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.     

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。     

盾构施工引起地表沉降的影响因素分析

在Loganathan公式的基础上,利用正交试验方法,分析了盾构施工中注浆填充率、支护压力比、偏心率、盾构埋深4个因素对地表沉降的影响程度,分析结果可以为施工提供重要的指导。     

Experimental study on working parameters of earth pressure balance shield machine tunneling in soft ground

Deep sedimentary deposits of soft clays are widely distributed in coastal areas as well as many interior major cities in China. In order to study the stratum adaptability of earth pressure balance (EPB) shield machine tunneling in such types of soft ground, model tests of tunneling excavation, using the running tunnel of the Shanghai Metro Line M8 as a background, are carried out with different over burden ratios, opening rates of cutter head, driving speeds and rotation speeds of screw conveyor. Based on the test results, the interrelationships between chamber pressure and mucking efficiency, mucking rate and driving speed, thrust force and torque are obtained. The influences of tunnel depth, opening rate of cutter head and driving speed on thrust force and torque are revealed. Such findings can not only facilitate establishing relationships between shield working parameters and soil properties, but also serve as a guide for the design and construction of shield tunnel in soft ground. __________ Translated from China Civil Engineering Journal, 2007, 40(9): 87–94 [译自: 岩土工程学报]     

土压平衡盾构掘进地表沉降规律及控制方法

对采用盾构法施工引起地表沉降的一般规律及类型进行了介绍,阐述了地面沉降产生的原因和机理,并对地面沉降量的大小,分布及具体控制方法作了说明,以期指导实践。     

复杂环境下地铁隧道盾构施工诱发地表土体变形的智能预测

在复杂地质环境下,地铁盾构施工参数会有较大不同,使得施工过程中的地表沉降难以控制.常规的监测手段具有滞后性,难以应对突发情况.基于此,本文提出基于BP神经网络地铁隧道盾构施工诱发地表土体变形智能预测模型,通过与杭富城际铁路11标段盾构施工时的地表沉降、右线沉降和左线沉降的实测数据对比发现,BP神经网络能够准确预测复杂环...     

小转弯半径曲线盾构隧道开挖引发地表沉降计算

小转弯半径曲线盾构隧道施工引发的地表沉降变形规律极为复杂,但相应的变形预测解析公式仍未明确。依据前人研究成果,构建曲线段盾构隧道施工的地层损失模型,基于镜像法及Mindlin解,推导曲线盾构隧道开挖引发地表沉降的计算公式,并将其应用于工程实例计算,最后分析曲线盾构隧道施工引发地表变形规律及其影响因素。研究表明:构建的小转弯半径曲线段地层损失模型合理,推导所得公式适用于实际工程计算;地表纵向沉降在靠近刀盘3倍洞径范围内变化极大,刀盘前方3倍洞径范围内地表会产生轻微隆起,刀盘后方3~4倍洞径处出现最大沉降;地表横向沉降槽为非对称分布,最大沉降位置位于弯道内侧,距刀盘中心线约1倍洞径;地层损失引起的地表横向沉降大小主要受转弯半径及盾壳长度影响,地表横向沉降槽偏移程度主要由刀盘直径大小决定。     

管幕工程地表变形的人工神经网络预测研究

管幕工法是一种新型的地下空间暗挖技术.国内首次应用于上海市中环线浦西段的北虹路下立交工程.该工法为解决软土地区超大断面地下工程的施工变形问题开创了新的领域.管幕工法虽然可以减少对周边环境的影响,但并不能完全消除.作者在充分研究钢管幕顶进施工过程中引起的地表变形特征基础上,建立相应的预测模型,应用人工神经网络智能滚动预测方法,对管幕工程的地表变形进行预测研究.研究表明：人工神经网络的一步滚动预测可以满足实际的工程需要,但精度相对偏低.而多步滚动预测虽可以得到较高的预测精度,但在实际工程应用中还需解决量的优化问题.