Abstract The integration of artificial intelligence (AI) into blasting operations has demonstrated significant improvements in precision, safety, and operational efficiency. By leveraging AI algorithms to optimize blast design, monitor field conditions, and analyze fragmentation data, more informed decision-making is achieved. In small-scale mining, safe and efficient blasting practices are critical to protecting workers, maximizing resource extraction, and minimizing environmental impacts. This study first reviews the applications, advantages, and limitations of various AI techniques used in predicting blast performance and environmental effects, with specific attention to the overlooked impact of multicollinearity and the absence of explicit mathematical expressions in many soft computing models. In the experimental section, an imperialist competitive algorithm (ICA)-optimized artificial neural network (ANN) model is developed to predict the percentage of oversized material produced by small-scale blasting. Field data, including blast parameters and rock strength, were collected from a dolomite quarry in Akoko, Edo State, Nigeria. Fragmentation analysis was conducted using WipFrag 4.0 software across 48 blast rounds, using the primary crusher gape as the decision threshold. Input parameter selection was guided by multicollinearity analysis to ensure robust modeling. Evaluation metrics such as root-mean-square error (RMSE), correlation coefficient (R²), mean absolute percentage error (MAPE), variance accounted for (VAF), Nash–Sutcliffe efficiency (NSE), and performance index (PI) confirmed that the ICA-ANN model significantly outperformed the standard ANN. While the conventional ANN model underestimated oversize by 14.7%, the ICA-ANN achieved a lower prediction error of 2.7%. The proposed model offers a practical and accurate tool for predicting oversized fragmentation in small-scale rock engineering scenarios, contributing to improved blasting efficiency and sustainability in the mining sector.

Creep is a time-dependent plastic deformation that occurs in materials subjected to sustained underground stresses. This phenomenon is particularly significant in rocksalt, where understanding its behavior is critical due to its direct impact on mining operations and the long-term stability of underground structures. This study investigates the creep behavior of rocksalt from the Khewra Mine, located in Pakistan, through a combination of laboratory testing and numerical analysis. Triaxial creep tests were conducted on selected samples from the Khewra Salt Mine, and the resulting data were incorporated into a numerical model. Due to limited resources, certain parameters were assumed based on data from the Asse Mine in Germany. A symmetrical single-pillar model was developed in FLAC3D to simulate the mechanical response, using dilatancy and failure strength criteria to evaluate the pillar's utilization factor. The simulation results indicate the early formation of micro-fractures throughout the pillar, while macro-fractures gradually develop along its outer boundary over time. Zones between 3.4 and 4.1 meters from the center show significantly high tensile stresses, suggesting potential instability and risk of failure at the pillar's edges. These findings highlight the need for a more comprehensive investigation of the mechanical properties and creep behavior of Khewra rocksalt to ensure safe and sustainable mining practices.

Heterogeneity of natural rock mass differs from most other engineering materials. Although the heterogeneity, such as macroscopic fracture, potentially contributes to the deformability of rock mass, evidence for macroscopic heterogeneity from field studies has been circumstantial. We present the results of field drilling energy experiment on the rock mass of tuff, limestone and marble types that shows the evidence for the rock mass deformability from macroscopic heterogeneity caused by fracture, reflecting borehole macroscopic heterogeneity associated with drill energy. The experimental results show that the macroscopic heterogeneity is expected to vary linearly with the fracture frequency, and depends on rock types and drilling energy. The contributions of macroscopic heterogeneity for deformability of rock mass have undergone a leading role.

Friction coefficient, as a parameter of mechanical state, plays a crucial role in the shear failure of rocks in the field of Earth sciences. This paper investigates the frictional characteristics and anisotropy of rock by analyzing the coefficient of variation of the friction coefficient (f) and the anisotropy index of rock friction coefficients Af. Rotational friction tests were conducted using cylindrical granite against square samples of granite, sandstone, and andesite in three directions to analyze the relationship between the friction coefficient and various drilling parameters. This study reveals the variations in the friction coefficient and notable changes in the friction coefficient’s anisotropy. The results indicate a correlation between the alignment of turning points during the frictional stage and the rock strength. During the experiment, the friction coefficient undergoes cyclic variation before gradually stabilizing. The anisotropy of rotational friction follows the order: granite > andesite > sandstone, suggesting that the higher rock strength corresponds to greater frictional anisotropy. The rotational friction control coefficient C is derived and linked to the rotational friction stage. The duration of effective contact between rock surfaces and directional cutting efficiency are the primary factors contributing to anisotropy. The results offer practical implications for drilling design and seismic risk assessment in anisotropic rock formations.

The utilization of blasting has been prevalent in mining and civil engineering domains due to its cost-effectiveness and affordability as a method for fracturing rock. The achievement of an ideal blast results in the most effective fragmentation while ensuring safety, cost-effectiveness, and environmental sustainability. In developing blast efficiency model, this study considered uniaxial compressive strength (UCS), spacing, hole depth, stemming length, point load index, powder factor, charge weight and burden. The model was trained by artificial neural network (ANN) and linear multivariate regression (LMVR) using 85 production datasets. After training four-layer ANN architecture 8-4-1 was found to be optimum. The prediction accurateness of two developed models was analysed using mean square error (MSE), performance index (PI), variance accounted for (VAF), root mean square error (RMSE), and co-efficient of determination (R2). The obtained values of performance parameters reveals ANN model to be more accurate as compared to the LMVR model. The ANN and LMVR model have R2 value of 90.9% and 56.3%. The optimized model was employed to achieve the optimal blast design for high strength granite to enhance blast efficiency. The test data result was utilized to optimize the blast parameters, including spacing, stemming length, burden, charge length, and charge. The values chosen for these parameters were 1.8 m, 1.8 m, 1.5 m, 157.17 kg, and 1.35 kg/m3, respectively, based on the optimum model.

To study the variations in the damping ratio of rock at different frequencies, an external excitation test and a cyclic loading test were designed, and the relationship between the damping ratio of rock and the frequency under conditions of low and high frequency was determined. The damping mechanism was analyzed from the viewpoints of structure and lithology. The results show that: (1) On the basis of the method used for calculating the damping ratio of soil, a new method for calculating the damping ratio of rock was proposed, which is more suitable for the stress–strain curve of rock. (2) The damping ratio of rock increased with frequency at low frequency but decreased at high frequency, which indicated that there is a peak value in the curve of changes in the damping ratio with frequency. (3) The damping ratio of sandstone was greater than that of granite, which was explained from the viewpoint of the structure and the formation conditions of the rocks. From the viewpoint of the source of viscosity, it was explained why the damping ratio first increased and then decreased with an increase in frequency.

In this paper, 114 uniaxial compressive strength tests were carried out on specimens of veined gneiss with diameters ranging from 14 mm to 100 mm. The main objective of the study was to investigate the influence of the specimen size on the strength behavior of this metamorphic, heterogeneous rock. This size effect results in an increase in strength from small 14-mm diameter specimens up to 50-mm diameter specimens. Thereafter, a mild decrease in results is observed from 50-mm to 100-mm diameter specimens, in line with traditionally considered size-effect approaches. The findings generally agree with previous studies on size effects in sedimentary and igneous rocks, suggesting that metamorphic rocks may also tend to follow the Unified Size-Effect Law (USEL), accounting for general and reverse size-effects in strength. Nevertheless, some variability observed in the results, mainly attributed to inherent heterogeneity of the studied rock could influence how clearly this ascending-descending trend is captured by the model.

As multifunctional structures, deep rock underground structures are built all over the world. Their lifespan is generally expected to exceed a hundred years. However, they are inexorable to rock creep which controls their lasting safety and stability. This article describes the strong factors affecting rock creep and the lasting stability of deep rock engineering, based on pertinent research works. It shows that temperature, water content, hydraulic pressure, stress level, and damage are major factors that significantly affect the creep behavior of host rocks of deep underground structures. Overall, such factors govern the creep life of rocks. Specifically, the increase in these factors causes an increase in the creep strain rate, a shortening of the steady creep phase, an acceleration of the onset of tertiary creep, and thus a shortening of the time-to-failure of rocks. This is due in particular to the fact that fluctuations in these factors disintegrate the internal structure of the rocks and make them increasingly weakened. As a result, the mechanical properties of the rocks are altered and the creep process proceeds at a higher rate than expected. Hence, the creep life of surrounding rocks is reduced, which significantly limits the prolonged stability of underground structures. Appropriate countermeasures, such as long-term monitoring, are strongly recommended.

This research aims to optimize ground support systems for underground tunnels in geologically challenging environments, specifically addressing the reduction of Fall of Ground (FOG) incidents in a gold mine in Mashava, Zimbabwe. The study integrates advanced detection and classification methodologies to enhance tunnel stability and safety. Tunnel Reflection Tomography (TRT) was employed to identify unfavorable geological structures ahead of excavation, while core logging at 20 locations on level 7 provided rock mass quality assessments using three classification systems: Bieniawski’s Rock Mass Rating (RMR), Laubscher’s Mining Rock Mass Rating (MRMR), and Barton’s Q-system. The results consistently indicated poor rock mass quality, informing the design and refinement of a robust ground support system. Fallout height data from past FOG incidents and probabilistic key block analysis using J-Block software further validated the support system's effectiveness. The findings significantly reduce collapse risks and downtime, enhancing operational safety and efficiency. This research contributes to developing practical strategies and tools for improving tunnel stability in complex geological settings, offering valuable insights for future advancements in mining support technologies. The study's necessity stems from the industry's growing demand for innovative solutions to enhance tunnel stability in adverse geological settings, particularly in regions with limited access to advanced technologies or methodologies.

This paper proposes a novel approach to rock mass characterization by adapting the coefficient of uniformity (Cu) and coefficient of curvature (Cc) from soil mechanics, redefining their mathematical formulations to align with RQD-based block size measurements. Specifically, Cu and Cc are calculated using D10, D30, and D60, derived from cumulative RQD data, while accounting for the increasing scale of block size distributions in rock masses. An illustrative case study demonstrates the application of this method, yielding insights into block size variability and heterogeneity in rock masses. The proposed coefficients enrich rock mass classification, offering enhanced quantitative tools for engineering and geological analyses.