隧道岩体质量智能动态分级KNN方法

施工期隧道岩体质量动态分级,是评价隧道工作面围岩质量最直接的方法,也是预防隧道施工地质灾害,决定施工开挖工法与支护措施的重要依据。由于传统的Q值法和国标BQ岩体质量分级评价方法需要进行现场和室内试验及分析,岩体质量评价时间滞后,常常降低施工效率,或错过预防突发性施工地质灾害的窗口时间,快速准确地对隧道工作面进行岩体质量分级,成为施工期公路隧道岩体质量动态分级需要解决的重要问题。人工智能算法为解决隧道岩体质量实时快速准确评价提供了方法和手段。以北京冬奥会延庆—崇礼高速公路为例,提出了工作面采用隧道掌子面图片人工智能岩体结构参数辨识,建立7个指标参数体系,采用KNN智能算法对隧道岩体质量进行评价,选取8条隧道40个工作面150个样本进行训练学习,另外选取50个样本进行岩体质量评价校验,与BQ岩体质量评价结果相比,准确率达到了90%,得出如下结论:(1)公路隧道岩体质量智能动态分级KNN方法—一种利用人工智能技术快速高效进行岩体质量动态分级的方法,能够在现场实时获得岩体质量评价结果;(2)KNN分级方法中选用了7个判定指标,综合考虑了隧道围岩体的赋存环境、岩体构造、地质结构等特性,并体现了这些指标在实际工程评判中的可操作性和适用性;(3)KNN分级方法误判率很低,在判别分类中排除了评分时人为因素的干扰,具有较强的判别能力,为TBM围岩实时分级做方法储备。     

数字图像处理技术在隧道掌子面的应用

在隧道施工过程中,为了解开挖方量以及隧道前方的地质构造等信息,有必要对掌子面图像进行分析。传统分析中大多数以人工素描为主,效果因人而异。为了克服传统方法的局限,将图形、图像处理及三维建模技术引入对掌子面图像的处理中,建立隧道掌子面地质图像画像系统,对一系列跟踪拍摄的掌子面图像进行处理,自动提取出掌子面上不同岩层的边界,获取岩层的特征信息,以此对围岩分级。根据相邻掌子面上岩层目标的对应关系,建立起隧道的三维模型,为隧道施工提供必要的参考信息。     

Porous Structure Reconstruction Using Convolutional Neural Networks

The three-dimensional high-resolution imaging of rock samples is the basis for pore-scale characterization of reservoirs. Micro X-ray computed tomography (µ-CT) is considered the most direct means of obtaining the three-dimensional inner structure of porous media without deconstruction. The micrometer resolution of µ-CT, however, limits its application in the detection of small structures such as nanochannels, which are critical for fluid transportation. An effective strategy for solving this problem is applying numerical reconstruction methods to improve the resolution of the µ-CT images. In this paper, a convolutional neural network reconstruction method is introduced to reconstruct high-resolution porous structures based on low-resolution µ-CT images and high-resolution scanning electron microscope (SEM) images. The proposed method involves four steps. First, a three-dimensional low-resolution tomographic image of a rock sample is obtained by µ-CT scanning. Next, one or more sections in the rock sample are selected for scanning by SEM to obtain high-resolution two-dimensional images. The high-resolution segmented SEM images and their corresponding low-resolution µ-CT slices are then applied to train a convolutional neural network (CNN) model. Finally, the trained CNN model is used to reconstruct the entire low-resolution three-dimensional µ-CT image. Because the SEM images are segmented and have a higher resolution than the µ-CT image, this algorithm integrates the super-resolution and segmentation processes. The input data are low-resolution µ-CT images, and the output data are high-resolution segmented porous structures. The experimental results show that the proposed method can achieve state-of-the-art performance.     

某公路瓦斯隧道综合勘察技术应用

瓦斯赋存位置的确定和瓦斯动态监测是瓦斯隧道勘察的两大关键问题。针对某公路隧道掘进过程中发现的瓦斯气体,采用地质调绘、施工地质预报（物探、地质超前钻探）、瓦斯监测等手段进行综合勘察,研究瓦斯储气构造,分析瓦斯成因,并对该隧道未开挖洞段的围岩瓦斯特征进行了预测预报,提出瓦斯风险段落。研究表明,虽然该隧道具有充分的瓦斯形成地质背景,但瓦斯赋存特点是分散型、浓度低、储量低;瓦斯通过单斜构造中的岩石裂隙、孔隙富集运移,分析认为,该地区不具备大量瓦斯生成的地质构造条件。综合勘察技术的应用有助于提高预报精度,为保证隧道施工安全提供了可靠的地质依据,对类似隧道工程建设具有一定的指导作用。     

山岭隧道工程综合地质勘察方法探讨

山岭隧道工程具有隐蔽性、施工复杂性、地层条件和周围环境不确定性等特点,采用科学的勘察方法,是查明隧道岩土体工程地质条件的有效手段。本文以海淀区西山隧道为依托,针对隧道工程勘察中的关键地质问题,运用工程地质测绘、钻探、工程物探、水文地质勘查等综合勘察方法,有效地查明隧址区的地质构造、岩土体结构和地下水分布特征,全面、客观地评价隧道进出口段边坡及仰坡稳定性、隧道围岩质量与稳定性、隧道涌水量、地应力及有害气体等工程地质问题,并针对不良地质现象提出防治对策,以期为工期紧张、地形困难且日趋增多的山岭隧道工程地质勘察,提供可以借鉴的模式和方法。     

公路隧道围岩地质条件评价方法及其富溪隧道应用研究

为了达到快速、准确、可靠的围岩分类,有效指导隧道施工,在充分研究和吸取国内外有关围岩分类的经验和成果基础上,针对隧道施工期间的围岩类别鉴定方法,提出了一种可用于隧道施工期间围岩类别鉴定的快速分类方法,该方法以定量与定性相结合、多专家评分的方式在开挖掌子面现场进行观察、量测及评价,无需复杂试验或测量以及繁杂计算,可迅速得出评价结果。为了更加全面地反映隧道围岩情况,准确评价围岩工程性质,结合目前国际上流行的Q分类系统,在富溪隧道第一手实测资料的基础上,根据快速分类结果和Q指标分类结果对富溪隧道围岩条件进行综合评价,为其隧道施工提供了合理的支护参数。     

隧道掘进中掌子面前方岩石结构的超前预报

以地球物理勘探方法进行隧道掘进中前方岩石结构的超前预报,具有快捷、准确和实时处理及显示的优点。通过该方法可及时、详细地了解开挖掌子面前方岩石结构情况,为施工单位合理安排施工进度和减少工程隐患提供依据。以吉林省白山市石碑岭隧道掘进中所进行的超前预报为例,介绍了地质雷达和地震反射波法在这一领域里的应用。     

基于数字钻进技术和量子遗传-径向基函数神经网络的围岩类别超前识别技术研究

围岩类别超前分类是隧道施工过程中必须开展的一项工作,其直接关系到后续的开挖及施工支护方案。为有效地进行隧道围岩类别超前分类,提出了基于数字钻进技术和量子遗传（QGA）-径向基函数（RBF）神经网络的围岩类别超前分类方法。以数字钻进技术为基础,从钻进参数中提取有用信息,构建围岩类别超前分类指标体系。采用量子计算原理对遗传算法进行改进,通过量子位编码和量子旋转门更新种群,以此来确定RBF神经网络的参数,建立了基于QGA-RBF神经网络的围岩类别超前识别系统。最后将该方法应用于青岛胶州湾海底隧道的围岩类别超前识别中,结果表明,该方法具有较高的准确性,其结果为围岩类别超前分类提供了一种新思路。     

浙江苍岭隧道岩爆工程地质特征分析与防治措施研究

根据在浙江苍岭隧道施工中发生的岩爆,通过现场地质观测资料,具体地分析了其形成的规模、位置、诱发因素以及地质条件,从地质工程的角度,对岩爆发生地段隧道的岩石组成、地质构造、地应力特征以及地下水情况进行了探讨,发现在苍岭隧道施工中发生岩爆的岩石具有岩体结构面发育适中、弹性模量大、P波波速高、地质构造简单、现代水平构造应力强且主压应力轴σ1大角度相交于隧道中轴线和地下水不发育的特征,并在此基础上,提出了掌子面喷水、布设释放地应力锚杆、减少隧道壁聚能结构等有效的岩爆防治措施。     

张家湾2号隧道下伏煤矿采空区地基稳定性分析

地下煤炭资源的开采造成了采空区,采空区的稳定性对公路建设的工程设计、施工方法、公路工程质量等工作均产生直接影响,其中对隧道工程围岩稳定性和围岩级别的划分有严重影响,公路采空区的勘察与治理作为公路建设的基础环节就显得尤为重要。本文选取山西省国道307线柳林县城区段公路改线工程中张家湾2号隧道采空区勘察为典型案例,分析了开采时间、开采方式、埋藏深度、上覆岩体特征等因素对采空区地基稳定性的影响,通过定量计算评价采空区的地基稳定性,划分采空区冒落带、裂隙带的范围,为采空区治理设计提供可靠地质依据。     

基于云模型的隧洞围岩工程地质分类方法及应用

本文将云模型理论应用于隧洞围岩工程地质分类,通过建立隧洞围岩分类多级定量指标体系及评价等级标准,计算隧洞围岩云模型隶属度,将定性评价与定量划分成果进行结合,判定隧洞围岩工程地质类别。通过工程实践应用,该方法对围岩分类问题中的模糊性和随机性进行了统一,围岩分类结果与多位地质工程师联合判断结果相比较,在共计15段围岩中有14段相同,具有高的准确度,云模型理论应用于隧洞围岩分类是合理可行的。     

Spatial predictions of geological rock mass properties based on in-situ interpretations of multi-dimensional seismic data

The article presents a statistical approach to characterize and predict engineering geological conditions in the up to 2000 m deep Faido tunnel and Gotthard base tunnel in Switzerland. Seismic investigations were conducted to improve the technology of interpreting seismic tomographic images. Overall, the goal of this study was to predict spacial maps of geological rock mass properties, such as, uniaxial compressive strength or total fracture spacing, by using up to six seismic features in combination, e.g., compression-wave and shear-wave velocities and dynamic Poisson's ratio. Self-Organizing Mapping (SOM), an artificial intelligent method, was used for the purposes of interpreting multi-dimensional geophysical attributes derived from seismic profiles of tomographic images along tunnel sidewalls. The SOM-method was applied in the Faido tunnel to delineate complex physical relations between the geological and seismic parameters. Then, the method was applied to predict geological properties around a segment of the Gotthard base tunnel with unknown geological–geotechnical conditions. The results illuminate that correlation analyses (pairwise parameter classification) are substantially less powerful than the SOM-method (multi-parameter classification) in order to interpret geological features from seismic in-situ data. Moreover, predicted spatial distributions of the total fracture spacing and the uniaxial compressive strength, for example, corresponded well with drill core and tunnel mapping results. The SOM-approach was a helpful tool for practitioners in predicting zones of instabilities and geological complexity during underground excavation processes of the Gotthard base tunnel. It is suggested to use such an interpretation method as decision support for purposes of sub/surface exploration and long-term geophysical monitoring of large-scale geoengineering projects, such as, disposals of nuclear waste and greenhouse gases or geopower plants for renewable energy (geothermal, biosoils).     

遥感解译在内蒙古额济纳旗地区1：5万地质填图中的应用

遥感技术是地质填图工作的重要辅助技术方法。针对内蒙古额济纳旗地区的荒漠戈壁地貌景观特点,在地质填图中选取国产资源三号卫星遥感数据和ETM+遥感数据作为遥感解译的数据源,并分别对获取的遥感数据进行数据融合、几何校正（或精校正）、图像校正和镶嵌等数据处理。鉴于测区植被不发育,地表多以基岩和戈壁滩为主,资源三号遥感图像颜色单调。特将校正的资源三号图像与ETM+图像进行图像融合,融合后的图像既具有ETM+图像的丰富色彩信息,又保证了资源三号卫星图像的高空间分辨率,便于实施人机交互地质矿产信息提取。根据遥感影像特征,建立了地层、侵入体和构造的解译标志,提取了与岩性和构造相关的各类信息,结合地质资料进行综合判别解译,提高了地质填图工作的准确性,为荒漠戈壁地貌区的地质填图提供了技术支持。     

浅埋双连拱隧道围岩-边坡体系变形机理及稳定性分析

双连拱隧道是一种新的隧道形式, 由于其整体跨度大、结构复杂、施工工序繁琐, 在地形偏压、地质条件复杂的情况下修建双连拱隧道难度较高, 尤其在洞口段容易出现衬砌开裂、边坡变形等一系列工程问题。结合安徽铜黄高速公路汤屯段富溪隧道进口段工程, 采用地质条件研究与数值模拟分析相结合的研究手段, 对复杂地质条件下偏压双连拱隧道围岩① 边坡体系在施工过程中应力应变发展过程进行了研究。综合分析表明, 富溪隧道进口段处于F5断层影响带内, 岩体呈碎裂结构,同时, 受到地形偏压影响, 隧道开挖后衬砌和围岩表现为沉降变形和侧向变形, 进口边坡在隧道围岩变形的诱导下, 表现为蠕滑- 拉裂变形破裂。根据以上研究成果, 提出了富溪隧道变形治理应以控制进口段隧道拱顶的变形为主。     

莲花隧道软弱围岩大变形预测方法适用性评价研究

评估地质条件以及开挖风险是地下空间设计和施工中的重要阶段之一。在选择合适的开挖方法和支护系统时,识别和估计岩体的变形潜在趋势非常重要。在本研究中,对萍莲高速莲花隧道中的岩体变形潜在趋势进行了研究。首先介绍了莲花隧道的工程地质环境、隧道围岩工程特性、岩体质量评价以及现场实测的隧道变形情况,然后运用经验法和半经验-半理论法预测莲花隧道变形趋势,并将预测结果与实际变形监测情况进行对比。结果表明,莲花隧道的大变形主要受松散破碎、遇水膨胀的软弱围岩和丰富的地下与地表水以及断层破碎带与构造活动的影响。对于莲花隧道而言,现行大变形预测方法普遍存在一定问题：经验法主要依据岩体质量分级结果进行变形趋势预测,具有一定的主观性,其预测结果与实际变形情况存在一定偏差;半经验-半理论方法中运用围岩强度与应力关系进行预测效果较好,但基于围岩强度应力比的Jethwa法、Hoek法与ISRM法预测结果偏保守,且针对无变形段的预测效果较差。综上所述,在工程勘察与设计阶段,应客观、细致地进行围岩质量分级、地应力量测、地下水与地质构造勘探等工作,结合经验法、半经验-半理论方法对大变形趋势和变形量值进行预测,综合研判隧洞沿线...     

Discontinuous deformation analysis of super section tunnel surrounding rock stability based on joint distribution simulation

Based on binocular stereo photography measurement technology, the actual distribution information of joints and fractures in the tunnel face were obtained via image processing and feature extraction, and the preliminary evaluation of surrounding rock stability of Laohushan tunnel was conducted according to surrounding rock classification method. Since all available surrounding rock classification approaches didn’t consider the influences of the size effect of tunnel excavation span and unfavorable geologic bodies such as weak-fracture zones, an improved discontinuous deformation analysis (DDARF) method was adopted to conduct a numerical simulation of the deformation and fracture processes of the surrounding rock. Using the traveling wave method, triangle DDA blocks were automatically generated in the calculation zone, and the block boundaries were divided into real joints and virtual joints. Based on the real joint information obtained via aforementioned photographic measurement, the real joints in the tunnel face were dynamically modified, in order to achieve the simulation of joint distribution. The results revealed that the fracture evolution regularity, deformation failure mechanism, and block dropping phenomenon that the DDARF joint simulation model calculated are in good agreement with actual conditions, while those obtained based on conventional models present differences from field situation. Additionally, focusing on the localised rockfall phenomenon of Laohushan tunnel, the crack extension rate was introduced to conduct a quantitative comparison of the rock crack evolution process with or without anchor supporting. The research results offer practical guidance for field construction and anchorage support scheme optimization.     

基于Hoek-Brown强度准则的隧道软弱围岩稳定性分析

因长期遭受地质作用和构造力的改造作用,地下岩体中存在大量的软弱破碎带,隧道开挖穿越这一地带很容易出现较大的变形,甚至出现塌方等事故。论文采用TGP超前地质预报与掌子面围岩调查相结合的方法进行隧道掌子面及前方未开挖岩体的精细化地质调查,获取了隧道围岩的Hoek-Brown参数。采用FLAC3D数值模拟方法,分析了破碎带围岩在既定支护条件下的稳定性,并与现场监测数据进行对比,验证此方法的正确性。研究结果表明,数值模拟结果与实际监测结果较为吻合,可以将此方法用于指导未开挖段隧道的稳定性预测,以确保隧道掘进过程的施工安全。     

Extreme deformation characteristics and countermeasures for a tunnel in difficult grounds in southern Shaanxi,China

The Qingling–Bashan (QB) mountain region in southern Shaanxi mainly consists of strongly compressive zones from east to west, with tight folds and compressive fractures. There is a wide distribution of soft rocks of various types, such as phyllite and slate, accompanied by complex geological structures. Ironically, tunnel construction in these difficult grounds with complicated geological conditions embraces a high risk of extreme deformation due to various unpredictable reasons, which can frequently cause collapse and result in budget overruns during the construction period. Therefore, it is crucial to conduct effective countermeasures to eliminate or avoid such adverse impacts. This paper provides a case study on the “Yingfeng tunnel” (a tunnel constructed in soft rock consisting of a slate ground) based on a geological survey, indoor experiments and in situ monitoring. A successive rock mass deformation resulted in the tunnel lining seriously intruding into construction clearance and some other sections, even collapsing during the construction. The maximum displacement amount was 62.5 cm, while the maximum deformation speed reached as high as 34.18 mm/day. Additionally, to evaluate the construction impacts of tunnelling-induced geo-hazards, an investigation on extreme deformation was conducted. Considering the time-dependent features of the rock mass deformation, the constraint-convergence method was used to put forward applicable countermeasures in this paper. Finally, from the feedbacks of monitoring results, extreme deformation of the Yingfeng tunnel was effectively controlled.     

基于功效系数法和地应力场反演的深埋长大隧道岩爆预测研究

岩爆是深埋长大隧道面临的主要地质灾害之一,其“孕育-发生-发展”全过程异常复杂,使其成为地下工程中的世界性难题。准确反映地应力变化规律以及区域内地质构造影响,结合实测资料进行岩爆分级预测,对保障隧道前期勘察设计及后期安全施工具有重要意义。根据隧道工程地质资料,通过COMSOL Multiphysics和Rhino建立三维数值计算模型,反演分析得到整个区域的初始地应力场。在综合分析影响岩爆关键因素的基础上,从“储能性-倾向性-突发性”研究角度,选取岩石单轴抗压强度与围岩洞壁最大主应力比(σ_c/σ_max)、围岩洞壁最大切向应力与岩石单轴抗压强度比(σ_θ/σ_c)、岩石强度脆性系数(σ_c/σ_t)及岩石弹性能指数(W_et)作为评价指标。采用熵权法确定指标权重,运用功效系数法加权计算总功效系数值,构建了一种基于功效系数法和地应力场反演的深埋长大隧道岩爆预测模型,并将其应用于川藏铁路桑珠岭隧道。研究结果表明,该模型具有较高的准确性和可靠性,为类似深埋长大隧道岩爆预测提供了一种新的参考。     

张集线旧堡隧道工程地质条件和岩体结构特征研究

新建的张集铁路（张家口 集宁段）旧堡隧道是全线关键性控制工程,位于河北省万全县旧堡乡与尚义县土夭村之间,隧道穿越由晚太古代马市口组(Arm)麻粒岩和黑云母斜长片麻岩组成的一套高级变质岩建造,断裂构造极为发育,岩体破碎。原设计Ⅱ、Ⅲ级围岩洞段占隧道线路总长的71.8%,而已施工揭露的工程地质条件较差,全部变更为Ⅲ级加强及Ⅳ、Ⅴ级围岩,变更率高达80.3%。施工过程中多次发生挤压大变形、塌方、突涌水等施工地质灾害,共处理大塌方段8处小塌方21处计130m,处理大变形18段计550m。本文分析了DK30+520～910洞段地层岩性、地质构造、地应力、地下水等隧道围岩主要工程地质条件,从结构面和工程地质岩组的物理力学特性出发,研究了该洞段特殊的岩体结构,指出该隧道围岩岩体结构特征主要受与隧道轴线小角度相交的构造挤压破碎带及软硬交替产出的岩组控制,隧道围岩变形破坏受岩体结构控制作用明显,并总结了施工中可能遇到的几种岩体结构。该研究对类似工程地质条件地区隧道工程围岩分类、支护设计和施工有一定的借鉴意义。