Abstract In civil and mining engineering applications, predicting overbreak is crucial to optimise excavation processes and ensure safety. This study boards on a comprehensive exploration of overbreak prediction-based 3D photogrammetry utilising advanced analytical methods such as principal component analysis (PCA), maximum relevance minimum redundancy (mRMR), and machine learning (ML) regression models, enhanced by generative adversarial networks (GAN) for data augmentation. Initially, correlations and multicollinearity amongst geological and operational variables were investigated. Ten geological parameters from tunnel face mapping were analysed to reveal the causative factor of the blasting mechanism between the rock mass’s complex geological parameters and overbreak. Initially, PCA and mRMR facilitated feature extraction and selection, revealing significant variables influencing overbreak. After the reduction of the dimensionality of the input parameter, the research compares the result of the target and comparative models. Moreover, to address the limited availability of tunnel observations for machine learning, the original 210 datasets of input and target parameters were expanded to 1000 datasets using the GAN method. Subsequently, ML regression models, enriched by GAN-augmented datasets, were employed to unravel the impacts of the selected features on overbreak prediction. Augmenting the dataset fivefold via GANs markedly improved ML regression model efficacy, especially for the ANN model, which exhibited a substantial $${R}^{2}$$ R 2 increase from 29 to 96.4% and a 68% reduction in MSE to 0.402E-3 when compared to the original dataset. This robust methodology underscores the relevance of comprehensive feature analysis and data augmentation in improving overbreak prediction in excavation projects, thereby contributing substantively to tunnel excavation.
This work investigates the application of artificial neural network (ANN)-based regression models to predict the static and dynamic characteristics of GaN impact avalanche transit time (IMPATT) sources in the terahertz (THz) frequency regime. A comprehensive dataset, derived from self-consistent quantum drift-diffusion (SCQDD) simulations of GaN IMPATT structures designed for a wide frequency range from the microwave frequency bands, up to 5 THz, is used to train the ANN models. The models effectively capture the impact of variations in structural, doping, and biasing parameters on device performance. The proposed ANN approach significantly reduces computational time for predicting breakdown characteristics, power output, and conversion efficiency properties of IMPATT sources, achieving similar accuracy to traditional SCQDD simulations while requiring only 7.8–20.1% of the computational time. Mean square errors are observed to be on the order of <inline-formula> <tex-math notation="LaTeX">$10^{-4}$ </tex-math></inline-formula>–<inline-formula> <tex-math notation="LaTeX">$10^{-6}$ </tex-math></inline-formula>, demonstrating the models’ high accuracy. Experimental validation shows strong agreement in terms of breakdown voltage, power output, and efficiency, supporting the potential of machine learning to streamline the design and optimization of high-frequency semiconductor devices.
Cave mines operating at greater depths are faced with higher draw column heights, typically ranging from several hundred metres to over one kilometre. This results in significantly higher cave stress on the production level, making reliable stress estimation critical for assessing long-term stability. The current approach to estimating cave stresses in the draw column relies on Janssen's equation, developed initially using the Method of Differential Slices (MDS) and based on laboratory observations of corn and bulk solids in storage silos. This article first reviews the MDS and the assumptions used to derive Janssen's equation. The article also discusses how the limitations of the analogues (e.g. corn material and full-to-empty silo condition) used to develop the equation do not represent conditions equivalent to those observed in cave mining (e.g. fragmented rock blocks undergoing fragmentation and no-column to full-column condition as cave propagates). These mechanistic differences may lead to erroneous estimations of cave stresses. While Janssen's equation is a valuable initial tool for estimating cave stresses, practitioners must carefully assess its assumptions and limitations before applying it to engineering designs.
Extension of ore pass length has become increasingly critical for optimising energy-efficient underground mining operations. Long and ultra-long ore passes, spanning from 300 to 700 m, can significantly improve the functionality and viability of underground mass mining operations though suboptimal performance has an extremely adverse impact on production. The public domain lacks substantial information regarding the primary engineering, geological, and geotechnical risks and challenges associated with the design, implementation, operation, and maintenance of such long ore passes. Therefore, the aggregation of past experiences and the insights of experts assume paramount significance. An innovative methodology is introduced to address this evident data deficiency and to establish comprehensive guidelines for the resilient design of such lengthy ore passes — combining gap analysis with expert elicitation techniques. This equips design engineers with the necessary tools to formulate and adapt strategies for assessing the numerous challenges and uncertainties that invariably accompany their projects. Expert elicitation techniques are summarised, and a gap analysis is conducted with subject matter experts, from various countries, collating their extensive ore pass design experience, to create a comprehensive list of effective parameters and key risks that must be considered. Quantitative analysis of the survey results enabled the identification and ranking of the numerous factors affecting the design, operation, and maintenance of long and ultra-long ore passes and highlights the complex technical challenges (substantial damage from rock particle impact, increased dynamic mining stresses leading to failure, air-blasts and back blasts, dust, preferential flow, turbulent and dynamic material flow) that are uncommon in shorter ore passes. Additionally, increasing length heightens the probability of intersecting weak rock or discontinuities, leading to a higher risk of structural failure and instabilities. Faulting, folding, and large-scale structures are also critical geological factors to be considered in the design of such structures. The key geotechnical factor is also the rock type surrounding the pass. Experts highlighted the lack of clear guidelines for decision-making, resilient design, and construction so this work suggests future investigations to determine the complex interaction between the effective parameters, using approaches like the rock engineering system, discovery of cascading hazards, and optimal controls.
Mining machinery constitutes essential assets for a mining corporation. Due to economies of scale, technological innovations and stringent quality and safety requirements, the size, complexity, functionality and diversity of industrial machinery have expanded markedly over the last two decades. This growth has increased sensitivity to machine availability and reliability. Mining operations install comprehensive maintenance units tasked with inspection, repair, replacement and inventory management for the machines in use. Leveraging the proliferation of sensor technologies integrated within the machines, maintenance units obtain rich data streams synchronously disclosing machine health and performance metrics, which enables a predictive maintenance programme. This programme performs prognostic detections of anomalies and permits timely intervention to avert catastrophic breakdowns. However, such sensor-driven predictive maintenance scheme for machinery in the mining sector is limited. The present paper utilises the Gaussian process, a powerful predictive modelling technique, to show its potential in addressing this challenge. The efficacy of this approach is validated through three case studies. Each case study is equipped with sensor data and represents a typical predictive maintenance task for mining assets. The developed Gaussian process models successfully capture meaningful temporal patterns in sensor data and generate credible predictions across all three tasks: temporal prediction of sensor data degradation trends, remaining useful lifespan prediction and simultaneous monitoring and prediction of multiple machine conditions. Furthermore, the models offer uncertainty estimates to the prediction outcomes, potentially facilitating maintenance decision-making process.
Silvânia Alves Braga de Castro, André Carlos Silva
Abstract The modeling of mineral deposits has been improved over the years with the incorporation of mineralogical and metallurgical information obtained from drilling samples that make up the pillars for the construction of resource models. However, sampling data is being made available in large quantities, causing current databases to grow exponentially. The use of machine learning (ML) algorithms has been applied to deal with multidimensional data problems. Principal component analysis (PCA) is a multivariate analysis (MA) technique whose aim is to reduce the dimension of multivariate data. Studies show that results obtained with the reduction of variables were satisfactory in different areas of activity. The purpose of this article is to test variable selection criteria using PCA for geometallurgical data and to check the feasibility of the technique for simplifying variable types and defining typological domains.
The purpose of this study is to establish the effect of training and development on employee attraction and retention in the mining sector in Zimbabwe. The mining industry in Zimbabwe has been extensively affected by the loss of key personnel in key areas such as engineering, metallurgy and geology among others. The loss of such vital employees in the mining sector has had a negative impact on output and consequently loss of the much-needed revenue to the Zimbabwean economy. It is against this background that there is need to establish the establish the effect of training and development on employee attraction and retention in the mining sector. The quantitative method research was employed in this study. An interview guide was used to collect data during consultative meetings and semi-structured interview platforms. The purposive sampling technique was employed in this study. The main findings were poor employee motivation due to the failure to train and develop personnel but poor leadership style being employed, lack of employee ascension to higher levels within the organisation. This study recommends that managers in the Zimbabwe mining sector should strive to train their employees so that their skills remain current as well as developing employees in a bid to expose them to perform additional duties and assume positions of importance in the organisational hierarchy.
Introduction. The exposure to industrial aerosols triggers the response of the adaptive and innate mucosal immunity in the upper airways. Objective: To analyze the impact of work-related risk factors on the development of local mucosal immunity in workers engaged in extraction of vanadium-bearing iron ore, and cast iron and steel production. Materials and methods. We examined one thousand five hundred forty seven male workers of two mining and metallurgical industries. The first cohort included 788 vanadium-bearing iron ore miners and the second cohort comprised 719 cast iron and steel production workers, both standardized by age and years of employment. Occupational risk factors identified in both cohorts included the exposure to fibrous aerosols and aliphatic hydrocarbons, and poor microclimate (high or low air temperature) at workplaces. The workers of the second cohort were also exposed to manganese compounds, vanadium (V) oxide, chromium, nickel, and iron compounds. The control group consisted of 40 engineering and technical personnel. Results. A significant increase in secretory immunoglobulin A (sIgA) was detected in the miners exposed to aliphatic hydrocarbons and low air temperature. In the ferrous metallurgy workers, the exposure to low air temperature, crystalline silicon, and aliphatic hydrocarbons caused a significant decrease in the level of sIgA while the exposure to manganese oxides induced a decrease in the bactericidal function of neutrophils. Limitations. The main limitations of the research were related to the selected criterion of inclusion in the merged occupational cohorts with account for exposure to adverse microclimate parameters, silicon-containing aerosols, aliphatic hydrocarbons, and manganese compounds. In view of the multiplicity of occupational risk factors in the industry, it is important to conduct additional studies of a larger sample for qualitative and quantitative presentation of convincing evidence of health effects of other factors of the work environment. Conclusions: We established a multidirectional response of the mucosal immunity to production factors in the examined workers. A combined exposure to chemical and physical occupational factors has a stronger health effect than a single one. Differences in the level of sIgA in workers exposed to different occupational hazards prove the advisability of an in-depth immunological examination combined with an assessment of the functional status as indicators of occupational adaptation.
Al–50Si alloys were prepared by powder extrusion and characterized for electronic packaging. The optimization of powder size, extrusion temperature, and heat treatment parameters was performed to enhance the microstructure and thermo-physical properties. The alloy exhibits a high relative density >99 %, a low coefficient of thermal expansion (CTE) < 10 × 10−6/K, and a good thermal conductivity (TC) ∼117 Wm−1K−1 achieved by employing a large size powder and high extrusion temperature during the extrusion process. Subsequent heat treatment of the optimized alloy at 550 °C for various time reveals a fluctuating increasing trend in TC during the heat treatment process. The TC values exhibit periodic fluctuations as they alternate between increments and decrements, primarily resulting from the recrystallization and secondary recrystallization of Al grains during heat treatment process. Notably, the maximum TC value (∼159.1 Wm−1K−1) at room temperature is obtained after heating the alloy to 550 °C for 26 h. Compared to the as-extruded alloy, the TC of heat-treated alloy increases by approximately 36 %, which can be attributed to the elimination of eutectic Si and growth of Si and Al grains within the alloy. The study may shed light on the mechanism underlying the improvement in thermal conductivity of Al–50Si alloy by microstructural evolution.
Super austenitic stainless steel (SASS) was prepared by non-consumable vacuum arc melting for the first time. The effects of rare earth (RE) elements on its solidification microstructure and segregation behavior were investigated. The σ phase is the main precipitation phase in SASS. The addition of RE elements can refine the solidification microstructure and the dendrite spacing. The addition of RE elements reduced the secondary dendrite spacing at top (S1) by 5.22 μm. The elements as Cr, Mn, and Mo have positive segregation, and elements as Ni and Fe have negative segregation. The addition of RE elements has the trend of reducing element segregation, thereby inhibiting the σ phase precipitation. And the addition of RE reduces the hardness of the secondary phase.