预测压气法隧道施工中的漏气量的模型研究

在阐述压气法隧道施工原理的基础上,建立了水–气二相流模型来模拟压气法隧道施工过程中超压空气驱替隧道周围土体的孔隙水的水–气二相流过程。该模型同时考虑了土体中气相和水相的流动以及水相和气相相互作用的影响,比较符合水–气二相渗流过程的物理意义。通过工程算例,计算出不同施工进度下开挖面和隧道混凝土衬砌上的空气损失速率以及空气入流对隧道周围土体渗流场的影响,结果表明:在均质的地质条件下,开挖面上的漏气速率一般为常数,而衬砌上的漏气速率将随着隧道长度的增加而线性增大。最后,提出了利用水–气二相流模型进一步提高压气法隧道施工的漏气量的数值模拟精度,需要深入研究的两点意见。     

压气新奥法隧道施工中的渗流分析

在各种隧道施工过程中，根据新奥法基本原理，所采用的施工方法都必须尽可能地降低对周围岩土体及地下水状态的扰动。而在城市地铁隧道、跨海及过江隧道施工过程中，出于环境保护、城市建筑和景观保护、施工安全及减少地面沉降等因素的考虑，施工排水方法受到特别重视。压气新奥法隧道施工可以有效地解决地下水问题，同时可以明显减小地面沉陷并提供一定的支持力，而造价法要比盾构法施工低廉得多。压气新奥法隧道施工的主要问题之一是如何清楚地了解渗流场（水流和气流）的分机和变化规律及其对原有地下水分布的影响，并预测施工过程中的补气量，保证气压稳定和施工安全。采用数值方法对这一问题进行分析，根据渗流场的分布，讨论压气新奥法隧道施工过程中压缩空气的影响区域、漏气量及选用合理的隧道施工工作气压等问题。     

Prediction of TBM jamming risk in squeezing grounds using Bayesian and artificial neural networks

This study presents an application of artificial neural network(ANN) and Bayesian network(BN) for evaluation of jamming risk of the shielded tunnel boring machines(TBMs) in adverse ground conditions such as squeezing grounds.The analysis is based on database of tunneling cases by numerical modeling to evaluate the ground convergence and possibility of machine entrapment.The results of initial numerical analysis were verified in comparison with some case studies.A dataset was established by performing additional numerical modeling of various scenarios based on variation of the most critical parameters affecting shield jamming.This includes compressive strength and deformation modulus of rock mass,tunnel radius,shield length,shield thickness,in situ stresses,depth of over-excavation,and skin friction between shield and rock.Using the dataset,an ANN was trained to predict the contact pressures from a series of ground properties and machine parameters.Furthermore,the continuous and discretized BNs were used to analyze the risk of shield jamming.The results of these two different BN methods are compared to the field observations and summarized in this paper.The developed risk models can estimate the required thrust force in both cases.The BN models can also be used in the cases with incomplete geological and geomechanical properties.     

Field measurements during construction of a compressed air tunnel in Cairo

An in-sity monitoring program was implemented during construction of the spine tunnel of the Greater Cairo Wastewater Project. The test section was located at an area where the 5-m shielded tunnel was advancing under compressed air through alluvial Nile deposits. Soil displacements around the tunnel were measured during the tunnel advance using an array of magnetic multi-point extensometers and surface settlement points. Piezometers were also utilized to monitor the groundwater response at different distances from the tunnel centreline. This paper presents field measurements compiled from the instrumentation monitoring program. The general trends of ground and groundwater responses to tunneling under the encountered conditions are identified. The results are compared with available guidelines of prediction of soil settlement above shielded tunnels.     

Ground–liner interaction in rock tunneling

Tunnel constructions are gradually increasing because of the development and upgrade of infrastructures such as highway, subway, railway, and many other facilities. Most of tunnels are excavated either by using drilling and blasting or by using tunnel excavation machines such as TBM (tunneling boring machine) or Shield. NATM (new Austrian tunneling method) is one of most frequently used tunneling methods and it uses drilling and blasting to excavate a tunnel in rock. While tunnel excavation using TBM or Shield machines produces quite a regular and smooth tunnel excavation surface, the tunnel excavation using drilling and blasting results in a very irregular and rough excavation surface. The stress behavior in a shotcrete tunnel liner installed along the excavation surface is very dependent on the surface status and tunnel engineer should consider the surface condition for the design of a shotcrete tunnel liner.Numerical analyses are conducted to investigate the effect of the irregularity of tunnel excavation surface on the response of the shotcrete tunnel liner. For the investigations, the controlled parameters include the irregularity of the excavation surface, the stiffness of the surrounding ground, and the coefficient of earth pressure at rest. The investigations show that the response of a shotcrete tunnel liner is highly dependent on the parameters and for the same earth pressure condition the effect is more evident when the irregularity is more severe and the surrounding ground is less stiff.     

Prediction of tunneling-induced ground movement with the multi-layer perceptron

This paper presents a method to predict ground movement around tunnels with artificial neural networks. Surface settlement above a tunnel and horizontal ground movement due to a tunnel construction are predicted with the help of input variables that have direct physical significance. A MATLAB based multi-layer backpropagation neural network model is developed, trained and tested with parameters obtained from the detailed investigation of different tunnel projects published in literature. The settlement is taken as a function of tunnel diameter, depth to the tunnel axis, normalized volume loss, soil strength, groundwater characteristics and construction methods. The output variables are settlement and trough width. Parameters for the prediction of horizontal ground movement include diameter to depth ratio (D/Z), unit weight of soil and cohesion. The neural network demonstrated a promising result and predicted the desired goal fairly successfully.     

Investigations on air pressure and air losses in compressed air tunneling through saturated clayey soil

Determination of air pressure and assessment of air losses in clayey soil are of great importance to implementation of compressed air tunneling. In the present work, a series of air flow tests were performed to provide a more reasonable method based on flow characteristics of snap-off pressure and the dissolution/diffusion. Results showed that, the nonlinear air flow behavior and gas breakthrough were presented with the increase in air pressure. After that, the excessive pressure decreased continuously to reach an equilibrium termed as the snap-off. For the tested clayey soil, snap-off pressures around 250 kPa could be adopted as the air pressure, which was significantly lower than the gas breakthrough pressures. Diffusion coefficient of 1.5 × 10^-11 m²/s could be determined in the followed dissolution/diffusion stage, which bring 3 orders of decreasing magnitude in air losses compared to the capillary flow occurred after gas breakthrough. As a conclusion, the adoption of snap-off pressure in compressed air tunneling could effectively prevent the continuous air/water flow in clayey soil and create a more human-friendly environment. Additionally, less air losses could be presented compared to that using gas breakthrough pressure, indicating tremendous energy savings in field implementation.     

基于BP神经网络的水下岩溶地层#br# 盾构掘进参数预测与分析

随着我国城市地铁网的建设,越来越多的隧道将不可避免的穿越水下岩溶区,受制于岩溶地层的复杂性、注浆加固后地层的诸多不确定性,盾构穿越该类地层施工风险极大,而选取合理的盾构掘进参数是确保盾构安全与高效掘进的关键。以长沙地铁三号线盾构穿越水下岩溶段为工程依托,首先通过统计与分析钻探数据,明确了岩溶分布特征;其次,通过输入地层特征参数和隧道特征参数,建立了可输出盾构掘进速度、推力、刀盘扭矩、开挖仓压力、气垫仓压力和同步注浆量等掘进参数的BP神经网络水下岩溶盾构掘进参数预测模型;最后,对样本数据进行了训练,并成功应用于工程实践。研究结果表明：训练的输出值与期望值吻合度较高,构建的BP神经网络模型具有较好的适应性;输出的预测结果能有效反映实际盾构掘进参数的变化趋势,预测值与实际期望值的平均误差均低于13%,在误差可接受范围内。现场应用结果表明,地表沉降在安全范围内,盾构掘进过程中未发生工程事故,盾构掘进参数选取合理,姿态控制较好。研究成果可用于指导水下岩溶盾构隧道工程施工,且该方法的提出也为其他复杂地层盾构掘进参数合理选取提供了新思路。     

PSO-based Elman neural network model for predictive control of air chamber pressure in slurry shield tunneling under Yangtze River

The excavation face stability is crucial for safety and risk management in slurry shield tunneling, especially for the river-crossing tunnel. To avoid face collapse or blow-out, shield operators need to keep air chamber pressure balanced using their own experience, which would be difficult, discontinuous and less reliable in the process of construction. Considering the disadvantage of the manual control process, this paper presents a predictive control system for air chamber pressure in slurry shield tunneling using Elman neural network (ENN) model. It mainly contains a theoretical model, an ENN predictor and an ENN controller to set optimal control parameters automatically tracking the desired air chamber pressure. Moreover, to improve the learning capability of ENN model, a particle swarm optimization (PSO) algorithm is implemented. This system has been tested with collected data of slurry shield operation parameters in the Yangtze riverbed metro tunnel project in Wuhan, China. Analysis revealed that the predictive control system using PSO-based Elman neural network model in this paper has the potential for enhancing face stability in slurry shield tunneling.     

基于循环神经网络的盾构隧道#br# 引发地面最大沉降预测

伴随着计算机技术的快速发展,机器学习等新兴算法正在被越来越多地运用于预测隧道掘进引发的地面最大沉降。在隧道施工过程中,由盾构机和地面监测点位采集的数据具有很强的序列化特征,而传统的机器学习算法对序列数据的处理存在一定的局限性。循环神经网络(RNN)具有极强的对时序型数据的处理能力,在视频识别、语音翻译等领域有着广泛的应用。采用两种RNN模型(LSTM、GRU)和传统的BP神经网络模型,以地质参数、几何参数和盾构机参数作为输入,对隧道施工过程中引发的地面最大沉降进行预测分析。结果显示,RNN对隧道沉降的预测结果优于传统的BP神经网络模型,并且RNN在连续未知区段的预测结果比BPNN更加稳定。     

Ground movement induced by triple stacked tunneling with different construction sequences

This study tried to explore the ground movement induced by triple stacked tunneling(TST) with different construction sequences. A case study in Tianjin, China was used to investigate the ground movement during the TST(upper tunneling(UT)). For this, a modified Peck formula was proposed to predict the surface settlement induced by TST. Next, three sets of finite element analyses(FEA) were used to compare the effects of construction sequences(i.e. UT, middle tunneling(MT), and lower tunneling(LT))...     

盾构施工引起地基变位的神经网络预测

通过分析盾构施工引起地基变位的影响因素,在盾构试掘进基础上,提出应用人工神经网络建立地层条件及施工参数与盾构施工引起周围地基变形之间的关系,并分析了人工神经网络技术应用于盾构隧道地表变形预报中的一些关键技术,为盾构法施工中人工神经网络的应用提出一些意见和建议。并对某一地铁工程中实测资料,应用简单的 BP 神经网络进行地表变形预测。     

基于BP神经网络的复合地层盾构掘进参数预测与分析

复杂地质条件下盾构机掘进参数的有效预测可以对盾构施工进行针对性的指导。基于深圳地铁11号线车公庙站～红树湾站和南山站～前海湾站两个区间Φ7m盾构施工现场监测的掘进参数,首先采用BP人工神经网络方法建立了复合地层条件下盾构掘进参数的预测模型|其次,以地层参数为输入组和盾构掘进参数为输出组,通过对数据样本进行训练,得到的输出值基本与原始数据一致,说明该预测模型具有很好的非线性映射能力;最后,采用盾构区间典型地段的地层参数,利用所建立的模型预测了复合地层条件下的盾构掘进参数,预测值与实际数据变化规律相近,平均误差在15%以内。本文建立的BP神经网络模型可用于复合地层条件下同类型盾构掘进参数的预测。     

Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling

Numerous empirical and analytical relations exist between shield tunnel characteristics and surface and subsurface deformation. Also, 2-D and 3-D numerical analyses have been applied to such tunneling problems. Similar but substantially fewer approaches have been developed for earth pressure balance (EPB) tunneling. In the Bangkok MRTA project, data on ground deformation and shield operation were collected. The tunnel sizes are practically identical and the subsurface conditions over long distances are comparable, which allow one to establish relationships between ground characteristics and EPB – operation on the one hand, and surface deformations on the other hand. After using the information to identify which ground- and EPB-characteristic have the greatest influence on ground movements, an approach based on artificial neural networks (ANN) was used to develop predictive relations. Since the method has the ability to map input to output patterns, ANN enable one to map all influencing parameters to surface settlements. Combining the extensive computerized database and the knowledge of what influences the surface settlements, ANN can become a useful predictive method. This paper attempts to evaluate the potential as well as the limitations of ANN for predicting surface settlements caused by EPB shield tunneling and to develop optimal neural network models for this objective.     

深埋长大泰宁隧道快速施工关键技术研究

泰宁隧道属特长、大断面、深埋、高地应力隧道,施工过程中面临诸多技术挑战。通过采取“择机封堵、超前帷幕注浆、径向灌浆、模袋和索囊封堵灌浆”等技术,有效封堵了高压大流量地下水;通过采用长短距离相结合的综合地质超前预报方法,提高了不良地质体和地下水的预报精度;通过采取“超前应力解除、控制爆破、水胀式锚杆、挂网、钢筋拱肋、喷超细沸石粉添加剂混凝土为主”的岩爆预防体系,有效防治了岩爆灾害;通过采用斜井送排式纵向分段通风,解决了隧道施工、运营通风技术难题。可为类似工程提供参考和借鉴。     

A subsurface “drift and pile” protection scheme for the construction of a shallow metro tunnel

In the construction of a shallow running-tunnel for Beijing metro line No. 13, due to restrictions by the surface environment of the area, a subsurface protection scheme was applied: two small cross-section drifts with shotcrete linings were constructed at above each side of the subway running tunnel, and reinforced concrete piles were installed into the ground from within the drifts. The piles were rigidly connected with the floor slabs of the drift linings, so that the drifts could effectively help extend the height of the protected zone of ground. With no disturbance to the normal living of the residents in the area, the major objective of the scheme was to separate the negative effects of tunneling on two nearby high-rise residential buildings, one at each side of the tunnel, respectively. Relating to the scheme, this paper presents the relevant site conditions, design concepts and analyses, constructions and monitoring highlights.     

Real-time rock mass condition prediction with TBM tunneling big data using a novel rock–machine mutual feedback perception method

Real-time perception of rock mass information is of great importance to efficient tunneling and hazard prevention in tunnel boring machines (TBMs). In this study, a TBM–rock mutual feedback perception method based on data mining (DM) is proposed, which takes 10 tunneling parameters related to surrounding rock conditions as input features. For implementation, first, the database of TBM tunneling parameters was established, in which 10,807 tunneling cycles from the Songhua River water conveyance tunnel were accommodated. Then, the spectral clustering (SC) algorithm based on graph theory was introduced to cluster the TBM tunneling data. According to the clustering results and rock mass boreability index, the rock mass conditions were classified into four classes, and the reasonable distribution intervals of the main tunneling parameters corresponding to each class were presented. Meanwhile, based on the deep neural network (DNN), the real-time prediction model regarding different rock conditions was established. Finally, the rationality and adaptability of the proposed method were validated via analyzing the tunneling specific energy, feature importance, and training dataset size. The proposed TBM–rock mutual feedback perception method enables the automatic identification of rock mass conditions and the dynamic adjustment of tunneling parameters during TBM driving. Furthermore, in terms of the prediction performance, the method can predict the rock mass conditions ahead of the tunnel face in real time more accurately than the traditional machine learning prediction methods.     

导洞隔离桩墙结构对浅埋暗挖隧道周边地层移动的限制作用

以北京城市铁路某浅埋暗挖区间隧道工程为例，分析了导洞隔离桩墙结构对中洞法双连拱隧道施工变形影响的限制作用。由于地面环境的制约，该工程在隧道侧上方开挖了两个小断面导洞，采用喷混凝土衬砌，并在导洞内向下施作钢筋混凝土排桩，以隔离隧道施工对附近两座高层建筑的不良影响。在分析导洞隔离桩墙工作机理的基础上，提出了一种解析解来估算隔离结构及附近地层的变形情况，并对施工过程的变形影响进行了三维有限元模拟。把解析解和有限元计算结果与施工监测数据进行了比较，总结了影响隔离结构作用效果的关键因素。     

Prediction of geological hazardous zones in front of a tunnel face using TSP-203 and artificial neural networks

This research aims at improving the methods of prediction of hazardous geotechnical structures in the front of a tunnel face. We propose and showcase our methodology using a case study on a water supply system in Cheshmeh Roozieh, Iran. Geotechnical investigations had previously reported three measurements of the newly established method of TSP-203 (Tunnel Seismic Prediction) along 684 m of the 3200 m long tunnel up to a depth of 600 m. We use the results of TSP-203 in a trained artificial neural network (ANN) to estimate the unknown nonlinear relationships between TSP-203 results and those obtained by the methods of Rock Mass Rating classification (RMR – treated here as real values). Our results show that an appropriately trained neural network can reliably predict the weak geological zones in front of a tunnel face accurately.     

Fault-tolerant control for outdoor ventilation air flow rate in buildings based on neural network

This paper describes a supervisory control scheme that adapts to the presence of the measurement faults in outdoor air flow rate control using sensor-based demand-controlled ventilation, maintains an adequate indoor air quality and minimizes the resulting increase in energy consumption. A strategy, which is based on neural network models, is employed to diagnose the measurement faults of outdoor and supply flow sensor, and accomplishes the fault-tolerant control of outdoor air flow when faults occur. The neural network models are trained using the data collected under various normal conditions. The residuals between the measurements of flow sensors and the outputs of the neural network models are used to diagnose the faults. When the fault of outdoor or supply air flow sensor occurs, the recovered estimate of outdoor or supply air flow rate obtained on the basis of the neural network models is used in the feedback control loop to regain the control of outdoor air flow. Tests using dynamic system simulation are conducted to validate the strategy. The control, IAQ and energy performances of the system under fault-tolerant control strategy in the presence of the faults in air flow sensor are also presented.