Intelligent direct analysis of physical and mechanical parameters of tunnel surrounding rock based on adaptive immunity algorithm and BP neural network

Because of complexity and non-predictability of the tunnel surrounding rock, the problem with the determination of the physical and mechanical parameters of the surrounding rock has become a main obstacle to theoretical research and numerical analysis in tunnel engineering. During design, it is a frequent practice, therefore, to give recommended values by analog based on experience. It is a key point in current research to make use of the displacement back analytic method to comparatively accurately determine the parameters of the surrounding rock whereas artificial intelligence possesses an exceptionally strong capability of identifying, expressing and coping with such complex non-linear relationships. The parameters can be verified by searching the optimal network structure, using back analysis on measured data to search optimal parameters and performing direct computation of the obtained results. In the current paper, the direct analysis is performed with the biological emulation system and the software of Fast Lagrangian Analysis of Continua (FLAC3D. The high non-linearity, network reasoning and coupling ability of the neural network are employed. The output vector required of the training of the neural network is obtained with the numerical analysis software. And the overall space search is conducted by employing the Adaptive Immunity Algorithm. As a result, we are able to avoid the shortcoming that multiple parameters and optimized parameters are easy to fall into a local extremum. At the same time, the computing speed and efficiency are increased as well. Further, in the paper satisfactory conclusions are arrived at through the intelligent direct-back analysis on the monitored and measured data at the Erdaoya tunneling project. The results show that the physical and mechanical parameters obtained by the intelligent direct-back analysis proposed in the current paper have effectively improved the recommended values in the original prospecting data. This is of practical significance to the appraisal of stability and informationization design of the surrounding rock.

Analytical solution of a circular lined tunnel with alterable mechanical property under hydrostatic stress and internal pressure

The influence of the interaction between surrounding rock and lining on the long-term behaviour of a tunnel in service is significant.In this paper,we proposed a mechanical model of the circular lined tunnel with the alterable mechanical property under hydrostatic stress and radially inner surface pressure of the lining.The alterable mechanical properties of the surrounding rock and the lining are embodied by the changing of their elasticity modulus with service time and radial direction of the tunnel,respectively.The proposed mechanical model is successfully validated by comparison with the existing theoretical models and the numerical simulation,respectively.The influences of the main parameters of the proposed mechanical model,such as the radial power-law indexes and the time-varying coefficients of the surrounding rock and the lining,as well as the radially inner surface pressure of the lining,on the interface displacement and pressure between surrounding rock and lining are investigated.The research results can provide some valuable references for timely diagnosis and correct evaluation of the long-term behaviours of a tunnel in service.

Optimization of construction scheme and supporting technology for HJS soft rock tunnel

For a soft rock tunnel under high stress in jointed and swell soft rock （HJS）, two construction schemes pilot-tunneling enlarging excavation and step-by-step excavation were optimized using FLAC20, and the deformation effects of the two construction schemes were verified by field tests. Based on engineer- ing geological investigation and mechanical analysis of large deformations, the complex deformation mechanisms of stress expansion and structural deformation of the soft rock tunnel were confirmed, and support countermeasures from the complex deformation mechanism converted to a single type were proposed, and the support parameters were optimized by field tests. These technologies were proved by engineering practice, which produced significant technical and economic benefits.

Intelligent classification model of surrounding rock of tunnel using drilling and blasting method

Classification of surrounding rock is the cornerstone of tunnel design and construction.The traditional methods are mainly qualitative and manual and require extensive professional knowledge and engineering experience.To minimize the effect of the empirical judgment on the accuracy of surrounding rock classification,it is necessary to reduce human participation.An intelligent classification technique based on information technology and artificial intelligence could overcome these issues.In this regard,using 299 groups of drilling parameters collected automatically using intelligent drill jumbos in tunnels for the Zhengzhou-Wanzhou high-speed railway in China,an intelligent-classification surrounding-rock database is constructed in this study.Based on a machine learning algorithm,an intelligent classification model is then developed,which has an overall accuracy of 91.9%.Finally,using the core of the model,the intelligent classification system for the surrounding rock of drilled and blasted tunnels is integrated,and the system is carried by intelligent jumbos to perform automatic recording and transmission of drilling parameters and intelligent classification of the surrounding rock.This approach provides a foundation for the dynamic design and construction(both conventional and intelligent)of tunnels.

Study on influence of key blasthole parameters on tunnel overbreak

To determine the influence of key blasthole parameters on tunnel overbreak during blasting construction,an intelligent detection sys-tem for tunnel blasting construction is independently developed.And the key blasthole parameters and overbreak of a typical section of a single line tunnel under the condition of Class V surrounding rock are analyzed and detected.The actual data obtained is compared with the results of numerical simulations and theoretical calculations.The results are as follows:(1)Quantitative analysis is performed based on the blasthole angle,opening position,and charge mass by the self-developed intelligent detection equipment for blasthole parameters,which can be used to guide the drilling construction.Intelligent scanning equipment for outline excavation can be used to image the actual excavation section in real-time and has the advantages of high precision and fast speed;(2)Tunnel overbreak can be regarded as consisting of two parts:the surrounding rock damage caused by the blasting load,and the collapse of the surrounding rock caused by the blasthole opening position.Every parameter of the peripheral hole will affect the tunnel overbreak;however,the key parameter is the blasthole opening position;(3)The distributions of the tunnel overbreak volume obtained with the theoretical analysis,finite element simulation,and measurements are basically consistent.Under the condition of Class V surrounding rock,the overbreak of this single line tunnel can reach 14.1–78.2 cm.To meet the specification requirements,the opening position and construction accuracy of the peripheral hole should be strictly controlled.

Refined model analysis of basement rock degradation mechanism of heavy-haul railway tunnel

This study investigated the degradation mechanism of the surrounding rock of a heavy-haul railway under a water-rich condition,based on the construction of the Taihangshan tunnel for the Wari Railway,a heavy-haul railway that used standard construction practices for axle loads of 30 t.Remote monitoring demonstrated that the coupling effect between the dynamic load of a heavy-haul train and the groundwater leads to the deterioration and hollowing of the surrounding rock.This study clarified the void evolution process and deterioration mechanism of the basement rock under the comprehensive influence of the groundwater–train dynamic load using a refined discrete element numerical simulation.The results revealed that the groundwater was the primary influencing factor in the deterioration of the lower part of the heavy-haul railway tunnel.Rock particles were gradually lost under the effects of long-term erosion due to groundwater and heavy-haul trains,which inevitably damaged the basement rock after the construction was completed.Based on this observation,the critical conditions for the deterioration and attenuation law of the physical parameters of the basement rock were obtained.The results of this study can provide ideas and serve as a reference for the forecasting and disaster treatment of basement rock damage in heavy-haul railway tunnels.

高地应力软岩隧道仰拱结构受力特性与参数优化

为探索高地应力软岩隧道施工期间仰拱结构受力特性与合理支护参数,以陕西省宝汉高速公路连城山隧道工程为依托,针对仰拱施工病害及其主要影响因子,采用现场试验与数值模拟相结合的方法,探讨了不同影响因素下的仰拱结构变形与力学响应,分析了仰拱结构变形与受力对不同影响因素的敏感性,基于仰拱结构病害特征及数值模拟结果,对仰拱半径(深度)、仰拱厚度等支护参数进行了优化,并进行了工程验证。结果表明:连城山隧道施工期间仰拱二次衬砌最大接触压力达1.034 MPa,混凝土最大应力超过其抗压强度(30 MPa),出现了仰拱回填隆起、开裂等病害,仰拱设计支护参数难以保障结构稳定;地应力水平和基底围岩劣化对仰拱结构变形与受力状态均有显著影响,其中基底软化深度的影响最为突出,地应力水平次之;减小仰拱半径、增大仰拱厚度、增大仰拱钢筋直径、减小仰拱钢筋间距均能显著抑制仰拱变形,而提高混凝土强度等级对控制仰拱变形效果不明显,且经济性较差;优化后的仰拱受力得以明显改善,有效控制了仰拱结构病害,避免了频繁拆换仰拱,保障了隧道结构安全稳定。研究成果可为类似软岩隧道仰拱变形控制及病害防治提供重要借鉴。

基于炮孔钻进参数的隧道掌子面围岩三维精细化分级方法

长进尺、大断面开挖条件下,隧道开挖掌子面-未支护段围岩三维稳定性具有更大挑战,围岩三维精细化分级是解决该问题的关键。基于现场收集的大量钻进参数样本,运用极端随机树算法,建立围岩智能分级机器学习模型;在此基础上,利用凿岩台车扫描定位系统及坐标系转换关系确定各炮孔钻进参数对应的三维坐标,并利用克里金空间插值技术构建开挖循环范围内钻进参数三维数据空间;结合隧道工程实际,进一步将钻进参数三维数据空间纵向分段、横向分块(分层、分区),利用围岩智能分级模型实现各尺度三维精细化分级,为制定、调整施工方案提供建议。研究有助于促进基于钻进参数的围岩智能分级的应用,提升施工阶段的围岩分级水平,为精细化设计奠定基础。

黄土盾构隧道围岩强度指标结构性参数表征与荷载计算

为了考虑黄土地层特征,获取合理的围岩压力以指导黄土盾构隧道结构设计,通过对比盾构隧道与新奥法隧道围岩压力现场测试数据,结合黄土盾构施工实践,验证形变围岩压力计算黄土盾构隧道围岩荷载的合理性;考虑黄土地层的强度参数,通过芬纳公式构建黄土盾构隧道形变围岩压力的计算方法;采用三轴剪切实验,探究原状黄土的应力应变关系以及应力结构性参数的变化规律,构建应力结构性参数下黄土强度指标的计算方法;结合盾构隧道开挖支护下围岩的应力应变变化规律,建立深埋黄土盾构隧道围岩结构性参数场的计算框架,结合结构性参数修正的黄土强度准则,给出深埋黄土盾构隧道围岩压力的计算方法。研究发现,使用形变压力理论计算黄土盾构隧道围岩荷载具有合理性;原状黄土相比重塑黄土有明显的应力峰值及应变软化现象;黄土应力结构性参数与粘聚力存在较好的拟合关系,与内摩擦角相关性低;当仅考虑地层浸水造成黄土结构性演变引起的围岩压力变化时,当含水率由1%增加到25%,塑性圈半径由4.6 m增加为5 m,围岩压力由587 kPa增加到622 kPa。

水平层状碳质页岩地层高速铁路大断面隧道基底变形机理研究

我国西部、西南部地区在建及建成的高速铁路隧道常发生仰拱隆起病害,严重威胁着隧道施工进度及运营安全。依托兴山东隧道典型的水平层状碳质页岩地层,开展仰拱基底隆起机理研究,对仰拱基底以下的围岩进行模型简化,应用构件试验定性分析、数值模拟定量计算的方法,揭示了不同层厚、层间黏聚力以及材料强度对层状岩体破坏模式的影响,分析导致水平层状围岩隧道底鼓的原因,并提出相应的底鼓控制处置技术。研究结果表明:(1)层厚的减小降低了层状复合岩体抵抗变形和破坏的能力,主要表现为弹性阶段的缩短和变形速率的加快;层间黏结强度的降低破坏了层状复合岩体的整体性,导致层状岩体加速进入单一岩层受力阶段,但对极限承载力劣化效应不明显;(2)岩体本身材料强度降低极大地降低了层状复合岩层的承载能力,使得破坏过程显著加快,影响程度和范围进一步加深,结合数值模拟结果进一步证明了岩体本身强度在层状岩体的变形和破坏当中占据主导位置;(3)列车振动的疲劳损伤、地下水聚集的弱化作用以及围岩的长期力学性能均将影响隧道仰拱的稳定性,变形控制效果排序为:加深仰拱>基底注浆>仰拱锚杆。

南山口抽水蓄能电站地下厂房围岩工程特性评价

基于数据库的三维地质建模已广泛应用于地质勘测领域,本文以南山口抽水蓄能电站为例,展示利用CnGIM_ma三维地质软件构建的地下厂房围岩的三维模型,并通过对围岩进行等级分类准确评估其力学参数。结果显示,利用三维模型能更准确地反映岩体的真实条件,为地下厂房的建设及开发提供参数基础,并及时呈现地质信息成果。

锚杆锚固下深部岩爆倾向巷道围岩承载层演化机理及特性分析

锚杆锚固下深部岩爆倾向巷道围岩承载层的演化机理及特性分析表明,围岩内部残余强度和剪胀扩容效应是主要影响因素。高残余强度使承载层厚度减小,提高围岩稳定性,降低变形量;而剪胀角越大,承载层厚度越大,围岩稳定性越差,变形量增大。增大支护阻力能够有效控制围岩变形,优化承载层结构,确保巷道的安全和稳定。

广义章-朱准则在深埋隧道数值分析中的适用性研究

深部岩体隧道的智能建造是当今隧道工程建设的重要发展趋势。为准确模拟深部岩体的三维应力状态,提高深埋隧道数值计算精度,将广义章-朱岩体强度准则引入深埋隧道数值分析中,采用理论分析和数值计算相结合的方法从岩体强度准则的特性、参数以及工程应用3个角度对广义章-朱准则在深埋隧道数值分析中的适用性展开研究。结果表明:1)从准则特性的角度,广义章-朱准则能反映深部岩体的非线性特征以及中间主应力效应,适用于深埋隧道数值分析;2)从参数选取角度,提出了一种广义章-朱准则参数估算方法,有利于提高广义章-朱准则的适用性;3)工程案例表明广义章-朱准则具有较高的计算精度,在深埋条件下采用广义Hoek-Brown准则计算得到的围岩变形误差达到23%~30%,建议采用广义章-朱准则进行深埋隧道数值分析。

岩体力学参数旋切钻进测试方法研究进展

岩体力学参数的准确获取是矿山巷道围岩稳定性分析与支护设计的前提,传统采用围岩取心进行实验室测试的方法,难以适应煤矿深部开采与智能化发展对岩体力学参数获取的时效性要求。数字钻进测试技术是一种利用钻孔过程中实时监测的钻速、转速、钻压、扭矩等随钻参数对岩体力学参数进行反分析的方法,该方法为实现巷道现场围岩力学参数的原位实时获取提供了新途径,其关键在于建立随钻参数与岩体力学参数的定量关系,并研发与随钻测试理论相匹配的智能钻进设备。设计研发了数字解析钻头,得到了基于旋切钻进参数的岩体切削强度与切削能量理论解,建立了岩体抗压强度与弹性模量随钻反演模型。研发了真三轴岩体数字钻进试验系统(TRD系统)和高精度岩体智能旋切试验系统(RCT系统),开展了系列岩体数字钻进试验。在此基础上,研发了智能地质随钻探测系统(IDE系统),建立了巷道围岩力学参数随钻原位探测方法。研究成果为巷道围岩原位实时智能感知提供了理论与技术支撑。

知识驱动和数据驱动在TBM智能施工机器学习中的应用

依托引绰济辽工程(YC)和引松供水工程(YS),从理论分析、统计检验等方面系统回顾并总结基于知识驱动方法提取的现场贯入指标FPI和扭矩贯入指标TPI在TBM智能施工机器学习中的应用。从智能预测围岩分类和掘进参数两方面出发,将基于特征参数的预测结果与通过数据驱动获得的结果进行比较。研究结果表明:通过知识驱动获取的参数FPI和TPI可以降低数据维度和噪音,提高预测效率。在围岩分类智能预测方面,知识驱动和数据驱动方法均表现出较好的精度水平;在掘进参数预测方面,知识驱动的预测精度远高于数据驱动。作者认为单独使用FPI和TPI或者将其与数据驱动参数结合,可以丰富TBM领域机器学习的输入参数,获得较好的预测成果。

基于TBM掘进大数据和特征参数的引水隧洞塌方分析

针对TBM掘进过程中缺乏对围岩质量和塌方风险快捷、精准的预测预警方法,通过对TBM掘进大数据的深入挖掘,结合对实际工程塌方数据的剖析,提出潜在塌方风险的辅助判断依据。首先,对冗杂、连续的原始采集数据进行预处理,获取高质量的分析数据;然后,基于参数的相关性分析提出围岩特征参数的计算方法,并围绕特征参数的合理性和适用性,通过理论推导、室内试验和现场原位掘进试验进行论证;最后,结合实际的TBM塌方案例分析特征参数与围岩地质情况的相关性,提出塌方风险快速判断依据。结果表明:基于TBM掘进数据获取的围岩特征参数在一定程度上反映了围岩质量,其数值与围岩质量正相关,当其数值显著降低、变幅超过69.2%时,当前的掘进循环极大可能存在塌方风险。

基于钻进参数和岩性的钻爆法隧道围岩智能分级模型

为进一步提高基于钻进参数的围岩智能分级模型判识准确率,引入围岩岩性作为已知条件,对不同岩性分别建立基于钻进参数的围岩智能分级模型。首先,依托宜兴高铁、郑万高铁隧道工程中凿岩台车采集到的钻进参数,将其根据围岩岩性划分为白云岩、花岗闪长岩、灰岩、砂岩、页岩5类子数据集;然后,进行数据清洗、特征提取,对各子数据集及原始数据集按照4∶1的比例拆分为训练集和测试集,分别以提取的特征和原始特征均值2类特征集合作为输入;最后,使用机器学习随机森林算法建立5个基于钻进参数和岩性的围岩智能分级模型以及基于钻进参数的围岩智能分级模型,评估每个模型的泛化性能。结果显示:1)以提取特征集合为输入的白云岩、花岗闪长岩、灰岩、砂岩、页岩5种围岩智能分级模型在测试集上的准确率分别为85.48%、92.16%、88.62%、85.00%、89.47%,不考虑岩性的围岩智能分级模型的测试集准确率为84.91%。2)相比不考虑岩性的围岩智能分级模型,基于钻进参数和岩性的围岩智能分级模型测试集准确率提高0.09%~7.25%;相比不进行钻进参数特征提取,围岩智能分级模型准确率提升1.61%~13.82%。由此表明:进行钻进参数特征提取能够有效提升围岩智能分级模型的准确率;相比不考虑岩性的围岩智能分级模型,考虑岩性的围岩智能分级模型稳定性提高,模型的泛化能力提升。

地质突变条件下基于组合模型的围岩等级和TBM掘进参数预测

为了提高硬岩隧道掘进机(TBM)施工的安全性和智能化,基于TBM掘进数据,提出了一种将双向长短期记忆(BiLSTM)网络与支持向量机回归(SVR)算法相结合的可以同时进行围岩等级和TBM掘进参数预测的组合模型(BiLSTM-SVR模型)。实例验证结果表明:BiLSTM-SVR模型对围岩等级的预测准确度较高,均方根误差均小于0.0265、平均绝对百分比误差均小于0.95%;BiLSTM-SVR掘进参数预测中,推力和扭矩的预测准确度最高,净掘进速度和开挖比能的预测准确度最低;BiLSTM-SVR模型比BiLSTM模型和SVR模型的掘进参数预测准确度有较大的提高,因此进行单一模型的组合可以有效提高模型预测的准确度和鲁棒性。

倾斜煤系地层大断面客专隧道大变形原因分析及处置

针对沪昆铁路刘家庄隧道穿越煤系地层施工中发生的大变形现象,基于理论分析、数值模拟和现场监测方法,分析隧道发生大变形的原因,推导并验证了产生大变形的起始位置,得到了掌子面上方煤层单元体沿倾斜面方向的应力状态与隧道进入含倾斜煤系地层水平距离之间的变化规律,对倾斜煤层单元体与初期支护结构的应力与变形进行了分析。结果表明:掌子面上方煤体单元应力状态变化随掌子面进入倾斜煤层下方水平距离的增加,围岩经历挤压、压剪和剪切滑移3个变形阶段。围岩大变形与初期支护结构破坏均发生在剪切滑移阶段的初期,应在压剪变形阶段结合现场监测数据对掌子面进行喷射混凝土封闭、注浆加固掌子面上方松散煤层和加强初期支护结构刚度等措施以预防隧道产生大变形。

TBM隧洞围岩分级方法及支护体系研究

目前TBM隧洞设计施工主要采用基于矿山法的围岩分级方法,但由于TBM法与矿山法隧洞施工存在很大差异,传统矿山法的围岩分级方法难以适用于TBM施工。为解决该问题,依托北疆供水二期工程,综合考虑围岩稳定性和围岩可掘性,选取围岩基本质量指标BQ、岩石单轴饱和抗压强度Rc、岩体完整性系数KV和岩石磨蚀性指数CAI作为评价隧洞围岩性质的主要指标,统计18台TBM集群施工收集的近3000组BQ、Rc、KV等岩性指标数据,分析各项岩性指标与纯掘进速度PR及安全系数FS的变化规律,将TBM隧洞围岩分为Ⅰ~Ⅴ级共10个亚级。在此基础上,分析了敞开式TBM的施工特性,进而采用数值模拟方法,对各级围岩在不同支护参数下的稳定性进行对比分析,提出了适用于北疆地区水工隧洞各级围岩的隧洞支护体系及支护参数,共形成7套支护体系设计图,并结合现场实际工程对本文提出的围岩分级支护体系进行验证。现场监测数据表明,本文提出的TBM隧洞围岩分级支护体系有较好的适用性。