In order to enhance the accuracy and efficiency of coal and gas outburst prediction, a novel approach combining Kernel Principal Component Analysis (KPCA) with an Improved Whale Optimization Algorithm (IWOA) optimized extreme learning machine (ELM) is proposed for precise forecasting of coal and gas outburst disasters in mines. Firstly, based on the influencing factors of coal and gas outburst disasters, nine coupling indexes are selected, including gas pressure, geological structure, initial velocity of gas emission, and coal structure type. The correlation between each index was analyzed using the Pearson correlation coefficient matrix in SPSS 27, followed by extraction of the principal components of the original data through Kernel Principal Component Analysis (KPCA). The Whale Optimization Algorithm (WOA) was enhanced by incorporating adaptive weight, variable helix position update, and optimal neighborhood disturbance to augment its performance. The improved Whale Optimization Algorithm (IWOA) is subsequently employed to optimize the weight ф of the Extreme Learning Machine (ELM) input layer and the threshold g of the hidden layer, thereby enhancing its predictive accuracy and mitigating the issue of "over-fitting" associated with ELM to some extent. The principal components extracted by KPCA were utilized as input, while the outburst risk grade served as output. Subsequently, a comparative analysis was conducted between these results and those obtained from WOA-SVC, PSO-BPNN, and SSA-RF models. The IWOA-ELM model accurately predicts the risk grade of coal and gas outburst disasters, with results consistent with actual situations. Compared to other models tested, the model's performance showed an increase in Ac by 0.2, 0.3, and 0.2 respectively; P increased by 0.15, 0.2167, and 0.1333 respectively; R increased by 0.25, 0.3, and 0.2333 respectively; F1-Score increased by 0.2031, 0.2607, and 0.1864 respectively; Kappa coefficient k increased by 0.3226, 0.4762 and 0.3175, respectively. The practicality and stability of the IWOA-ELM model were verified through its application in a coal mine in Shanxi Province where the predicted values exactly matched the actual values. This indicates that this model is more suitable for predicting coal and gas outburst disaster risks.
In order to more accurately classify the stability of roadway surrounding rock and identify dangerous areas in a timely manner to prevent roadway collapse and other disasters, this study proposes an Improved Northern Gok algorithm (INGO) and Random Forest (RF) roadway surrounding rock stability prediction model. This model combines the improved INGO-RF based on the analysis of influencing factors of roadway surrounding rock stability. First, three strategies were employed to enhance the Northern Gob algorithm (NGO): logistic chaotic mapping, refraction reverse learning, and improved sine and cosine. Subsequently, INGO was utilized to optimize the number of decision trees and the minimum number of leaf nodes for RF species in order to improve the prediction accuracy of RF. Secondly, a data set consisting of 34 groups of roadway surrounding rock data is selected. The input indexes of the model include the roof strength, two-wall strength, floor strength, burial depth, roadway pillar width, ratio of direct roof thickness to mining height, and surrounding rock integrity. Meanwhile, surrounding rock stability is considered as the output index. Particle swarm optimization backpropagation neural network (PSO-BPNN), genetic algorithm optimization support vector machine (GA-SVM), Sparrow Search Algorithm optimization RF (SSA-RF) models were introduced to compare the predictive results with the INGO-RF model, and the results showed that: INGO-RF model has the best performance in the comparison of various performance indicators; compared with other models, the accuracy rate (Ac) in the test set has increased by 0.12-0.40, the accuracy rate (Pr) has increased by 0.07-0.65, and the recall rate (Re) has increased by 0.08-0.37; the harmonic mean (F1-Score) of the recall rate increased by 0.08-0.52, the mean absolute error (MAE) decreased by 0.1428-0.4285, the mean absolute percentage error (MAPE) decreased by 7.15%-28.57 %, and the root mean square error (RMSE) decreased by 0.1565-0.3779; and finally, the data on surrounding rock conditions of roadways in multiple mining areas in Shanxi Province were collected to test the INGO-RF model. The results indicate that the predicted outcomes closely align with the actual results, demonstrating a certain level of reliability and stability, which can better meet the practical needs of engineering and avoid the occurrence of mine disasters.
Landslides pose a significant threat to the lives and livelihoods of marginalised communities residing in rural areas and the delicate ecological balance of the environment. Implementing advanced technologies is crucial for improving hazard risk assessment and enhancing preparedness measures in regions characterised by diverse topography and complex geological formations. Geospatial applications and modelling techniques have emerged as indispensable in mitigating landslide risks, particularly in environmentally sensitive areas. This study presents a comprehensive approach to landslide susceptibility mapping in the Nilgiri District of Tamil Nadu, India, leveraging the power of Artificial Neural Networks (ANNs) and integrating multi-dimensional geospatial datasets. Integrating ANN-based modelling and geospatial techniques offers significant advantages in terms of statistical robustness, reproducibility, and the ability to analyze the complex interplay of factors influencing landslide hazards quantitatively. The methodology involves rigorous pre-processing and integrating spatial data, including landslide event occurrences as the dependent variable and ten independent parameters influencing landslide susceptibility. These parameters encompass elevation, slope aspect, slope degree, distance to roads, land use patterns, geomorphology, lithology, drainage density, lineament density, and rainfall distribution. Feature extraction and selection techniques are employed to effectively model the complex interactions between these factors and landslide occurrences. This process identifies the most relevant variables influencing landslide susceptibility, enhancing the model's predictive capabilities. The state-of-the-art ANNs are trained using historical landslide occurrence data and the selected influencing factors, enabling the development of a robust and accurate landslide susceptibility model. The performance of the developed model is rigorously evaluated using a comprehensive suite of metrics, including accuracy, precision, and the Area under the Receiver Operating Characteristic (ROC) curve. Preliminary results indicate that the ANN-based landslide susceptibility model outperforms traditional zonation methods, demonstrating higher accuracy and reliability in predicting landslide-prone areas. The resulting Landslide Susceptibility Map (LSM) categorises the study area into five distinct hazard zones, ranging from very high (664.1 km2), high (598.9 km2), moderate (639.7 km2), low (478.9 km2) and to very low (170.9 km2). Notably, the eastern and central regions of the district emerge as particularly vulnerable to landslide occurrences. The study's findings have far-reaching implications for disaster risk reduction efforts, land-use planning, and sustainable development strategies in the ecologically sensitive Nilgiri District and beyond.
Effective control of blasting outcomes depends on a thorough understanding of rock geology and the integration of geological characteristics with blast design parameters. This study underscores the importance of adapting blast design parameters to geological conditions to optimize the utilization of explosive energy for rock fragmentation. To achieve this, data on fifty geo-blast design parameters were collected and used to train machine learning algorithms. The objective was to develop predictive models for estimating the blast oversize percentage, incorporating seven controlled components and one uncontrollable index. The study employed a combination of hybrid long-short-term memory (LSTM), support vector regression, and random forest algorithms. Among these, the LSTM model enhanced with the tree seed algorithm (LSTM-TSA) demonstrated the highest prediction accuracy when handling large datasets. The LSTM-TSA soft computing model was specifically leveraged to optimize various blast parameters such as burden, spacing, stemming length, drill hole length, charge length, powder factor, and joint set number. The estimated percentage oversize values for these parameters were determined as 0.7 m, 0.9 m, 0.65 m, 1.4 m, 0.7 m, 1.03 kg/m3, 35 %, and 2, respectively. Application of the LSTM-TSA model resulted in a significant 28.1 % increase in the crusher's production rate, showcasing its effectiveness in improving blasting operations.
In order to improve the stability of the slope and prevent the occurrence of landslide disaster, this study took the east slope of the first mining area of Zhundong Open-pit Coal Mine as the engineering background, and used a combination of the two-dimensional limit equilibrium method and three-dimensional numerical simulation to optimize the shape of the east slope. By selecting a typical calculation profile based on the Bishop method and the residual thrust method in the two-dimensional rigid body limit equilibrium method, this research carried out the stability analysis of the profile slope, and preliminarily designed the slope shape of the profile position meeting the requirements of the safety reserve coefficient and stripping ratio. Based on the three-dimensional finite element strength reduction method, this paper investigated the reasonably change of the width of the transport plate to solve the problem of the slope shape that does not meet the requirements of safety reserve coefficient and stripping ratio, and established a three-dimensional numerical simulation model of various schemes. It also studied the influence of different tracking distances and slope angles on slope stability, calculated the three-dimensional stability of the slope under different spatial forms, then determined the optimal tracking distance and optimal slope angle, and further optimize the slope stability and stripping ratio. The results show that: when the width of the transport plate of the DBS3 section slope is 8 m, it does not meet the requirement of safety reserve coefficient 1.2; when the width of the transport plate is set to 24 m, it meets the requirement of a safety reserve coefficient of 1.2 and an economic stripping ratio of not more than 8.0 m3/t. The three-dimensional numerical simulation results concluded that the optimal tracking distance on the east side is 50 m, and the optimal slope angle is 35°. After the optimization design of a two-dimensional and three-dimensional slope shape, 2.456 million tons of coal resources were mined, creating a profit of about 21.1268 million yuan. It not only prevents landslide disasters, but also further improve the recovery rate of coal resources.
To ensure the on-site implementation of regulations and technical measures for rock burst prevention and control, this study takes Yankuang Energy Group Co., Ltd. as an example, establishes an on-site technical management system for preventing and controlling rock burst in coal mines. This on-site technical management system is based on the principles of zero rock burst accident, graded management and control, general manager and chief engineer responsibility, as well as scientific, systematic, streamlined, and efficient management. This system includes a technical management system and an on-site management mode, among which the former includes an organizational system, an institutional system, a technical data management system, and a comprehensive supervision and management system. The on-site management mode includes five aspects and six links. The construction of an on-site technical management system for rock burst prevention and control can ensure the timely detection and rectification of problems, remove management loopholes, and prevent the occurrence of rock burst disasters.
Effective monitoring techniques and equipment are essential for the prevention and control of coal and rock dynamic disasters such as rockburst. Based on the fact that there is charge generation during deformation and rupture of coal rock body and the charge signals contain a large amount of information about the mechanical process of deformation and rupture of coal rock, the rockburst charge sensing monitoring technology has been formed. In order to improve the charge sensing technology for monitoring and early warning of rockburst disasters, this paper develops a new generation of portable coal rock charge monitoring instrument on the basis of the original instrument and carries out laboratory and underground field application. The primary advancement involves enhancing the external structure of the sensor and increasing the charge sensing area, which can more comprehensively capture the charge signals from the loaded rupture of the coal rock body. The overall structure of the data acquisition instrument has been improved, the monitoring channels have been increased, and the function of displaying the monitoring data curve has been added, so that the coal and rock body force status can be grasped in time. The results of the experimental study show that the abnormal charge signals can be monitored during the rupture process of rock samples under loading, and the monitored charge signals are in good agreement with the sudden change of stress in the rock samples and the formation of crack extension. There is a precursor charge signal before the stress mutation, and the larger the loading rate is, the earlier the precursor charge signal appears. The charge monitoring instrument can monitor the charge signal of the coal seam roadway under strong mining pressure. In the zone of elevated overburden pressure, the amount of induced charge is large, and anomalously high value charge signals can be monitored when a coal shot occurs. The change trend of the charge at different measuring points of strike and inclination has a good consistency with the distribution of overrunning support pressure and lateral support pressure, which can reflect the stress distribution and the degree of stress concentration of the coal body through the size and location of the charge, foster early warning and analysis of rockburst, and provide target guidance for the prevention and control of rockburst.
Engineering disasters, such as rockburst and collapse, are closely related to structural instability caused by insufficient bearing capacity of geological materials. Uniaxial compressive strength (UCS) holds considerable significance in rock engineering projects. Consequently, this study endeavors to devise efficient models for the expeditious and economical estimation of UCS. Using a dataset of 729 samples, including the Schmidt hammer rebound number, P-wave velocity, and point load index data, we evaluated six algorithms, namely Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and Extra Trees (ET) and utilized Bayesian Optimization (BO) to optimize the aforementioned algorithms. Moreover, we applied model evaluation metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Variance Accounted For (VAF), Nash-Sutcliffe Efficiency (NSE), Weighted Mean Absolute Percentage Error (WMAPE), Coefficient of Correlation (R), and Coefficient of Determination (R2). Among the six models, BO-ET emerged as the most optimal performer during training (RMSE = 4.5042, MAE = 3.2328, VAF = 0.9898, NSE = 0.9898, WMAPE = 0.0538, R = 0.9955, R2 = 0.9898) and testing (RMSE = 4.8234, MAE = 3.9737, VAF = 0.9881, NSE = 0.9875, WMAPE = 0.2515, R = 0.9940, R2 = 0.9875) phases. Additionally, we conducted a systematic comparison between ensemble and traditional single machine learning models such as decision tree, support vector machine, and K-Nearest Neighbors, thus highlighting the advantages of ensemble learning. Furthermore, the enhancement effect of BO on generalization performance was assessed. Finally, a BO-ET-based Graphical User Interface (GUI) system was developed and validated in a Tunnel Boring Machine-excavated tunnel.
The instability of retaining wall is a key factor for many geo-hazards, such as landslides. To estimate the stability of retaining wall, the distribution of earth pressure is necessary. The results of in-situ observations and indoor experiments demonstrate that the distribution of earth pressure behind the retaining wall exhibits remarkable nonlinearity. When the results are analyzed in details, the oscillation and quasi-periodicity of the distribution of earth pressure are observed, which has not been given widely concerns and cannot be described by the existing analytical models. Based on the internal variable gradient theory and operator averaging method, a gradient-enhanced softening constitutive model is proposed in this paper to describe the oscillation and quasi-periodicity of the distribution of earth pressure acting on the retaining wall, by introducing the high-order gradient terms of the hydrostatic pressure into Mohr-Coulomb yield condition. In order to check the applicability of the proposed formulation, the predictions from the formulations are compared with the full-scale and laboratory-scale test results as well as the existing formulations. It is noted from the comparisons between predicted and measured values that the results of gradient-dependent softening constitutive model provides the comparable approximations for active earth pressure and describes the oscillation and quasi-periodicity very well. This model may enhance the comprehension of soil mechanics and provide a novel view for the design of the retaining wall.
In order to solve the problem of gas overlimit in corner corners of coal and gas prominent mines, through the combination of air leakage mechanism in the goaf, near-field fissure expansion and rich area division, blocking material development and optimization, performance measurement of blocking materials and on-site test, we started to study the causes of gas concentration in corner corners, analysis of roof collapse and transparency in corners and performance test of blocking materials, and optimized the blocking materials by combining laboratory test and engineering test. Considering the thickness of the sealing film, the attenuation ratio of the sealing film thickness, the gelation time, and the gelation viscosity under different ratios, we designed a multi factor orthogonal experiment to optimize the optimal ratio suitable for the engineering site. Factors affecting blocking effectiveness, such as gel water retention and gel flame resistance, were also tested. The sealing scheme was implemented in the 2109 working face of a coal and gas outburst mine in Gansu, China. Through on-site monitoring of the changes in temperature, gas concentration, and air leakage at each monitoring point before and after the use of sealing materials, the analysis of the detection results shows that the temperature changes at each monitoring point after the use of sealing materials do not exceed 0.2°C; The change in oxygen concentration is less than 0.27 %; The gas concentration has decreased by more than 60 %, with a decrease of 71.32 % in the gas concentration in the upper corner. The air leakage has decreased by more than 53 %, and the proportion of decrease in air leakage at the upper corner is as high as 56.83 %. This air leakage control technology has remarkable blocking effect, meets the requirements of corner near-field fissure blocking material, and is easy to prepare, inexpensive, non-toxic, tasteless and green, providing a successful experience for the treatment of similar coal and gas outburst mines that can be referenced.
This study investigated the fault nucleation and rupture processes driven by stress and fluid pressure in fine-grained granite by monitoring acoustic emissions (AEs). Through detailed analysis of the spatiotemporal distribution of the AE hypocenter, P-wave velocity, stress-strain, and other experimental observation data under different confining pressures for stress-driven fractures and under different water injection conditions for fluid-driven fractures, it was found that fluid has the following effects: 1) complicating the fault nucleation process, 2) exhibiting episodic AE activity corresponding to fault branching and the formation of multiple faults, 3) extending the spatiotemporal scale of nucleation processes and pre-slip, and 4) reducing the dynamic rupture velocity and stress drop. The experiments also show that 1) during the fault nucleation process, the b- value for AEs changes from 1 to 1.3 to 0.5 before dynamic rupture, and then rapidly recovers to around 1-1.2 during aftershock activity and 2) the hydraulic diffusivity gradually increases from an initial pre-rupture order of 0.1 m2/s to 10-100 m2/ s after dynamic rupture. These results provide a reasonable fault pre-slip model, indicating that hydraulic fracturing promotes shear slip before dynamic rupture, as well as laboratory-scale insights into ensuring the safety and effectiveness of hydraulic fracturing operations related to activities such as geothermal development, evaluating the seismic risk induced by water injection, and further researching the precursory preparation process for deep fluid-driven or fluid-involved natural earthquakes. The publicly available dataset is expected to be used for various purposes, including 1) as training data for artificial intelligence related to microseismic data processing and analysis, 2) predicting the remaining time before rock fractures, and 3) establishing models and assessment methods for the relationship between microseismic characteristics and rock hydraulic properties, which will deepen our understanding of the interaction mechanisms between fluid migration and rock deformation and fracture.
The blast-induced vibration during excavation by drilling and blasting method has an important impact on the surrounding structures. In particular, with the development of tunnel engineering, the impact of blasting vibration on tunnel construction has attracted extensive attention. In this paper, the propagation attenuation characteristics of blast-induced vibration (PPV, peak particle velocity) on different tunnel structures were systematically studied based on the field monitoring data. Initially, the attenuation characteristics of blasting vibration PPV on the lower bench surface, the side wall of the excavated tunnel and the closely spaced adjacent tunnel were investigated. Subsequently, the capacity of several widely utilized empirical prediction equations to estimate the PPV on tunnel structures was examined, along with a comparative analysis of their prediction accuracy. The research findings indicate that it is feasible to predict the PPV on the tunnel structures using empirical equations. The attenuation characteristics of blasting vibration PPV are different in different structures and directions. The prediction accuracy of the empirical equations varies, while the discrepancies are minimal. The principal variation among these equations lies in the site-specific coefficients k, β, λ, highlighting the differential impact of structural and directional considerations on the predictive efficacy. Based on the empirical equation and safe PPV provided by the blasting vibration safe standards on tunnels of China (GB6722-2014), and considering the influence of all structures and directions, it is determined that the safe distance of blasting vibration in the tested tunnel project should be larger than 20.28-18.31 m, 18.31-16.16 m, and 16.16-13.75 m for blasting vibration frequency located in ≤10 Hz, 10-50 Hz, and >50 Hz.
In the 21st century, the surge in natural and human-induced disasters necessitates robust disaster management frameworks. This research addresses a critical gap, exploring dynamics in the successful implementation and performance monitoring of disaster management. Focusing on eleven key elements like Vulnerability and Risk Assessment, Training, Disaster Preparedness, Communication, and Community Resilience, the study utilizes Scopus Database for secondary data, employing Text Mining and MS-Excel for analysis and data management. IBM SPSS (26) and IBM AMOS (20) facilitate Exploratory Factor Analysis (EFA) and Structural Equation Modeling (SEM) for model evaluation.
The research raises questions about crafting a comprehensive, adaptable model, understanding the interplay between vulnerability assessment, training, and disaster preparedness, and integrating effective communication and collaboration. Findings offer actionable insights for policy, practice, and community resilience against disasters. By scrutinizing each factor's role and interactions, the research lays the groundwork for a flexible model. Ultimately, the study aspires to cultivate more resilient communities amid the escalating threats of an unpredictable world, fostering effective navigation and thriving.
In the construction process of soft rock tunnels, determining a reasonable amount of reserved deformation is important to ensure the tunnel stability. This article presents the viscoelastic solution of reserved deformation for deep soft rock tunnels considering the support effects. Based on the analytical solution of the Burgers model, the expression of surrounding rock displacement was derived by considering reserved deformation and optimal reserved deformation. Subsequently, based on numerical simulation experiments, the variation laws and errors of the numerical and analytical solutions of the expressions of reserved deformation and surrounding rock displacement were analyzed. To gain a better understanding of the factors that affect reserved deformation, the factors influencing the expression of optimal reserved deformation were analyzed. The errors in the numerical simulation and analytical solution results were within 10%. This study could provide a theoretical basis for determining the amount of reserved deformation and analyzing the variation law of surrounding rock affected by the amount of reserved deformation.
In recent years, many useful experimental results on the cracking behaviors of fractured rocks have been obtained via uniaxial, biaxial, triaxial, and Split Hopkinson Pressure Bar (SHPB) tests. In this paper, the influence of the inclination angle of flaws, number of flaws, and patterns of cracks on the mechanical properties during the failure process under static loading and dynamic loading conditions is introduced and reviewed. The results show that the presence of cracks can decrease the strengths of precracked specimens, and the inclination angles, numbers, and crack patterns of pre-existing flaws can change the mechanical properties and cracking behaviors of precracked specimens. Under static loading, the closer the inclination angle is to 90°, the greater the strength, the elastic modulus, and the peak strain of the precracked specimen. However, under dynamic loading, the influence of the inclination angle varies, and the strength can increase or decrease, possibly in a V-shaped manner. This change can be determined by multiple factors, such as the loading path, the materials of the precracked specimen, and the number of pre-existing cracks. Under dynamic loading, the precracked specimen usually exhibits an X-shaped conjugated failure. Additionally, some problems in the study of the cracking behaviors of fractured rocks and related future research are described and presented, and corresponding suggestions and solutions are given. In particular, excavation in deep rock engineering, support of the rock surrounding the tunnel, and mining engineering have important scientific and engineering significance.