Research and prospect of surface deformation prediction of shield tunneling based on machine learning
DING Zhi1, LI Xinjia2, ZHANG Xiao2
1. Department of Civil Engineering, Zhejiang University City College, Hangzhou 310015, Zhejiang, China; 2. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, Zhejiang, China
Abstract: In order to clarify the key points of machine learning in surface deformation prediction of shield tunneling, the development background of machine learning was introduced, and the engineering application of machine learning was summarized from the aspects of database establishment, data preprocessing, model framework construction and model evaluation. It was pointed out that the shortcomings of the current relevant research were the lack of professional public database and the uneven quality of engineering data; for engineering with different stratum types, the model was prone to over fitting. At the same time, the further development direction of machine learning in shield tunneling surface deformation prediction was discussed, including the effective combination of algorithms could learn from each other; there was still a large research and application space for feature selection and super parameter optimization.
丁智, 李鑫家, 张霄. 基于机器学习的盾构掘进地表变形预测研究与展望[J]. 隧道与地下工程灾害防治, 2022, 4(3): 1-9.
DING Zhi, LI Xinjia, ZHANG Xiao. Research and prospect of surface deformation prediction of shield tunneling based on machine learning. Hazard Control in Tunnelling and Underground Engineering, 2022, 4(3): 1-9.
[1] 2021年上半年中国内地城轨交通线路概况[J]. 城市轨道交通, 2021, 5:1-2. Overview of urban rail transit lines in mainland China in the first half of 2021[J]. Urban Rail Transit, 2021, 5:1-2. [2] 张云,殷宗泽,徐永福.盾构法隧道引起的地表变形分析[J]. 岩石力学与工程学报, 2002, 21(3):388-392. ZHANG Yun, YIN Zongze, XU Yongfu. Analysis on three-dimensional ground surface deformations due to shield tunnel[J]. Chinese Journal of Rock Mechanics and Engineering, 2002, 21(3):388-392. [3] 梁荣柱, 夏唐代, 林存刚, 等. 盾构推进引起地表变形及深层土体水平位移分析[J]. 岩石力学与工程学报, 2015,34(3):583-593. LIANG Rongzhu, XIA Tangdai, LIN Cungang, et al. Analysis of ground surface displacement and horizontal movement of deep soils induced by shield advancing[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34(3):583-593. [4] 张品. 基于机器学习算法的盾构掘进地表沉降预测及控制[D]. 长沙: 湖南大学, 2019. ZHANG Pin. Prediction and control of tunneling-induced settlement using machine learning algorithms[D]. Changsha: Hunan University, 2019. [5] 朱才辉,李宁.地铁施工诱发地表最大沉降量估算及规律分析[J].岩石力学与工程学报,2017,36(增刊1):3543-3560. ZHU Caihui, LI Ning. Estimation and regularity analysis of maximal surface settlement induced by subway construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(Suppl.1):3543-3560. [6] KARAKUS M, FOWELLR J. 2-D and 3-D finite element analyses for the settlement due to soft ground tunnelling[J]. Tunnelling & Underground Space Technology, 2006, 21(3):392. [7] 包子阳.神经网络与深度学习——基于TensorFlow框架和Python技术实现[M]. 北京:电子工业出版社, 2019. [8] 黄鲁成, 薛爽. 机器学习技术发展现状与国际竞争分析[J]. 现代情报, 2019, 39(10): 165-176. HUANG Lucheng, XUE Shuang. The development status and international competition analysis of machine learning[J]. Journal of Modern Information, 2019, 39(10): 165-176. [9] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. [10] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297. [11] 李欣海. 随机森林模型在分类与回归分析中的应用[J]. 应用昆虫学报, 2013,50(4):1190-1197. LI Xinhai. Using “random forest” for classification and regression[J]. Chinese Journal of Applied Entomology, 2013, 50(4):1190-1197. [12] LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551. [13] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. [14] KIM C Y, BAE G J, HONG S W, et al. Neural network based prediction of ground surface settlements due to tunnelling[J]. Computers and Geotechnics, 2001, 28(6/7): 517-547. [15] SUWANSAWAT S, EINSTEIN H H. Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling[J]. Tunnelling and Underground Space Technology, 2006, 21(2): 133-150. [16] DING Lieyun, WANG Fan, LUO Haobin, et al. Feedforward analysis for shield-ground system[J]. Journal of Computing in Civil Engineering, 2013, 27(3): 231-242. [17] CHEN Dongfang, FENG Xiating, XU Dingping, et al. Use of an improved ANN model to predict collapse depth of thin and extremely thin layered rock strata during tunnelling[J]. Tunnelling and Underground Space Technology, 2016, 51:372-386. [18] FENG Xiating, ZHANG Chuanqing, QIU Shili, et al. Dynamic design method for deep hard rock tunnels and its application[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2016, 8(4):443-461. [19] CHEN Renpeng, YIN Xinsheng, TANG Lüjun, et al. Centrifugal model tests on face failure of earth pressure balance shield induced by steady state seepage in saturated sandy silt ground[J]. Tunnelling and Underground Space Technology, 2018, 81: 315-325. [20] 江英超, 何川, 胡雄玉, 等. 砂土地层盾构隧道施工对地层扰动的室内掘进试验研究[J]. 岩石力学与工程学报, 2013, 32(12): 2550-2559. JIANG Yingchao, HE Chuan, HU Xiongyu, et al. Laboratory test study of soil disturbance caused by shield tunnelling in sandy strata[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32(12): 2550-2559. [21] ZHANG Pin, WU Huaina, CHEN Renpeng, et al. A critical evaluation of machine learning and deep learning in shield-ground interaction prediction[J].Tunnelling and Underground Space Technology, 2020, 106:103593. [22] ZHANG Kun, LÜ Haimin, SHEN Shuilong, et al. Evolutionary hybrid neural network approach to predict shield tunneling-induced ground settlements[J]. Tunnelling and Underground Space Technology, 2020, 106,103594. [23] CHEN Renpeng, ZHANG Pin, KANG Xin, et al. Prediction of maximum surface settlement caused by earth pressure balance(EPB)shield tunneling with ANN methods[J]. Soils and Foundations, 2019, 59(2):284-295. [24] 杨欢欢, 杨双锁, 罗百胜. 地铁盾构施工地表变形的神经网络预测及应用[J]. 中国科技论文, 2019,14(6):625-629. YANG Huanhuan, YANG Shuangsuo, LUO Baisheng. Prediction and application of neural network on surface deformation from subway shield tunneling construction[J]. China Sciencepaper, 2019, 14(6):625-629. [25] 韩冰, 袁颖. 基于主成分分析的GA-SVM地表沉降预测模型[J]. 中国科技论文, 2018, 13(9):1045-1049. HAN Bing, YUAN Ying. Application of GA-SVM model based on principal component nalysis to prediction of surface settlement of shield construction[J]. China Sciencepaper, 2018, 13(9):1045-1049. [26] 李兴春, 李兴高. 基于神经模糊推理系统的盾构施工地表沉降预测[J]. 北京交通大学学报, 2018,42(1):18-24. LI Xingchun, LI Xinggao. Prediction of ground surface settlement induced by shield tunneling construction based on neural fuzzy inference system[J]. Journal of Beijing Jiaotong University, 2018, 42(1):18-24. [27] 郝如江, 季雁鹏, 倪振利. 基于DEACO-WNN的盾构施工地表沉降预测[J]. 铁道工程学报, 2015, 32(1):12-16. HAO Rujiang, JI Yanpeng, NI Zhenli. Study on predicting the surface settlement for shield tunneling based on DEACO-WNN[J]. Journal of Railway Engineering Society, 2015, 32(1):12-16. [28] 潘宇平, 倪静, 李林, 等. 基于LIB-SVM的盾构隧道地表沉降预测方法研究[J]. 水资源与水工程学报, 2018,29(3):231-235. PAN Yuping, NI Jing, LI Lin, et al. Prediction method of ground surface settlement caused by shield tunnel construction based on LIB-SVM[J]. Journal of Water Resources and Water Engineering, 2018, 29(3): 231-235. [29] 李洛宾, 龚晓南, 甘晓露, 等. 基于循环神经网络的盾构隧道引发地面最大沉降预测[J]. 土木工程学报, 2020,53(增刊1):13-19. LI Luobin, GONG Xiaonan, GAN Xiaolu, et al. Prediction of maximum ground settlement induced by shield tunneling based on recurrent neural network[J]. China Civil Engineering Journal, 2020, 53(Suppl.1):13-19. [30] 陈仁朋, 戴田, 张品, 等. 基于机器学习算法的盾构掘进地表沉降预测方法[J]. 湖南大学学报(自然科学版), 2021,48(7):111-118. CHEN Renpeng, DAI Tian, ZHANG Pin, et al. Prediction method of tunneling-induced settlement using machine learning algorithms[J]. Journal of Hunan University(Natural Sciences), 2021, 48(7):111-118. [31] BOUAYAD D, EMERIAULT F. Modeling the relationship between ground surface settlements induced by shield tunneling and the operational and geological parameters based on the hybrid PCA/ANFIS method[J]. Tunnelling and Underground Space Technology, 2017, 68: 142-152. [32] 张勇. 基于大数据的盾构机掘进参数研究[D]. 石家庄:石家庄铁道大学, 2019. ZHANG Yong. Study on tunneling parameters of shield machine based on big data[D]. Shijiazhuang: Shijiazhuang Tiedao University, 2019. [33] 贾波. 宁波轨道交通土性指标的统计分析及工程应用研究[D]. 宁波: 宁波大学, 2013. JIA Bo. The statistical analysis and engineering application study on the soil index in of Ningbo rail transit[D]. Ningbo, China: Ningbo University, 2013. [34] ZHANG Qianli, LIU Zhenyu, TAN Jianrong. Prediction of geological conditions for a tunnel boring machine using big operational data[J]. Automation in Construction, 2019, 100:73-83. [35] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016. [36] 谭鹏, 曹平. 基于灰色关联支持向量机的地表沉降预测[J]. 中南大学学报(自然科学版), 2012, 43(2):632-637. TAN Peng, CAO Ping. Predicting surface settlement of tunnel using grey relational-support vector machine[J]. Journal of Central South University(Science and Technology), 2012, 43(2):632-637. [37] CHENG Zhiliang, ZHOU Wanhuan, DING Zhi, et al. Estimation of spatiotemporal response of rooted soil using a machine learning approach [J]. Journal of Zhejiang University-Science A(Applied Physics & Engineering), 2020, 21(6):462-477. [38] SHI Jingsheng, ORTIGAO J A R, BAI Junli. Modular neural networks for predicting settlements during tunneling[J].Journal of Geotechnical and Geoenvironmental Engineering, 1998, 124(5): 389-395. [39] POURTAGHI A, LOTFOLLAHI-YAGHIN M A.Wavenet ability assessment in comparison to ANN for predicting the maximum surface settlement caused by tunneling[J]. Tunnelling and Underground Space Technology, 2012, 28: 257-271. [40] 陈喜凤, 刘岭, 黄腾. 紧邻大型深基坑的地铁隧道沉降预测方法研究[J]. 现代隧道技术, 2014, 51(6):94-100. CHEN Xifeng, LIU Ling, HUANG Teng. Settlement prediction for a metro tunnel adjacent to a deep large-scale foundation pit[J]. Modern Tunnelling Technology, 2014, 51(6):94-100. [41] WANG Fan, GOU Biancai, QIN Yawei. Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine[J]. Computers and Geotechnics, 2013, 54:125-132. [42] ZHOU Jian, SHI Xiuzhi, DU Kun, et al. Feasibility of random-forest approach for prediction of ground settlements induced by the construction of a shield-driven tunnel[J]. International Journal of Geomechanics, 2017, 17(6): 04016129. [43] 武铁路. 基于深度学习的破碎带盾构施工沉降预测分析[J]. 隧道建设(中英文), 2019, 39(2):197-203. WU Tielu. Ground settlement prediction of shield tunneling in fractured zone based on deep learning method[J]. Tunnel Construction, 2019, 39(2):197-203. [44] 岳岭, 刘方, 刘辉, 等. 基于人工神经网络的大直径盾构隧道施工地层变形预测分析[J]. 铁道标准设计, 2020, 64(1):122-126. YUE Ling, LIU Fang, LIU Hui, et al. Prediction and analysis of ground deformation in large diameter shield tunnel construction based on artificial neural network[J]. Railway Standard Design, 2020, 64(1):122-126. [45] 孙钧,袁金荣. 盾构施工扰动与地层移动及其智能神经网络预测[J]. 岩土工程学报, 2001, 23(3):261-267. SUN Jun, YUAN Jinrong. Soil disturbance and ground movement under shield tunnelling and its intelligent prediction by using ANN technology[J]. Chinese Journal of Geotechnical Engineering, 2001, 23(3):261-267. [46] NEAUPANE K M, ADHIKARI N R. Prediction of tunneling-induced ground movement with the multi-layer perceptron[J]. Tunnelling and Underground Space Technology, 2006, 21(2): 151-159. [47] SANTOS O J, CELESTINO T B. Artificial neural networks analysis of São Paulo subway tunnel settlement data[J]. Tunnelling and Underground Space Technology, 2008, 23(5): 481-491. [48] BOUBOU R, EMERIAULT F, KASTNER R. Artificial neural network application for the prediction of ground surface movements induced by shield tunnelling[J]. Canadian Geotechnical Journal, 2010, 47(11): 1214-1233. [49] DARABI A, AHANGARI K, NOORZAD A, et al. Subsidence estimation utilizing various approaches—a case study: Tehran No. 3 Subway Line[J]. Tunnelling and Underground Space Technology, 2012, 31: 117-127. [50] ZHANG Limao, WU Xianguo, JI Wenying, et al. Intelligent approach to estimation of tunnel-induced ground settlement using wavelet packet and support vector machines[J].Journal of Computing in Civil Engineering, 2017, 31(2): 04016053. [51] 白永学, 漆泰岳, 李有道, 等. 基于LSSVM对盾构施工诱发地面塌陷变形预测[J]. 岩石力学与工程学报, 2013,32(增刊2): 3666-3674. BAI Yongxue, QI Taiyue, LI Youdao, et al. Prediction for surface collapse deformation of shield construction based on lssvm[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32(Suppl.2): 3666-3674. [52] AHANGARI K, MOEINOSSADAT S R, BEHNIA D. Estimation of tunnelling-induced settlement by modern intelligent methods[J]. Soils and Foundations, 2015, 55(4): 737-748. [53] HOUHOU M N, EMERIAULT F, KASTNER R, et al. Rétro-analyse tridimensionnelle d'une excavation profonde multisupportée instrumentée[J]. European Journal of Environmental and Civil Engineering, 2010, 14(1): 55-86. [54] 赵凤阳. 小波神经网络在隧道施工沉降预测中的应用[J]. 测绘科学, 2016, 41(12):283-287. ZHAO Fengyang. Application of wavelet neural network in the monitoring of tunnel settlement[J]. Science of Surveying and Mapping, 2016, 41(12):283-287. [55] BREUEL T M. The effects of hyperparameters on SGD training of neural networks[J]. Computer Science, 2015: 1-19. [56] YOUNG S R, ROSE D C, KARNOWSKI T P, et al. Optimizing deep learning hyper-parameters through an evolutionary algorithm[C] // Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments. New York, USA: ACM Press, 2015: 1-5. [57] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359-366. [58] 王鹏. 基于机器学习的地铁隧道施工扰动控制研究[J]. 现代隧道技术, 2019, 56(增刊2):368-373. WANG Peng. Control of construction disturbance induced by shield tunnelling based on machine learning[J]. Modern Tunnelling Technology, 2019, 56(Suppl.2):368-373. [59] 高彩云,崔希民,高宁.熵权遗传算法及极限学习机地铁隧道沉降预测[J]. 测绘科学, 2016, 41(2):71-75. GAO Caiyun, CUI Ximin, GAO Ning. Metro tunnel settlement prediction based on entropy weight GA-ELM model[J]. Science of Surveying and Mapping, 2016, 41(2):71-75. [60] 陈柚州, 任涛, 邓朋, 等. 基于人工蜂群优化小波神经网络的隧道沉降预测[J]. 现代隧道技术, 2019,56(4): 56-61. CHEN Youzhou, REN Tao, DENG Peng, et al. Prediction of tunnel settlements by optimized wavelet neural network based on ABC[J]. Modern Tunnelling Technology, 2019, 56(4): 56-61. [61] TSERANIDIS S, BROWN N C, MUELLER C T. Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures[J]. Automation in Construction, 2016, 72: 279-293.
2022, Vol. 4 
