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.

Advances in statistical mechanics of rock masses and its engineering applications

To efficiently link the continuum mechanics for rocks with the structural statistics of rock masses,a theoretical and methodological system called the statistical mechanics of rock masses(SMRM)was developed in the past three decades.In SMRM,equivalent continuum models of stressestrain relationship,strength and failure probability for jointed rock masses were established,which were based on the geometric probability models characterising the rock mass structure.This follows the statistical physics,the continuum mechanics,the fracture mechanics and the weakest link hypothesis.A general constitutive model and complete stressestrain models under compressive and shear conditions were also developed as the derivatives of the SMRM theory.An SMRM calculation system was then developed to provide fast and precise solutions for parameter estimations of rock masses,such as full-direction rock quality designation(RQD),elastic modulus,Coulomb compressive strength,rock mass quality rating,and Poisson’s ratio and shear strength.The constitutive equations involved in SMRM were integrated into a FLAC3D based numerical module to apply for engineering rock masses.It is also capable of analysing the complete deformation of rock masses and active reinforcement of engineering rock masses.Examples of engineering applications of SMRM were presented,including a rock mass at QBT hydropower station in northwestern China,a dam slope of Zongo II hydropower station in D.R.Congo,an open-pit mine in Dexing,China,an underground powerhouse of Jinping I hydropower station in southwestern China,and a typical circular tunnel in Lanzhou-Chongqing railway,China.These applications verified the reliability of the SMRM and demonstrated its applicability to broad engineering issues associated with jointed rock masses.

Numerical method to determine mechanical parameters of engineering design in rock masses

This paper proposes a new continuity model for engineering in rock masses and a new schematic method for reporting the engineering of rock continuity. This method can be used to evaluate the mechanics of every kind of medium;and is a new way to determine the mechanical parameters used in engineering design in rock masses. In the numerical simulation, the experimental parameters of intact rock were combined with the structural properties of field rock. Theexperimental results for orthogonally-jointed rock are given. The results included the curves of the stress-strain relationship of some rock masses, the curve of the relationship between the dimension Δ and the uniaxial pressure-resistant strength σc of these rock masses, and pictures of the destructive procedure of some rock masses in uniaxial or triaxial tests, etc. Application of the method to engineering design in rock masses showed the potential of its application to engineering practice.

Determination of rock mass integrity coefficient using a non-invasive geophysical approach

Determination of rock mechanical parameters is the most important step in rock mass quality evaluation and has significant impacts on geotechnical engineering practice.Rock mass integrity coefficient(KV)is one of the most efficient parameters,which is conventionally determined from boreholes.Such approaches,however,are time-consuming and expensive,offer low data coverage of point measurements,require heavy equipment,and are hardly conducted in steep topographic sites.Hence,borehole approaches cannot assess the subsurface thoroughly for rock mass quality evaluation.Alternatively,use of geophysical methods is non-invasive,rapid and economical.The proposed geophysical approach makes useful empirical correlation between geophysical and geotechnical parameters.We evaluated the rock mass quality via integration between KV measured from the limited boreholes and inverted resistivity obtained from electrical resistivity tomography(ERT).The borehole-ERT correlation provided KV along various geophysical profiles for more detailed 2D/3D(two-/three-dimensional)mapping of rock mass quality.The subsurface was thoroughly evaluated for rock masses with different engineering qualities,including highly weathered rock,semi-weathered rock,and fresh rock.Furthermore,ERT was integrated with induced polarization(IP)to resolve the uncertainty caused by water/clay content.Our results show that the proposed method,compared with the conventional approaches,can reduce the ambiguities caused by inadequate data,and give more accurate insights into the subsurface for rock mass quality evaluation.

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.

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.

Displacement-based back analysis of mitigating the effects of displacement loss in underground engineering

Displacement-monitoring-based back analysis is a popular method for geomechanical parameter estimation.However,due to the delayed installation of multi-point extensometers,the monitoring curve is only a part of the overall one,leading to displacement loss.Besides,the monitoring and construction time on the monitoring curve is difficult to determine.In the literature,the final displacement was selected for the back analysis,which could induce unreliable results.In this paper,a displacement-based back analysis method to mitigate the influence of displacement loss is developed.A robust hybrid optimization algorithm is proposed as a substitute for time-consuming numerical simulation.It integrates the strengths of the nonlinear mapping and prediction capability of the support vector machine(SVM)algorithm,the global searching and optimization characteristics of the optimized particle swarm optimization(OPSO)algorithm,and the nonlinear numerical simulation capability of ABAQUS.To avoid being trapped in the local optimum and to improve the efficiency of optimization,the standard PSO algorithm is improved and is compared with other three algorithms(genetic algorithm(GA),simulated annealing(SA),and standard PSO).The results indicate the superiority of OPSO algorithm.Finally,the hybrid optimization algorithm is applied to an engineering project.The back-analyzed parameters are submitted to numerical analysis,and comparison between the calculated and monitoring displacement curve shows that this hybrid algorithm can offer a reasonable reference for geomechanical parameters estimation.

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.

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.

Investigation of long-wavelength elastic wave propagation through wet bentonite-filled rock joints

The saturation of the compacted bentonite buffer in the deep geological repository can cause bentonite swelling,intrusion into rock fractures,and erosion.Inevitably,erosion and subsequent bentonite mass loss due to groundwater inflow can aggravate the overall integrity of the engineered barrier system.Therefore,the coupled hydro-mechanical interaction between the buffer and rock during groundwater inflow and bentonite intrusion should be evaluated to guarantee the long-term safety of deep geological disposal.This study investigated the effect of bentonite erosion and intrusion on the elastic wave propagation characteristics in jointed rocks using a quasi-static resonant column test.Jointed rock specimens with different joint conditions(i.e.joint surface saturation and bentonite filling)were prepared using granite rock discs sampled from the Korea Underground Research Tunnel(KURT)and Gyeongju bentonite.The long-wavelength longitudinal and shear wave velocities were measured under different normal stress levels.A Hertzian-type power model was used to fit the wave velocities,and the relationship between the two fitted parameters provided the trend of joint conditions.Numerical simulations using three-dimensional distinct element code(3DEC)were conducted to better understand how the long-wavelength wave propagates through wet bentonite-filled rock joints.

Evolution process of rock mass engineering system using systems science

The rock mass engineering system （RMES） basically consists ofrock mass engineering （RME）, water system and surroundingecological environments, etc. The RMES is characterized by nonlinearity,occurrence of chaos and self-organization （Tazaka, 1998;Tsuda, 1998; Kishida, 2000）. From construction to abandonmentof RME, the RMES will experience four stages, i.e. initial phase,development phase, declining phase and failure phase. In thiscircumstance, the RMES boundary conditions, structural safetyand surrounding environments are varied at each phase, so arethe evolution characteristics and disasters （Wang et al., 2014）.

Failure evaluation and control factor analysis of slope block instability along traffic corridor in Southeastern Tibet

The instability of slope blocks occurred frequently along traffic corridor in Southeastern Tibet(TCST),which was primarily controlled by the rock mass structures.A rapid method evaluating the control effects of rock mass structures was proposed through field statistics of the slopes and rock mass structures along TCST,which combined the stereographic projection method,modified M-JCS model,and limit equilibrium theory.The instabilities of slope blocks along TCST were then evaluated rapidly,and the different control factors of instability were analyzed.Results showed that the probabilities of toppling(5.31%),planar(16.15%),and wedge(35.37%)failure of slope blocks along TCST increased sequentially.These instability modes were respectively controlled by the anti-dip joint,the joint parallel to slope surface with a dip angle smaller than the slope angle(singlejoint),and two groups of joints inclined out of the slope(double-joints).Regarding the control effects on slope block instability,the stabilization ability of doublejoints(72.7%),anti-dip joint(67.4%),and single-joint(57.6%)decreased sequentially,resulting in different probabilities of slope block instability.Additionally,nearby regional faults significantly influenced the joints,leading to spatial heterogeneity and segmental clustering in the stabilization ability provided by joints to the slope blocks.Consequently,the stability of slope blocks gradually weakened as they approached the fault zones.This paper can provide guidance and assistance for investigating the development characteristics of rock mass structures and the stability of slope blocks.

Classification and rating of disintegrated dolomite strata for slope stability analysis

Although disintegrated dolomite,widely distributed across the globe,has conventionally been a focus of research in underground engineering,the issue of slope stability issues in disintegrated dolomite strata is gaining increasing prominence.This is primarily due to their unique properties,including low strength and loose structure.Current methods for evaluating slope stability,such as basic quality(BQ)and slope stability probability classification(SSPC),do not adequately account for the poor integrity and structural fragmentation characteristic of disintegrated dolomite.To address this challenge,an analysis of the applicability of the limit equilibrium method(LEM),BQ,and SSPC methods was conducted on eight disintegrated dolomite slopes located in Baoshan,Southwest China.However,conflicting results were obtained.Therefore,this paper introduces a novel method,SMRDDS,to provide rapid and accurate assessment of disintegrated dolomite slope stability.This method incorporates parameters such as disintegrated grade,joint state,groundwater conditions,and excavation methods.The findings reveal that six slopes exhibit stability,while two are considered partially unstable.Notably,the proposed method demonstrates a closer match with the actual conditions and is more time-efficient compared with the BQ and SSPC methods.However,due to the limited research on disintegrated dolomite slopes,the results of the SMRDDS method tend to be conservative as a safety precaution.In conclusion,the SMRDDS method can quickly evaluate the current situation of disintegrated dolomite slopes in the field.This contributes significantly to disaster risk reduction for disintegrated dolomite slopes.

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.

Rapid profiling rock mass quality underneath tunnel face for Sichuan-Xizang Railway

The Sichuan-Xizang Railway is a global challenge,surpassing other known railway projects in terms of geological and topographical complexity.This paper presents an approach for rapidly profiling rock mass quality underneath tunnel face for the ongoing construction of the Sichuan-Xizang Railway.It adopts the time-series method and carries out the quantitative analysis of the rock mass quality using the depth-series measurement-while-drilling(MWD)data associated with drilling of blastholes.A tunnel face with 15 blastholes is examined for illustration.The results include identification of the boundary of homogeneous geomaterial by plotting the blasthole depth against the net drilling time,as well as quantification of rock mass quality through the recalculation of the new specific energy.The new specific energy profile is compared and highly consistent with laboratory test,manual logging and tunnel seismic prediction results.This consistency can enhance the blasthole pattern design and facilitate the dynamic determination of charge placement and amount.This paper highlights the importance of digital monitoring during blasthole drilling for rapidly profiling rock mass quality underneath and ahead of tunnel face.It upgrades the MWD technique for rapid profiling rock mass quality in drilling and blasting tunnels.

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.

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

Engineering rock mechanics practices in the underground powerhouse at JinpingⅠhydropower station

Based on the analyses of data obtained from the underground powerhouse at Jinping I hydropower station, a comprehensive review of engineering rock mechanics practice in the underground powerhouse is first conducted. The distribution of strata, lithology, and initial geo-stress, the excavation process and corresponding rock mass support measures, the deformation and failure characteristics of the surrounding rock mass, the stress characteristics of anchorage structures in the cavern complex, and numerical simulations of surrounding rock mass stability and anchor support performance are presented. The results indicate that the underground powerhouse of Jinping I hydropower station is characterized by high to extremely high geo-stresses during rock excavation. Excessive surrounding rock mass deformation and high stress of anchorage structures, surrounding rock mass unloading damage, and local cracking failure of surrounding rock masses, etc., are mainly caused by rock mass excavation. Deformations of surrounding rock masses and stresses in anchorage structures here are larger than those found elsewhere： 20% of extensometers in the main powerhouse record more than 50 mm with the maximum at around 250 mm observed in the downstream sidewall of the transformer hall. There are about 25% of the anchor bolts having recorded stresses of more than 200 MPa. Jinping I hydropower plant is the first to have an underground powerhouse construction conducted in host rocks under extremely high geo-stress conditions, with the ratio of rock mass strength to geo-stress of less than 2.0. The results can provide a reference to underground powerhouse construction in similar geological conditions.