025)04-0634-12

作者:

张建^*

(中铁十二局集团第四工程有限公司,陕西 西安 710021)

Author(s):

ZHANG Jian^*

(The 4th Engineering Co., Ltd. of China Railway 12th Bureau Group, Xi'an 710021, Shaanxi, China)

关键词:

隧道工程;  围岩;  变形预测;  DBO-BiLSTM模型;  深度学习;  长短时记忆网络;  蜣螂优化算法

Keywords:

tunnel engineering;  surrounding rock;  deformation prediction;  DBO-BiLSTM model;  deep learning;  long short-term memory network;  dung beetle optimizer algorithm

分类号:

U457; TP18; U451⁺.2

DOI:

10.19814/j.jese.2024.12051

文献标志码:

A

摘要:

隧道软弱围岩变形预测是确保隧道建设及施工运营安全等诸多环节中的核心要素。目前隧道软弱围岩变形预测主要依托围岩变形监测数据,而监测数据统计分析结果的可靠性、鲁棒性及泛化性依然不能满足工程建设的要求。针对该问题,对比LSTM、BiLSTM、CNN-LSTM、GRU、CNN-RNN 模型的准确性、可靠性和稳定性,优选出BiLSTM 模型为初步预测模型; 考虑双向长短时记忆(BiLSTM)网络的灵活交互性和蜣螂优化(DBO)算法的数据驱动优势,构建基于深度学习的隧道软弱围岩变形预测模型——DBO-BiLSTM模型; 最后,以西十高速铁路云岭一号隧道断面软弱围岩为案例,运用DBO-BiLSTM模型和BiLSTM模型对该隧道软弱围岩变形进行预测,并与监测数据进行对比。结果表明:DBO-BiLSTM模型较BiLSTM模型预测结果更优,其均方误差(MSE)、均方根误差(RMSE)、平均绝对误差(MAE)、平均百分比误差(MAPE)、判定系数(R²)分别为0.001 6、0.040 6、0.031 8、1.43%、0.998 5; 云岭一号隧道软弱围岩变形情况均经历了先陡增后缓增、最终趋于稳定的过程,拱顶沉降最大累计变形量为14.79 mm,水平收敛最大累计变形量为16.80 mm。

Abstract:

The deformation prediction of weak surrounding rock of the tunnel is the core element to ensure the safety of tunnel construction and operation. At present, the deformation prediction of weak surrounding rock of the tunnel relies on the monitoring data of surrounding rock deformation, and the reliability, robustness and generalization of the statistical results of monitoring data still do not meet the requirements of engineering construction. For this problem, the accuracy, reliability and stability of LSTM, BiLSTM, CNN-LSTM, GRU and CNN-RNN models were compared, and BiLSTM model was selected as the preliminary prediction model; considering the flexible interactivity of bidirectional long short-term memory(BiLSTM)networks and the data-driven advantages of dung beetle optimizer(DBO)algorithm, a deformation prediction model of weak surrounding rock of the tunnel based on deep learning, named as DBO-BiLSTM model, was constructed; taking the surrounding rock section of Yunling No.1 tunnel in Xi'an-Shiyan high-speed railway as an example, BiLSTM model and DBO-BiLSTM model were used to accurately predict the deformation of weak surrounding rock of the tunnel. The results show that the prediction results of DBO-BiLSTM model are better than those of BiLSTM model; the mean square error(MSE), root mean square error(RMSE), mean absolute error(MAE), mean percentage error(MAPE), and determination coefficient(R²)are 0.001 6, 0.040 6, 0.031 8, 1.43%, and 0.998 5, respectively; the deformation of weak surrounding rock of Yunling No.1 tunnel has experienced a process of steep increase first, then slow increase and finally stabilized; the maximum cumulative deformation of vault settlement is 14.79 mm, and the maximum cumulative deformation of horizontal convergence is 16.80 mm.

参考文献/References:

[1] AYDAN Ö,AKAGI T,KAWAMOTO T.Tunneling Through Squeezing Rocks Around Tunnels:Theory and Prediction[J].Rock Mechanics and Rock Engineering,1987,20(4):151-166.
[2] AYDAN Ö,AKAGI T,KAWAMOTO T.The Squeezing Potential of Rock Around Tunnels:Theory and Prediction with Examples Taken from Japan[J].Rock Mechanics and Rock Engineering,1996,29(3):125-143.
[3] 张广泽,柴春阳,宋 章,等.软岩大变形发生的边界条件及对策探讨[J].铁道工程学报,2018,35(8):27-31.
ZHANG Guang-ze,CHAI Chun-yang,SONG Zhang,et al.The Discussion of Boundary Condition for Large Deformation of Soft Rockmass and Its Control Countermeasures[J].Journal of Railway Engineering Society,2018,35(8):27-31.
[4] 廖烟开,郭德平,刘志强,等.隧道周边应变与挤压因子法在隧道围岩大变形预测中的应用[J].现代隧道技术,2020,57(4):20-26.
LIAO Yan-kai,GUO De-ping,LIU Zhi-qiang,et al.Application of Peripheral Strain and Squeezing Factor Methods in the Prediction of Large Deformation of Tunnel Surrounding Rocks[J].Modern Tunnelling Technology,2020,57(4):20-26.
[5] 胡元芳,刘志强,王建宇.高地应力软岩条件下挤压变形预测及应用[J].现代隧道技术,2011,48(3):28-34.
HU Yuan-fang,LIU Zhi-qiang,WANG Jian-yu.Squ-eezing Deformation Prediction of Soft Rocks Under High Ground Stress and Its Application[J].Modern Tunnelling Technology,2011,48(3):28-34.
[6] 周 航,陈仕阔,刘 彤,等.挤压性围岩大变形危险性评价的组合赋权-理想点模型[J].中南大学学报(自然科学版),2021,52(10):3647-3658.
ZHOU Hang,CHEN Shi-kuo,LIU Tong,et al.Combination Weight and Ideal Point Method Model for Risk Evaluation on Squeezing Large Deformation[J].Journal of Central South University(Science and Technology),2021,52(10):3647-3658.
[7] 陈子全,何 川,吴 迪,等.高地应力层状软岩隧道大变形预测分级研究[J].西南交通大学学报,2018,53(6):1237-1244.
CHEN Zi-quan,HE Chuan,WU Di,et al.Study of Large Deformation Classification Criterion for Lay-ered Soft Rock Tunnels Under High Geostress[J].Journal of Southwest Jiaotong University,2018,53(6):1237-1244.
[8] 陈兴海,周 航,张广泽,等.山岭隧道大变形危险性评价的功效系数法研究[J].铁道工程学报,2022,39(8):59-65.
CHEN Xing-hai,ZHOU Hang,ZHANG Guang-ze,et al.Efficiency Coefficient Method for Large Defor-mation Risk Assessment of Mountain Tunnel[J].Journal of Railway Engineering Society,2022,39(8):59-65.
[9] 邵珠山,李柏霄.泥质粉砂岩隧道变形及长期稳定性研究[J].地下空间与工程学报,2021,17(3):883-896.
SHAO Zhu-shan,LI Bo-xiao.Study on Deformation and Secular Stability of Argillaceous Siltstone Tunnel[J].Chinese Journal of Underground Space and Engineering,2021,17(3):883-896.
[10] 刘 军,邓鹏海.基于FDEM数值模拟的软岩隧洞大变形预测[J].西北水电,2023(1):28-35.
LIU Jun,DENG Peng-hai.Large Deformation Prediction of Soft Rock Tunnel Based on FDEM Numerical Simulation[J].Northwest Hydropower,2023(1):28-35.
[11] 郭新新,汪 波,王振宇,等.考虑蠕变特性的高应力软岩隧道变形预测方法与实践[J].岩土工程学报,2023,45(3):652-660.
GUO Xin-xin,WANG Bo,WANG Zhen-yu,et al.Methods and Practices for Deformation Prediction in High-stress Soft Rock Tunnels Considering Creep Characteristics[J].Chinese Journal of Geotechnical Engineering,2023,45(3):652-660.
[12] WU X G,FENG Z B,LIU Y,et al.Enhanced Safety Prediction of Vault Settlement in Urban Tunnels Using the Pair-Copula and Bayesian Network[J].Applied Soft Computing,2023,132:109711.
[13] 李海斌,翟秋柱,张 优,等.PSO-BP 神经网络在隧道围岩变形预测中的应用[J].路基工程,2017(5):164-169.
LI Hai-bin,ZHAI Qiu-zhu,ZHANG You,et al.Application of PSO-BP Neural Network in Prediction of Tunnel Rock Deformation[J].Subgrade Engineering,2017(5):164-169.
[14] 张 锦,陈 林,赖祖龙.改进遗传算法优化灰色神经网络隧道变形预测[J].测绘科学,2021,46(2):55-61,77.
ZHANG Jin,CHEN Lin,LAI Zu-long.Tunnel Deformation Prediction Based on Grey Neural Network with Improved Genetic Algorithm[J].Science of Surveying and Mapping,2021,46(2):55-61,77.
[15] 姚 凯,朱向阳,张克宏,等.基于FOA-GRNN的软岩隧道围岩变形预测模型[J].地下空间与工程学报,2019,15(增2):908-913.
YAO Kai,ZHU Xiang-yang,ZHANG Ke-hong,et al.Prediction Model of Surrounding Rock Deformation in Soft Rock Tunnel Based on FOA-GRNN[J].Chinese Journal of Underground Space and Engineering,2019,15(S2):908-913.
[16] 朱双丽.挤压性围岩隧道大变形综合评价及变形潜势预测方法研究[D].长沙:中南大学,2022.
ZHU Shuang-li.Research on Comprehensive Evaluation of Large Deformation and Prediction Method of Deformation Potential for Squeezed Surrounding Rock Tunnel[D].Changsha:Central South University,2022.
[17] 黄 震,廖敏杏,张皓量,等.基于SVM-BP模型非完整数据的隧道围岩挤压变形预测[J].现代隧道技术,2020,57(增1):129-138.
HUANG Zhen,LIAO Min-xing,ZHANG Hao-liang,et al.Prediction of Tunnel Surrounding Rock Extrusion Deformation Based on SVM-BP Model with Incomplete Data[J].Modern Tunneling Technology,2020,57(S1):129-138.
[18] 孟陆波,李天斌,龚 勇.基于模糊层次综合评判的大变形预测方法[J].成都理工大学学报(自然科学版),2010,37(2):195-200.
MENG Lu-bo,LI Tian-bin,GONG Yong.Large Deformation Forecasting Method Based on Fuzzy Hie-rarchical Integrated Evaluation[J].Journal of Chengdu University of Technology(Science & Technology Edition),2010,37(2):195-200.
[19] 杨文波,王宗学,田浩晟,等.基于PSO-SVM算法的层状软岩隧道大变形预测方法[J].隧道与地下工程灾害防治,2022,4(1):29-37.
YANG Wen-bo,WANG Zong-xue,TIAN Hao-sheng,et al.Large Deformation Prediction Method of Layered Soft Rock Tunnel Based on PSO-SVM Algorithm[J].Hazard Control in Tunnelling and Underground Engineering,2022,4(1):29-37.
[20] 曾学宏,赵义花.LSTM网络在地铁隧道沉降预测中的应用研究[J].甘肃科学学报,2019,31(6):117-122.
ZENG Xue-hong,ZHAO Yi-hua.Study on the Application of LSTM Network in Subway Tunnel Subsi-dence Prediction[J].Journal of Gansu Sciences,2019,31(6):117-122.
[21] 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):1590-1600.
LYU Qing-feng,LI Yu,NIU Rong,et al.Research on Deformation Prediction of Surrounding Rock in Special Geotechnical Tunnels Based on Deep Learning[J].Journal of Basic Science and Engineering,2023,31(6):1590-1600.
[22] 刘 智,李欣雨,李 震,等.基于Bayes-LSTM的公路隧道围岩变形预测方法研究[J].中外公路,2024,44(1):166-176.
LIU Zhi,LI Xin-yu,LI Zhen,et al.Prediction Method of Surrounding Rock Deformation of Highway Tunnels Based on Bayes-LSTM[J].Journal of China & Foreign Highway,2024,44(1):166-176.
[23] 王 锋.基于SSA-LSTM模型的软岩隧道变形特征智能预测及应用研究[J].现代隧道技术,2024,61(1):56-66.
WANG Feng.Study on Intelligent Prediction of the Deformation Characteristics of Soft Rock Tunnel Ba-sed on SSA-LSTM Model and Its Application[J].Mo-dern Tunnelling Technology,2024,61(1):56-66.
[24] 吴 浩,陈运涛,朱赵辉,等.改进一维卷积神经网络的隧道围岩收敛变形分级预测[J].应用基础与工程科学学报,2024,32(1):145-159.
WU Hao,CHEN Yun-tao,ZHU Zhao-hui,et al.Prediction of Tunnel Squeezing Classification Based on Improved One-dimensional Convolutional Neural Network[J].Journal of Basic Science and Engineering,2024,32(1):145-159.
[25] 赵永智.基于LSTM-ARIMA模型的隧道围岩变形预测方法研究[J].国防交通工程与技术,2024,22(4):21-26.
ZHAO Yong-zhi.Research on the Prediction Method of Tunnel Surrounding Rock Deformation Based on LSTM-ARIMA Model[J].Traffic Engineering and Technology for National Defence,2024,22(4):21-26.
[26] XU W,CHENG M,XU X Y,et al.Deep Learning Method on Deformation Prediction for Large-section Tunnels[J].Symmetry,2022,14(10):2019.
[27] MA K,CHEN L P,FANG Q,et al.Machine Learning in Conventional Tunnel Deformation in High In-situ Stress Regions[J].Symmetry,2022,14(3):513.
[28] 尹 泉,周 怡,饶军应.基于深度学习的盾构隧道施工地表沉降预测方法[J].中南大学学报(自然科学版),2024,55(2):607-617.
YIN Quan,ZHOU Yi,RAO Jun-ying.A Deep Learning-based Method for Predicting Surface Settlement Induced by Shield Tunnel Construction[J].Journal of Central South University(Science and Technology),2024,55(2):607-617.
[29] 满 轲,曹子祥,刘晓丽,等.基于GRU-RF模型的TBM掘进参数预测研究[J].应用基础与工程科学学报,2023,31(6):1519-1539.
MAN Ke,CAO Zi-xiang,LIU Xiao-li,et al.Research on Prediction of TBM Tunnelling Parameters Based on GRU-RF Model[J].Journal of Basic Science and Engineering,2023,31(6):1519-1539.
[30] 邱道宏,傅 康,薛翊国,等.深埋隧道TBM掘进参数LSTM时序预测模型及应用研究[J].中南大学学报(自然科学版),2021,52(8):2646-2660.
QIU Dao-hong,FU Kang,XUE Yi-guo,et al.LSTM Time-series Prediction Model for TBM Tunneling Parameters of Deep-buried Tunnels and Application Research[J].Journal of Central South University(Science and Technology),2021,52(8):2646-2660.
[31] 满 轲,武立文,刘晓丽,等.基于CNN-LSTM模型的TBM隧道掘进参数及岩爆等级预测[J].煤炭科学技术,2024,52(增2):21-37.
MAN Ke,WU Li-wen,LIU Xiao-li,et al.The Prediction of TBM Tunnel Boring Parameters and Rockburst Grade Based on CNN-LSTM Model[J].Coal Science and Technology,2024,52(S2):21-37.

相似文献/References:

[1]陈新建,孙琳,李新星,等.隧道工程地质评价的内容和方法[J].地球科学与环境学报,2004,26(01):41.
　CHEN Xin-jian,SUN Lin,LI Xin-xing,et al.Contents and methods of the tunnel engineering geology evaluation[J].Journal of Earth Sciences and Environment,2004,26(04):41.
[2]周潇朗,张常亮,乔朋腾.变质岩区隧道开挖作用下围岩应力场变化及其稳定性分析[J].地球科学与环境学报,2018,40(04):497.
　ZHOU Xiao-lang,ZHANG Chang-liang,QIAO Peng-teng.Stress Field Variation and Stability Analysis of Surrounding Rocks in Excavation of Metamorphic Rock Tunnel[J].Journal of Earth Sciences and Environment,2018,40(04):497.
[3]凤永刚,梁 婷,雷如雄,等.稀有金属伟晶岩过度冷却与侵位之关系——基于野外地质观察及年代学的思考[J].地球科学与环境学报,2021,43(01):100.[doi:10.19814/j.jese.2020.11027]
　FENG Yong-gang,LIANG Ting,LEI Ru-xiong,et al.Relationship Between Undercooling and Emplacement of Rare-element Pegmatites—Thinking Based on Field Observations and Pegmatite Geochronology[J].Journal of Earth Sciences and Environment,2021,43(04):100.[doi:10.19814/j.jese.2020.11027]
[4]邓兆宁,常洲,鲁志方,等.穿越富水断层时红层泥岩隧道的受力响应[J].地球科学与环境学报,2024,46(03):414.[doi:10.19814/j.jese.2023.12056]
　DENG Zhao-ning,CHANG Zhou,LU Zhi-fang,et al.Stress Response of Red Mudstone Tunnel Crossing Water-rich Fault[J].Journal of Earth Sciences and Environment,2024,46(04):414.[doi:10.19814/j.jese.2023.12056]
[5]郭哲昊,黄强兵*,苟玉轩,等.地铁隧道暗挖施工穿越地裂缝带围岩响应规律——以西安地铁6号线为例[J].地球科学与环境学报,2025,47(03):356.[doi:10.19814/j.jese.2024.09008]
　GUO Zhe-hao,HUANG Qiang-bing*,GOU Yu-xuan,et al.Response Law of Surrounding Rock of Metro Tunnel Concealed Excavation Crossing Ground Fissure Zone—Taking Xi'an Metro Line 6 in Shaanxi, China as an Example[J].Journal of Earth Sciences and Environment,2025,47(04):356.[doi:10.19814/j.jese.2024.09008]

备注/Memo

备注/Memo:

收稿日期:2024-12-30; 修回日期:2025-04-28
基金项目:国家自然科学基金项目(12472406)
*通信作者:张 建(1977-),男,羌族,四川绵阳人,高级工程师,E-mail:12770665@qq.com。

常用功能

更新日期/Last Update: 2025-07-25