Rockburst Phenomena Research Articles

Investigation and application of data balancing and combined discriminant model in rock burst severity prediction

In the development of intelligent rock burst prediction models, issues such as incomplete data coverage and data imbalance are frequently encountered. These issues may lead to risks of overfitting in predictive models, poor generalization capabilities, and increased bias, which in turn may result in misjudgments and unpredictable losses. To accurately predict rock burst disasters and mitigate or eliminate related threats, this paper proposes a composite prediction model that integrates Density-Based Nonlinear Resampling (DBNR)-Tomek Link data balancing algorithms with Bayesian Optimization (BO)-Multilayer Perceptron (MLP)-Random Forest (RF). Initially, this study collected and organized a total of 301 recorded rock burst disaster field observation data, covering various tectonic plates, engineering types, rock origins, rock textures, and rock burst types. Subsequently, from a data analysis perspective, we employed the PCA-SSA-K-means unsupervised clustering algorithm to delve into the underlying information contained within the data, thereby validating the rationality of categorizing rock bursts into four grades. Then, using the L2 norm to optimize the dimensionality of the indicators and supplementing with indicator importance ranking and hypothesis testing, we selected the maximum tangential stress of the surrounding rock, the ratio of the maximum tangential stress of the surrounding rock to the uniaxial compressive strength of the rock (stress coefficient), and the elastic energy index as the criteria for rock burst intensity grading. Following that, the DBNR-Tomek Link sampling method was applied to balance the sample data, optimizing the data sample ratio and ultimately expanding the sample size to 396, improving the proportion of data samples from 2:3:4:1 to 1:1:2:1, thereby enhancing the model’s generalization performance. Ultimately, a BO-MLP-RF composite prediction model was constructed based on Bayesian Optimization (BO), Multilayer Perceptron (MLP), and Random Forest (RF) algorithms, with the Bayesian Optimization method ensuring that the model fits the training data well and generalizes to the test data. The results of tenfold cross-validation demonstrated that the model’s accuracy is consistently around 92.5%, combining the training results of rock burst models with imbalanced datasets, proving that the MLP model, adept at modeling nonlinear data, and the RF model, skilled in modeling large-scale data, serve as basic classifiers. This demonstrates that the application of data balancing and combined discriminative model schemes have enhanced the model’s predictive performance and stability. The model is capable of providing high-accuracy, high-efficiency early warning monitoring services for rock burst phenomena in rock engineering, thereby ensuring engineering safety.

Experimental study on the failure characteristics and mechanism between spalling failure and rockburst

To reveal the differences in the failure characteristics and mechanisms between rockburst and spalling failure, the comparison experiment between spalling failure and rockburst occurred in a circular cavity were carried out. Experiment results reveal that rockburst is accompanied by the intense ejection of fragments, whereas spalling failure features with the slow detachment of fragments. Additionally, besides the plate and flaky fragment, the rockburst fragment exhibits more pronounced blocky features. In terms of strength and deformation characteristics, the peak stress for rockburst is 1.04 times that of spalling failure, whereas the plastic deformation of spalling failure is 1.75 times that of rockburst. Furthermore, considering the micro failure and energy evolution process, three interpretations were proposed to elucidate the distinct mechanisms between rockburst and spalling failure, including: (i) The swift invasion of shear cracks triggers the buckling failure of pre-existing plate-like fractures, causing the fragment ejection observed in rockburst. When shear cracks not substantially contribute to the evolutionary process, the continuous penetrating of the pre-existing tensile cracks will culminate in the gradual delamination and spalling failure of the sidewall. (ii) The energy dissipating behavior determines the distinct mechanisms of rockburst and spalling failure. Almost all of the energy input preceding rockburst is converted into the elastic strain energy of rock units, whereas the energy input preceding spalling failure results in greater energy dissipation (about 1.85 times that of rockburst). (iii) under the framework of Mohr-Coulomb strength criterion, it has been revealed that the rock units of spalling failure adhere to the minimum failure energy criterion. However, the energy accumulated by the rock units prior to rockburst surpasses the minimum energy necessary for failure. This residual energy provides the fractured rock mass with kinetic energy, ultimately leading to a violent ejection phenomenon of rockburst.

Mechanical mechanism analysis of rockburst in deep-buried tunnel with high in-situ stress

The Qinling water conveyance tunnel has a large buried depth and high in-situ stress level, and rockburst disasters frequently occurred during excavation. In order to find out the mechanical mechanism of rockburst, the research work in this paper is as follows: (1) In-situ three-dimensional hydraulic fracturing method was used to measure the in-situ stress of the deep buried tunnel crossing the ridge. (2) Based on the measured in-situ stress results, the stress distribution characteristics of the tunnel crossing the ridge were obtained by the multiple linear regression method, and the rockburst tendency during construction was predicted. (3) A three-dimensional numerical model of tunnel excavation was established to analyze the dynamic adjustment characteristics of the surrounding rock stress and elastic strain energy during TBM excavation, and to clarify the mechanical mechanism of rockburst. The research results show that the maximum principal stress of the deep-buried tunnel crossing the ridge of Qinling is 40–66 MPa, which belongs to extremely high in-situ stress level, and medium-strong rockburst may occur during excavation. In the process of TBM excavation, the stress of the surrounding rock in the range of 2.6 times the diameter of the tunnel before and after the working face is adjusted violently, and the concentrated zones after the stress redistribution are mainly distributed in the arch roof and arch bottom, and the stress concentration coefficient can reach 2.06. The arch roof, arch waist, and arch bottom are susceptible to immediate rockburst due to stress transient unloading at the moment of excavation. After the elastic strain energy of the surrounding rock at the arch roof and the arch bottom is released and accumulated, it is easy to cause time delayed rockburst, and the depth of the rockburst pit can reach 3.5 m, which is consistent with the rockburst phenomenon in the field.

Fuzzy Cognitive Map for Evaluating Critical Factors Causing Rockbursts in Underground Construction: A Fundamental Study

The rockburst phenomenon in excavation endeavours reveals a multitude of complexities and obstacles that significantly impact both the technical and financial dimensions of project execution. Investigating critical rockburst factors in underground excavations is of considerable importance for addressing pivotal safety issues and operational complexities within the field of underground excavation projects. This research proposes an innovative approach based on an expert-based fuzzy cognitive map (FCM) framework, aiming to identify and prioritize the key critical rockburst factors prevalent in underground excavations and tunnelling. A tailored cognitive map of the parameters of problem was constructed, integrating 56 critical and critical factors meticulously curated by a team of seasoned managers, engineers, deputy managers, trainee engineers and assistant managers. The structured cognitive map was meticulously developed, considering the relative weights of the identified critical factors and their intricate interrelationships—all informed by the invaluable insights and expertise of seasoned engineers in the field. Subsequently, the cognitive map underwent a systematic solution process, whereby the causal relationships and influences amongst the identified critical factors were analysed and factored in. The outcomes of the comprehensive analysis unveiled several critical factors: lack of rockburst risk assessments, high in situ stress, presence of rock seams and weak layers, rock quality variations, and geological heterogeneity as the most paramount concerns demanding immediate attention and strategic intervention. By adopting the proposed FCM approach and leveraging the collective expertise of industry professionals, this research offers a robust and systematic framework for comprehensively assessing and addressing the key challenges associated with rockburst events in underground excavations and tunnelling projects, thereby fostering enhanced project performance and efficacy within the field.

Experimental Investigation on the Influence of Water on Rockburst in Rock-like Material with Voids and Multiple Fractures.

To investigate the influence of water content on the rockburst phenomena in tunnels with horizontal joints, experiments were conducted on simulated rock specimens exhibiting five distinct levels of water absorption. Real-time monitoring of the entire blasting process was facilitated through a high-speed camera system, while the microscopic structure of the rockburst debris was analyzed using scanning electron microscopy (SEM) and a particle size analyzer. The experimental findings revealed that under varying degrees of water absorption, the specimens experienced three stages: debris ejection; rockburst; and debris spalling. As water content increased gradually, the intensity of rockburst in the specimens was mitigated. This was substantiated by a decline in peak stress intensity, a decrease in elastic modulus, delayed manifestation of pre-peak stress drop, enhanced amplitude, diminished elastic potential energy, and augmented dissipation energy, resulting in an expanded angle of rockburst debris ejection. With increasing water content, the bond strength between micro-particles was attenuated, resulting in the disintegration of the bonding material. Deformation failure was defined by the expansion of minuscule pores, gradual propagation of micro-cracks, augmentation of fluffy fine particles, exacerbation of structural surface damage akin to a honeycomb structure, diminishment of particle diameter, and a notable increase in quantity. Furthermore, the augmentation of secondary cracks and shear cracks, coupled with the enlargement of spalling areas, signified the escalation of deformation failure. Simultaneously, the total mass of rockburst debris gradually diminished, accompanied by a corresponding decrease in the proportion of micro and fine particles within the debris.

Rockburst risk control and mitigation in deep mining

It is important to understand and manage rockburst challenges in deep mining operations. This paper presents a systematic study of rockburst risk in underground mining, offering a detailed examination of influencing factors, risk assessment, and various control and mitigation methods. The complexities of rockburst phenomena are explained by examining factors that lead to the occurrence of rockbursts. A rockburst risk assessment using a bow-tie analysis is conducted, which provides insights into both risk evaluation and proactive control and mitigation systems.The core of the paper presents a comprehensive array of rockburst risk control and mitigation methods, which range from controls to reduce rockburst hazard, and excavation vulnerability, to controls and mitigations to reduce exposure. Strategic engineering control methods, including mine design and mining sequencing, are discussed. Tactical engineering control measures, such as ground pre-conditioning and rock support, are scrutinized, along with administrative controls like evacuation and re-entry protocols and the use of mechanized equipment. A multiple-line defense system is advocated for rockburst risk management to address the uncertainties involved in the process.Finally, emerging technologies and innovations as well as challenges are discussed, providing a roadmap for continued advancements in rockburst risk management in the future. This work serves as a valuable resource for mining professionals, researchers, and policymakers seeking a comprehensive understanding of rockburst risk management in deep mining.

Thermal monitoring and deep learning approach for early warning prediction of rock burst in underground structures

The occurrence of rockburst has the potential to result in significant economic and human losses in underground mining and excavation operations. The accuracy of traditional methods for early prediction is considerably affected by factors such as site conditions, noise levels, accessibility, and other variables. This study proposes a methodology for identifying the most defected region in a hard rock sample by integrating motion thermogram data obtained from the laboratory monitoring of rock burst phenomena with a cutting-edge deep neural network approach based on a regional convolutional network (i.e. Mask RCNN). The efficacy of the suggested approach was evaluated by determining the F1 score and average precision matrices based on a specific intersection over union value. The findings demonstrate that the proposed approach possesses satisfactory precision with respect to detection, localization, and segmentation, thereby establishing its potential utility as an autonomous predictor of rock bursts.

Numerical and Analytical Determination of Rockburst Characteristics: Case Study from Polish Deep Copper Mine

A simplified analytical method useful for ductile ground support design in underground mine workings is presented. This approach allows for maintaining the stability of sidewalls in rectangular openings extracted in competent and homogeneous rocks, especially in high-pressure conditions, favoring rockburst event occurrence. The proposed design procedure involves the typical assumptions governing the limit equilibrium method (LEM) with respect to a triangular rock block expelled from a sidewall of a long mine excavation subjected to normal stresses of the values determined based on the Maugis’s analytical solution concerned with stress distribution around the elliptical opening extracted within the homogeneous infinite elastic space. This stage of the local assessment of rock susceptibility to ejection from the walls of the excavation allowed for determining the geometry of the block whose ejection is most likely in a given geological and mining situation. Having extensive information about the geometry of the excavations and the properties of the surrounding rocks, it was possible to make an exemplary map of the risk from rockburst hazard, developed as the 2D contours of safety indexes’ values, for special-purpose excavations such as heavy machinery chambers, main excavations, etc. in conditions of selected mining panel of the deep copper mine at Legnica-Głogów Copper Basin, Poland. Another important element of the obtained results is the calculated values of the horizontal forces potentially pushing out the predetermined rock blocks. These forces are the surplus over the potential of frictional resistance and cohesion on the surfaces of previously identified discontinuities or on new cracks appearing as a result of overloading of the sidewalls. Finally, the presented algorithm allows us to perform quantitative tracking of rockburst phenomena as a function of time by determination of acceleration, velocity, and displacement of expelled rocks. Such information may be useful at the stage of designing the support for underground workings.

Fracture evolution characteristics of strainburst under different gradient stress

AbstractStrainburst often occurs in the loading process of tangential stress concentration from surrounding rocks after excavation and unloading of deep rock mass. The concentrated tangential stress is relatively larger on the tunnel walls, which decreases towards the interior of surrounding rocks with a certain gradient. To explore the fracture evolution characteristics of surrounding rocks under different tangential gradient stresses and understand various phenomena in the strainburst process, a large‐scale true‐triaxial gradient and hydraulic‐pneumatic composite loading rockburst test device was adopted to carry out the strainburst tests under four different gradient stresses. Based on the macroscopic failure phenomena, distribution of rockburst debris, macro‐micro morphology of failure cross section, and monitored data of acoustic emission (AE), the fracture evolution of rockburst specimens was analyzed under different stress gradient loadings. The results indicate that the stress gradient has an obvious influence on the fracture characteristics, resulting in different rockburst phenomena. With the increase of stress gradient, the failure stress of rockburst decreases, while the dynamic failure characteristics of rockburst trends to be significant. The increase of stress gradient contributes to higher fragmentation degree of debris, more uniform distribution and better continuity. The total number of cracks in the model decreases with the rise of the stress gradient, and the proportion of shear failure increases, which is the main reason for the enhancement of the rockburst intensity.

Crack Evolution Behaviors and Bursting Liability of Sandstone with Different Sizes: An Experimental Study.

The size ranges of ore pillars play important roles in preventing the occurrences of rock burst phenomena. Due to the lack of research on the relationship between crack evolution behaviors and bursting liability of rocks with different sizes, uniaxial compression tests on sandstone with different height-to-diameter ratios (H/D) were conducted. The results showed that the mechanical parameters of sandstone have obvious size effects, in which both the peak strength and peak strain decrease with increases in the H/D. Moreover, the brittle index modified value (BIM) decreased, but the impact energy index increased gradually, which indicated the increase of bursting liability. With the increases in the BIM, the overall crack strain parameters increased, thereby indicating a positive correlation. With the increase in the impact energy index, the crack strain decreased and the bursting liability became higher. Although the axial crack closure stress and axial crack damage stress increased with the increases in BIM (indicating a positive correlation), the bursting liability became increasingly smaller. The crack stress decreased with the increases in the impact energy index, and the bursting liability became stronger. The findings of this study will potentially provide experimental references for furthering the current understanding of the mechanism of rock bursts in underground coal mines in China.

Unified Mechanism of Rock Burst Induced by Coal Mine Earthquake and Its Activity and Response Characteristics

The occurrence regularity of the coal mine earthquake under the influence of hard roof, fault, and mining was studied by theoretical analysis, field investigation, and monitoring data analysis for the phenomenon of rock burst induced by coal mine earthquakes. The dissipation characteristics of coal mine earthquake energy propagation considering a hypocenter scale were described, and the coal mine earthquake response characteristics were analyzed. The two principles of rock burst induced by hard rock fractured type coal mine earthquakes and the three principle of rock burst induced by fault were described. Based on this, the unified mechanism rock burst induced by different types of coal mine earthquakes was proposed. The results show that the microseismic energy increases sharply and decreases sharply when mining in the fault area. The amplitude and frequency of support resistance increased before and after the heavy coal mine earthquake occurred. The periodic characteristics of the coal mine earthquake in the 43upper 13 working face of the Dongtan coal mine show that there are 50 m small periods within 100 m large periods. The multiparameter field monitoring can make it possible for instantaneous capture of the coal mine earthquake dynamic responses. The unified rock burst mechanism induced different types of coal mine earthquake and is the difference energy between the superposition energy of the rock burst source region and the energy consumed by coal-rock instability increases suddenly under the action of coal mine earthquakes. Meanwhile, the violent rock burst accident occurs when the stiffness condition is satisfied.

Characterization of true triaxial rock bursts in sandstones with different water contents

The rockburst phenomenon occurs in dry red sandstone under high in situ stress, and the rockburst effect is weaker for a water-bearing rock. The rockburst effect on red sandstone with different water contents is analyzed in this paper. A true triaxial testing machine is used to conduct the loading, and acoustic emission recording equipment and a high-speed camera are used to monitor the acoustic signal inside the rock and the rock-caving situation throughout the entire process in order to analyze the characteristics of the acoustic emissions and the ejection form of the rockburst. The results show that rockburst occurs in dry red sandstone and 50% saturated red sandstone but not in saturated red sandstone. The phrase characteristics of the stress–strain curve of the dry rock vary more significantly than those of the water-bearing rock, and the elastic strain energy inside the rock decreases gradually as the water content increases. The double peak of the acoustic emissions curve occurs during the failure process of the dry rock and gradually transitions to a stepped pattern as the water content increases. The ejected fragments of dry red sandstone during the rockburst are abundant and large. The true triaxial test results illustrate the characteristic effect of the rockburst on red sandstone with different water contents, reveal the failure mode and ejection characteristics of red sandstone with different water contents, and demonstrate the influence of the water content on the rockburst characteristics of red sandstone. The results of this study provide a theoretical reference for the study of the rockburst mechanisms of similar hard rocks.

Numerical Simulation Study of the Effect of Fine View Pore Structure on Rock Burst

With the gradual shift of coal mining to deeper levels in recent years, rock burst has become one of the primary dynamic hazards faced in deep mining. It has been shown that the pore structure in rocks affects the mechanical properties, but the relationship with the rock burst phenomenon still needs to be clarified. In this paper, we investigated the causes and effects of pore structure on impact mechanical properties using RFPA2D numerical simulation software, established several numerical models with different porosities and pore diameters, and analyzed the stress-strain curves, the relationships between porosity and pore diameter and each the bursting liability indices of the coal rock body were elaborated, and the fitting equations in the range of porosity (0%~10%) and pore diameter (0.25~2.0 mm) were obtained. The results showed that the increase in porosity and pore diameter effectively attenuated the bursting ability of coal rocks, which has some reference significance for the study of early warning and prevention of rock burst phenomenon.

Laboratory-Scale Rockburst Physical Model Testing Using a True-Triaxial Cell

Assessment of rockburst risk is one of the most fundamental challenges in tunnel design and construction in rocks. The rockburst phenomenon is typically related to rock brittle failure properties, which result in significant strain-energy release, spalling, fractures, and damage near the tunnel opening. This research aims to present a preliminary analysis of rockburst in an unsupported circular tunnel using a novel experimental approach to model tunnel boring machine excavated opening through brittle fracture material. In this physical model testing, the true-triaxial cell utilizes a cube of synthetic sandstone of 300 mm dimensions with a freshly excavated 51 mm diameter tunnel, 150 mm depth on the center top side using a miniature tunnel boring machine. The six sides of the specimen cube are loaded in a true-triaxial manner, allowing for various magnitudes of principal stresses and stress levels that reflect actual in-situ conditions. In addition, the experimental setup employs acoustic emission monitoring to observe the tunnel response during excavation and loading increment. However, the sample in this preliminary experiment was loaded under hydrostatic circumstances and gradually increased until the sample showed a reduction in the acoustic emission activity and failed. The experiment results suggest that the physical model can better understand rockburst in a tunnel through the acoustic emission analysis. The model can outline the damage and spalling during strain energy release near the tunnel boundary.

Application of KNN-based isometric mapping and fuzzy c-means algorithm to predict short-term rockburst risk in deep underground projects.

The rockburst phenomenon is the major source of the high number of casualties and fatalities during the construction of deep underground projects. Rockburst poses a severe hazard to the safety of employees and equipment in subsurface mining operations. It is a hot topic in recent years to examine and overcome rockburst risks for the safe installation of deep urban engineering designs. Therefore, for a cost-effective and safe underground environment, it is crucial to determine and predict rockburst intensity prior to its occurrence. A novel model is presented in this study that combines unsupervised and supervised machine learning approaches in order to predict rockburst risk. The database for this study was built using authentic microseismic monitoring occurrences from the Jinping-II hydropower project in China, which consists of 93 short-term rockburst occurrences with six influential features. The prediction process was succeeded in three steps. Firstly, the original rockburst database's magnification was reduced using a state-of-the-art method called isometric mapping (ISOMAP) algorithm. Secondly, the dataset acquired from ISOMAP was categorized using the fuzzy c-means algorithm (FCM) to reduce the minor spectral heterogeneity impact in homogenous areas. Thirdly, K-Nearest neighbor (KNN) was employed to anticipate different levels of short-term rockburst datasets. The KNN's classification performance was examined using several performance metrics. The proposed model correctly classified about 96% of the rockbursts events in the testing datasets. Hence, the suggested model is a realistic and effective tool for evaluating rockburst intensity. Therefore, the proposed model can be employed to forecast the rockburst risk in the early stages of underground projects that will help to minimize casualties from rockburst.

Safety and Protection Measures of Underground Non-Coal Mines with Mining Depth over 800 m: A Case Study in Shandong, China

With the increase in mining depth, the risk of ground pressure disasters in yellow gold mines is becoming more and more serious. This paper carries out a borehole test for the pressure behavior in a non-coal mining area with a mining depth of more than 800 m in the Jiaodong area. The test results show that under a depth of 1050 m, the increase in the vertical principal stress is the same as the increase in the minimum horizontal principal stress, which is about 3 MPa per 100 m. When the depth increases to 1350 m, the vertical principal stress increases by about 3% per 100 m, and the self-weight stress and the maximum horizontal principal stress maintain a steady growth rate of about 3 MPa per 100 m. In addition, based on the test results, the operation of the ground pressure monitoring system in each mine is investigated. The investigation results show that in some of the roadway and stope mines with depths of more than 800 m, varying degrees of rock mass instability have occurred, and a few mines have had sporadic slight rockbursts, accounting for about 5%. There was a stress concentration area in the lower part of the goaf formed in the early stage of mining, and slight rockburst phenomena such as rock mass ejection have occurred; meanwhile, the area stability for normal production and construction was good, and there was no obvious ground pressure. This paper compares the researched mines horizontally as well as to international high-level mines and puts forward some suggestions, including: carrying out ground pressure investigations and improving the level of intelligence, which would provide countermeasures to balance the safety risks of deep mining, reducing all kinds of safety production accidents and providing a solid basis for risk prevention and supervision.

Experimental and Numerical Investigation of Energy Evolution Characteristic of Granite considering the Loading Rate Effect

In order to investigate the loading rate effect of energy evolution in granite, the indoor physical simulation test of single face fast unloading-three directions and five faces stress-vertical continuous loading under different loading rates was conducted using a new true triaxial rockbursttest system. The energy accumulation-dissipation-release characteristics in the process of rock deformation and failure were revealed. Based on the three-dimensional discrete element theory and the polycrystalline modeling technique (randomly generated Voronoi mineral grains), the entire process of rockburst inoculation-occurrence-development, as well as the energy evolution characteristics under true triaxial single face unloading conditions, were studied. The test results indicate that the energy transport and conversion of rock samples under different loading rates exhibit distinct stage characteristics. It can be divided into the initial energy accumulation stage, steady energy accumulation stage, rapid energy dissipation stage, and rapid energy release stage. With a rise in loading rate, the specimen in the process of energy accumulation is accompanied by energy dissipation, more external input energy, and elastic strain energy release amount into the kinetic energy of fragments, resulting in the rockburst phenomenon. As the loading rate increases, the elastic strain energy conversion rate (Ue/U) falls, while the dissipative energy conversion rate (Ud/U) increases. The higher the elastic strain energy conversion rate and the lower the dissipative energy conversion rate, the more serious the rockburst occurs. Numerical simulation results show that the entire process of rockburst inoculation-occurrence-development is successfully simulated using the crystal scale fine model (CSFM) considering the grain mineral composition. The ejection failure process can be divided into four stages, including grains ejection, rock spalling into plates, rock shearing into fragments, and rock fragments ejection. The relationships between the peak strength, elastic strain energy of rock samples, and loading rates are obtained, which is consistent with the laboratory test results. The high rate linear growth of kinetic energy evolution between the two inflection points can provide precursor information for rockburst prediction.

Numerical and Machine learning modeling of hard rock failure induced by structural planes around deep tunnels

The Rockburst phenomenon is one of the hazards in deep underground mines and tunnels that can be exacerbated by faults or structural features. An accurate understanding of this phenomenon can control or reduce its destructive impacts. Using methods that can accurately estimate or predict this phenomenon is a critical issue for experts in the field. Since studying rockburst with the help of laboratory and numerical methods is a complex issue and, at the same time, requires high time and cost, in this paper, the machine learning method of extreme gradient boosting (XGBoost) was used for predicting this phenomenon. For this purpose, numerical modelling was used in the Abaqus software environment to generate 300 datasets. A fault around the modelled tunnel was considered to show the impact of faults on the phenomenon of rockburst in tunnels. The datasets included 13 effective input parameters on the rockburst phenomenon. Among the 300 datasets, 250 data were used for training and 50 data for the test. The comprehensive results indicated that the XGBoost model has the potential ability to estimate the rockburst phenomenon that may occur during deep tunnelling near fault zones. The results revealed that faults around deep tunnels could significantly increase the risk of rockburst if the fault is positioned and oriented in such a way that it promotes high stress. The MIT method revealed that, among the 13 input parameters considered in this study, fault length and density have the most and least impact on the rockburst phenomenon, respectively. Finally, to have good knowledge of the rockburst phenomenon in tunnelling projects, this article recommends using the XGBoost method to predict the rockburst in deep tunnels near the fault zones. The importance of the proposed model is that it can provide a reasonable estimate of the rockburst phenomenon in the deep tunnels, based on which geotechnical engineers can take the necessary measures to deal with it in the pre-construction designs.

Rockburst mechanism of rock mass with structural planes in underground chamber excavation

Natural rock mass generally contains discontinuous structural planes, such as joints, fractures and faults, which have great influence on the occurrence of rockburst. The rockburst mechanism of rock mass with structural planes in underground chamber excavation is studied by means of model test and numerical simulation in this paper. Firstly, quartz sand, barite powder, gypsum powder, cement and water are selected as raw materials to configure the similar materials suitable for the rockburst model test. Secondly, four working conditions of none structural plane, single structural plane, multiple structural planes and through structural plane are designed, and the corresponding rockburst model tests are carried out. The stress and displacement laws of surrounding rock during excavation are analyzed. Finally, the numerical calculation of chamber excavation is conducted under the above four working conditions and the model test is verified. The failure modes and laws of surrounding rock mass with different structural planes during chamber excavation are obtained. The results show that: (i) After the tunnel excavation in rock mass with single structural plane, the tension of structural plane and the expansion of fractures occur, accompanied by small-scale rockburst. (ii) After the tunnel excavation in rock mass with multiple structural planes, the stress level of surrounding rock mass decreases significantly and no rockburst occurs, but the surrounding rock is prone to large-scale collapse or spalling. (iii) After the tunnel excavation in rock mass with through structural plane, the fractures appear in the vault and arch bottom and expand rapidly, accompanied by rockburst phenomena such as granules ejection. The research results of this paper are of great significance for understanding the deformation and failure mechanism of rock mass with structural planes in the underground chamber excavation.

Analysis of rock microseismic signal based on blind source wavelet decomposition algorithm

At present, microseismic technology is a widely used method for monitoring the rock burst phenomenon during the construction of deep-buried tunnels. The rock fracture in the tunnel will generate seismic waves. The seismic wave has strong randomness and low energy and is usually mixed with environmental noise, which is called the microseismic signal. The microseismic signal received by the geophone will contain other noises. So, there is an urgent need for an algorithm that can quickly decompose the mixed signal. To solve this problem, this paper proposes a blind source wavelet algorithm to extract the rock fracture signal. First, the signal is preprocessed, and the mixed signal matrix is established. Second, the blind source decomposition algorithm is used to process the signal, and the effective signal is reconstructed. Finally, the wavelet algorithm is used to further remove the noise to enhance the microseismic signal. The proposed method is compared with the wavelet decomposition method and the empirical mode decomposition (EMD) method through the laboratory simulation data and the actual signal of Baihetan Hydropower Station. It is concluded that the proposed algorithm can effectively decompose and remove the noise in the mixed signal, and the decomposition accuracy is better than the wavelet decomposition method and the EMD method. The proposed algorithm has certain practical significance for the identification of microseismic signals of rock fracture and for rock burst early warning.