Search Documents

By Paul Culvenor, Brad Gyngell

Large language models (LLMs) have generated a lot of hype since ChatGPT was released in early 2023. In essence, they allow people to interact with computer systems through natural language and have the ability to generate highly complex text, images and videos (Patil and Gudivada, 2024). It is clear that this technology has significant potential, however most mining companies have not yet found practical applications for it within their operations. In this paper, we present a range of such applications along with the tactical considerations associated with developing and implementing them. We have identified use cases across a variety of operational and functional areas within the mining industry and evaluated them based on their potential business value and ease of implementation. Firstly, we provide an overview of how LLMs work and a review of how LLMs are being applied in other industries to provide best practice inspiration for mining. Next, we present a list of possible applications in mining and a critical assessment of each use case. This section also includes a technical deep dive into the different methodologies for developing the technologies as well as an analysis of barriers to adoption within mining organizations. Finally, we share a discussion of the potential path forward for LLMs in mining and the impact they could have on the industry. We analyze the potential differences between early adopters and laggards in the artificial intelligence (AI) space. This research draws on interviews and surveys with artificial intelligence experts as well as mining subject matter experts to connect cutting edge thought leadership with the specific problems faced by our industry.

Feb 1, 2025

By Ron Derrick

SX operators have conducted extensive shut-downs and repairs over the years to mitigate solution leaks from failed stainless steel false floors and walls in rectangular mixersettler mix boxes. Hydrodynamic modeling using first principles and constitutive equations of fluid mechanics can inform an efficient structural redesign sufficient to eliminate the plate failures. Updated mix boxes have been performing without failure for over a decade. Given the extensive construction of the original Holmes and Narver mixer-settler design throughout the world that includes stainless steel lined rectangular primary and auxiliary mix boxes, SX operators may benefit from the approach, eliminating costly shutdowns, leaks to containment, and hazardous repairs.

Feb 1, 2024

By Taekhee Lee, Steven Mischler, Shawn Vanderslice

Diesel-powered equipment is widely used in the underground mining industry and their popularity results from properties including efficiency, versatility, reliability, and durability. In the U.S. approximately 7,700 diesel engines were used in 177 underground metal and nonmetal mines as of 2005 [MSHA 2005], and these numbers have likely increased since that time. Diesel engines have been shown to be a major contributor to submicron carbonaceous, respirable, and total particulate mass in the air of underground metal mines [Zielinska et al. 2002, McDonald et al. 2003], and their extensive use results in approximately 13,000 underground metal/nonmetal (M/NM) miners (MSHA 2005) in the U.S. being potentially exposed to aerosols and gases emitted by diesel engines (MSHA 2001, MSHA 2006). Exposure to diesel exhaust has been linked to adverse health outcomes including cancer, cardiovascular, and respiratory diseases (Attfield et al. 2012, Silverman et al. 2012), and in 2012 diesel exhaust was categorized by the International Agency for Research on Cancer (IARC) as a Group 1 human carcinogen (IARC 2012). Exposure to diesel particulate matter (DPM) is especially concerning for underground miners since underground mine environments have been shown to have some of the highest levels of diesel exhaust in the U.S. (EPA 2002, MSHA 2001, MSHA 2006, Pronk et al. 2009). Due to the potential for elevated DPM concentrations in mines, the Mine Safety and Health Administration (MSHA) promulgated a rule to limit exposures of metal/ nonmetal underground miners to DPM to an eight-hour time-weighted average (TWA) of 160 μg/m3 total carbon (TC) (MSHA 2001, MSHA 2006, MSHA 2008). Since this rule went into effect, DPM exposures have been reduced, but are still elevated when compared to other occupations (Pronk et al. 2009, Noll et al. 2015). MSHA compliance data between 2005 to the present show that underground blasters represent 21% of all DPM overexposures in M/NM mines and are one of the highest exposed professions in mining often resulting from low ventilation in the area where blasters are working. Because mines have difficulty controlling DPM in these low ventilation areas, additional control technologies may be needed to reduce exposures. Administrative controls, where miners work on off schedules or upstream of diesel vehicles to avoid the exposures to DPM (Noll et al. 2015) is one possibility, but these types of solutions are not always feasible or practical. A canopy air curtain is another potential control technology to help reduce exposures of blasters to DPM. Listak and Beck (2012) showed that this control technology reduced respirable dust concentration under a roof bolter’s canopy by 67%–75% and recommended air velocities greater than 0.5 m/s for dust reductions of greater than 50%. Additional work showed that a canopy air curtain could be designed for a shuttle car, and some initial testing by the National Institute for Occupational Safety and Health (NIOSH) showed reductions of respirable mine dust between 66% to 70%. As seen in Figure 1, the canopy air curtain delivers clean air over the operator’s breathing zone. A fan draws in air through a filter to capture the dust and then supplies clean air beneath the canopy where a miner is working. The use of the canopy air curtain to reduce exposures to diesel particulate matter was first discussed by Noll et al. (2020). In this study the diesel canopy air curtain (DCAC) reduced the DPM concentrations under the canopy by up to 90%. For this research the DCAC was designed to attach to the basket cover of an ammonium nitrate fuel oil ( ANFO) loader (Figure 2) and provide clean air blowing over the miners as they work in the basket. The initial tests used clean air drawn from the mine’s intake and did not try to filter the DPM from the air. Filtering DPM has extra challenges when compared to filtering mine dust particles. The particles of DPM are smaller (submicron and nanometer) than dust particles (greater than 1 micron); therefore, the filtration system must be adjusted to capture submicron particles. A MERV 13 filter was used in previous canopy air curtain research on mine dust control, but this filter is only designed to capture 50%–75% of submicron particles, and this capture efficiency is too low for removing DPM, so a higher efficiency filter is needed. Higher efficiency filters increase the pressure across the filter media which results in decreased airflow or leaks around the filter and reduces the effectiveness of the control for protecting miners from DPM. The optimal filter needs to capture DPM particles at a high efficiency while still allowing the needed airflows to prevent contaminated air from entering the miner’s breathing zone. Listak and Beck (2012) recommended velocities greater than 0.5 m/s for dust reductions of greater than 50%. However, airflows too high have been shown to reduce miners’ thermal comfort; Roghanchi et al. (2016) suggest the optimal velocity for thermal comfort is between 1–2 m/s. Thus, airflow over the miner should be limited to the range of 0.5 to 2.0 m/s. This current study presents the results from research evaluating the reduction of DPM concentrations, under the DCAC, when using a higher efficiency filter (MERV 16) to remove DPM from the DCAC airstream.

Feb 1, 2024

By Wei Zhang, Jinhong Zhang

An atomic force microscopy (AFM) image analysis has been applied to study in situ the adsorption of hydroxamic acid collector, i.e., octanohydroxamic acid (OHA), on malachite in aqueous solutions. AFM images show that hydroxamic acid collector adsorbs strongly on malachite mainly in the form of insoluble copper hydroxamate complex. Increasing the collectors’ concentration and the adsorption time both increase the adsorption of hydroxamic collectors on malachite. Results from the attenuated total reflectance–Fourier transform infrared spectrometry (ATR-FTIR) also show that the collector adsorbs strongly onto malachite, with strong absorbance spectra being detected, and the ATR-FTIR results confirm those as obtained by AFM. This specific adsorption mechanism explains that a high selectivity with a moderate collectivity will be achieved with a hydroxamic acid collector for the flotation of malachite. The findings of present study also show that AFM image analysis is a powerful tool for the study of the hydroxamic acid collectors’ adsorption on malachite surface and it can help with the development of novel collectors for malachite flotation.

Feb 1, 2025

By Morgan M. Sears, Mark Morris, Joseph Bright

In an effort to advance the science underlying modern coal pillar stability analysis, researchers at the National Institute for Occupational Safety and Health are currently involved in research aimed at better understanding the impact of an in-seam rock parting on the strength of coal pillars. The purpose of this study is to determine a suitable virtual mining height that could be applied using current pillar stability analysis tools. To accomplish this, the boundary element model LaModel was used to back analyze data collected on pillar performance in a room-and-pillar panel at the Maple Eagle Mine located in Southern West Virginia. In a previous work, data collected from borehole pressure cells (BPCs) and extensometers were taken from three instrumentation sites. Data collected from the back bleeders were used to measure the rear abutment stresses, and data collected from two instrumentation sites in the wraparound bleeder were used to measure the front and side abutment stresses as well as the peak strength and performance of the slabbed leave pillar. The utilization of two nearly identical instrumentation sites in the wrap-around bleeder provided much needed repeatability of the obtained measurements. In this study, the data collected from BPCs at the three instrumentation sites was calibrated to match the Bieniawski pillar stress gradient. To model the measured pillar behavior, the LaModel program was selected due to its capability of being directly comparable to the Analysis of Retreat Mining Pillar Stability (ARMPS) and Analysis of Coal Pillar Stability (ACPS) programs. The model was then calibrated to match the measured abutment extent and abutment stress. Finally, the model was validated by reducing the modeled mining height until the yielding of the slabbed leave pillars in the model matched what was measured in the field. The final calibrated mining heights show that a reduction of the shale parting thickness, not including any clay layers, of 52% is applicable. This research study provides the first known measurement of the ARMPS/ACPS “50% Rule” and its applicability to this panel of the Maple Eagle Mine. This finding provides a proof of concept and could have significant implications for future research.

Feb 1, 2024

By Kadri Dagdelen, Steven Hoerger

For gold mines, orebody uncertainty is one of the leading causes of differences between planned and actual production. Geostatistical conditional simulations create multiple equally probable orebody block model realizations which are conditional to the current drilling information and demonstrate the sampled grade distributions and spatial statistics. These simulated block models are key inputs for a stochastic evaluation to show the likely range of grades and cash flows to be delivered by a mine plan. The stochastic evaluation outputs can be used to compare different mine plans in terms of expected values and risks to planned grades, production, costs, Net Present Value (NPV) and other plan metrics. For the McLaughlin gold mine, risk profiles are demonstrated to show how different mine, cut-off and stockpile strategies can reduce risk and improve expected value. The strategies considered were effective in improving expected NPV and reducing or eliminating tonnage uncertainty, but the strategies had little impact on reducing the uncertainty of NPV’s or mill grades. The stochastic evaluation process is also used to compare the risk impact of orebody uncertainty against the risk of not achieving planned mining tonnages or vertical advance rates. Risks for plans created with and without stochastic mine plan optimization are also compared.

Feb 1, 2025

By Ashish Ranjan Kumar, Barbara Arnold, Luis Sanchez Gonzalez

Mining operations adopt a variety of measures to combat dust underground. These include ventilation systems, water sprays, physical barriers, and personal protective equipment (PPE). Respirators are a class of PPE that can provide clean particulate- free air to the users. Powered Air-Purifying Respirators (PAPRs), used commonly in medical and other sectors, are not prevalent in the mining industry. PAPRs use P100 filters that have 99.97% dust capture efficiency. We present our results from computational fluid dynamics (CFD) simulations performed to understand the impact of a PAPR on airflow and dust particle concentration in the vicinity of a miner. These results show that donning PAPRs can lower the miners’ exposure to respirable coal dust in their workplace.

Feb 1, 2025

By Paul Culvenor, Brad Gyngell

Ensuring effective management of contractual processes is essential for maintaining profitability and operational efficiency in mining. However, due to limited capacity and resources, sites often struggle to manage these processes effectively, leading to oversights and financial losses. Recent advancements in Artificial Intelligence (AI) offer promising solutions to these challenges. Large Language Models (LLMs), like those powering ChatGPT, now enable machines to understand unstructured data like contracts. These can therefore be applied to address these challenges by taking some of the heavy lifting off of humans. In this paper, we analyze a real-world case study of the application of LLM tools for preventing a $400k contractual issue on an underground gold mine in Western Australia. We provide a gap analysis of the failure modes in existing processes that led to the issue. We then describe the application of LLM tools to flag it early and facilitate a collaborative solution between the operator and the supplier. This includes a comparative analysis of base case vs LLM case to evaluate the impact on project cost and time. Finally, we discuss how the integration of AI can foster improved relationships between clients and contractors across a broad range of potential contractual applications, allowing the time required for collaborative and proactive problem solving.

Feb 1, 2025

By Trevor Riters

Advancements in Emerson’s instrumentation technology have brought value and efficiencies to the mining industry. Some think of instrumentation as basic sensors and valves, but with our solutions, we equip operators with real time, accurate, and reliable data that they can use to operate more effectively. Working with Caltrol, an Emerson Impact Partner, we successfully engineered wireless skids for a leach pad to provide precise measurement and control of raffinate solution to many of the large mine sites in Arizona.

Feb 1, 2025

By CASSANDRA L. HOEBBEL, Jennica L. Bellanca

High-fidelity, immersive training is known for its learning and logistical benefits. While other industries have used virtual reality (VR) for decades, the same uptake has not been seen in mining. NIOSH recently developed an adaptable, scalable VR training platform, VR Mine Rescue Training (VR-MRT), which has attracted significant industry interest. NIOSH is using VR-MRT to understand the barriers to adoption and implementation of VR. As a part of a larger effort to assess the effectiveness and implementation of VR-MRT, researchers have conducted pre-implementation interviews. In this paper, the authors use feedback from individuals at various implementation levels to assess the acceptability and appropriateness of VR-MRT and identify potential implementation barriers for VR more generally. Researchers also describe ongoing efforts to overcome these barriers as NIOSH works to position VR-MRT as a supplemental resource more generally for mine safety training.

Feb 1, 2025

By Steven Hoerger

Mixed integer linear programming (MILP) production scheduling models can be used to evaluate if tonnage improvement projects will deliver value over all time periods and whether new bottlenecks will be created. These MILP models can evaluate the interconnected effects of mine and process capacities, mining locations, cutoff grades, stockpiles, and orebody grade/tonnage distributions. A case study compares potential value creation from a mine capacity increase, a mill capacity increase, or a simultaneous increase in all capacities. For perspective, project valuations for capacity increases are compared against valuations for cost reduction projects, mine planning improvements such as phase design, dynamic cutoff grades and stockpiling, and the impact of geostatistics improvements in the areas of block model accuracy and ore control selectivity.

Feb 1, 2024

By Lauren M. Roberts, Ralph R. Sacrison

Pipeline or borehole free-fall transfer of material has long been done in support of underground mining. This paper addresses some characteristics and design elements in selecting systems suitable to the transferred media and the mine requirements. Though aspects of overall systems are discussed, principal attention is directed to the slickline/dropline/transfer line and the discharge diverter/rockbox/energy dissipator/boot. These terms are common to these systems, often used interchangeably, and will be used as appropriate to the material, equipment and construction. Following several design sections, fabrication and construction, and system operating and maintenance procedures are discussed.

Feb 1, 2025

By Karl Ingmarsson

Larger mines spend millions of dollars annually on rock drilling tools, but often purchase based on historic consumption. The results vary from excess inventory to acute tools shortages. These lead to emergency sourcing, sometimes mixing products that don’t perform optimally. Boart Longyear analyzed the usage pattern of 96 thousand drill bits at thirteen different underground mining contracts, showing very high variability. The monthly standard deviation on a product level was 42%, with the highest for development and low volume bits. A new rule of thumb is suggested to carry only one month of safety stock for high volume bits, but increase to three months for low volume bits. This balance will reduce the risk of outages with less inventory. The accuracy can be improved by considering the specific conditions at each mine and reclassifying individual bits for a different safety stock level. Root cause analysis and collaborative forecasting between mines and suppliers can lead to further optimization of availability and inventory levels.

Feb 1, 2024

By Alexander Darío Huamán Ccorahua, Cayo Fernando Soto Buendía, Jhonatan Raphael Rojas Ventura

Lithium is a top-quality mineral in the energy market, with growing demand. It has many applications in medical, nuclear, and energy industries. The purpose of this article is to quantify and analyze the economic potential and projected global demand for lithium annually. It aims to determine Peru’s (specifically Puno) positioning in the global context in 2025 and 2030. The article also seeks to identify the main regulatory, environmental, and social challenges to sustainably exploit lithium in Peru. The study employs applied research (mixed approach), descriptive-correlational scope, and observational, crosssectional design. The methodology demonstrates the use of statistical techniques to model and make predictions about this energy-transition metal. Academic sources were reviewed to enable a comparative approach and projection into the future of lithium for development in the mining industry. In the last 10 years, lithium demand has grown, noting a 600% increase in the economy and projected annual growth of +26%. Exponential growth in resources is projected, where econometric, R-multivariable and R-linear models estimate that Peru could supply 1.5% in 2025 and 3% in 2030 of global lithium. Estimated growth of 5–15% in socio-environmental conflicts is projected with the start of lithium exploitation (Peru – Puno). The global potential of lithium demonstrates exponential growth. Lithium reserves in Puno - Peru would rank 13th between 2025 and 2030. It is necessary to establish a clear regulatory framework to avoid excessive increase in socio-environmental conflicts.

Feb 1, 2024

By Virginia T. McLemore

The Black Hawk district in New Mexico hosts an unusual type of deposit: arsenide five-element veins. These deposits are Ag-Co-Ni-Bi-As-bearing carbonate veins with local concentrations of U, Pb, Zn, Sb, and other elements. They are high-grade silver deposits (1000s g/t Ag), but low tonnage (<1 Mt) and difficult to find. By 1881, claims were staked and a town developed. It is estimated that >$1,500,000 was produced in 1883–1893, when Ag prices dropped due to the 1893 Ag panic. Solid Silver Mining Co. produced $600,000 from the Black Hawk mine; one car load contained $28,000 worth of silver! The town of Black Hawk grew to 125 population by November 1883. By the end of 1893, the town was vacant; nothing remains. The district was idle until 1916, and the mines operated sporadically since because of lack of available capital, water issues, and difficulty in finding ore shoots. The area is a favorite for mineral collectors. Tungsten was found in the district in 1935 in quartz veins associated with pegmatites. Metal production from 1881–1960 is estimated as 3,000 lbs Cu, 1,000 oz Au, 1,286,000 oz Ag, and 4,000 lbs Pb. In addition, 10,542 short tons of 2.7–71% WO ore and 615 short tons of fluorspar ore have been produced from the district.

Feb 1, 2025

By Sakshi Hazuria Anderson, Angela Binder, Oscar Jaime Restrepo Baena, Simit Raval, Sandra Nowosad

As the mining industry faces times of change, new challenges arise to ensure raw material supply for the younger and future generations. Different scenarios are currently shaping the way we mine and teach mining engineering. Led by an increasing demand for raw materials, net zero requirements for improving long-term operation performance, technological advancements such as automation and digitalization, safety improvements, environmental considerations and a need for social acceptance, mining is pursuing to change and adapt to these requirements at a faster pace. Such changing times raise new concerns, one of the most relevant is the lower number of students interested or enrolling in mining engineering and related fields leaving mining engineering as one of the less preferred career options between the younger generations. Nonetheless, it is essential to continue addressing and supplying the skill sets that are suited to the contemporary and future mining industry. To this end, globally, academia is currently undergoing several initiatives such as curricula updates and adaptation, up skilling, improving teaching practices and techniques, including e-learning techniques, enhancing industry-academia and inter-university collaboration, and much more. In countries like Australia, where mining plays a crucial role in the economy, the need for curriculum updates is more pressing than ever. As the mining industry evolves with new technologies and sustainable practices, there is a growing demand for a workforce skilled in these modern approaches. Recognizing this necessity, universities such as the University of New South Wales and Curtin University have taken significant steps to revamp their educational programs. By updating their academic offerings, both universities aim to equip graduates with the necessary skills to drive innovation and sustainability in mining, supporting Australia’s development as a leader in this critical sector. Moreover, the selection of topics that drive curricula update and the focus of the research institutions in mining engineering must extend beyond mere technological and technical aspects to include social and ethical dimensions. In this context, the Universidad Nacional de Colombia, in association with the Colorado School of Mines, has introduced the topic of Humanitarian Engineering (HE) in 2020. HE is a socio-technical approach that focuses on developing engineering solutions that promote the sustainable development of communities addressing their basic needs and aiming to improve their quality of life (10, 18). By focusing on sustainable development, community engagement, and equitable resource distribution, HE helps the industry build positive relationships with stakeholders, reduce conflicts, and foster social license to operate. As the mining industry seeks sustainable and socially responsible practices, future engineers require training in this area to understand the broader impacts of their work, fostering a mindset that prioritizes community well-being and environmental stewardship alongside technical proficiency.

Feb 1, 2025

By R. E. McIvor, Brian Cornish, J. A. Finch, Yue Tan, Claude Gagnon

Fred C. Bond is recognized throughout the mineral processing world as the father of comminution equipment applied science and engineering. The Bond Work Index became a universal standard, and is the most widely used measurement tool for comminution energy consumption. This biography is the story of his lifetime of study, work experiences, experimentation, analyses and findings. His numerous published writings are reviewed. His legacy is one of comminution process engineering that will be used in perpetuity.

Feb 1, 2024

By Roderick Eggert, Dipesh Dipu

We look at the empirical evidence of coal block auctions in India to understand how competitive intensity affects the bid amounts in common value auctions. The results suggest that competitive intensity measured through the number of bidders for a coal block is instrumental in determining the bidding outcomes. The presence of higher numbers of bidders in the auction leads to higher bids - every additional bidder causes the bid amount to rise by INR 142.67 per tonne of coal for auctions studied for 127 coal blocks from 2014 to 2023. The paper also examines the moderating and mediating effect of competition on bids and on excess of bids from the comparative market price of coal from alternative source of Coal India Limited. The results indicate that competitive intensity does not have statistically significant impact on the relationship between common value of coal blocks and bids, neither as a moderator nor as a mediator. The strategic behavior of the bidders has also been observed as bidders have been seen to bid in a higher than market price in order to outbid the competitors.

Feb 1, 2025

By Karl Gugel, Dante Garcia, Peter Czel, Eduardo Nunez, Joshua Morales, Boris Sullcahuaman

Real-time operational excellence is achieved through the seamless integration of various components. Key aspects include precise instrumentation, real-time data collection, data analytics, and an efficient optimization platform. Additionally, to ensure success, the real-time optimization platform must be incorporated into the site’s internal process control system (Nunez, 2022). This paper provides an overview of practical lessons and best practices for autogenous (AG), semi-autogenous (SAG), and ball mill (BM) grinding. It highlights the implementation of advanced instrumentation, specifically vibration sensors on the rotating mill shell. The paper also delves into the application of advanced analytics necessary for generating new measurements that accurately represent real-time grinding activity in the mill. These Advanced Analytics Measurements (AAM) are compared with well-known grinding curves to determine the optimal grinding point. The discussion focuses on key industry opportunities using real-time mill shell vibration results to derive new correlations and optimize the grinding process.

Feb 1, 2025

By Patricio Zarate

Due to the intrinsic variability in orebodies, similar metallurgical behaviour of all material sent to the concentrator is expected to have some variability. Still some specific ores have anomalous performance which can severely impact on the concentrator’s production of metal, in this case copper. The study first will show the mineralogical characteristics of “usual ore” and of this specific “abnormal ore” which will have to be processed by the concentrator in the future. After that base conditions on both ores and flotation test procedure will be explained. Later the different alternatives tested regarding collectors and modifiers results will be compared. Finally, after discussing the different results with different reagents and considering operational variables of the concentrator, Floticor PD 702 is recommended to obtain the best copper recovery without increase in excess mass recovery.

Feb 1, 2025