An efficient physics-guided Bayesian framework for predicting ground settlement profile during excavations in clay

Recently,the application of Bayesian updating to predict excavation-induced deformation has proven successful and improved prediction accuracy significantly.However,updating the ground settlement profile,which is crucial for determining potential damage to nearby infrastructures,has received limited attention.To address this,this paper proposes a physics-guided simplified model combined with a Bayesian updating framework to accurately predict the ground settlement profile.The advantage of this model is that it eliminates the need for complex finite element modeling and makes the updating framework user-friendly.Furthermore,the model is physically interpretable,which can provide valuable references for construction adjustments.The effectiveness of the proposed method is demonstrated through two field case studies,showing that it can yield satisfactory predictions for the settlement profile.

Ground settlement and tunnel response due to twin-curved shield tunnelling in soft ground with small clear distance

Twin curved tunnels are often encountered in shield tunnelling,where significant complexities in densely exploited underground space are observed.In this study,the ground settlement and tunnel deformation due to twin-curved shield tunnelling in soft ground were investigated using numerical simulation and field monitoring.Different curvature radii of twin curved tunnels and subsequent effects of tunnel construction were considered to reveal the tunnelling effect on ground surface settlement and tunnel deformation.The results show that the settlement trough yields one offset towards inside of curved shield tunnelling.The location of settlement trough and maximum settlement were affected by curvature radius but except for the shape and width of settlement trough.Adjacent parallel twin-curved shield tunnelling could increase the offset of existing settlement trough and maximum settlement.Then,an empirical prediction of surface settlement trough due to twin-curved shield tunnelling with same tunnel diameters in soft clay was proposed,which was applicable to curvature radius less than 800 m.Finally,a minimum radius of 600 m of curvature tunnel was proposed in terms of allowable convergence deformation of tunnel.The result could provide guidance on safety evaluation for twin curved shield tunnelling construction.

Effectiveness of predicting tunneling-induced ground settlements using machine learning methods with small datasets

Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.

Study on influence of ground settlement in bored metro tunnel

At present the bored construction method is one of the main construction methods of metro and tunnel construction in China. The empirical estimated formulas of tunnel ground surface settlement using the bored construction method were obtained, combining the mechanical stimulant calculated result of tunnel model of different embedded depth, different cross section and different construction method and the actual measurement data of Beijing metro construction. According to the regressed analysis of calculated data, the calculated equations of ground surface settlement value and settlement range of tunnel section under the condition of different embedded depth, different cross section and different construction method were gained. Among them there are some empirical formulas can apply to the construction design of metro tunnel directly.

Ground settlement sedimentation time-space effect and ground settlement control standards

Since different underground engineering contains different geological conditions,structure and excavation methods,their disturbing degree on the ground also differs,but ground surface settlement caused by excavation has one common point that they will form a ground surface settlement curve.Based on data statistical analysis,the article puts forward the relationship between point of inflection in digging tunnels with shallowburied method and the span of tunnel excavation against typical geological conditions in Changchun so as to predict the impact of tunnel excavation and improve reasonable ground surface settlement control standard.Research result will be useful for study on ground surface control standard in digging tunnels with shallow-buried method and setting settlement standard.

Analytical solutions of ground settlement induced by yaw in a space curved shield tunnel

This paper aims to provide the analytical solutions of the ground settlement for a space curved shield tunnel in the case of yaw construction.Settlement inducements include ground loss and construction loads,and two corresponding analytical models have been proposed in this study.Three-dimensional image theory has been adopted to calculate the ground settlement due to ground loss.Yawrelated parameters are introduced into the calculation model to deduce the relevant laws of the ground settlement.Based on modified Mindlin solutions,analytical models are established to calculate the ground settlement induced by construction loads,such as the frontal additional thrust,axial friction of shield shell,and the grouting pressure.The method of calculating the position of the shield machine in the ground is refined,and the influence area of construction loads from the shield machine is optimized.Subsequently,the obtained solutions are validated by a numerical model and field data.Besides,a comparison reveals that the proposed model is the composition of three classical analytical models,thus it excels them in solving the problem mentioned.Finally,parametric analyses of yaw are conducted to examine yaw angle and pitch angle on ground settlement.The proposed model can effectively predict ground settlement caused by the spatial linear shield tunneling process.

Shallow Tunneling Method and Control Measure for Ground Surface Settlement

In order to ensure that the tunnel deformation and surface settlement are controlled within the allowable range during the construction process,the design unit has compiled technical measures and monitoring schemes for ground settlement control of this project.Based on the example of a shallow tunneling project on Subway line 8,this paper analyzes and discusses the shallow tunneling method in detail and puts forward corresponding technical measures for ground settlement control.

Analytical solutions to ground settlement induced by ground loss and construction loadings during curved shield tunneling

This paper focuses on the ground settlement induced by the construction of a curved shield tunnel.Ground loss and construction loadings are the two factors causing ground settlement,and two corresponding analytical models were developed.First,the ground settlement due to ground loss was analyzed based on 3D image theory.The"integrative gap at shield tail"(IGST)and overcutting gap of a curved tunnel were considered.Second,the ground settlement due to construction loadings was analyzed by modifying Mindlin's solutions.The additional thrust,frictional force,and grouting pressure were considered.Subsequently,a case study and a parameter analysis were conducted.Finally,the obtained solutions were compared with a classical analytical solution,numerical simulations,and monitored results.The proposed model could effectively predict the ground settlement in-duced during curved shield tunneling.

Ground settlement during tunneling in groundwater drawdown environment-Influencing factors

In this paper,the results of a parametric study on groundwater drawdown-induced surface settlement during tunneling in waterbearing ground are presented.A calibrated stress–pore pressure coupled finite element model was adopted for the parametric analysis.The results were analyzed to establish the relationships between key design issues,such as the ground surface settlement and groundwater drawdown,and influencing factors.An artificial neural network(ANN)-based sensitivity analysis was performed to obtain insight into the relative importance of the influencing factors.The results indicated that the primary influencing factors on the settlement development are the thickness and stiffness of the soil layer within the drawdown zone and the lining permeability,while the initial void ratio and the permeability of the soil layer were considered secondary influencing factors.Practical implications and findings of the study are discussed.

Analysis of ground surface settlement in anisotropic clays using extreme gradient boosting and random forest regression models

Excessive ground surface settlement induced by pit excavation(i.e.braced excavation) can potentially result in damage to the nearby buildings and facilities.In this paper,extensive finite element analyses have been carried out to evaluate the effects of various structural,soil and geometric properties on the maximum ground surface settlement induced by braced excavation in anisotropic clays.The anisotropic soil properties considered include the plane strain shear strength ratio(i.e.the ratio of the passive undrained shear strength to the active one) and the unloading shear modulus ratio.Other parameters considered include the support system stiffness,the excavation width to excavation depth ratio,and the wall penetration depth to excavation depth ratio.Subsequently,the maximum ground surface settlement of a total of 1479 hypothetical cases were analyzed by various machine learning algorithms including the ensemble learning methods(extreme gradient boosting(XGBoost) and random forest regression(RFR)algorithms).The prediction models developed by the XGBoost and RFR are compared with that of two conventional regression methods,and the predictive accuracy of these models are assessed.This study aims to highlight the technical feasibility and applicability of advanced ensemble learning methods in geotechnical engineering practice.

Failure mechanism of large-diameter shield tunnels and its effects on ground surface settlements

A new technique for the analysis of the three-dimensional collapse failure mechanism and the ground surface settlements for the large-diameter shield tunnels were presented.The technique is based on a velocity field model using more different truncated solid conical blocks to clarify the multiblock failure mechanism.Furthermore,the shape of blocks between the failure surface and the tunnel face was considered as an entire circle,and the supporting pressure was assumed as non-uniform distribution on the tunnel face and increased with the tunnel embedded depth.The ground surface settlements and failure mechanism above large-diameter shield tunnels were also investigated under different supporting pressures by the finite difference method.

基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测

复合地层中盾构掘进诱发地表沉降的准确预测是隧道工程安全建设与施工决策的关键问题。基于隧道施工诱发地层变形机制构建隧道收敛变形与掘进位置的联系,并将其耦合至深度神经网络(deep neural network,简称DNN)框架,建立了预测盾构掘进诱发地层变形的物理信息神经网络(physics-informed neural network,简称PINN)模型。针对隧道上覆多个地层的地质特征,提出了多域物理信息神经网络(multi-physics-informed neural network,简称MPINN)模型,实现了在统一的框架内对不同地层的物理信息分区域表达。结果表明:MPINN模型高度还原了有限差分法的计算结果,可以准确预测复合地层中隧道开挖诱发的地表沉降;由于融入了物理机制,MPINN模型对隧道施工诱发地表沉降的问题具有普适性,可应用于不同地质和几何条件下隧道诱发地表沉降的预测;基于工程实测数据,提出的MPINN模型准确预测了监测断面的地表沉降曲线,可为复合地层下盾构掘进过程中地表沉降的预测预警提供参考。

砂卵石地层矿山法隧道长管棚支护机理及应用

研究目的:砂卵石地层由于卵石强度高且颗粒分布无序,因此长管棚施工地层扰动大且支护效果难以保证,已成为制约隧道实际应用的一大瓶颈。本文以某轨道交通暗挖法车站为依托工程,采用理论分析、现场测试与数值模拟相结合的方法,对不同直径、不同环向间距条件下长管棚的支护效果进行了深入研究,以期揭示砂卵石地层矿山法隧道长管棚支护机理,提出最佳支护参数。研究结论:(1)砂卵石地层,暗挖隧道管棚超前支护条件下,地层沉降变形在向地表传递过程中,沿高度方向的折减率约为0.91 mm/m;(2)管棚超前支护效果对矿山法隧道工程安全具有决定性作用,须采取措施减小管棚施工扰动及相应地层变形;(3)根据单因素敏感性分析结果,地表沉降随管棚支护长度的增加而增大,随管棚环向间距的增大而增加,且基本呈正相关;(4)为有效控制地表沉降并提高工程经济效益,建议直径127 mm管棚环向间距宜为35 cm,支护长度宜为40 m;直径159 mm管棚建议环向间距宜为40 cm,支护长度宜为40 m;直径209 mm管棚建议环向间距宜为45 cm,支护长度宜为50 m;管棚直径与其最佳打设长度正相关;(5)本研究结论可为砂卵石地层矿山法隧道支护措施提供借鉴与参考。

墙顶支撑对开挖前抽水引发基坑变形控制效果研究

基坑内抽水可诱发基坑围挡向坑内偏转并进而导致坑外土体随动沉降;在基坑土方开挖前,由于基坑内的支撑体系尚不能被完整架设,仅坑内土体可起到约束围挡变形的作用,此时,坑内抽水引起的围挡偏转十分明显。本文系统研究了围挡顶部支撑对土方开挖前抽水引发基坑变形的控制效果,首先通过抽水试验探究了坑内外强水力连通时墙顶支撑对抽水引发基坑变形的影响,并建立了三维数值计算模型,研究了若干典型参数(如,坑内降水深度等)对围挡顶部支撑控制基坑变形效果的影响。研究发现,围挡顶部支撑仅能有效限制浅埋范围内的围挡侧移(本文约埋深11 m范围内),对深埋位置围挡侧移的限制效果十分有限,且随着降水深度的增加,变形控制效果越弱;对于开挖前抽水深度较大的工程,仅采用围挡顶部设置支撑的方法可能无法有效限制围挡侧移的发展;另外,围挡顶部支撑仅能有效限制基坑围挡后方一定范围内(本文约10 m)的地表沉降,且当坑内外有水力联系时,由于坑外水位下降是引起地面沉降的主导因素,围挡顶部支撑并不能明显体现限制坑外最大地面沉降的作用,此时,应结合坑外地下水回灌进行沉降控制。

河南地矿CORS省域地面沉降监测与机理分析

为了进一步研究省域尺度范围地面沉降,分析河南地矿CORS省域地面沉降的监测方法与其形成机理:针对河南省地面沉降分布特征,采用河南省地质信息连续采集运行系统(HNGICS)的62个基准站数据,时间序列为2012—2019年,获得国际地球参考框架下无净旋转条件的河南省三维速度场;然后分解三维速度场获得河南垂直速度场,发现河南省地面沉降呈现“西稳东沉”的现象,开封附近出现沉降漏斗;最后将河南省地质图、河南省耕地面积占比、河南省年均降雨量与沉降等值线对比分析。结果表明:不同地质条件下,河南省地面沉降分布于豫东地区的第四系冲积层,而相同地质条件下,耕地占比和区域年均降雨量是地表差异性沉降的主要原因,如豫东地区耕地约占总面积的70%,地下水用于农业灌溉是豫东平原出现沉降漏斗的主要原因。

基于SSA-BP的深基坑地表变形预测研究

文中采用麻雀搜索算法优化BP神经网络,对深圳市某在建地铁车站深基坑周围地表沉降监测点进行变形预测。通过对基坑地表变形监测点DBC16-4的118期监测数据进行训练学习,并与粒子群算法优化BP神经网络、遗传算法优化BP神经网络和标准BP神经网络横向对比,验证了训练效果。结果表明,麻雀搜索算法对BP神经网络权重寻优速度较快,收敛精度更高,麻雀搜索算法优化BP神经网络模型预测平均相对误差仅为1.72%,拟合精度较其他算法更高,预测效果良好。

富水砂卵石层盾构施工影响因素及敏感性分析

砂卵石地层具有渗透性强、孔隙率大、自稳性差和受扰反应大等特点,若盾构施工参数控制不当则会发生掌子面失稳、坍塌和涌水等安全事故。确定富水砂卵石层盾构掘进引起地表沉降和管片隧道变形的影响因素,对于安全施工具有重要的指导意义。本文以洛阳地铁区间盾构穿越洛河富水砂卵石地层为工程背景,基于流固耦合理论,运用ABAQUS软件构建盾构掘进的三维有限元模型,数值模拟和现场实测的地表沉降数据基本吻合,验证了模型的准确性。采用单因素分析法研究了盾构掘进压力、同步注浆压力和等代层厚度等3个参数对地表沉降与管片变形的影响规律,研究结果表明:增大盾构掘进压力和同步注浆压力,减小等代层厚度,均能减小地表和隧道的拱顶沉降;而增大盾构掘进压力,减小同步注浆压力和等代层厚度,可减小隧道拱腰的水平变形。采用正交试验方法确定了3个影响因素对地表沉降和管片拱顶沉降两个指标的敏感性,从大到小排序均为:同步注浆压力、盾构掘进压力和等代层厚度。

基坑开挖卸荷对侧方隧道的影响研究——以南京市某地铁车站基坑开挖为例

为研究基坑土体开挖卸荷对围护结构、墙后土体变形以及隧道的影响,针对南京地区地铁车站基坑开挖对侧方既有隧道的影响进行研究,借助有限元软件ABAQUS建立二维隧道-基坑数值模型,重点对隧道水平和竖向位移、隧道结构应力、支护桩水平位移以及基坑周边地表沉降进行分析。研究表明,由于拱顶处混凝土厚度较薄,抵抗变形能力较差,水平位移最大值出现在南侧隧道拱顶位置,基坑开挖过程中,第二和第三层土体开挖对隧道竖向位移影响最大;隧道结构的拉应力整体上随基坑开挖的进展呈现逐渐增加的趋势,第二层土体开挖对隧道结构的拉应力和压应力影响最大;隧道的存在会在一定程度上提高周围土体的刚度,使得土体变形减小,支护桩水平位移曲线呈现“两端小,中间大”,受隧道的“遮挡效应”影响,近隧道水平位移小于远隧道侧;基坑开挖过程中地表沉降变形形态呈“凹槽型”,隧道结构的存在能有效控制近隧道侧地表变形。

基于迭代协同克里金反演的非均质地基固结沉降预测研究

目前地基固结沉降反演预测多是以土体均质或分层假设为前提,然而天然地基水文、力学参数具有空间变异性是客观事实。鉴于此,提出了一种基于迭代协同克里金的非均质地基土体参数反演方法,据此开展了利用沉降和超孔隙水压力观测数据反演非均质地基土参数的数值试验研究,并结合敏感度分析解释了不同类型观测数据对非均质地基参数反演解析度的影响机制。结果表明:此方法反演的参数场是最优无偏估计;同时采用沉降和超孔隙水压力观测数据反演刻画非均质地基比单独采用沉降或超孔压数据反演刻画的非均质地基解析度更高,用于地基固结沉降预测效果也更好;不同类型观测信息对不同参数反演刻画解析度高低与观测信息对参数敏感度数量级呈正相关关系。

盾构隧道下穿对高速铁路CFG桩复合路基影响规律研究

针对城市地铁隧道下穿高速铁路的施工过程中,CFG桩复合路基对地层沉降的响应机理不明确、路基的沉降预测与控制理论缺乏的问题,依托郑州轨道交通8号线盾构区间下穿郑州东站咽喉区工程,提出CFG桩复合路基沉降预测方法 .基于地基加固理论,分析CFG桩对路基的加固效果,并通过物理模型试验,研究盾构隧道下穿对高速铁路CFG桩复合路基的影响规律.研究结果表明:CFG桩可以大幅提升路基压缩模量,盾构隧道下穿不会影响CFG桩复合路基的整体性,复合路基的变形规律符合Peck沉降曲线;CFG桩复合路基能够将地层的等效内摩擦角提高约50%,降低约23%的地层沉降量;盾构隧道下穿引起CFG桩复合路基的沉降量最大值为1.65 mm,在盾构隧道掌子面距离路基中线10 m时地层开始发生显著沉降变形,其中83.6%沉降量发生在盾构穿越阶段;盾构远离阶段,路基沉降量仍会继续增大,建议沉降监测持续到沉降稳定.研究结果可为盾构隧道下穿高速铁路CFG桩复合路基的沉降预测和加固处理提供参考.