Correction of soil parameters in calculation of embankment settlement using a BP network back-analysis model

Finite element method (FEM) have been widely used for the calculation of settlement of embankment on soft soils in the last decade. However, due to the complexity of construction, spatial inhomogeneity of soils, as well as sensitivity of numerical results to the variation of soil parameters, large discrepancy typically exists between numerical outputs and field observations. This paper presents a novel method, combining FEM and an improved back-propagation (BP) neural network, for correction of soil parameters in numerical prediction of embankment settlement. Duncan–Chang hyperbolic soil model is adopted with the sensitivity of eight constitutive parameters numerically investigated. The soil parameters with large sensitivity are identified, and together with the representative settlements, are used for the training of the improved BP neural network which, once established, generates correction factors of soil parameters for subsequent more accurate FEM forward predictions. It is demonstrated that the proposed numerical back-analysis framework is very efficient in practical engineering applications to calculate highway settlement.     

结构性黏土的压缩变形特性

海相软黏土的结构性对土体的变形与强度特性有着重要的影响,这种影响与爆炸挤淤置换法处理软基的置换深度直接相关,是海堤基础沉降与稳定性分析的不确定因素。为了探究结构性对海堤地基沉降的影响,并对海相软黏土的压缩特性进行定量分析,建立结构性黏土的压缩变形模型,同时给出模型参数的确定方法。利用文献中的试验数据对模型进行了验证,结果表明模型不仅适用于一维应力状态下的变形分析,能够描述三轴应力状态下结构性黏土的压缩特性。利用所建模型对浙江漩门地区海相软黏土的压缩特性进行模拟,分析表明,模型能较好地考虑结构性对该地区软黏土压缩变形的影响,为该地区海堤沉降的预测提供量化分析的手段,有助于加强结构性黏土地区海堤地基设计与施工的理论基础。     

Using and Improving Neural Network Models for Ground Settlement Prediction

Earth-fill structures such as embankments, which are constructed for the preservation of land and infrastructure, show significant amount of settlement during and after construction in lowland areas with soft grounds. Settlements are often still predicted with large uncertainty and frequently observational methods are applied using settlement monitoring results in the early stage after construction to predict the long term settlement. Most of these methods require a significant amount of measurements to enable accurate predictions. In this paper, an artificial neural network model for settlement prediction is evaluated and improved using measurement records from a test embankment in The Netherlands. Based on a learning pattern that focuses on convergence of the settlement rate, the basic model predicted settlements which were in good agreement with the measurements, when the amount of measured data used as teach data for the model exceeded a degree of consolidation of 69 %. For lower amounts of teach data the accuracy of settlement prediction was limited. To improve the accuracy of settlement prediction, it is proposed to add short-term predicted values that satisfy predefined statistical criteria of low coefficient of variance or low standard deviation to the teach data, after which the model is allowed to relearn and repredict the settlement. This procedure is repeated until all predicted values satisfy the criterion. Using the improved network model resulted in significantly better predictions. Predicted settlements were in good agreement with the measurements, even when only the measurements up to a consolidation stage of 35 % were used as initial teach data.     

Laboratory model tests about the sand embankment supported by piles with a cap beam

Piled embankment is widely used in soft soil areas. Most researches focused on effects of embankment height-net pile spacing ratios and equal settlement plane; there are limited publications paying attention to the shape of slip surfaces occurring in the embankment. In some extreme conditions, such as the ground being quite soft or embankment height needed to be restricted, to reduce the differential settlement and lateral displacement, piles are usually installed in several rows and cap beams or isolated caps are placed on the heads of piles. In this paper, five laboratory tests were carried out to investigate the effect of embankment height on the slip surfaces and stress exerted on the subsoil. Based on the observation of the slip surface’s shape within the embankment fill, a new calculation model is proposed to predict the stress exerted on the subsoil. In comparison with the experimental results, the accuracy of this new method is verified. From the perspective of reducing the differential settlement and cost savings, the embankment height is about four times net pile spacing according to this calculation model, since continuing to increase the embankment will not make an obvious difference to the reduction of soil stress exerted on the subsoil.     

三角形周期荷载作用下软基路堤沉降研究

采用能够同时考虑主次固结变形的Yin-Graham一维弹黏塑性模型,对三角形周期荷载作用下软土路堤运行期间和运行期结束时的长期沉降进行了理论分析,获得三角形周期荷载作用下软基路堤运行期结束时的总沉降计算公式和工后沉降计算公式。分析了三角形周期荷载作用下软基不考虑流固耦合与考虑流固耦合时长期沉降之间的相互关系,证明了三角形周期荷载作用下当循环荷载次数趋向于无穷大时软基具有最终沉降量与应力随时间增长的模式无关的性质。按照文中提供的总沉降计算公式,针对具体工程的土工参数,对路堤运行期结束时的总沉降量进行了计算,并由此确定运行期开始时软基应发生的沉降量,为合理确定高速公路路面铺筑时机提供沉降标准。     

Ground improvement using SPVD and RPE

Excessive total and differential settlement at the intersection of a surcharged prefabricated vertical drain (SPVD) and a rigid piled embankment on soft ground during the post-construction period leads to considerable time and costs being spent on repetitive remedial works in the future. This paper presents a sustainable design approach for high and long embankment filling on soft clay at the approach to the structure by introducing the intersection of an SPVD at the transition to a rigid piled embankment in order to regulate the differential settlement between the two conventional ground treatment approaches. This paper also presents a full-scale field study to validate the performance of the intersection of the SPVD at the transition to the rigid piled embankment. By introducing the intersection ground treatment, post-construction settlement and differential settlement are minimised significantly, while the post-construction total settlement at the rigid transition piled embankment (TPE) zone is reduced significantly by about 80 to 95% of the total settlement, as compared to a conventional TPE.     

公路软基沉降函数干涉神经网络预测模型

建立了基于函数干涉神经网络的公路软基沉降预测模型。工程实例表明,所建议的模型外延性好,而且,可以由较短预压期内沉降观测资料预测远期沉降发展,与传统沉降预测模型相比具有显著的优越性,工程应用前景广阔。     

Modelling the settlement behaviour of a strip footing on sloping sandy fill under cyclic loading conditions

This paper investigates the settlement behaviour of a strip footing seating on the crest of an embankment and subjected to cyclic loading. The embankment fill is a dense sand and the issue is the gradual accumulation of settlement over a large number of load repetitions. Cyclic triaxial tests were first conducted to develop a consistent but simple material model for numerical implementation. Particular emphasis was placed on linking the stress-strain behaviour of an unload-reload cycle to the accumulation of permanent strain, with only five input parameters required to model the cyclic behaviour. The material model was implemented in a numerical analysis to compute the settlement behaviour obtained from model tests conducted by another researcher. It is pertinent to highlight that the same soil, compacted to same density at same moisture content, was used for both the cyclic triaxial tests and model tests. Reasonable to good agreement between the experimental and numerical results was achieved.     

Prediction of pile settlement using artificial neural networks based on standard penetration test data

In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on standard penetration test (SPT) data. Approximately 1000 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions.     

Application of an Expert System for the Assessment of Blast Vibration

The purpose of this article is to evaluate and predict the blast induced ground vibration using different conventional vibration predictors and artificial neural network (ANN) at a surface coal mine of India. Ground Vibration is a seismic wave that spread out from the blast hole when detonated in a confined manner. 128 blast vibrations were recorded and monitored in and around the surface coal mine at different strategic and vulnerable locations. Among these, 103 blast vibrations data sets were used for the training of the ANN network as well as to determine site constants of various conventional vibration predictors, whereas rest 25 blast vibration data sets were used for the validation and comparison by ANN and empirical formulas. Two types of ANN model based on two parameters (maximum charge per delay and distance between blast face to monitoring point) and multiple parameters (burden, spacing, charge length, maximum charge per delay and distance between blast face to monitoring point) were used in the present study to predict the peak particle velocity. Finally, it is found that the ANN model based on multiple input parameters have better prediction capability over two input parameters ANN model and conventional vibration predictors.     

考虑软土流变特性的沉降预测模型研究

增长曲线模型自身的特点决定了其能很好地预测地基沉降的发展趋势。先将该模型推广到多级填土荷载下的路堤沉降预测中,接着基于绝对时间坐标系下的软土次压缩计算式,提出了带软土流变项的新型增长曲线模型,并采用数学中的最优化技术,结合前期沉降实测资料对模型中待定参数进行反演。实例计算表明：该模型对沉降预测精度高,能合理地反映出土颗粒骨架的蠕变过程,且能较准确地给出不同时刻的次压缩量,具有一定的工程参考价值。     

路堤荷载作用下软基沉降特性研究

为探究路基断面几何参数对软基沉降特性的影响，基于弹性Biot三维固结有限元程序PDSS，就路基顶面宽度、路基高度及边坡坡比等断面几何参数对软基沉降特性的影响进行较深入的模拟分析，重点探讨现行各类铁路、公路路基宽度下软基沉降变形的模式。宽窄路堤荷载作用下软基的沉降模式不同，宽路堤软土路基沉降盆表现为“W”形状，而窄路堤软土路基的沉降盆表现为“V”形状。     

Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine

Accurate prediction of ground surface settlement is necessary for effectively controlling the settlement that develops during tunneling. Many models have been established for this purpose by extracting the relationship between the settlement and the factors that influence it. However, most of the models focused on the maximum ground surface settlement and do not involve dynamic and real-time predictions. This paper investigated how tunneling-induced ground surface settlement developed using a smooth relevance vector machine with a wavelet kernel (wsRVM). Various factors that affect this settlement, including geometrical, geological and shield operational parameters were considered. The model was applied to earth pressure balance (EPB) shield-driven tunnels. The results indicate that the prediction model performs well and that the distribution of the predictions can provide a measure of the prediction uncertainty. Unlike conventional methods that requireadditional efforts to determine relevant model parameters, the proposed method can optimize the parameters in the training process. The results of the parametric study conducted show that the model performance can be improved by the optimization and that the method can serve as a simple tool for practitioners to use in estimating ground surface settlement development during tunneling.     

软土路基沉降变权重组合S型曲线预测方法研究

通过对软土路基沉降发展规律及其沉降曲线特点进行深入研究,在S型单项预测模型基础上,基于5种S型增长曲线模型,引进组合预测的思想,重点探讨了软土路基沉降发展的预测方法与理论,并建立了软土路基沉降预测的变权重组合S型增长模型,通过数学规划方法求解,从而可根据有限的实测沉降观测数据预测软土路基沉降发展过程。工程实例分析表明,利用该模型与方法得到的预测曲线与实测曲线吻合良好,能够满足工程要求,此外,变权重组合预测模型比其它单项模型具有明显的优越性,为软土路基沉降发展预测提供了一种有效而实用的方法。     

A combined method to predict the long-term settlements of roads on soft soil under cyclic traffic loadings

In order to investigate the mechanism of the long-term settlement of road on the soft soil, an in situ measurement of a highway in southeast China was conducted during both the construction and post-construction stage. In the theoretical analysis, the long-term settlement of the pavement on thick soft soils was divided into three main components: the consolidation settlement, the creep deformation and the traffic load-induced deformation. The equivalent time line model based on the viscous–elastic–plastic theory was adopted to simulate the road settlement caused by the consolidation and creep of the subsoil. A cyclic strain accumulation model, which was obtained from laboratory tests of soil elements, was adopted to consider the road settlement induced by cyclic traffic loadings. A pavement dynamic response model was used to calculate the dynamic stresses in the subsoil generated by moving traffic loads when the road was open to service. It was found that the equivalent time line model combined with the cyclic strain accumulation model could predict the road settlement accurately at both the construction and post-construction stage. Numerical results showed that the traffic speed had limited effect on the post-construction road settlements for the speed range considered. The post-construction settlement of the road, mainly composed of the traffic-induced settlement and soil creep deformation, could be reduced significantly by increasing the embankment surcharge during the construction stage. The creep component accounted for over 10% of the total post-construction settlement, while the percentage of the creep deformation in total post-construction settlement decreased rapidly as the embankment surcharge increased.     

高速公路扩建工程软基拓宽的沉降监测与分析

高速公路拓宽建设中新老路基特别是软土路基的固结沉降与力学性质的差异将引起严重的路面开裂,因而控制其差异沉降、防止拼接处路面开裂成为扩建工程软基处理中的技术关键。针对采用薄壁管桩和粉喷桩处理的软基路段,选取具有典型地质条件及较高填方的断面,通过埋设地面沉降板,对拓宽路基及新老路堤结合部进行了为期9个月的沉降动态监测。监测结果表明,拓宽路基的累计沉降及差异沉降均很小,后期沉降速率小于控制标准,为新老路基差异沉降的评价提供了依据;薄壁管桩用于处理埋深大、层厚大的拓宽软基及粉喷桩用于处理埋深浅、层厚较小的拓宽软基具有各自的适用性,拓宽后的新老路基已形成整体性强的复合地基,达到了路基拓宽的理想效果。     

Efficient and flexible Bayesian updating of embankment settlement on soft soils based on different monitoring datasets

Acta Geotechnica - In situ monitoring provides valuable information to update the predictions of the embankment settlement on soft soils. Observational data obtained at different monitoring moments...     

Appraising stone column settlement prediction methods using finite element analyses

Numerous approaches exist for the prediction of the settlement improvement offered by the vibro-replacement technique in weak or marginal soil deposits. The majority of the settlement prediction methods are based on the unit cell assumption, with a small number based on plane strain or homogenisation techniques. In this paper, a comprehensive review and assessment of the more popular settlement prediction methods is carried out with a view to establishing which method(s) is/are in best agreement with finite element predictions from a series of PLAXIS 2D axisymmetric analyses on an end-bearing column. The Hardening Soil Model in PLAXIS 2D has been used to model the behaviour of both the granular column material and the treated soft clay soil. This study has shown that purely elastic settlement prediction methods overestimate the settlement improvement for large modular ratios, while the methods based on elastic–plastic theory are in better agreement with finite element predictions at higher modular ratios. In addition, a parameter sensitivity study has been carried out to establish the influence of a range of different design parameters on predictions obtained using a selection of elastic–plastic methods.     

新型桩板结构对高速铁路软基沉降控制作用离心试验

在CFG、PHC等刚性桩桩顶加设50 cm厚筏型钢筋混凝土形成板桩板结构控制深厚软土路基沉降,是高速铁路建设中提出的新型地基处理形式,以满足高标准铁路路基变形要求。通过对群桩处理的深厚软土路基在有无钢筋混凝土板时路基沉降的离心模拟,重点研究了钢筋混凝土板对路基沉降的控制作用以及桩、板与土体之间的相对变形。试验结果表明,在群桩处理地基上部铺设一定厚度的钢筋混凝土板,可以使路基整体沉降减小12 %,并使路基整体沉降更加均匀;桩端平面上部1/3桩长范围内土体由软塑状态转变为硬塑状态,密度和含水率变化显著;加载作用对路基变形影响深度大于40 m。