Time series prediction of the surrounding rock displacement of a soft rock tunnel in the Central Yunnan Water Diversion Project
CUI Jingqi1,3, WU Shunchuan1,3, CHENG Haiyong1,3, WANG Tao2, JIANG Guanzhao1,3, PU Shijiang1,3, REN Zijian1,3
1. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Yunnan 650093, China; 2. Central Yunnan Water Diversion Engineering Co., Ltd., Kunming 650000, China; 3. Key Laboratory of Geohazard Forecast and Geoecological Restoration in Plateau Mountainous Area, Ministry of Natural Resources of the People's Republic of China, Kunming 650093, China
Abstract：[Objective] The monitoring value of surrounding rock displacement has the characteristics of complexity and nonlinear dynamic change, and the static one-time learning of previous optimization algorithms combined with a single regression model cannot be practically applied in real scenarios. The regression fitting model uses several displacement monitoring point data to construct a general model of the surrounding rock displacement change, which cannot be applied to predict the future changes in monitoring points. The autocorrelation of the surrounding rock displacement data makes it more practical as a time series prediction problem. However, the generalization performance of a single model is easily disrupted by historical monitoring data, resulting in inaccurate prediction of test applications. In this study, a dynamic prediction method for surrounding rock displacement time series combined with time series monitoring data preprocessing is proposed. [Methods] First, the displacement monitoring data of the tunnel-surrounding rock are preprocessed. The intercepted stability monitoring data are isometrized by cubic spline interpolation, and the monitoring data are decomposed into trend and random term displacement components by variational mode decomposition signal processing. Adaboost integrates 10 long short-term memory networks to construct an integrated optimization model for time series prediction. Then, the weights of the training samples are initialized, the weight coefficients of the base model in the integration are calculated by training the first base model, and the weights of the training samples of the next base model are updated. Finally, the weight coefficients of all base models are obtained. After Adaboost integration optimization, the prediction results are calculated using all base models and their weight coefficients. After training and learning, single-step dynamic prediction is performed, and monitoring changes are updated in real time to model learning. The cumulative displacement prediction results can be obtained by superimposing the trend and random term displacement sequences using the time series decomposition principle. [Results] The displacement components of the rock surrounding the Central Yunnan Water Diversion Project were predicted and superimposed, and three displacement data were obtained. Compared with the traditional time series prediction model, each displacement index exhibited good performance. The complete data of the surrounding rock displacement time series were obtained by the FLAC 3D numerical simulation engineering section, and the application performance of the integrated optimization model was verified. Results showed that the integrated optimization model exhibited good performance in each component and cumulative displacement and was less affected by deformation rate fluctuation than the traditional model. [Conclusions] After preprocessing the time series data, the influencing factors of surrounding rock displacement and deformation are decomposed, and multiple time series prediction models are integrated for single-step dynamic prediction, which improves the shortcomings of previous studies. The correction determination coefficient and symmetrical average absolute percentage error are used as performance indicators to verify that the prediction accuracy achieves the expected goal and is superior to the traditional classical model in solving the time series problem, which promotes the predictability of surrounding rock displacement in practical applications.
崔靖奇, 吴顺川, 程海勇, 王涛, 姜关照, 浦仕江, 任子健. 滇中引水软岩隧洞围岩位移时序预测[J]. 清华大学学报（自然科学版）, 2024, 64(7): 1215-1225.
CUI Jingqi, WU Shunchuan, CHENG Haiyong, WANG Tao, JIANG Guanzhao, PU Shijiang, REN Zijian. Time series prediction of the surrounding rock displacement of a soft rock tunnel in the Central Yunnan Water Diversion Project. Journal of Tsinghua University(Science and Technology), 2024, 64(7): 1215-1225.
[1] ZHANG Y, SU G S, LIU B C, et al. A novel displacement back analysis method considering the displacement loss for underground rock mass engineering[J]. Tunnelling and Underground Space Technology, 2020, 95:103141. [2] 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(S2):359-364. WU Q J, WANG M N, LIU D G. 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) [3] KOVAČEVIĆ M S, BAČIĆ M, GAVIN K, et al. Assessment of long-term deformation of a tunnel in soft rock by utilizing particle swarm optimized neural network[J]. Tunnelling and Underground Space Technology, 2021, 110:103838. [4] QIU H Z, CHEN X Q, WU Q H, et al. Deformation mechanism and collapse treatment of the rock surrounding a shallow tunnel based on on-site monitoring[J]. Journal of Mountain Science, 2020, 17(12):2897-2914. [5] 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):1443-1453. [6] CUI J Q, WU S C, CHENG H Y, et al. Composite interpretability optimization ensemble learning inversion surrounding rock mechanical parameters and support optimization in soft rock tunnels[J]. Computers and Geotechnics, 2024, 165:105877. [7] ZHANG X L, NGUYEN H, BUI X N, et al. Evaluating and predicting the stability of roadways in tunnelling and underground space using artificial neural network-based particle swarm optimization[J]. Tunnelling and Underground Space Technology, 2020, 103:103517. [8] LI C Q, MEI X C. Application of SVR models built with AOA and Chaos mapping for predicting tunnel crown displacement induced by blasting excavation[J]. Applied Soft Computing, 2023, 147:110808. [9] YAO B Z, YANG C Y, YAO J B, et al. Tunnel surrounding rock displacement prediction using support vector machine[J]. International Journal of Computational Intelligence Systems, 2010, 3(6):843-852. [10] YAO B, YAO J, ZHANG M H, et al. Improved support vector machine regression in multi-step-ahead prediction for rock displacement surrounding a tunnel[J]. Scientia Iranica, 2014, 21(4):1309-1316. [11] NSUBUGA S, TSAKIRI M, GEORGIANNOU V. A smart decision tool for the prediction of tunnel crown displacements[J]. Applied Geomatics, 2021, 13(S1):77-91. [12] HUANG Z K, ZHANG D M, XIE X C. A practical ANN model for predicting the excavation-induced tunnel horizontal displacement in soft soils[J]. Underground Space, 2022, 7(2):278-293. [13] MAHDEVARI S, TORABI S R. Prediction of tunnel convergence using artificial neural networks[J]. Tunnelling and Underground Space Technology, 2012, 28:218-228. [14] 肖明,董正中,陈俊涛.隧道施工监测数据处理与反馈稳定预测分析[J].现代隧道技术, 2016, 53(2):121-127. XIAO M, DONG Z Z, CHEN J T. Monitoring data processing, feedback analysis and stability prediction during tunnel construction[J]. Modern Tunnelling Technology, 2016, 53(2):121-127.(in Chinese) [15] 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. WANG S H, ZHU B Q. 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) [16] 李麟玮,吴益平,苗发盛,等.基于变分模态分解与GWO-MIC-SVR模型的滑坡位移预测研究[J].岩石力学与工程学报, 2018, 37(6):1395-1406. LI L W, WU Y P, MIAO F S, et al. Displacement prediction of landslides based on variational mode decomposition and GWO-MIC-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(6):1395-1406.(in Chinese) [17] YU Y, SI X S, HU C H, et al. A review of recurrent neural networks:LSTM cells and network architectures[J]. Neural Computation, 2019, 31(7):1235-1270. [18] CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. PeerJ Computer Science, 2021, 7:e623. [19] AKOSSOU A Y J, PALM R. Impact of data structure on the estimators R-square and adjusted R-square in linear regression[J]. International Journal of Mathematics and Computation, 2013, 20(3):84-93. [20] XUE Y G, GONG H M, KONG F M, et al. Stability analysis and optimization of excavation method of double-arch tunnel with an extra-large span based on numerical investigation[J]. Frontiers of Structural and Civil Engineering, 2021, 15(1):136-146. [21] YU K P, REN F Y, PUSCASU R, et al. Optimization of combined support in soft-rock roadway[J]. Tunnelling and Underground Space Technology, 2020, 103:103502. [22] 中华人民共和国住房和城乡建设部,中华人民共和国国家质量监督检验检疫总局.岩土锚杆与喷射混凝土支护工程技术规范:GB 50086-2015[S].北京:中国计划出版社, 2016. Ministry of Housing and Urban-Rural Development of the People's Republic of China, General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China. Technical code for engineering of ground anchorages and shotcrete support:GB 50086-2015[S]. Beijing:China Planning Press, 2016.(in Chinese) [23] ZHU B, ZHOU C B, JIANG N. Dynamic characteristics and safety control of mortar bolts under tunnel blasting vibration loads[J]. Tunnelling and Underground Space Technology, 2023, 135:105005. 1] 张小宝,司富安,段世委,等.深埋水工长隧洞主要工程地质问题与勘察经验[J].水利规划与设计, 2021(12):55-60. ZHANG X B, SI F A, DUAN S W, et al. Main engineering geological problems and survey experience of deep buried hydraulic long tunnel[J]. Water Resources Planning and Design, 2021(12):55-60.(in Chinese) [2] 钮新强,张传健.复杂地质条件下跨流域调水超长深埋隧洞建设需研究的关键技术问题[J].隧道建设(中英文), 2019, 39(4):523-536. NIU X Q, ZHANG C J. Some key technical issues on construction of ultra-long deep-buried water conveyance tunnel under complex geological conditions[J]. Tunnel Construction, 2019, 39(4):523-536.(in Chinese) [3] 王建秀,杨立中,何静.深埋隧道外水压力计算的解析-数值法[J].水文地质工程地质, 2002, 29(3):17-19, 28. WANG J X, YANG L Z, HE J. The simulation of deep tunnel external water pressure by analytical-numerical method[J]. Hydrogeology&Engineering Geology, 2002, 29(3):17-19, 28.(in Chinese) [4] 王建秀,杨立中,何静.深埋隧道衬砌水荷载计算的基本理论[J].岩石力学与工程学报, 2002, 21(9):1339-1343. WANG J X, YANG L Z, HE J. Introduction to the calculation of external water pressure of tunnel lining[J]. Chinese Journal of Rock Mechanics and Engineering, 2002, 21(9):1339-1343.(in Chinese) [5] 李宗利,任青文,王亚红.考虑渗流场影响深埋圆形隧洞的弹塑性解[J].岩石力学与工程学报, 2004, 23(8):1291-1295. LI Z L, REN Q W, WANG Y H. Elasto-plastic analytical solution of deep-buried circle tunnel considering fluid flow field[J]. Chinese Journal of Rock Mechanics and Engineering, 2004, 23(8):1291-1295.(in Chinese) [6] ZHANG Q, SHAO C, SU H J, et al. A closed-form hydraulic-mechanical coupling solution of a circular tunnel in elastic-brittle-plastic rock mass[J]. European Journal of Environmental and Civil Engineering, 2022, 26(8):3594-3611. [7] 刘立鹏,汪小刚,贾志欣,等.水岩分算隧道衬砌外水压力折减系数取值方法[J].岩土工程学报, 2013, 35(3):495-500. LIU L P, WANG X G, JIA Z X, et al. Method to determine reduction factor of water pressure acting on tunnel linings using water-rock independent calculation methodology[J]. Chinese Journal of Geotechnical Engineering, 2013, 35(3):495-500.(in Chinese) [8] 李家斌.富水深竖井衬砌外水压力折减规律及工程影响研究[D].北京:北京交通大学, 2022. LI J B. Study on reduction law of external water pressure of rich water depth shaft lining and engineering influence[D]. Beijing:Beijing Jiaotong University, 2022.(in Chinese) [9] 张有天.岩石隧道衬砌外水压力问题的讨论[J].现代隧道技术, 2003, 40(3):1-4, 10. ZHANG Y T. Discussion on external hydraulic pressure upon rock tunnel lining[J]. Modern Tunnelling Technology, 2003, 40(3):1-4, 10.(in Chinese) [10] 陈卫忠,杨建平,杨家岭,等.裂隙岩体应力渗流耦合模型在压力隧洞工程中的应用[J].岩石力学与工程学报, 2006, 25(12):2384-2391. CHEN W Z, YANG J P, YANG J L, et al. Hydromechanical coupled model of jointed rock mass and its application to pressure tunnels[J]. Chinese Journal of Rock Mechanics and Engineering, 2006, 25(12):2384-2391.(in Chinese) [11] 张东旭.基于宏观地质模型分类的深埋隧洞衬砌外水压力研究[D].西安:西安理工大学, 2022. ZHANG D X. Study on the external water pressure on lining in deep buried tunnel based on the classification of macroscopic geological model[D]. Xi'an:Xi'an University of Technology, 2022.(in Chinese) [12] 王新越,王如宾,王丹,等.滇中引水松林隧洞高外水压力作用数值模拟分析[J].隧道与地下工程灾害防治, 2023, 5(4):72-80. WANG X Y, WANG R B, WANG D, et al. Numerical simulation analysis of high external water pressure effect in songlin tunnel of central Yunnan water diversion[J]. Hazard Control in Tunnelling and Underground Engineering, 2023, 5(4):72-80.(in Chinese) [13] 中华人民共和国水利部.水工隧洞设计规范:SL 279-2016[S].北京:中国水利水电出版社, 2016. Ministry of Water Resources of the People's Republic of China. Specification for design of hydraulic tunnel:SL 279-2016[S]. Beijing:China Water&Power Press, 2016.(in Chinese) [14] 刘立鹏,汪小刚,段庆伟,等.高压富水地层水工隧洞衬砌外水压力确定与应对措施[J].岩土工程学报, 2022, 44(8):1549-1557. LIU L P, WANG X G, DUAN Q W, et al. Methods to cope with external water pressure of hydraulic tunnel linings in high-pressure groundwater-rich strata[J]. Chinese Journal of Geotechnical Engineering, 2022, 44(8):1549-1557.(in Chinese) [15] 黄威,孙云,张建平,等.深埋隧洞高外水压力研究进展[J].三峡大学学报(自然科学版), 2023, 45(5):1-11. HUANG W, SUN Y, ZHANG J P, et al. Research review on high external water pressure of deep-buried tunnels[J]. Journal of China Three Gorges University (Natural Sciences), 2023, 45(5):1-11.(in Chinese)
2024, Vol. 64 
