Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods

Abstract In order to determine the appropriate model for predicting the maximum surface settlement caused by EPB shield tunneling, three artificial neural network (ANN) methods, back-propagation (BP) neural network, the radial basis function (RBF) neural network, and the general regression neural network (GRNN), were employed and the results were compared. The nonlinear relationship between maximum ground surface settlements and geometry, geological conditions, and shield operation parameters were considered in the ANN models. A total number of 200 data sets obtained from the Changsha metro line 4 project were used to train and validate the ANN models. A modified index that defines the physical significance of the input parameters was proposed to quantify the geological parameters, which improves the prediction accuracy of ANN models. Based on the analysis, the GRNN model was found to outperform the BP and RBF neural networks in terms of accuracy and computational time. Analysis results also indicated that strong correlations were established between the predicted and measured settlements in GRNN model with MAE = 1.10, and RMSE = 1.35, respectively. Error analysis revealed that it is necessary to update datasets during EPB shield tunneling, though the database is huge.

[1]  Kaveh Ahangari,et al.  Estimation of tunnelling-induced settlement by modern intelligent methods , 2015 .

[2]  Hongwei Huang,et al.  Simplified procedure for finite element analysis of the longitudinal performance of shield tunnels considering spatial soil variability in longitudinal direction , 2015 .

[3]  Herbert H. Einstein,et al.  Describing settlement troughs over twin tunnels using a superposition technique , 2007 .

[4]  Kenichi Soga,et al.  Long-term tunnel behaviour and ground movements after tunnelling in clayey soils , 2017 .

[5]  Xiaolin Tang,et al.  Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study , 2018, Comput. Ind. Eng..

[6]  Xin Kang,et al.  Strain-Controlled Cyclic Simple Shear Tests on Sand with Radial Strain Measurements , 2016 .

[7]  J. R. Booker,et al.  Surface settlements due to deformation of a tunnel in an elastic half plane , 1996 .

[8]  Fabrice Emeriault,et al.  Modeling the relationship between ground surface settlements induced by shield tunneling and the operational and geological parameters based on the hybrid PCA/ANFIS method , 2017 .

[9]  Afshin Tatar,et al.  Utilization of the RBF network to model the nucleate pool boiling heat transfer properties of refrigerant-oil mixtures with nanoparticles , 2017 .

[10]  K. Ahangari,et al.  Subsidence estimation utilizing various approaches - A case study: Tehran No. 3 subway line , 2012 .

[11]  Reza Rooki,et al.  Prediction of Rare Earth Elements in Neutral Alkaline Mine Drainage from Razi Coal Mine, Golestan Province, Northeast Iran, Using General Regression Neural Network , 2013 .

[12]  Mohammad Ali Lotfollahi-Yaghin,et al.  Wavenet ability assessment in comparison to ANN for predicting the maximum surface settlement caused by tunneling , 2012 .

[13]  S. W. Hong,et al.  Neural network based prediction of ground surface settlements due to tunnelling , 2001 .

[14]  Roman Lackner,et al.  Back analysis of model parameters in geotechnical engineering by means of soft computing , 2003 .

[15]  Quan Jiang,et al.  Use of an improved ANN model to predict collapse depth of thin and extremely thin layered rock strata during tunnelling , 2016 .

[16]  P B Attewell,et al.  SETTLEMENT DEVELOPMENT CAUSED BY TUNNELLING IN SOIL , 1985 .

[17]  Chee Nan Chen,et al.  Stress redistribution and ground arch development during tunneling , 2011 .

[18]  Alessandra Paternesi,et al.  Numerical analyses of stability and deformation behavior of reinforced and unreinforced tunnel faces , 2017 .

[19]  Shunde Yin,et al.  Characterization of In Situ Stress State and Joint Properties from Extended Leak-Off Tests in Fractured Reservoirs , 2017 .

[20]  Tianqi Zhang,et al.  Study of the collapse mechanism of shield tunnels due to the failure of segments in sandy ground , 2017 .

[21]  Harry G. Poulos,et al.  Analytical Prediction for Tunneling-Induced Ground Movements in Clays , 1998 .

[22]  Farzin Yaghmaee,et al.  Application of GRNN neural network in non-texture image inpainting and restoration , 2015, Pattern Recognit. Lett..

[23]  Mark B. Jaksa,et al.  Load-settlement behavior modeling of single piles using artificial neural networks and CPT data , 2017 .

[24]  Jingsheng Shi,et al.  MODULAR NEURAL NETWORKS FOR PREDICTING SETTLEMENTS DURING TUNNELING , 1998 .

[25]  B. B. V. L. Deepak,et al.  Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol , 2016 .

[26]  Wei-Che Chang,et al.  Directional projection in stereographic representation of three-dimensional stress redistribution during tunnelling , 2017 .

[27]  S. Suwansawat,et al.  Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling , 2006 .

[28]  Ping Jiang,et al.  Displacement prediction of landslide based on generalized regression neural networks with K-fold cross-validation , 2016, Neurocomputing.

[29]  C. Kayadelen,et al.  Soil liquefaction modeling by Genetic Expression Programming and Neuro-Fuzzy , 2011, Expert Syst. Appl..

[30]  Chang-Yu Ou,et al.  Failure Investigation at a Collapsed Deep Excavation in Very Sensitive Organic Soft Clay , 2015 .

[31]  Giuseppe Modoni,et al.  Prediction of the diameter of jet grouting columns with artificial neural networks , 2015 .

[32]  Masoud Monjezi,et al.  Application of artificial intelligence algorithms in predicting tunnel convergence to avoid TBM jamming phenomenon , 2012 .

[33]  A. Bobet,et al.  Predictions of ground deformations in shallow tunnels in clay , 2002 .

[34]  Antonio Bobet,et al.  Analytical Solutions for Shallow Tunnels in Saturated Ground , 2001 .

[35]  O. J. Santos,et al.  Artificial neural networks analysis of São Paulo subway tunnel settlement data , 2008 .

[36]  Eric Leca,et al.  Settlements induced by tunneling in Soft Ground , 2007 .

[37]  Tarcisio B. Celestino,et al.  Errors in ground distortions due to settlement trough adjustment , 2000 .

[38]  Fabrice Emeriault,et al.  Artificial neural network application for the prediction of ground surface movements induced by shield tunnelling , 2010 .

[39]  C Sagaseta,et al.  ANALYSIS OF UNDRAINED SOIL DEFORMATION DUE TO GROUND LOSS , 1987 .

[40]  K. Soga,et al.  Estimating the Effects of Tunneling on Existing Pipelines , 2005 .

[41]  Junneng Ye,et al.  Investigation of response of metro tunnels due to adjacent large excavation and protective measures in soft soils , 2016 .

[42]  Sung Eun Cho,et al.  Probabilistic stability analyses of slopes using the ANN-based response surface , 2009 .

[43]  Marina Theodosiou,et al.  Disaggregation & aggregation of time series components: A hybrid forecasting approach using generalized regression neural networks and the theta method , 2011, Neurocomputing.

[44]  Somnath Mukherjee,et al.  Kinetic Data Analysis by MLR and ANN Models for Phenol Attenuation in Peat Soil , 2017 .