Construction Of Underground Tunnels Research Articles

Exploring the impacts of liquid accelerators on sulfate resistance and calcium leaching behavior of wet-mixed shotcrete

The performance of shotcrete used in underground tunnel construction is often compromised by the challenging service environment, causing severe deterioration and structural integrity concerns. Developing high-quality accelerating agents can be a viable approach to mitigate this effect. This study formulates alkali-free fluorine-free (AF-I); alkali-free fluorine-containing (AF-II); and low-alkaline (AC) liquid accelerators and explores their impacts on sulfate resistance and calcium leaching behavior of shotcrete, utilizing semi-immersion and short-term tank water testing protocols on a time-resolved basis. Microstructural analysis of eroded shotcrete was conducted employing XRD, TGA and SEM to reveal underlying mechanisms. Additionally, ionic analyses of simulated leaching systems, including groundwater and 5 % sodium sulfate solution were performed using ICP-OES to monitor calcium activity and assess leaching behaviors. Results indicate that shotcrete accelerated with AF-II exhibits the strongest resistance, whereas shotcrete with AC suffers the severest deterioration. The primary deterioration mechanism of shotcrete with AC was majorly due to high ettringite and gypsum corrosion, whereas AF-I and AF-II induces little ettringite corrosion. In terms of leaching behavior, AF-II demonstrates superior calcium leaching mitigation, with leachability indices in groundwater and sodium sulfate solution measuring 0.06 and 0.19, and 0.02 and 0.16 higher values, respectively, compared to AF-I and AC. Findings of this study provide valuable insights into the application and performance of shotcrete in sulfate-prone environments, aiming to mitigate potential deterioration through optimal accelerator selection.

Environmental simulation and refrigeration demand analysis for shield tunnel construction in hot summer and cold winter regions

The thermal hazards generated during the tunnel boring machine construction process significantly impact the physical and mental health of personnel. A field test was conducted on the tunnel of Metro Line 1 in Changsha, China, where the average temperature in the work zone reached up to 33.16 °C, and the air velocity was generally below 0.2 m/s. These conditions were unfavorable for ventilation and heat dissipation. In this paper, a full-scale CFD simulation model was established to simulate the construction environment and analyze the cooling demand. The results indicated that increasing the fresh air velocity could lower the temperature in the work zone; however, this effect was limited. When the fresh air temperature exceeded a certain threshold, it actually raised the average temperature of the work zone. Consequently, there is a need for supplementary cooling of the fresh air during the hot summer months. At a fresh air velocity of 15 m/s, the maximum temperature in the work zone was recorded at 27.8 °C when the fresh air was cooled down to 22.5 °C through auxiliary cooling measures. This approach effectively controlled the temperature in the work zone, reduced flow dead zones, and significantly improved air distribution and heat dissipation. Additionally, it ensured the physical and mental well-being of the construction workers and the safe operation of the equipment. This study provides valuable guidance for managing thermal environments in underground tunnel construction.

Inhibitory effect of calcium carbonate precipitation induced by Triton X-100 and microorganisms on coal dust

During underground tunnel construction, dust endangers the safety and health of workers. Microbially induced calcium carbonate precipitation (MICP) represents a novel green dust suppression technology for addressing coal dust pollution, capable of effectively mitigating coal dust pollution. Nevertheless, the concentration of urease will exert a certain influence on the performance of MICP to some extent. Therefore, how to improve the efficiency of urease activity on coal dust suppression is a popular research topic. In this study, based on MICP technology, the properties of microbial dust suppression materials were investigated through contact angle, surface tension, and unconfined compressive strength (UCS) tests in combination with molecular dynamics simulations, scanning electron microscopy, and X-ray diffraction using Bacillus megaterium and the nonionic surfactant Triton X-100. The results demonstrate that when the concentration of the bacterial solution is 20 % and the concentrations of urea and calcium chloride are 0.7 mol·L–1, the addition of 1 % Triton X-100 can increase the yield of calcium carbonate to 21.83 %, enhance the structural density of the gel, and increase the UCS by 15.63 %. The calcite and quartz formed on the coal dust surface improved its wettability with a contact angle of only 22°, showing an excellent dust-suppression effect. These research findings serve as a reference for enhancing the MICP dust suppression efficacy and have significant implications for the development and application of microbial dust-suppression agents. This dust suppression method has potential applications in quarries and underground environments.

Stability Evaluation of Lanedada Twin Tunnel in KTFT

The construction of underground tunnels, particularly in roadway systems, is a highly complicated and demanding process, necessitating careful consideration of geological variability, environmental impact, and safety concerns. This thesis emphasizes the critical importance of determining the optimal separation between twin tunnels, balancing the need for environmental conservation, economic efficiency, and structural stability. The study particularly focuses on the Kathmandu Terai/Madhesh Fasttrack (KTFT), a major expressway project in Nepal, which includes twin tunnels at three different sites under varying geological conditions. A detailed case study is conducted on the Lanedada Twin Tunnel, spanning 1.430 kilometers through the Siwalik Hill. Various methodologies, including empirical, analytical, and numerical approaches, are employed to assess tunnel stability. The findings reveal discrepancies in predictions of tunnel squeezing, with Singh et al.'s method indicating no squeezing potential, while Goel et al.'s method identifies squeezing in half of the evaluated sections. Additionally, the approaches by Hoek and Marino (2000) and Shrestha and Panthi (2015) are applied to estimate tunnel deformation at six specific locations. An analysis of rock support systems using the Rock Massm Rating (RMR) classification and the Q system is presented. Special attention is given to the section at 34+160, where the RS2 software is utilized to simulate varying pillar widths between the twin tunnels, allowing for a comparative analysis of different scenarios. This research aims to contribute to the understanding and implementation of safer, more feasible twin tunnel constructions, thereby enhancing the effectiveness of large-scale infrastructure projects.

Three-Dimensional ERT Advanced Detection Method with Source-Position Electrode Excitation for Tunnel-Boring Machines

Tunnel-boring machines (TBMs) are widely used in urban underground tunnel construction due to their fast and efficient features. However, shield-tunnel construction faces increasingly complex geological environments and may encounter geological hazards such as faults, fracture zones, water surges, and collapses, which can cause significant property damage and casualties. Existing geophysical methods are subject to many limitations in the shield-tunnel environment, where the detection space is extremely small, and a variety of advanced detection methods are unable to meet the required detection requirements. Therefore, it is crucial to accurately detect the geological conditions in front of the tunnel face in real time during the tunnel boring process of TBM tunnels. In this paper, a 3D-ERT advanced detection method using source-position electrode excitation is proposed. First, a source-position electrode array integrated into the TBM cutterhead is designed for the shield-tunnel construction environment, which provides data security for the inverse imaging of the anomalous bodies. Secondly, a 3D finite element tunnel model containing high- and low-resistance anomalous bodies is established, and the GREIT reconstruction algorithm is utilized to reconstruct 3D images of the anomalous body in front of the tunnel face. Finally, a physical simulation experiment platform is built, and the effectiveness of the method is verified by laboratory physical modeling experiments with two different anomalous bodies. The results show that the position and shape of the anomalous body in front of the tunnel face can be well reconstructed, and the method provides a new idea for the continuous detection of shield construction tunnels with boring.

Data-driven intelligent prediction of TBM surrounding rock and personalized evaluation of disaster-inducing factors

With the widespread application of tunnel boring machines (TBM) in underground tunnel construction, the accurate and real-time identification of geological indicators has become a key factor for ensuring construction safety. In this study, we introduced the nomogram method into the field of civil engineering for the first time to predict surrounding rock grades. Against the backdrop of a major water conservancy project in China, an in-depth analysis of construction data from the ascending phase was conducted to establish the relationship between surrounding rock grade predictions and key construction parameters. Compared with traditional models, the nomogram method has shown advantages in terms of prediction accuracy. Furthermore, by providing a personalized scoring mechanism for specific construction data, the nomogram method not only achieves the real-time prediction of rock grades but also clearly reveals the dynamic relationships between input parameters and rock grades, clarifying the entire prediction process. We identified the main factors related to rock grade prediction among TBM construction parameters, including the slurry conveyor belt speed, jacking pressure, cutterhead torque, cutterhead thrust, thrust pressure, and actual rotation speed. The training process revealed that the nomogram prediction model achieved optimal performance with seven input parameters, balancing accuracy and training time. According to the prediction results, the nomogram model’s area under the curve index is 0.92, providing greater accuracy than the traditional random forest model (0.89). Therefore, this study enhances the transparency and interpretability of model predictions by providing personalized assessments of construction parameters for predicting surrounding rock grades, overcoming the black-box issue of existing prediction methods and offering a novel and effective tool for rock grade prediction.

Underground Radio Communications and Radio Observation

The problems of underground radio communications and radio observation are considered. The need for radio communication with people working underground is especially obvious during underground accidents. Radio observation makes it possible to monitor underground channels to detect their changes, caused, for example, by underground tunnel construction work in the border zone. Solving these problems is complicated by the sharp weakening of the signal in the ground and the presence of an interfering parallel signal propagating above the ground. Options for antennas to solve the described problems and methods for dealing with interfering signals are proposed. Receiving and transmitting centers for placing antennas are described.

Geological detection of hard rocks by GPR and signal time-frequency characteristics analysis in urban underground trenchless construction

Abstract The hard rocks in the stratum can pose safety risks and hinder the progress of urban underground tunnel construction using shield and jacking methods, thereby reducing construction efficiency and increasing construction costs. This paper utilizes wavelet scale energy spectrum, wavelet packet theory and statistical methods to conduct research on the detection of special geological formations such as hard rocks and voids, as well as the analysis of their signal time-frequency characteristics based on the ground-penetrating radar (GPR) technique. On the basis of calibrating the permittivity of different types of rock blocks, we established a forward model for detecting hard rocks and voids, and the simulated signals were analyzed in the time and frequency domains. Subsequently, laboratory experiments were conducted to perform GPR tests on different types of hard rocks in natural and water-saturated states and voids, to explore the time-frequency characteristics, frequency band energy variations, and statistical patterns of typical single-trace signals. The results show that the granite detection signal contains more low-frequency components, the sandstone detection signal contains more medium-low frequency components, while the limestone detection signal contains more medium-high frequency components in their natural state; the signal from the karst cave has relatively more low-frequency components than the signal from the empty cavity. The geometric shape of the rock has no influence on the dominant frequency and time-frequency distribution of its reflection signal. Generally, rocks with higher rebound values (hardness) also exhibit larger variance and standard deviation in frequency band energy. The research has important theoretical significance and practical value for the measurement and assessment of special geological features such as hard rocks and voids in urban underground trenchless construction.

Risk analysis in underground tunnel construction with tunnel boring machines using the Best–Worst method and data envelopment analysis

BackgroundThe use of tunnel boring machines is continuously increasing; however, this activity faces many risks, resulting in negative events. MethodsA novel approach using the best–worst method and a data envelopment analysis model was proposed to analyze the risks of underground tunnel construction with tunnel boring machines. The proposed approach was validated using a realistic case study of metro construction in Thailand. ResultsThe proposed approach efficiently analyzed the risks and produced more solid findings. The most critical and least affected risks can be identified according to risk scores in descending order. ImplicationThis study contributes a new method of risk analysis that benefits project managers and stakeholders who design risk management plans to reduce the occurrence and mitigate the severity of metro works. OriginalityThe new risk analysis can obtain the best compromise ranking of risks based on decision-makers’ preferences, probabilities, and various consequences under different circumstances.

Vote-Based Feature Selection Method for Stratigraphic Recognition in Tunnelling Process of Shield Machine

Shield machines are currently the main tool for underground tunnel construction. Due to the complexity and variability of the underground construction environment, it is necessary to accurately identify the ground in real-time during the tunnel construction process to match and adjust the tunnel parameters according to the geological conditions to ensure construction safety. Compared with the traditional method of stratum identification based on staged drilling sampling, the real-time stratum identification method based on construction data has the advantages of low cost and high precision. Due to the huge amount of sensor data of the ultra-large diameter mud-water balance shield machine, in order to balance the identification time and recognition accuracy of the formation, it is necessary to screen the multivariate data features collected by hundreds of sensors. In response to this problem, this paper proposes a voting-based feature extraction method (VFS), which integrates multiple feature extraction algorithms FSM, and the frequency of each feature in all feature extraction algorithms is the basis for voting. At the same time, in order to verify the wide applicability of the method, several commonly used classification models are used to train and test the obtained effective feature data, and the model accuracy and recognition time are used as evaluation indicators, and the classification with the best combination with VFS is obtained. The experimental results of shield machine data of 6 different geological structures show that the average accuracy of 13 features obtained by VFS combined with different classification algorithms is 91%; among them, the random forest model takes less time and has the highest recognition accuracy, reaching 93%, showing best compatibility with VFS. Therefore, the VFS algorithm proposed in this paper has high reliability and wide applicability for stratum identification in the process of tunnel construction, and can be matched with a variety of classifier algorithms. By combining 13 features selected from shield machine data features with random forest, the identification of the construction stratum environment of shield tunnels can be well realized, and further theoretical guidance for underground engineering construction can be provided.

Field monitoring of vibration characteristics during advanced ductule installation in sandy cobble stratum

The sandy cobble stratum presents a high risk for underground tunnel construction due to its low cohesive properties and susceptibility to loosening and falling. The use of Advanced ductule for grouting reinforcement inevitably results in vibrations, and understanding how these vibrations propagate is crucial in selecting tunnel engineering support schemes and responding to accident risks. Based on a bored tunnel under construction in Xi’an, field vibration propagation characteristics testing were carried out for advanced ductile installation. The time-history response and frequency distribution characteristics of the vibration velocity within the tunnel face under sandy cobble stratum conditions were studied, and the law of vibration propagation attenuation within the tunnel face range was obtained. The results showed that: 1) During the conduit drilling process, the tunnel face mainly experienced vertical vibrations, with the horizontal velocity amplitude accounting for only 15%–20% of the vertical velocity amplitude. At a distance of 1.0 m from the conduit, the vertical velocity amplitude reaches 10.602 mm/s, and the vibration energy concentrates mainly in the frequency range of 150–250 Hz. At a distance of 1.5 m from the conduit, the bidirectional vibration velocity significantly attenuates; 2) The vibration characteristics within the tunnel face can be classified into three primary areas: “Loose and Falling” area, “Significant Vibration” area, and “Vibration Attenuation” area. Loose, falling and significant vibrations occurred mainly within a range of about 1.25 m around the conduit. 3) As the diameter of the conduit decreases, the amplitude of vertical vibration velocity decreases by about 20%. By reducing the design diameter of the advanced ductule in a reasonable manner, it is possible to effectively mitigate the impact of vibration caused by the sandy cobble stratum during installation. This can yield a positive impact, curtailing the occurrence of the tunnel’s collapse phenomenon and ensuring its stability.

RELIABILITY OF RMR CLASSIFICATION DURING THE CONSTRUCTION OF ZENICA TUNNEL

Construction of underground tunnels in the rock mass is a very complex task from the aspect of stability of the rock mass in the secondary state of stress and defining the method of support. The method of excavation and the construction of the primary support are adapted to the state of the rock mass, which is why an adequate analysis of the rock mass as a work environment is of great importance. In order to define as precisely as possible, the quality of the rock mass as a work environment, classifications of the rock mass have been developed in recent times. The classifications are based on which the condition is assessed and its characteristics important for design are defined. In tunnel construction in Bosnia and Herzegovina, the RMR classification is most often used, the reliability of which varies depending on the characteristics of the rock mass in which the room is made. The paper analyzed the reliability of the RMR classification for the construction of the "Zenica" road tunnel, which was built in complex geotechnical conditions. Key words: rock mass, uniaxial compressive strength, reliability, RMR classification

Compressive stress–strain behaviour of masonry prisms made of low elastic modulus burnt clay bricks

Masonry, being a quasi-brittle material, displays mechanical properties and manifests non-linear behaviour, which is influenced by the specific attributes of its constituent units and mortar. The compressive stress–strain behaviour of masonry is a vital factor in the realistic analysis of masonry structures when subjected to ground deformations arising from construction activities such as excavation, underground tunnel construction, utility installations, and for evaluating their seismic vulnerability. In India, the commonly used masonry unit is burnt clay bricks, which are highly localized due to changes in the constituent material and manufacturing process. This leads to variations in the strength and stiffness of brick units from region to region. An experimental investigation was conducted using twenty-four brick specimens, seventy-two mortar cube specimens and forty-eight four-unit single-wythe masonry prism specimens, subjected to displacement-controlled uniaxial compressive load. The specimen displacements of brick units and masonry prisms were obtained using Digital Image Correlation analysis. The stiffness of the brick units was significantly lower than those reported in studies conducted in India or elsewhere. Statistical analysis has been performed, and relations between the respective compressive strength and elastic modulus of brick units, mortar and masonry prism specimens have been obtained. An equation has been proposed to estimate masonry prisms’ elastic modulus from its components. An analytical model has been proposed for predicting the compressive stress–strain curve of masonry prisms, incorporating the elastic modulus of masonry prisms, which can be predicted using the expression proposed in this study. This is a fundamental improvement over the expressions available in the literature.

A novel framework for combining polarimetric Sentinel-1 InSAR time series in subsidence monitoring - A case study of Sydney

The rapid growth of the city of Sydney, Australia over the last decades, has led to significant development of residential and transportation infrastructure. Land subsidence associated with the urban development can lead to serious issues which should be thoroughly understood and carefully managed. To address this challenge, an enhanced polarisation time-series InSAR (Pol-TS-InSAR) processing framework was developed, using the dual polarisation (DP) Sentinel-1 data to integrate information from different polarimetric channels with different weighting during the TS-InSAR deformation analysis. Ninety DP Sentinel-1 images acquired between 2019 and 2022 are analysed using Pol-TS-InSAR to map the land subsidence in Sydney, with the assistance of the GPS measurements. Improvement of measurement points density from Pol-TS-InSAR is observed compared to the single polarimetric TS-InSAR counterpart for all land use types (ranging between 68% and 208%). The comparison between the Pol-TS-InSAR measurements and GPS measurements shows an absolute mean difference and RMS difference of 0.75 mm/yr and 0.95 mm/yr, respectively, in vertical direction. The results of the ground subsidence analysis revealed that the main subsidence factors in Sydney are related to groundwater extraction, mining activities, underground tunnel construction and landfill. The latter two factors were less well-known prior to this study. In additional to these factors, land subsidence related to high-rise building construction has also been observed, even though the impact seems to be less significant than other factors.

Numerical investigation of geostress influence on the grouting reinforcement effectiveness of tunnel surrounding rock mass in fault fracture zones

Grouting is a widely used approach to reinforce broken surrounding rock mass during the construction of underground tunnels in fault fracture zones, and its reinforcement effectiveness is highly affected by geostress. In this study, a numerical manifold method (NMM) based simulator has been developed to examine the impact of geostress conditions on grouting reinforcement during tunnel excavation. To develop this simulator, a detection technique for identifying slurry migration channels and an improved fluid-solid coupling (F–S) framework, which considers the influence of fracture properties and geostress states, is developed and incorporated into a zero-thickness cohesive element (ZE) based NMM (Co-NMM) for simulating tunnel excavation. Additionally, to simulate coagulation of injected slurry, a bonding repair algorithm is further proposed based on the ZE model. To verify the accuracy of the proposed simulator, a series of simulations about slurry migration in single fractures and fracture networks are numerically reproduced, and the results align well with analytical and laboratory test results. Furthermore, these numerical results show that neglecting the influence of geostress condition can lead to a serious overestimation of slurry migration range and reinforcement effectiveness. After validations, a series of simulations about tunnel grouting reinforcement and tunnel excavation in fault fracture zones with varying fracture densities under different geostress conditions are conducted. Based on these simulations, the influence of geostress conditions and the optimization of grouting schemes are discussed.

Hybrid Random Forest-Based Models for Earth Pressure Balance Tunneling-Induced Ground Settlement Prediction

Construction-induced ground settlement is a serious hazard in underground tunnel construction. Accurate ground settlement prediction has great significance in ensuring the surface building’s stability and human safety. To that end, 148 sets of data were collected from the Singapore Circle Line rail traffic project containing seven defining parameters to create a database for predicting ground settlement. These parameters are the tunnel depth (H), the tunnel advance rate (AR), the EPB earth pressure (EP), the mean SPTN value from the soil crown to the surface (Sm), the mean water content of the soil layer (MC), the mean modulus of elasticity of the soil layer (E), and the grout pressure used for injecting grout into the tail void (GP). Three hybrid models consisting of random forest (RF) and three types of meta-heuristics, Ant Lion Optimizier (ALO), Multi-Verse Optimizer (MVO), and Grasshopper Optimization Algorithm (GOA), were developed to predict ground settlement. Furthermore, the mean absolute error (MAE), the mean absolute percentage error (MAPE), the coefficient of determination (R2) and the root mean square error (RMSE) were used to assess predictive performance of the constructed models for predicting ground settlement. The evaluation results demonstrated that the GOA-RF with a population size of 10 has achieved the most outstanding predictive capability with the indices of MAE (Training set: 2.8224; Test set: 2.3507), MAPE (Training set: 40.5629; Test set: 38.5637), R2 (Training set: 0.9487; Test set: 0.9282), and RMSE (Training set: 4.93; Test set: 3.1576). Finally, the sensitivity analysis results indicated that MC, AR, Sm, and GP have a significant impact on ground settlement prediction based on the GOA-RF model.

A coupled deep learning approach for shield moving performance prediction of underground tunnel construction

Recently, deep learning methods have attracted great attentions for geotechnical engineering, especially for the safety construction of underground tunnels. In this regard, the control and regulation of operational parameters are vital for safety and intelligent tunnel construction. In this study, hybrid data-driven models on the basic of optimization approaches [particle swarm optimization (PSO), multilayer hierarchical heterogeneous PSO] and deep learning methods (long short-term memory and gated recurrent unit neural network) were developed. The optimization approaches were utilized to obtain the optimal parameters of deep learning methods. Apart from that, geological data sets were extended to match the scale of operational data sets using Kriging method, which considered the effects of local geology comprehensively. The developed hybrid models (DHMs) were utilized to estimate the speed of earth pressure balance (EPB) shield machine for a tunnel project in China. Results indicate that errors in estimated results by DHMs are acceptable in geotechnical engineering. Besides, the DHMs exist potentials to cope with time-series data sets from underground tunnel project. After that, Pearson correlation coefficient was used to evaluate the relative importance of influential factors on target variable. Results show that penetration has significant correlation relationship with excavation speed. The geological and operational parameters are equally important for the prediction performance of DHMs. The developed DHMs can provide a reference for regulating shield moving performance and attaining safety construction of underground tunnels.

New type of sawdust-based dust suppressant during tunnelling and underground space: Preparation, characterization and engineering application

In the process of underground tunnel construction, dust is the main killer endangering the safety and health of workers. New polymer dust suppressant materials have been proved to be an effective means to reduce dust concentration in restricted space. This study, based on the principle of waste utilization, is aimed at revealing a new degradable super absorbent dust suppressant (AA-SW-AMPS/ND), which is prepared by means of microwave-assisted chemical crosslinking with sawdust of China fir as the raw material. The micro morphology, reaction mechanism, water absorption and retention of AA-SW-AMPS/ND are studied through SEM, FTIR and swelling kinetic experiments. The product performance test shows that the dust suppression rate of AA-SW-AMPS/ND exceeds 95 %. The swelling rate in distilled water is more than 400 times, and the swelling rate in 1 % salt solution is maintained at about 100. After spraying AA-SW-AMPS/ND, the sample is in natural environment for 168 h, and the mass loss is less than 10 g; The synergy combustion performance time with coal sample is prolonged by about 50 s. By combining the new dust suppressant and its automatic adding device with the spray device, remarkable results have been achieved in the dust control of the fully mechanized face in the North seventh mining area of Tianchen coal mine. The average dust reduction rates of total dust and respirable dust have reached 90.07 % and 85.43 % respectively. The dust suppression and wetting mechanisms of AA-SW-AMPS/ND are explained by MS simulation, and the simulation results are consistent with the above experimental ones. This dust suppression method can potentially be applied in power plants, quarries, and other underground space environments.

Intelligent prediction of rockburst in tunnels based on back propagation neural network integrated beetle antennae search algorithm.

Rockburst is one of the major engineering geological disasters of underground engineering. Accurate rockburst intensity level prediction is vital for disaster control during underground tunnel construction. In this work, a hybrid model integrating the back propagation neural network (BPNN) with beetle antennae search algorithm (BAS) has been developed for rockburst prediction. Before model building, 173 groups of rockburst dataset were collected. Six geological parameters are selected as predictors for rockburst, including the maximum tangential stress of the surrounding rock σθ, the uniaxial compressive strength of rock σc, the tensile strength of rock σt, the stress ratio σθ/σc, the rock brittleness ratio σc/σt, and the elastic energy index Wet. After preprocessed by outlier detection and synthetic minority oversampling technique (SMOTE), the new dataset was divided into training and test parts. BAS could optimize the weights and biases of BPNN from the training process. Then the established hybrid model was applied to the test samples with predicted accuracy of 94.3%, proving that the hybrid model has practical value in researching rockburst prediction.

Probabilistic Stability Analysis of Deep Rock Tunnel Excavated by Mechanized Tunneling Considering Anisotropic Initial Stresses

Due to the complex geological conditions, the construction of underground tunnels in the rocks exhibiting creep behaviors is a great challenge and the structures’ long-term stability is of main importance. The excavation by tunnel boring machines (TBM) of a tunnel that is supported by a double flexible/concrete liner is considered a potential technical solution. However, the efficiency of such a support system on the stability at long-term of a tunnel must be verified in the real condition by considering both the effects of uncertainties of the time-dependent rock behavior and anisotropy of initial stress state. In this paper, the subset simulation and the Sobol global sensitivity analysis are chosen to estimate the failure probability of the tunnel supports and quantify the importance of different random parameters, respectively. The results reveal that considering the anisotropy of initial stresses increases the failure probability, especially in the concrete support elements. In addition, the parameters of initial stresses are the ones of main importance for both liners according to the Sobol indices. Therefore, the anisotropy of initial stresses and the related uncertainties should be considered for reliable tunnel designs.