Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

Multiscale hierarchical analysis of rock mass and prediction of its mechanical and hydraulic properties

Engineering geological and hydro-geological characteristics of foundation rock and surrounding rock mass are the main factors that affect the stability of underground engineering. This paper presents the concept of multiscale hierarchical digital rock mass models to describe the rock mass, including its structures in different scales and corresponding scale dependence. Four scales including regional scale,engineering scale, laboratory scale and microscale are determined, and the corresponding scaledependent geological structures and their characterization methods are provided. Image analysis and processing method, geostatistics and Monte Carlo simulation technique are used to establish the multiscale hierarchical digital rock mass models, in which the main micro-and macro-structures of rock mass in different geological units and scales are reflected and connected. A computer code is developed for numerically analyzing the strength, fracture behavior and hydraulic conductivity of rock mass using the multiscale hierarchical digital models. Using the models and methods provided in this paper, the geological information of rock mass in different geological units and scales can be considered sufficiently,and the influence of downscale characteristics(such as meso-scale) on the upscale characteristics(such as engineering scale) can be calculated by considering the discrete geological structures in the downscale model as equivalent continuous media in the upscale model. Thus the mechanical and hydraulic properties of rock mass may be evaluated rationally and precisely. The multiscale hierarchical digital rock mass models and the corresponding methods proposed in this paper provide a unified and simple solution for determining the mechanical and hydraulic properties of rock mass in different scales.

A-BQ,a classification system for anisotropic rock mass based on China National Standard

The rock mass in nature is in most cases anisotropic,while the existing classifications are mostly developed with the assumption of isotropic conditions that not always meet the engineering requirements.In this study,an anisotropic system based on China National Standard of BQ,named as A-BQ,is developed to address the classification of anisotropic rock mass incorporating the anisotropy degree as well as the quality of rock mass.Two series of basic rating factors are incorporated including inherent anisotropy and structure anisotropy.The anisotropy degree of rock mass is characterized by the ratio of maximum to minimum quality score and adjusted by the confining stress.The quality score of rock mass is determined by the key factors of anisotropic structure occurrence and the correction factors of stress state and groundwater condition.The quality of rock mass is characterized by a quality score and classified in five grades.The assessment of stability status and probable failure modes are also suggested for tunnel and slope engineering for different quality grades.Finally,two cases of tunnel and slope are presented to illustrate the application of the developed classification system into the rock masses under varied stress state.

Rock Mass Characteristics in Beishan,A Preselected Area for China's High-Level Radioactive Waste Disposal

Geological and hydrological characteristics, joint geometric features, rock physical and mechanical properties and rock mass quality are studied in the Beishan area, preselected for China5 s high-level radioactive waste(HLW) disposal engineering. A comprehensive survey method is developed to study joint geometric features in the outcrop and samples from borehole BS06 into the Xinchang rock mass were tested. The optimal joint sets are determined by rose diagrams and equal-area lower hemisphere plots of joint poles. Results show that: 1) the distribution of joint occurrence obeys a normal distribution, while the distribution of joint spacing obeys a negative exponential distribution; 2) concentric circular and tangent circular sampling windows are applied to study the trace length and the trace midpoint density. Results indicate that tangent circular sampling window is more stable and reasonable; 3) Beishan granite shows high density, low porosity and high strength based on many laboratory tests and the physical properties and mechanical properties are closely related; and4) a synthesis index, Joint Structure Rating(JSR), is applied to evaluate the quality of rock mass. Through the research results of rock mass characteristics, the Xinchang rock mass in the Beishan preselected area has the favorable conditions for China's HLW disposal repository site.

Computing in-situ strength of rock masses based upon RQD and modified joint factor: Using pressure and damage sensitive constitutive relationship

In th is study, a n e w m odel w as p re se n te d for com p u tin g stre n g th o f rock m asses based u p o n in -situo bservations o f RQD p o pularly kno w n as rock quality d esignation. This m odel links u p th e rock m assp aram eters from in -situ investigations w ith th e stre n g th p a ram eters o f jo in ted rocks obtain ed fromlaboratory scale ex p erim en tal observations. Using th e co n stitu tiv e relation, th e a u th o r derived a p ressu reand d am age sensitive plastic p a ra m e te r to d ete rm in e stre n g th o f rock m asses for varied ex te n ts ofd isco n tin u ity an d p ressu re induced dam age. The te s t results show th a t plasticity characterized byhard en in g an d softening inclusive o f dam ag e invariably d e p en d s u p o n m ean p ressu re an d e x te n t ofdefo rm atio n s alread y experien ced by rock m asses. The p re se n t w ork explores th e te s t d a ta th a t revealth e d ep en d en c e o f in -situ stren g th on increm ental jo in t p ara m e te rs o b tain ed from th e jo in t num ber,jo in t orien tatio n , jo in t roughness, gouge p a ram eters an d w a te r pressure. S ubstituting th e relationshipb e tw e e n th e RQD and m odified jo in t factor w ith th a t b e tw e e n m odulus ratio an d stren g th ratio, th em odel show s successfully th a t using d am age inclusive plastic p a ra m e te r an d RQD provides a relationshipfor estim atin g th e stre n g th o f rock m asses. One o f th e m ain objectives o f this w ork is to illustrate th a t th ep re se n t m odel is sensitive to p la s tic ity a n d dam ag e to g e th e r in estim atin g in -situ stre n g th o f rock m assesin foundations, u n d e rg ro u n d excavation an d tunnels.

Multiscale Hierarchical Digital Rock Mass Models and Numerical Testing on Mechanical and Hydaulic Properties of Rock Mass

Underground space utilization and exploration is an irreversible trend for promoting sustainable development especially in megacities.Geotechnical engineering safety is always one of the most important issues in all phases,including planning,design, construction and operation,of the underground project.Engineering geological and hydro-geological characteristics of the foundation rock mass

A novel approach to structural anisotropy classification for jointed rock masses using theoretical rock quality designation formulation adjusted to joint spacing

Rock quality designation(RQD)has been considered as a one-dimensional jointing degree property since it should be determined by measuring the core lengths obtained from drilling.Anisotropy index of jointing degree(AI_(jd))was formulated by Zheng et al.(2018)by considering maximum and minimum values of RQD for a jointed rock medium in three-dimensional space.In accordance with spacing terminology by ISRM(1981),defining the jointing degree for the rock masses composed of extremely closely spaced joints as well as for the rock masses including widely to extremely widely spaced joints is practically impossible because of the use of 10 cm as a threshold value in the conventional form of RQD.To overcome this limitation,theoretical RQD(TRQD_(t))introduced by Priest and Hudson(1976)can be taken into consideration only when the statistical distribution of discontinuity spacing has a negative exponential distribution.Anisotropy index of the jointing degree was improved using TRQD_(t) which was adjusted to wider joint spacing by considering Priest(1993)’s recommendation on the use of variable threshold value(t)in TRQD_(t) formulation.After applications of the improved anisotropy index of a jointing degree(AI'_(jd))to hypothetical jointed rock mass cases,the effect of persistency of joints on structural anisotropy of rock mass was introduced to the improved AI'_(jd) formulation by considering the ratings of persistency of joints as proposed by Bieniawski(1989)’s rock mass rating(RMR)classification.Two real cases were assessed in the stratified marl and the columnar basalt using the weighted anisotropy index of jointing degree(W_AI'_(jd)).A structural anisotropy classification was developed using the RQD classification proposed by Deere(1963).The proposed methodology is capable of defining the structural anisotropy of a rock mass including joint pattern from extremely closely to extremely widely spaced joints.

Rock mass quality classification based on deep learning:A feasibility study for stacked autoencoders

Objective and accurate evaluation of rock mass quality classification is the prerequisite for reliable sta-bility assessment.To develop a tool that can deliver quick and accurate evaluation of rock mass quality,a deep learning approach is developed,which uses stacked autoencoders(SAEs)with several autoencoders and a softmax net layer.Ten rock parameters of rock mass rating(RMR)system are calibrated in this model.The model is trained using 75%of the total database for training sample data.The SAEs trained model achieves a nearly 100%prediction accuracy.For comparison,other different models are also trained with the same dataset,using artificial neural network(ANN)and radial basis function(RBF).The results show that the SAEs classify all test samples correctly while the rating accuracies of ANN and RBF are 97.5%and 98.7%,repectively,which are calculated from the confusion matrix.Moreover,this model is further employed to predict the slope risk level of an abandoned quarry.The proposed approach using SAEs,or deep learning in general,is more objective and more accurate and requires less human inter-vention.The findings presented here shall shed light for engineers/researchers interested in analyzing rock mass classification criteria or performing field investigation.

Assessment of Rock Mass Quality and Support Estimation along Headrace Tunnel of a Small Hydropower in District Mansehra, Khyber Pakhtunkhwa, Pakistan

The main purpose of this study is to classify the rock mass quality by using rock mass quality (Q) and Rock Mass Rating (RMR) systems along headrace tunnel of small hydropower in Mansehra District, Khyber Pakhtunkhwa. Geological field work was carried out to determine the orientation, spacing, aperture, roughness and alteration of discontinuities of rock mass. The quality of rock mass along the tunnel route is classified as good to very poor quality by Q system, while very good to very poor by RMR classification system. The relatively good rock conditions are acquired via RMR values that are attributed to ground water conditions, joint spacing, RQD and favorable orientation of discontinuities with respect to the tunnel drive. The petrographic studies revealed that study area is mainly comprised of five major geological rock units namely quartz mica schist (QMS), garnet mica schist (GMS), garnet bearing quartz mica schist (G-QMS), calcareous schist (CS), marble (M). The collected samples of quartz mica schist, marble and garnet bearing quartz mica schist are fine to medium grained, compact and are cross cut by few discontinuities having greater spacing. Therefore, these rocks have greater average RQD, Q values, RMR ratings as compared to garnet mica schist and calcareous schist.

Quality index of bedded and joint-bearing rock mass and its applications

Based on the theory of Fuzzy Mathematics and Expert System, this paper presents the quantitative expression method of bedded and joint bearing rock mass quality "Stratum Quality Index"(SQI for short), and also introduces the successful application of the method in estimating stratum movement parameters.

A Geological Classification of Rock Mass Quality and Blast Ability for Widely Spaced Formations

Success in the excavation of geological formations is commonly known as being very important in asserting stability. Furthermore, when the subjected geological formation is rocky and the use of explosives is required, the demands of successful blasting are multiplied. The present paper proposes a classification system, named： BQS （blast ability quality system）, for rock masses with widely spaced discontinuities （spacing longer than l m）. It is obvious that rock quality is one of the main characteristics which define the blast ability of a rock. The BQS can be an easy and widely-used tool as it is a quick evaluator for blast ability and rock mass quality at one time. Taking into consideration the research calculations and the parameters of BQS, what has been at question in this paper is the effect of blast ability in a geological formation with widely spaced discontinuities.

针对基于三维激光扫描技术岩体结构面调查方法的评述

以三维激光扫描技术为研究对象,对岩体结构面非接触调查法的作业原理、设备分类、算法优化进行了详细介绍,同时通过应用实例对该技术的实用性进行了评述。该项技术较好的符合了现场实际条件,操作速度快,操作形式多样,工作适应性强,可使现场工作人员安全得到保障,能够满足矿山企业快速评价岩体质量的需求,能够作为选择工程结构参数、科学管理生产以及评价经济效益的重要依据。

Determination and applications of rock quality designation(RQD)

Characterization of rock masses and evaluation of their mechanical properties are important and challenging tasks in rock mechanics and rock engineering. Since in many cases rock quality designation （RQD） is the only rock mass classification index available, this paper outlines the key aspects on determination of RQD and evaluates the empirical methods based on RQD for determining the deformation modulus and unconfined compressive strength of rock masses. First, various methods for determining RQD are presented and the effects of different factors on determination of RQD are highlighted. Then, the empirical methods based on RQD for determining the deformation modulus and unconfined compressive strength of rock masses are briefly reviewed. Finally, the empirical methods based on RQD are used to determine the deformation modulus and unconfined compressive strength of rock masses at five different sites including 13 cases, and the results are compared with those obtained by other empirical methods based on rock mass classification indices such as rock mass rating （RMR）, Q-system （Q） and geological strength index （GSI）. It is shown that the empirical methods based on RQD tend to give deformation modulus values close to the lower bound （conservative） and unconfined compressive strength values in the middle of the corresponding values from different empirical methods based on RMR, Q and GSI. The empirical methods based on RQD provide a convenient way for estimating the mechanical properties of rock masses but, whenever possible, they should be used together with other empirical methods based on RMR, Qand GSI.

Geostatistics-block-based characterization of the relationship between rock mass quality and powder factor and its application on open-pit limit optimization

Accurately predicting the powder factor during blasting is essential for sustainable production planning in low-grade mines.This research presents a method for predicting powder factor based on the heterogeneity of rock mass rating(RMR).Considering a low-grade metal mine as an example,this study exploited geostatistical methods to obtain independent RMR for each block unit.A three-dimensional spatial distribution model for the powder factor was developed on the basis of the relationships between the RMR and the powder factor.Subsequently,models for blasting cost and mining value were built and employed to optimize the open-pit limit.The multi-variable model based on the RMR performed well in predicting the powder factor,achieving a correlation coefficient of 0.88(root mean square error of 4.3)and considerably outperforming the uniaxial compressive strength model.After model optimization,the mean size and standard deviation of the fragments in the blast pile decreased by 8.5%and 35.1%,respectively,whereas the boulder yield and its standard deviation decreased by 33.3%and 58.8%,respectively.Additionally,optimizing the open-pit limit using this method reduced the amount of rock,increased the amount of ore,and lowered blasting costs,thereby enhancing the economic efficiency of the mine.This study provides valuable insights for blasting design and mining decisions,demonstrating the advantages and potential applications of powder factor prediction based on the heterogeneity of rock mass quality.

基于BWO-RF模型的岩体质量评价方法

岩体质量分级是地下工程初期设计和施工的基础。为了更加高效准确地开展岩体质量评价,提出了一种基于白鲸优化(BWO)随机森林的岩体质量评价模型——BWO-RF模型,同时构建了麻雀搜索算法优化随机森林(SSA-RF)、粒子群优化随机森林(PSO-RF)和未优化随机森林(RF)的岩体质量评价模型进行对比。在模型构建前,建立了包含131组工程实例数据的数据库,运用该数据库最终完成了4种模型的训练和测试。基于模型测试结果,采用准确率、查准率、召回率、F1值和AUC值5个评价指标对模型进行对比优选。研究结果表明:BWO-RF模型各项评价指标均优于其余3种模型,具有更优的评价性能;经过工程实例验证,本研究所提出的BWO-RF模型预测准确率达90%,可为实际工程建设提供参考依据,具备实际工程应用价值。

基于岩体质量的井筒保安矿柱优化与应用

为兼顾井筒稳定和减少资源的不必要浪费,在常规的岩层移动角井筒保安矿柱圈定法基础上,采用工程类比法,将Ⅱ级岩体质量围岩部分的井筒保安矿柱尺寸优化为80m,形成上部台体下部圆柱体的保安矿柱。同时对优化后的保安矿柱周边压覆资源采取控制采场顶板暴露面积和分层充填的保护性开采措施。数值模拟结果表明:按优化后的保安矿柱范围开采周边矿体后,地表井架、卷扬机房及井筒内壁变形量均未超过最大允许变形值,说明优化方案具有可行性。

不同贮藏时间武夷岩茶风味品质化学差异

以7个不同贮藏时间的武夷岩茶(水仙)样品为研究对象,采用感官审评、非挥发性物质和挥发性物质检测,联合化学计量学方法探究贮藏时间对武夷岩茶风味品质的影响。结果表明,武夷岩茶贮藏期间风味品质可分为3个转化阶段:0~5、10~15、20~30 a。随着贮藏时间的延长,滋味逐渐由醇厚转化为陈香,贮藏中期出现酸味并在后期逐渐褪去;香气逐渐由花香、果香转化为陈香、木香、药香。茶多酚、儿茶素类、茶黄素等化合物含量的显著降低和可溶性糖含量的增加是滋味转化的主要原因。吲哚、反式-橙花叔醇、二氢猕猴桃内酯、脱氢芳樟醇、α-松油醇、水杨酸甲酯、β-紫罗兰酮、(Z)-己酸-3-己烯酯等15种特征挥发性物质的含量变化是影响香气转化的关键因子。本研究综合分析了武夷岩茶在贮藏过程中的风味变化并提出科学见解,以期为武夷岩茶贮藏及消费者科学饮用提供参考。

基于加权隶属度矩阵的岩体质量优化分级及支护研究

巷道围岩质量分级是巷道围岩稳定性分析、合理支护设计与施工的基础。提高分级结果的准确性,是提升支护效果和巷道围岩稳定性的关键途径。以RMR法为基础,以某一测点的分级因素指标值为例,构建RMR法各分级指标的隶属度矩阵,再结合熵值法确定分级指标的权重,得到加权隶属度矩阵,构造优化后的评分公式,进行指标优化评分和围岩质量分级,然后根据围岩质量分级结果及松动圈监测结果设计支护参数,利用FLAC3D进行模拟计算以巷道围岩塑性区体积和顶底板收敛量为评价指标,研究优化前后的支护效果。研究结果表明:经过优化后的指标评分和围岩等级更加准确,巷道支护参数设计更加合理,数值模拟结果显示其能有效地提升围岩的稳定性,并将优化后的支护设计参数应用于工程,取得了良好的效果。研究成果可有效解决巷道围岩分级因素指标值位于分级边界或分级跨度大的问题,为矿山岩体质量分级与支护设计提供参考。

坝肩岩体质量LDA-KNN分类模型

工程岩体质量分级评价对工程的安全、设计、经济效益等有重要影响。针对当前岩级划分方法中存在不确定性,人为因素干扰和忽视了传统定性分级中对岩体质量评价的重要性等问题,本文通过在工程实际中搜集样本建立数据库,从工程的实际需求出发,选择岩体完整性系数(K v)、结构面间距(D)、岩石质量指标(RQD)等合适的评价指标,通过引入LDA(Linear Discriminant Analysis)降维方法和K近邻分析(K-Nearest-Neighbor,KNN)相结合的多分类模型,实现了岩体的非线性分级预测。通过定性定量相结合实现了岩体多因素,多指标的综合分级,并解决了多指标判断时信息冗余,复杂程度高的问题。与其他判别方案相比较,模型得出的结果准确率高,符合工程实际,减少了人为因素的影响,体现出较强的预测判别能力。该研究为水电站大坝坝肩处的平硐岩体质量划分提出了一种可行的预测方案。

海南琼中岩-土体系重金属迁移特征及表土环境质量评价

地球关键带和土壤重金属污染是当今研究的前沿与热点,岩-土体系是地球关键带的重要组成部分。目前海南岛针对不同成壤母质岩-土体系的详细研究较少,并且重金属亟需基于新标准进行评价。为了查清岩-土体系中重金属元素迁移特征及污染状况,本文以海南岛琼中3个土壤垂向剖面及7115件表层土壤样品为研究对象,采用电感耦合等离子体质谱/发射光谱法(ICP-MS/OES)和原子荧光光谱法(AFS)等分析方法,测定岩石和土壤中Cu、Pb、Zn、Cr、Ni、Cd、As和Hg共8种重金属元素含量,利用土壤环境质量农用地土壤污染风险管控标准、内梅罗指数法和潜在生态危害指数法定量评价了表层土壤样品重金属污染状况及生态风险。结果表明,①海南岛琼中二长花岗岩岩-土体系中,不同重金属元素表现出明显的分异特征,Cu、Pb、Zn、Cr、Ni、Cd元素以亏损为主,As元素以富集为主,Hg元素则表现出不同的富集或亏损特征,As、Hg元素尤其富集在表层。②琼中绝大多数表层土壤中重金属元素含量低于土壤环境质量农用地土壤污染风险筛选值,土壤污染风险低。③以琼中和海南岛背景值为评价标准时,应关注Cr、Ni和As污染以及Hg、As和Cd的生态危害。以土壤环境质量为评价标准时,研究区表层土壤的环境质量总体清洁,生态风险较弱。