Surrounding Rock Classification Research Articles

Novel multifractal-based classification model for the quality grades of surrounding rock within tunnels

Understanding the variation patterns of tunnel boring machine (TBM) operational parameters is crucial for assessing engineering geological conditions and quality grades of surrounding rock within tunnels. Studying the multifractal characteristics of the TBM operational parameters can help identify the patterns, but the relevant research has not yet been explored. This paper proposed a novel classification model for quality grades of surrounding rock in TBM tunnels based on multifractal analysis theory. Initially, the statistical characteristics of eight TBM cycle data with different grades of surrounding rock were explored. Subsequently, the method of calculating and analyzing the multifractal characteristic parameters of the TBM operational data was deduced and summarized. The research results showed that the TBM operational parameters of cutterhead torque, total thrust, advance rate, and cutterhead rotation speed have significant multifractal characteristics. Its multifractal dimension, midpoint slope of the generalized fractal spectrum, and singularity strength range can be used to evaluate the surrounding rock grades of the tunnel. Finally, a novel classification model for the tunnel surrounding rocks based on the multifractal characteristic parameters was proposed using the multiple linear regression method, and the model was verified through four TBM cycle data containing different surrounding rock grades. The results showed that the proposed multifractal-based classification model for tunnel surrounding rocks has high accuracy and applicability. This study not only achieves multifractal feature representation and surrounding rock classification for TBM operational parameters but also holds the potential for adaptive adjustment of TBM operational parameters and automated tunneling applications.

Numerical Simulation Study on the Deformation Patterns of Surrounding Rock in Deeply Buried Roadways under Seepage Action

To reveal the deformation patterns of the surrounding rock in deeply buried straight-wall arch-shaped roadways under seepage action, this study, based on an FLAC3D numerical simulation and classic elastoplastic theory, investigates the influences of surrounding rock classification, roadway burial depth, pore water pressure, and roadway cross-sectional dimensions on the deformation of surrounding rock. A multivariate regression prediction model for rock deformation was established based on the numerical simulation conclusions, and the correctness of the conclusions was verified through comparative analysis. Correlation analysis of various factors with rock deformation was conducted, ranking their impact as follows: pore water pressure > roadway burial depth > surrounding rock classification > roadway height > roadway width. The research results can provide guidance for the construction and support of deeply buried roadways under seepage action.

Prediction method of TBM tunnel surrounding rock classification based on LSTM-SVM

TBM tunnel surrounding rock classification is a key indicator for supporting decision-making and ensuring safe construction. And predicting the surrounding rock type accurately in advance is of great significance for TBM intelligent construction. This paper established the surrounding rock classification model based on support vector machine (LIBSVM), including preprocesses historical tunneling parameters, extracts data information that can accurately reflect the relationship between rock and machine, analyzes the correlation between different parameters and surrounding rock categories, and obtains highly relevant parameters. Based on the long short-term memory (LSTM), the prediction model of total thrust, cutter head torque, gripper pressure, cutter head rotate speed, and propulsion speed are established, which is the strongly correlated parameters with surrounding rock. Combining the parameter prediction model with the surrounding rock classification algorithm, the LSTM-SVM tunnel surrounding rock classification prediction model is established. The results showed that the coefficient of determination of the total thrust model, the cutter head torque, the gripper pressure, the cutter head speed, and the propulsion speed were 0.9825, 0.9396, 0.9974, 0.9843, and 0.9636. The overall prediction accuracy of the surrounding rock category can reach 86.0686%, which can provide a certain reference for predicting the surrounding rock condition in a short distance.

A method to construct a main hole structural plane model based on advanced parallel adit geological body

The advanced parallel adit of tunnel refers to the adit parallel to the direction of the main hole. Generally it is spaced tens of meters from the axis of the positive hole. During the tunnel construction, the parallel adit is driven before the main hole. Main function of it is to provide geological reference for the subsequent excavation of the main hole. At the same time, it can also help improve the long-term construction and operation and maintenance efficiency of the main tunnel. In terms of providing geological prediction information for the main tunnel, the surrounding rock information disclosed in the advanced parallel adit excavation is mainly used for surrounding rock classification and geological sketch, so as to qualitative analysis the possible geological conditions when the positive tunnel is excavated near the distance where the advanced parallel adit is located. However, the above methods cannot accurately and quantitatively analysis the geological conditions that the main tunnel will face. The lack of research on the correlation between the main tunnel and the advanced parallel adit geological conditions results in the waste of the key factor of the horizontal geological information.In this paper, the improved DBSCAN clustering algorithm is used to group the dominant structural planes according to the attitude of rock and other information. Some non-primary structural planes are screened out. The average distance between the same group of structural planes is calculated according to the average attitude of the dominant structural plane. The structural planes that are close enough are fused. Then, the axial and radial projection was carried out to form a larger range of surrounding rock fracture models. When the main tunnel is excavated to the relevant area, the situation of the surrounding rock in front can be predicted according to the model, so that the countermeasures can be made in advance. The method in this paper is applied to a tunnel project with bidirectional single line and advanced parallel adit. The prediction results after tunnel excavated show that the method in this paper is reasonable and effective.

TBM tunneling strata automatic identification and working conditions decision support

It has become an important research topic to ensure the safe and efficient tunnel boring machine (TBM) tunneling in the construction of long distance and deep buried tunnels. This study aims to construct an assistant decision support system that integrates surrounding rock classification identification and tunneling parameters prediction optimization, providing quantitative decision guidance for driving TBM for main drivers. For this purpose, this study takes a TBM diversion tunnel project in Xinjiang as the research background, collects 8633 m length TBM on-site tunneling data, and constructs a TBM tunneling data sample database; The DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm was improved using kernel density estimation to achieve TBM tunnel surrounding rock classification based on tunneling performance and automatic identification. Compared with the traditional DBSCAN model, the Sk parameter average decreased by 30.0%, and the Ku parameter average increased by 181.9%; Adopting the opposition-based learning strategy and β-chaotic sequence method improved the MOGWO (multi-objective grey wolf optimization) algorithm to achieve optimal decision-making of TBM tunneling parameters under 12 working conditions. Compared to the traditional MOGWO model, the Pareto optimality solved by the improved MOGWO model increasing the improvement efficiency of the original value and sample mean by 14.82% and 11.46%, respectively. The on-site application results indicate that the assistant decision support system proposed in this study can provide construction guidance for TBM main drivers under different working conditions, improving the tunneling efficiency and safety of TBM.

A Review of Deep Learning Applications in Tunneling and Underground Engineering in China

With the advent of the era of big data and information technology, deep learning (DL) has become a hot trend in the research field of artificial intelligence (AI). The use of deep learning methods for parameter inversion, disease identification, detection, surrounding rock classification, disaster prediction, and other tunnel engineering problems has also become a new trend in recent years, both domestically and internationally. This paper briefly introduces the development process of deep learning. By reviewing a number of published papers on the application of deep learning in tunnel engineering over the past 20 years, this paper discusses the intelligent application of deep learning algorithms in tunnel engineering, including collapse risk assessment, water inrush prediction, crack identification, structural stability evaluation, and seepage erosion in mountain tunnels, urban subway tunnels, and subsea tunnels. Finally, it explores the future challenges and development prospects of deep learning in tunnel engineering.

An intelligent method for TBM surrounding rock classification based on time series segmentation of rock-machine interaction data

Accurate, continuous real-time perception of surrounding rock conditions on the tunnel boring machine (TBM) tunnel face provides particularly important prior information to ensure safe, economic, and efficient tunneling. This study presents an intelligent method for assessing the TBM surrounding rock conditions using a combination of time series segmentation and a deep clustering model (SSAE-FCM). In data preprocessing, fifteen operational parameters were selected as input features. And an adaptive piecewise constant approximation method was employed for the segmentation and compression of stable phase data. Then, a total of 69,214 data samples that can characterize the stable rock-machine interaction were obtained to construct a dataset. Thereafter, the SSAE-FCM model was established and trained to classify the surrounding rock conditions into four clusters. The distribution result of the main operational parameters and composite indexes (TPI, FPI, and SE) within these clusters demonstrated that the classification results are compatible with rock-machine interaction in engineering practice. Additionally, the rock mass assessment performance of the classification results was compared to BQ classification in terms of various rock mass parameters (UCS, Jv), fault sections, and collapse sections. These results indicate that the proposed classification method accurately reflects the stability and boreability of rock mass and is more sensitive to unfavorable geology than the BQ classification. From the three clustering evaluation indexes (SC, CHI, and DBI) perspective, SSAE-FCM was superior to the other clustering models (BIRCH + k-means++, FCM, and SSAE + FCM). In conclusion, the proposed intelligent method for TBM surrounding rock classification is reasonable and applicable for the evaluation of rock mass quality, as well as accurate and sensitive in real-time perception.

Prediction of the geological indicators in TBM tunnel based on optimized proportion of surrounding rock grades

With tunnel boring machine being used in underground engineering, accurate geological indicators have been the important basis for tunnel boring machine (TBM) construction. Back propagation neural network (BPNN) has been used to predict the geological indicators of tunnels in previous studies. Nevertheless, these studies ignored the imbalance proportion of surrounding rock grades, leading to the indiscriminate use of data, thus affecting the predictive effect of BPNN. In order to prove the importance of the proportion of surrounding rock grade in geological prediction, we mainly attempt to utilize particle swarm optimization (PSO) to optimize the proportion of sample data, and integrate with BPNN to establish a PSO-BPNN theoretical model to predict geological indicators. At the same time, combined with the actual engineering data, 5 tunneling indicators were selected as input and 4 geological indicators were selected as output by a variety of dimensionality reduction methods. The geological indicators are density, uniaxial compressive strength, internal friction angle (φ) and Poisson's ratio (ε). On this basis, the PSO-BPNN prediction model was established in detail. By comparing the prediction of traditional BPNN, PSO-BPNN and other optimization-integrated models, the result shows that optimized proportion of surrounding rock grades reduces the prediction error and improves the interpretability of the prediction model. Meanwhile, we combined the theory of surrounding rock partition to illustrate the rationality of surrounding rock proportion in PSO result, that is, the proportion of complex surrounding rock should be increased appropriately to improve the prediction result. Ultimately, based on the optimization-integrated models with engineering data and the surrounding rock classification theory, the importance of proportion of surrounding rock grades for tunnel geological prediction is confirmed.

Influences of tunnelling parameters in tunnel boring machine on stress and displacement characteristics of surrounding rocks

During the operation of a tunnel boring machine (TBM), the stress and displacement of the surrounding rock are closely related to the tunnelling parameters, and the judicious selection of these parameters is crucial for improving TBM’s tunnelling efficiency and equipment utilisation. This study uses finite-element software to develop a three-dimensional mechanical model of a TBM cutterhead and the surrounding rock under the combined action of thrust and torque. It simulates the impact of TBM tunnelling construction on the tunnel’s surrounding rock excavation. Through numerical simulation, the relationship and influence of the TBM tunnelling parameters under various surrounding rock conditions are investigated, as well as the distribution characteristics and laws of the surrounding rock stress and displacement near the tunnel face under different thrust and torque conditions and the mechanical behaviour of the TBM cutterhead regarding the front overall surrounding rock. The results indicated that the influence of thrust change on the surrounding rock is significantly greater than that of torque change, which is minimal and can be ignored. The influence range of thrust and torque under class-A surrounding rock is within 1 m of the tunnel face, and under class-B surrounding rock is within 2 m of the tunnel face. The surrounding rock stress and displacement are closely related to the surrounding rock classification: the higher the quality and integrity of the surrounding rock, the lower the surrounding rock stress and displacement, thereby maximising the surrounding rock’s self-supporting ability.

Improved Surrounding Rock Classification Method for the Middle Rock Pillar of a Small Clear-Distance Tunnel

In tunnel design and construction, proper and accurate classification of rock surrounding tunnels is needed to ensure tunnel construction safety, guarantee construction quality, and reduce project costs. With rapid urbanization, numerous small clear-distance tunnels have been constructed in dense urban road networks. Compared with ordinarily separated tunnels, the construction scale and difficulty of small clear-distance tunnels are greater, and the requirements for the classification of rock surrounding tunnels are accordingly higher. A small clear-distance tunnel in an urban super large and complex underground interchange hub of the Xiamen Haicang Evacuation Channel was selected as the background, and the classification method of the middle rock pillar in a small clear-distance tunnel is presented based on the general classification standard of surrounding rocks. Based on the geometric, physical, and mechanical factors of the middle rock pillar, six indices affecting the stability and quality of the middle rock pillar were selected, and the classification index system of the middle rock pillar was established from the two dimensions of the basic and auxiliary indices. The basic and auxiliary indices were scored using the scoring method, and the different grades of the middle rock pillar were divided according to different scores. The middle rock pillar classification standard was applied to the quality assessment of the middle rock pillar, which provided a basis for the on-site assessment of the quality of the middle rock pillar and proved the accuracy and superiority of the improved classification standard. The newly established classification standard can provide a reference for selecting the correct construction method and supporting structure type for small clear-distance tunnels.

Application of a Combined FEM/DEM Approach for Teaching a Deep Rock Mass Mechanics Course

Deep rock mass mechanics is a professional course which is offered to undergraduate and postgraduate students in some mining universities. This course mainly includes the following topics: the geological structure of deep rock mass, the mechanical properties of deep rocks, the strength theory of deep rock masses, stability analysis and control of deep surrounding rock classification of engineering rock masses, and the application of deep rock mechanics in underground mining engineering The purpose of this course is to present students with a basic theoretical knowledge of deep rock mass engineering. Analyzing the limitations of traditional deep rock mass mechanics teaching methods, here, we propose integrating a combined FEM/DEM (Finite Element Method/Discrete Element Method) approach into the teaching of a course on deep rock mass mechanics. The mechanical behaviors and failure instability process of rock at laboratory and engineering scales were analyzed using ELFEN software (a finite/discrete element code). The results show that a combined FEM/DEM approach as a deep rock mass mechanics teaching method is completely feasible and reasonable; this approach has the advantages of strong intuition, high reliability, time and labor savings, and low cost, which can offset the shortcomings of traditional teaching methods. Moreover, the proposed approach can stimulate students’ interests in a mining course on deep rock mass mechanics, deepen students’ understanding of the course curriculum, and cultivate students’ innovative abilities and subjective initiatives.

A real-time intelligent classification model using machine learning for tunnel surrounding rock and its application

ABSTRACT Real-time and accurate prediction of surrounding rock grade is crucial for tunnel dynamic construction and design. However, the internationally accepted semi-quantitative methods (e.g. rock mass rating (RMR), Q, and basic quality (BQ)) cannot provide fast and accurate classification in construction. This study proposed an intelligent surrounding rock classification method and a tunnel information management system, which can predict the surrounding rock grade in real-time and accurately. A database is collected with 286 cases in China, including seven geological parameters and surrounding rock grades. Based on different training parameters, 12 classification models are established using VGGNet, ResNet, and support vector machine (SVM) algorithms. The accuracy of the SVM classifier is 93.02%, which performs better than the VGGNet and ResNet classifiers. Moreover, precision, recall, F-measure, receiver operating characteristic (ROC), and 20-case verification show that the SVM classification model has greater robustness in learning and generalising for small and imbalanced samples. Additionally, a tunnel information management system is developed with cloud technology, which can accurately predict the surrounding rock grade within 10 s. Overall, the achievements of this study can provide valuable references for real-time rock mass classification in traffic tunnels and underground powerhouses.

Forward prediction for tunnel geology and classification of surrounding rock based on seismic wave velocity layered tomography

Excavation under complex geological conditions requires effective and accurate geological forward-prospecting to detect the unfavorable geological structure and estimate the classification of surrounding rock in front of the tunnel face. In this work, a forward-prediction method for tunnel geology and classification of surrounding rock is developed based on seismic wave velocity layered tomography. In particular, for the problem of strong multi-solution of wave velocity inversion caused by few ray paths in the narrow space of the tunnel, a layered inversion based on regularization is proposed. By reducing the inversion area of each iteration step and applying straight-line interface assumption, the convergence and accuracy of wave velocity inversion are effectively improved. Furthermore, a surrounding rock classification network based on autoencoder is constructed. The mapping relationship between wave velocity and classification of surrounding rock is established with density, Poisson's ratio and elastic modulus as links. Two numerical examples with geological conditions similar to that in the field tunnel and a field case study in an urban subway tunnel verify the potential of the proposed method for practical application.

TBM Tunnel Surrounding Rock Classification Method and Real-Time Identification Model Based on Tunneling Performance

TBM Tunnel Surrounding Rock Classification Method and Real-Time Identification Model Based on Tunneling Performance

Intelligent Classification of Surrounding Rock of Tunnel Based on 10 Machine Learning Algorithms

The quality evaluation of the surrounding rock is the cornerstone of tunnel design and construction. Previous studies have confirmed the existence of a relationship between drilling parameters and the quality of surrounding rock. The application of drilling parameters to the intelligent classification of surrounding rock has the natural advantages of automatic information collection, real-time analysis, and no extra work. In this work, we attempt to establish the intelligent surrounding rock classification model and software system driven by drilling parameters. We collected 912 samples containing four drilling parameters (penetration velocity, hammer pressure, rotation pressure, and feed pressure) and three surrounding rock (grade-III, grade-IV, and grade-V). Based on the python machine learning toolkit (Scikit-learn), 10 types of supervised machine learning algorithms were used to train the intelligent surrounding rock classification model with the model parameter selection technology of grid search cross validation. The results show that the average accuracy is 0.82, which proves the feasibility of this method. Finally, the tunnel surrounding rock intelligent classification system was established based on three models with better comprehensive performance among them. The classification accuracy of the system was 0.87 in the tunnel test section, which indicates that the system has good generalization performance and practical value.

Intelligent rating method of tunnel surrounding rock based on one-dimensional convolutional neural network

Accurate prediction of surrounding rock grades holds great significance to tunnel construction. This paper proposed an intelligent classification method for surrounding rock based on one-dimensional convolutional neural networks (1D CNNs). Six indicators collected in some tunnel construction sites are considered, and the degree of linear correlation between these indicators has been analyzed. The improved one-hot encoding method is put forward for transforming these non-image indicators into one-dimensional structural data and avoiding the sampling error in the indicators of surrounding rock collected in the field. We found that the 1D CNNs model based on the improved one-hot encoding method can best extract the features of surrounding rock classification indicators (in terms of both accuracy and efficiency). We applied the well-trained classification model of tunnel surrounding rock to a series of expressway tunnels in China, and the results show that our model could accurately predict the surrounding rock grade and has great application value in the construction of tunnel engineering. It provides a new research idea for the prediction of surrounding rock grades in tunnel engineering.

Q-method optimization of tunnel surrounding rock classification by fuzzy reasoning model and support vector machine

Q-method optimization of tunnel surrounding rock classification by fuzzy reasoning model and support vector machine

Effect of voids on the seismic vulnerability of mountain tunnels

Void defects directly affect the dynamic response of tunnels. These defects have been recognised as an important factor that exacerbates seismic damage and the destruction of tunnel linings. Existing studies that consider the tunnel-void dynamic interaction use deterministic analysis methods, but they lack a quantitative analysis based on a probability method, which can reflect the random nature of earthquakes and structures. In the present work, a series of 2D nonlinear dynamic analyses of tunnel seismic response that consider the tunnel-void interaction is carried out by using the incremental dynamic analysis method. The automatic extraction of the resulting data and the calculation of the maximum damage index (DImax) during the seismic response process are performed by a Python program. The fragility curves of the tunnels are obtained with consideration of void defects. The effects of void type, void location, void size, surrounding rock classification and seismic direction on the vulnerability of the tunnels are investigated. Results show that void size and type and surrounding rock condition exert considerable effects on the seismic vulnerability of tunnels. The presence of voids behind linings leads to increased tunnel vulnerability, which presents a nonlinear increase with the increment of void size. The degree of influence of void size on vulnerability varies with void location. Tunnels with voids between surrounding rocks and the primary support are more vulnerable than those with voids between the primary support and the secondary lining. Hence, void type cannot be ignored. The effects of voids on vulnerability become evident when tunnels are embedded in weak surrounding rocks. The vulnerability under the horizontal seismic direction is apparently greater than that under the vertical direction at the same seismic intensity. However, the sensitivities of vulnerability to seismic directions vary with different void locations.

Developing the network social media in graphic design based on artificial neural network

The purposes are to effectively solve the graphic design problems, develop an easy-to-use supporting design program, and make graphic design more reliable and accurate. Based on the analysis of the current graphic design framework, graphic design data are obtained from the network social media. A system of surrounding rock classification and support optimization design is developed by a deep neural network structure. The model’s effectiveness is verified by more than 3000 road conditions data. The results show that the three-layer network’s errors are 0.0062 with a training time of 12,455, and the five-layer network’s errors are 0.00019 with a training time of 69,895. With the input layer, hidden layer, and the output layer of 8, 15, and 5 respectively, the model performs best. In the deep learning algorithm, the deep backpropagation neural network (Deep BPNN) can obtain the best training effects with less training time. Therefore, the roadway drawing system’s application based on the deep learning algorithm to the roadway support design can improve design efficiency and scientificity.

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.