Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning

This paper adopts the NGI-ADP soil model to carry out finite element analysis,based on which the effects of soft clay anisotropy on the diaphragm wall deflections in the braced excavation were evaluated.More than one thousand finite element cases were numerically analyzed,followed by extensive parametric studies.Surrogate models were developed via ensemble learning methods(ELMs),including the e Xtreme Gradient Boosting(XGBoost),and Random Forest Regression(RFR)to predict the maximum lateral wall deformation(δhmax).Then the results of ELMs were compared with conventional soft computing methods such as Decision Tree Regression(DTR),Multilayer Perceptron Regression(MLPR),and Multivariate Adaptive Regression Splines(MARS).This study presents a cutting-edge application of ensemble learning in geotechnical engineering and a reasonable methodology that allows engineers to determine the wall deflection in a fast,alternative way.

Optimized functional linked neural network for predicting diaphragm wall deflection induced by braced excavations in clays

Deep excavation during the construction of underground systems can cause movement on the ground,especially in soft clay layers.At high levels,excessive ground movements can lead to severe damage to adjacent structures.In this study,finite element analyses(FEM)and the hardening small strain(HSS)model were performed to investigate the deflection of the diaphragm wall in the soft clay layer induced by braced excavations.Different geometric and mechanical properties of the wall were investigated to study the deflection behavior of the wall in soft clays.Accordingly,1090 hypothetical cases were surveyed and simulated based on the HSS model and FEM to evaluate the wall deflection behavior.The results were then used to develop an intelligent model for predicting wall deflection using the functional linked neural network(FLNN)with different functional expansions and activation functions.Although the FLNN is a novel approach to predict wall deflection;however,in order to improve the accuracy of the FLNN model in predicting wall deflection,three swarm-based optimization algorithms,such as artificial bee colony(ABC),Harris’s hawk’s optimization(HHO),and hunger games search(HGS),were hybridized to the FLNN model to generate three novel intelligent models,namely ABC-FLNN,HHO-FLNN,HGS-FLNN.The results of the hybrid models were then compared with the basic FLNN and MLP models.They revealed that FLNN is a good solution for predicting wall deflection,and the application of different functional expansions and activation functions has a significant effect on the outcome predictions of the wall deflection.It is remarkably interesting that the performance of the FLNN model was better than the MLP model with a mean absolute error(MAE)of 19.971,root-mean-squared error(RMSE)of 24.574,and determination coefficient(R^(2))of 0.878.Meanwhile,the performance of the MLP model only obtained an MAE of 20.321,RMSE of 27.091,and R^(2)of 0.851.Furthermore,the results also indicated that the proposed hybrid models,i.e.,ABC-FLNN,HHO-FLNN,HGS-FLNN,yielded more superior performances than those of the FLNN and MLP models in terms of the prediction of deflection behavior of diaphragm walls with an MAE in the range of 11.877 to 12.239,RMSE in the range of 15.821 to 16.045,and R^(2)in the range of 0.949 to 0.951.They can be used as an alternative tool to simulate diaphragm wall deflections under different conditions with a high degree of accuracy.

Deterministic and probabilistic analysis of great-depth braced excavations:A 32 m excavation case study in Paris

The Fort d’Issy-Vanves-Clamart(FIVC)braced excavation in France is analyzed to provide insights into the geotechnical serviceability assessment of excavations at great depth within deterministic and probabilistic frameworks.The FIVC excavation is excavated at 32 m below the ground surface in Parisian sedimentary basin and a plane-strain finite element analysis is implemented to examine the wall deflections and ground surface settlements.A stochastic finite element method based on the polynomial chaos Kriging metamodel(MSFEM)is then proposed for the probabilistic analyses.Comparisons with field measurements and former studies are carried out.Several academic cases are then conducted to investigate the great-depth excavation stability regarding the maximum horizontal wall deflection and maximum ground surface settlement.The results indicate that the proposed MSFEM is effective for probabilistic analyses and can provide useful insights for the excavation design and construction.A sensitivity analysis for seven considered random parameters is then implemented.The soil friction angle at the excavation bottom layer is the most significant one for design.The soil-wall interaction effects on the excavation stability are also given.

Numerical evaluation of the ground response induced by dewatering in a multi-aquifer system

This study presents a numerical investigation of dewatering-induced settlement and wall deflection during pumping tests in Tianjin,China.Based on the measured groundwater head and building settlement during the pumping test,a three-dimensional liquid-solid coupling model is established by using the finite element method(FEM).The void ratio,hydraulic conductivity,and elastic modulus of each layer are back-calculated through the numerical model.The groundwater drawdown,seepage field,ground settlement,horizontal ground displacement,and diaphragm wall lateral deflection are analyzed using the FEM model.The simulated results demonstrate that(i)the maximum ground settlement outside of the excavation reaches to 82 mm due to the leakage effect of aquitards;(ii)large horizontal displacement occurs in the soil during the pumping test with a maximum value of 28.3 mm,and the installation of the diaphragm wall in the aquifer can reduce the horizontal displacement of the ground;(iii)long-term pumping causes a large lateral deflection of the diaphragm wall,and a maximum value of 23.2 mm occurs at the layer where the screens of the wells are located;and(iv)long-term large-scale pumping should be avoided before excavation.

Influence of groundwater drawdown on excavation responses e A case history in Bukit Timah granitic residual soils

Performances of a braced cut-and-cover excavation system for mass rapid transit （MRT） stations of the Downtown Line Stage 2 in Singapore are presented. The excavation was carried out in the Bukit Timah granitic （BTG） residual soils and characterized by significant groundwater drawdown, due to dewatering work in complex site conditions, insufficient effective waterproof measures and more permeable soils. A two-dimensional numerical model was developed for back analysis of retaining wall movement and ground surface settlement. Comparisons of these measured excavation responses with the calculated performances were carried out, upon which the numerical simulation procedures were calibrated. In addition, the influences of groundwater drawdown on the wall deflection and ground surface settlement were numerically investigated and summarized. The performances were also compared with some commonly used empirical charts, and the results indicated that these charts are less applicable for cases with significant groundwater drawdowns. It is expected that these general behaviors will provide useful references and insights for future projects involving excavation in BTG residual soils under significant groundwater drawdowns.

An intelligent procedure for updating deformation prediction of braced excavation in clay using gated recurrent unit neural networks

This paper aims to establish an intelligent procedure that combines the observational method with the existing deep learning technique for updating deformation of braced excavation in clay.The gated recurrent unit(GRU) neural network is adopted to formulate the forecast model and learn the potential rules in the field observations using the Nesterov-accelerated Adam(Nadam) algorithm.In the proposed procedure,the GRU-based forecast model is first trained based on the field data of previous and current stages.Then,the field data of the current stage are used as input to predict the deformation response of the next stage via the previously trained GRU-based forecast model.This updating process will loop up till the end of the excavation.This procedure has the advantage of directly predicting the deformation response of unexcavated stages based on the monitoring data.The proposed intelligent procedure is verified on two well-documented cases in terms of accuracy and reliability.The results indicate that both wall deflection and ground settlement are accurately predicted as the excavation proceeds.Furthermore,the advantages of the proposed intelligent procedure compared with the Bayesian/o ptimization updating are illustrated.