Search Documents

When looking for indicators for the mining business ? and these days who isn?t? ? one might need to look no further than the SME Annual Meeting. Held in Phoenix, AZ Feb. 28 to March 3, the meeting was, by almost any measure, a record-breaking success. Attendance included 4,937 industry professionals. Many of whom, feeling rejuvenated following the worst economic recession since the great depression, were greeted with a record 630 exhibits and 103 technical sessions covering all aspects of the mining and minerals business. Adding to the general optimism of the future was a celebration of the past and re-cent achievements in safety and health. The theme of this year?s meeting was ?Celebrating 100 Years of Mining Research? and the emphasis on advancements in safety was evident from the keynote address that kicked off the conference, to the field trips, to the Resolution and Safford mines that concluded the meeting.

May 1, 2010

By R. R. Smith

The meaning of the title, "Blank Piece of Paper," refers to the need for management to take a completely fresh viewpoint to the problems facing our industry. These problems are so severe and some so new that conventional thinking may not be adequate to resolve them. Innovation has to be a part of every company's approach to the solutions, our concept is to start with a "Blank Piece of Paper.' The objective of 'this paper is to outline steps which can be taken to improve the profitability of a mining business. This is not an examination of technical solutions to individual problems, but rather recommendations for overall change in management thinking. This philosophy is based on our actual, hands-on experience in major open pit operations worldwide over the past 25 years.

Jan 1, 1987

By C. L. Karr

Researchers at the University of Alabama are investigating artificial intelligence based computer models of mineral processing systems. Two approaches have been found to be particularly effective in developing data-driven computer models. The first approach employs neural networks which are computational paradigms based on the mechanics of the human brain. They are able to extract the basic relationships between input and output variables from large data sets. The second approach combines fuzzy mathematics with genetic algorithms to produce an adaptive modeling system. Fuzzy mathematics provide computers with the capability of manipulating abstract concepts like those which humans use so effectively in decision making. Genetic algorithms are search algorithms that mimic evolutionary processes apparent in nature. Together, these two techniques can be used to produce an effective modeling system. In this paper, the two approaches to modeling are compared and contrasted with respect to accuracy and computational time while used to model three mineral processing systems: (1) a grinding circuit, (2) a hydrocyclone separator, and (3) a flotation circuit.

Jan 1, 1997

By Bright Oppong Afum, Kojo Boakye, Kwaku Boakye

This research developed and simulated a novel multi-indicator Fatigue Detection and Alert System (FDAS) designed to enhance fatigue detection accuracy in mining environments. The system integrates a comprehensive set of inputs: eye blink rate, eye closure duration, yawning frequency, distraction levels, Pre-shift Check-in Scores (Self-report) and Electroencephalography (EEG) Levels. Using MATLAB’s Fuzzy Logic Rule Viewer (FLRV) and Simulink, simulations demonstrated the FDAS’s robust ability to process these diverse physiological and behavioural indicators accurately. It effectively classified operator fatigue into low, moderate, and high fatigue levels, consistently providing appropriate outputs and corresponding intervention recommendations across various mixed-signal scenarios. The system achieved a calculated accuracy of 85.19% across 27 test entries, with a standard deviation of approximately 1.8459, confirming its reliability for real-time fatigue monitoring. These findings highlight the significant potential of this fuzzy logicbased approach to proactively identify early signs of fatigue, substantially enhancing safety and operational efficiency in demanding mining operations.

Feb 22, 2026

By Dejan Petrović, Pavle Stojković, Jelena Ivaz, Saša Stojadinović

In spite of the fact that flyrock phenomenon represents the real threat for personnel and machinery, it still remains insufficiently investigated. There are efforts, in the mining community, to explain the causes of flyrock, but the models capable to accurately predict flyrock occurrence and define the flyrock distance still do not exist. This article is an attempt to establish such a predictive model. The model utilized the adaptive nature of artificial neural networks and combined it with the accuracy of numerical modeling of physical phenomena. Necessary data were collected by high-speed camera recordings of actual blasts at three different surface mines and processed for further use for artificial network training. The result was a neuro-numerical couple which was capable to predict flyrock occurrence, estimate the launch velocity of flyrock fragments, and calculate the maximum distance of flyrock fragments. The safe distance was then calculated by multiplying the flyrock distance with a factor of safety. The article explains the procedure for data acquisition and processing, artificial network construction, training, and validation. It also explains the principles of flyrock distance calculation and, finally, provides a definition of factor of safety and safe distance. The results showed that the prediction was satisfactorily accurate and reliable.

Oct 22, 2021

By Justin Srednicki, Chenming Zhou

Ambient electromagnetic (EM) noise (natural or manmade) is a major limiting factor for the design and operation of many electronic devices, including through-the-earth (TTE) communications and tracking systems. Extensive studies on EM noise were conducted by the US Bureau of Mines in the 1970s and 1980s. Changes in the design and operation of electrical equipment since then, however, have resulted in changes in the EM noise environment. This paper reviews past research on surveying EM noise in the extremely low-frequency (ELF) and very-low-frequency (VLF) bands, which are the operating bands for TTE systems, and introduces a new battery-powered, rugged, portable measurement system for surveying EM noise in mining environments. Examples of surveyed EM noise measurement results in and above an active underground coal mine, using the new system, are presented in terms of absolute magnetic field strength levels. A new metric, average noise level (ANL), is introduced to characterize the noise level relative to a particular frequency band for a specific location. It is found that EM noise in mining environments varies significantly with time and location. EM noise levels at frequencies of 30 Hz that shifted from power harmonics (e.g., 90, 150, 210, 270 Hz) are relatively low and their variation with time can be statistically modeled by a Gaussian distribution. The conclusions and findings presented in this paper can help better design and operate TTE communications and tracking systems in underground mines.

Oct 14, 2022

By BHAMIDIPATI S. SASTRY, ANMAYA NAIK, ASIF AHMAD, Srivatsan Jayaraman Sridharan, ADITYA PANDEY

Wet kata cooling power (WKCP) as measured by a kata thermometer is a well-known heat stress index used in the mining industry. Although, over the years, several researchers proposed different heat indices and indicated limitations of the kata thermometer, WKCP is used in the South African gold mining industry due to its simplicity and rapidity of assessment. This paper presents a comparative analysis of the newly developed empirical expression for the WKCP and some of the more commonly used empirical models. For this purpose, WKCP measurements are obtained based on experiments conducted in a low-speed wind tunnel. Based on a regression technique, the analysis presented aims to assess the disagreement between the empirical model predictions and actual measurements. The correlation is also presented between WKCP and the well-established thermoregulation models using parameters from the low-speed wind tunnel experiments, including dry-bulb temperature (Td), wet-bulb temperature (Tw), barometric pressure (P), and wind speed (v). It is found that the proposed empirical model for the WKCP represents the bioclimatic interaction quite well under the specific parameters that defines the harsh thermal environment and air condition, such as metabolic activity, clothing of the person, and the velocity of the ventilating air in which the person is working. The statistical analyses performed show that the empirical model proposed for the WKCP produces satisfactory estimates of the thermal stress experienced under lower air velocities, light clothing, and higher metabolic activity rates.

Sep 2, 2021

By Yao Yevenyo Ziggah, Victor Amoako Temeng, Solomon Evans Kweku Koomson

Tyre hours/life deficit is a major operational challenge facing the mining industry which adversely affects materials production and costs. An accurate forecast of the tyre life is key in addressing this menace. This study for the first time employed the hybrid intelligent technique by utilising three metaheuristic optimisation algorithms, including particle swarm optimisation (PSO), genetic algorithm (GA), and whale optimisation algorithm (WOA), as trainers for the parametric weights and biases to optimise multilayer perceptron neural network (MLPNN) for enhancing prediction of on-site dump truck tyre life in the mine. Four hybrid models known as PSO-MLPNN, WOA-MLPNN, GA-MLPNN, and BP-MLPNN were developed using a total of 157 tyre dataset records obtained from a surface mine in Ghana. In assessing the prediction performances for the models developed, five statistical performance metrics of variance accounted for (VAF), Nash–Sutcliffe efficiency index (NASH), coefficient of determination (r2), mean absolute percentage error (MAPE), and correlation coefficient (r) were utilised. Moreover, ranking, uncertainty analysis and Bayesian information criterion (BIC) techniques were utilised to establish the most effective hybrid model, whereas sensitivity analysis was conducted on the input parameters. Results achieved showed that PSO-MLPNN was the best for prediction because it had the least MAPE value of 1.196% and relatively high values of VAF (99.642%), NASH (0.996), r2 (0.996), and r (0.998). Besides, PSO-MLPNN had the best selection criteria values of 6, 7.1725, and 444.834 for the ranking, uncertainty analysis and BIC respectively. Hence, PSO-MLPNN is recommended for the prediction of on-site dump truck tyre life for the studied mine.

Mar 11, 2024

By Kristian E. Waters, Hao Ma, Haibei Wang

Over the past few decades, ELM based separation processes have become an attractive and efficient way to remove toxic metal ions from the various aqueous waste effluent streams. This paper provides a comprehensive review of the generation, characterization, and applications of emulsion liquid membrane (ELM) from the more than 280 papers and books published so far. First, the ELM formation and the transport mechanism are introduced. Then the ELM stability and emulsion splitting methods are discussed in detail, followed by the latest research and findings of the extraction of copper and nickel using the ELM technique during the past few decades, including a thorough discussion of ELM operating parameters that impact ELM stability and extraction. In addition, the kinetics study and industrial application of this technique for the removal of coppers/nickel solutes are also presented and discussed.

Jan 6, 2023

By Pratt Rogers, Aaron Young

Digital transformation (DT) is the process by which entities adapt themselves to modern technology. As digital technology becomes more prevalent (automation, cameras, sensors, touchscreens, artificial intelligence, etc.), there will be increased pressure on companies to leverage it for additional gains. For many companies in the mining industry, this will involve overcoming a steep learning curve. Furthermore, as the long-term success of the mining industry is dependent on a labor force with new skills (data management, analytics, digital literacy, etc.), new curriculum will need to be appended to the mining engineering discipline. This paper considers the mining industry’s need for DT. Then, it presents a three-part review of the foundational components of the DT process–ubiquitous data, connectivity, and decision making. Finally, it provides a discussion on the future of DT in mining as well as a research direction, which identifies the need of academia to provide support for mining companies in the form of both research and the education of digitally literate, dynamically capable mining engineers into the coming decades.

By Daniel Roy, Danielle Bouffard, Antoine Berton, Simon Gariépy

Commissioning a mineral processing plant has always been a challenging task. The process includes pre- operational verification, dry and wet commissioning, and a gradual ramp-up to full production, all of which must be executed within the shortest possible timeframe, requiring numerous highly interdependent tasks to be conducted concurrently. This phase is under scrutiny by shareholders, corporate management, and other stakeholders who are keen to see a return on investment as the operation starts yielding results. Despite extensive documentation in the literature highlighting its significance, the impact of the commissioning phase remains underestimated in contemporary mining projects. This paper provides an overview of the commissioning process and its associated challenges before focusing on a critical success factor: building a dedicated commissioning team with the required competencies and personality profiles. The roadmap to achieving an efficient plant start-up is outlined. Drawing on over 15 years of experience with more than 20 concentrator commissioning and start-ups, a general framework is presented to maximize success. This method emphasizes the crucial role of the operation and metallurgy team in supporting these projects. Finally, insights from Soutex’s involvement in multiple start-ups are shared, offering lessons learned that emphasize best practices and challenges encountered in expediting the ramp-up process while maintaining high Health, Safety, and Environment (HSE) standards.

Feb 1, 2025

By James Boyd

JAMES BOYD 29.1-STAFF-AND-LINE ORGANIZATION Industrial organizations are established primarily to coordinate the activities of many individuals working toward a specific goal. In mining, the goals can vary widely, and the skills necessary to reach them likewise will vary from operation to operation. It is essential to keep in mind the principal point that an organization embodies the necessary skills which supplement each other and achieve a given objective. Those who direct such an organization are grouped together as "management" and accept the responsibilities for the regulation, administration, supervision and guidance of the enterprise. Those who comprise the "administration" and have supervisory authority are referred to as the "executives." In the early days of mining it was common for one executive to exercise virtually complete control over the entire organization, and direct its operation from a central office. However, the science of management has advanced significantly since then. Mining organization administration now allocates increased authority and flexibility to those in direct-line responsibility, and organizes competent people in specialized fields to provide supervisors with guidance where it is needed in day-to-day operations. Few mining companies today are confined to one operation. Therefore, highly developed skills can be provided in the staff which assists management. This is known as staff-and-line organization, illustrated, in general, in Fig. 29-1. Each operation requires diverse skills for the carrying out of specific functions. The acquisition and training of those with such skills is an important operation in assembling organizations. An organization normally is modified to accommodate individuals rather than being a "hard and fast" mold into which people are fitted. The modern manager is inclined to organize to minimize central direction, with delegation to line executives, providing staff whose day-to-day operations, in cooperation with line executives, coordinate a continuing drive toward the organization's objectives. The staff officers, therefore, tend to become what could be described as parts of the president's brain, dealing with specific areas requiring certain skills. They do not necessarily direct operations, but watch them to be sure that the skills which they have themselves developed can be transmitted to line operations by persuasion rather than by direct authority. The elements of management requiring staff assignments are: 1. Planning, which, at staff level, is only a coordinating activity. Planning is done at all levels in the organization. 2. Engineering. 3. Finance. 4. Control. 5. Personnel and industrial relations, which set personnel policies, including salary plans and the means of handling relations with the unions. 6. Research, which, in a modern organization, is essential to progress and needs to be overseen at the top. 7. Legal staff to see that all operations of the company are provided with sound legal advice, and that the company's policies stay within the law.

Jan 1, 1973

By R. Dewey

WHAT IS AI? It's very hard to say. Most researchers and practitioners disagree with nearly any attempted definition, but most would agree that A1 does deal with the development of computer-related methods o f problem-solving. Artificial intelligence is a discipline which seeks to emulate human anatomy and/or thought processes by applying computer science, electronics, and mechanical engineering to the development of natural language processing, machine vision, robotics, and knowledge-based expert systems. Integration of these four fields will someday produce the robots of today's science fiction. A1 addresses problems of structuring large amounts of knowledge and representing relationships with rules and semantic frameworks rather than with mathematical equations. A1 is convergent rather than divergent - - conventional conputer applications use relatively small quantities of input to generate large output, but A1 generally reduces large amounts of information to establish a few major conclusions. The development of A1 has prompted greatly increased efforts on the part of scientists and engineers to understand just how humans think, organize information, approach problem-solving, and form conclusions. Some of the more exciting and possibly far-reaching advances in A1 are coming in this more-or-less soft-science area. Thirty years of A1 research (dating from a 1956 conference at Dartmouth College at which the term A1 was coined) has already spawned many widespread, almost ordinary, products: window graphics, hand-held controllers (mouse). function menus, etc., all in an attempt to make computers and people more compatible. WHAT IS AN ES? A1 can be used to develop EXPERT SYSTEMS, which are computer programs or systems which contain knowledge and rules by which problems can be solved. or at least by which possible solutions can be suggested for very complex problems. A1 can be used to better define problems so that solutions can be found. An ES is designed not to process numbers, but to process information according to rules and logic derived from actual practice and experience. WHY AI? WHY ES? Companies are increasingly aware of the value of accumulated knowledge and experience in designing, building, operating, and maintaining the increasingly complex or expensive physical plants in any business. As knowledge branches out and becomes more specialized, the accumulated learning of a veteran operator or manager or engineer becomes a scarce resource well worth preserving. EXPERT SYSTEMS offer a means of doing that, reinforcing, not replacing, human capabilities.

Jan 1, 1987

By A. Podlesny, E. N. Rubinstein, J. J. Sammarco, B. Demich

Roof bolting typically follows the extraction of a commodity to help keep the roof from collapsing. During 2004 to 2013, roof bolter operators had the highest number of machinery-related injuries, accounting for 64.7 percent, at underground coal mines. This paper analyzes U.S. roof bolter fatal and nonfatal lost-time injury data at underground work locations for all commodities from 2004 through 2013 and determines risk indices for six roof bolting tasks. For fatal and nonfatal incidences combined, the roof bolting tasks in order of the highest to lowest risk index were bolting, handling of materials, setting the temporary roof support (TRS), drilling, tramming, and traversing. For fatalities, the roof bolting tasks in order of the highest to lowest risk index were handling of materials, setting the TRS, bolting, drilling, traversing, and tramming. Age was found to be a significant factor. Severity of injury, indicated by days lost, was found to increase with increasing age as well as with increasing experience, largely due to the confounding of age and experience. The operation of the roof bolting machine used in underground mining should be a research priority given the high frequency and severity of incidents. The results also suggest that temporal factors may exist, so additional research is warranted to better understand these factors and potentially develop interventions. This research provides a datadriven foundation from which future research can be conducted for safety interventions to reduce the frequency and severity of incidences involving the roof bolter activities of bolting, handling of materials, and setting the TRS.

Jan 1, 2016

By Yuting Xue, Khaled Mohamed

The failure of coal ribs is a major hazard in underground coal mines. Researchers from the National Institute for Occupational Safety and Health (NIOSH) have been working on the development of an engineering-based rib control method. A user-friendly standalone application, called Design of Rib Support (DORS), is being developed to ease the calculations of rib support. DORS can estimate the Primary Rib Support Density (PRSD, ton/ft2) for development loading. However, it still needs to take account of another key factor, bolt length, in rib support design. The bolt length can be estimated from the rib fracture depth, and this study focuses on the coal rib fracture depth analysis with numerical modeling and artificial neural network. A total of 331 FLAC3D simulations with different mining scenarios and rib conditions were conducted for this study. Machine learning was then used to predict coal rib fracture depth under different conditions. Based on the numerical simulations, the parameters for mining scenarios and rib conditions were collected as features for machine learning, and coal rib fracture depths were collected as the target to predict. Good data correlation (r-square) was obtained with the use of an artificial neural network. The

By Muhammet Mustafa Kahraman

Despite technological advancements and organizational adjustments, lost time accidents are major issues in occupational safety. However, there is very limited work that focuses on variables influencing days lost as a result of occupational accidents. In this study, decision tree and artificial neural network methods were used as machine learning techniques to investigate the impact of factors on accident lost day duration. Degree of injury, worker age, and worker activity were found to be the top three variables impacting loss of time from work. It was also identified that the mining method, location, and nature of injury had a moderate influence on duration lost due to occupational accidents. However, worker experience and ore type did not have any significant impact on the duration, which is an unexpected result. These results confirmed that some accident factors that might have a large influence on the number of mine accidents can be less critical when it comes to accident lost day duration.

Feb 3, 2021

By Turker Hudaverdi, Yasar Agan

This study tries to predict blast-induced flyrock using intelligent modelling techniques. Flyrock is a site-specific phenomenon. Design variables and rock properties highly influence flyrock throw distance. Site investigations were conducted in a sandstone quarry. Fundamental operational parameters, blast dimensions, bench face condition, and rock mass structure were monitored. Stepwise regression technique was applied for variable selection. Burden–hole diameter ratio, in situ block size, and powder factor were determined as the most significant parameters. Considering output of stepwise regression, artificial neural network, ANFIS, and Gaussian process regression techniques were applied to predict flyrock throw. A comprehensive validation was performed using twelve different performance indices. Pre-determination of input parameters supported development of successful soft computing applications. Rock block size was found to be an appropriate input variable for flyrock modelling. In addition to classical performance indices, standardized and symmetric accuracy metrics were quite useful in model validation process. The intelligent models predict flyrock range with an error less than 6 m. The mean percentage errors are lower than 10%. ANFIS seems to be the best model for flyrock prediction. The calculated mean absolute error is 5.36 for ANFIS model.

Nov 12, 2023

By Brianna Eiter, Max Barham, Tim Bauerle

Fatigue-related risk is a persistent safety concern for the mining industry. However, fatigue and sleepiness are often treated interchangeably, which can lead to confusion and potentially less effective reduction of safety risk. To provide clarity, we present an overview of similarities and differences between work-related fatigue risk and sleepiness including definitions, theories, measurements, and mitigation strategies. As a supplement, a summative visual model which highlights these similarities and differences is presented. Expanding industry knowledge in this area will assist safety professionals in crafting more targeted risk management practices appropriate for work-related fatigue risk, sleepiness, or both.

Dec 19, 2023

By B. Eiter, M. Barham, T. Bauerle

Fatigue-related risk is a persistent safety concern for the mining industry. However, fatigue and sleepiness are often treated interchangeably, which can lead to confusion and potentially less effective reduction of safety risk. To provide clarity, we present an overview of similarities and differences between work-related fatigue risk and sleepiness including definitions, theories, measurements, and mitigation strategies. As a supplement, a summative visual model which highlights these similarities and differences is presented. Expanding industry knowledge in this area will assist safety professionals in crafting more targeted risk management practices appropriate for work-related fatigue risk, sleepiness, or both.

Feb 1, 2023

By Babu R. Yama

Artificial Intelligence research has produced several tools for commercial application. Neural Networks, Fuzzy Logic and Expert Systems are some of the techniques that are widely used today. Artificial Neural Networks (ANNs) are excellent predictive, pattern recognition, and data analysis tools. In the mining industry, ANN techniques are being used commercially for real-time process control applications. Modeling of spatial data, ore reserve estimation, tunnel design, longwall stability prediction, and geologic roof classification are additional application areas in which neural networks have been applied successfully. A standard back-propagation algorithm was used to train a series of neural networks for a real-world predictive task. After training and optimizing the neural network architecture, performance of the network is measured on an independent validation set. Results indicate a correlation coefficient of up to 84 % between the actual and predicted values. A neural network model is developed for learning the spatial continuity of a mineral field and, consequently, for predicting sulfur values given coordinate values. The neural network performed not only satisfactorily, but in some cases performed better than the kriging model.

Jan 1, 1997