Search Documents

By Wei Victor Liu, Na Zhang, Chengkai Fan, Bei Jiang

The truck haulage data from open-pit mine sites are usually massive and multidimensional with multi-peak Gaussian distributions. Artificial neural networks (ANNs) are well-known machine learning algorithms to handle massive and multidimensional data for building models. Moreover, Gaussian mixture modeling (GMM) is a suitable option for processing the data under multi-peak Gaussian distributions and improving model accuracy. For the first time, this study used a back propagation neural network (BPNN), an extreme learning machine (ELM), and a Bayesian regularized neural network (BRNN) coupled with GMM to deal with the complex truck haulage data and build three weighted ensemble models (WE-BPNN, WE-ELM, and WE-BRNN models) to predict truck productivity at mine sites. Decision tree (DT), random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) were used to build models to be compared with the weighted ensemble models. The results showed that the WE-BRNN had a higher accuracy than the WE-BPNN and WE-ELM models. The proposed weighted ensemble models performed better than the benchmark models in predicting truck productivity, indicating that a weighted ensemble approach based on the GMM analysis significantly improved the model accuracy. Based on the relative importance analysis, haul distance was the most crucial input variable for predicting truck productivity. This study provides a new approach to predicting truck productivity, which will help mining companies make sound budget decisions and improve mine planning.

Mar 2, 2023

By D. W. Alexander

In 1993, CONSOL began investigating new methods of permanently filling coal mine shafts, which after ventilation is stopped, may contain a potentially hazardous atmosphere. Fill materials such as fly ash/cement can be pumped, are non-combustible and non-incendiary but tend to flow into the mine entries. A non-flowable mixture has been developed that minimizes the volume of fill used. The paper presents our recent shaft filling experience including fly ash material properties, mix designs, field problems, placement success, and gas testing techniques.

Jan 1, 1996

By K. Chief

American Indian lands contain a vast amount of renewable and non-renewable resources that have consequently been mined (Smith and Frehner). Therefore, it is understandable that tribes are concerned about environmental impacts from mining and their ability to minimize and mitigate these impacts. This has created a need to better understand mining and its environmental impacts. The University of Arizona Superfund Research Program Mining educational modules developed educational modules for tribal colleges focusing on environmental impacts of mining, remediation of mining wastes, and sociocultural impacts of mining. Educational modules are independently packaged units of study designed to enhance the learning process and can be modified and adapted to different learning scenarios and objectives. In addition to providing specialized knowledge, the modules feature hands-on activities, incorporation of technology, student involvement, discussion, and exchange of ideas. Modules will aim incorporate traditional ecological knowledge and approaches that promote effective science learning for native students. Modules are designed to augment existing associates of science programs (e.g. biology, chemistry) currently offered at tribal colleges and can be modified for use in K-12 education and for non-tribal audiences.

Feb 23, 2014

By R. Adsero

The volume of data produced by operating mines has increased substantially over the last 10 years. However, the volume of data and analytical capability has been negatively correlated to equipment productivity for at least the last seven years. In simple terms, as the volume of data has increased equipment performance has declined. Table (2010) tells us that ?The calamity of the information age is that the toxicity of data increases much faster than its benefits?. More data does not guarantee improving productivity; but more data is also not the cause of declining productivity. Similarly, when equipment performance does start to improve, (it must ? there really is no option if mines want to remain competitive), it will not be the data nor analytics which causes it; it will be the people using the resources at their disposal; including the data. Data and analytics can help if the toxicity of the data can be managed. The simplest form of business improvement using data is benchmarking. The objective of benchmarking is to understand and evaluate the current position of a process in relation to ?best practice? and to identify areas and means of performance improvement. The application of benchmarking involves four key steps: (1) Analyze and understand in detail existing processes; (2) Analyze and understand the processes of others; (3) Compare your own performance with that of the others analyzed; and (4) Design and implement the changes necessary to close the performance gap(s). There are however, many in the mining industries who have shunned equipment benchmarking because they believe that, ?every mine is a pilot?. In other words, the differences between mine operations make comparisons between them of little value. This paper will present a valid approach to benchmarking equipment performance and reliability, accounting for the differences and similarities between operations, producing a result which can be used to add value to mines around the world.

Feb 23, 2014

By B. Seegmiller, W. A. Hustrulid, O. Stephansson

Introduction The concept of in-the-wall haulage was formally introduced to the mining community in the early 1970s. The basic concept is simple. Rather than the traditional in-the-pit haulage/access ramp, single or twin ramps driven in the pit wall are used with crosscut connections on the working levels. The in-the-wall pit haulage system could be considered as part of the opening of a new mine, a way of completing to final depth an existing pit, or part of the transition from open-pit to underground mining with the ramp remaining as part of the access. This paper is intended to acquaint the reader, particularly mine planning engineers, with some of the possibilities presented by the concept. Nordstrom (1983) said, "In many countries, mining engineers are either open-pit or underground specialists and, hence, often don't consider the possibilities for combining the best aspects of each into a hybrid mining system." This is believed to be true. There are few "hybrid mines" employing, for example, open-pit methods with underground haulage systems. One reason is the variance with the experience of the mining company and the engineers involved. However, with today's low metal prices, innovative and unconventional thinking may be just what a property requires to remain in production. All the possible situations where an in-the-wall ramp might be considered cannot be presented here. Rather, a few examples will be discussed for illustration purposes. Potential savings in stripping costs A major cost in open-pit mining is associated with the removal of overburden and waste rock. Although much of this stripping cannot be avoided, the volume (V) associated with the presence of an in-pit haul road can be quite large, V 100 (pit depth) a (road width) 2 x road grade (%) As an example, consider a vertical ore body 400 m (1312 ft) long, 60 m (197 ft) thick, extending to a depth of 160 m (525 ft). Cross sections are shown in Fig. 1. Other data are: ore tonnage = 11 Mt (12 million st), ore density = 2.9 t/m3 (0.09 st per cu ft), waste rock density = 2.7 t/m3 (0.08 st per cu ft), road width = 20 m (66 ft), road gradient = 10%, and level interval = 10 m (33 ft). The evaluation has been made assuming that the pit slope (0) is constant around the pit except on the side with the haul road. On this side, the slope is decreased to allow for the road. Slope angles of 30° to 60° have been selected to indicate the dependence of stripping volume (V) on slope angle. The stripping at the ends have been calculated assuming representation by cones. The volume associated with the haul road is 2.6 Mm3 (92.8 million cu ft). A comparison of the strip volumes involved is shown in Table 1. As can be seen, the percent savings in strip volume varies from about 4% to 17% and depends greatly on the slope angle. It is perhaps more interesting to examine the savings in stripping costs that could then be used to cover the cost of the access ramp and the crosscuts for stripping costs of $3/m3 ($0.08 per cu ft). The cost with the road volume is 2.6 million x 3 = $7.8 million.

Jan 1, 1988

By F. W. Petersen

Slurry reactors are being used extensively throughout the chemical, biochemical and mineral processing industries. This paper describes the interaction between fine ore particles and granular porous adsorbents such as activated carbon and ion-exchange resins in a stirred tank reactor. Gold and silver cyanides were used as adsorbates to detect changes in the mass transfer characteristics of the adsorbents, which were ashed to determine the loading of ore particles. A simple kinetic model incorporating film diffusion, intrapanicle diffusion ~d the adsorption equilibrium, was used to interpret kinetic data and to estimate the effect of slurry conditions on the diffusion parameters. It was observed that the equilibrium loading of fines in the adsorbents was independent of their concentration in the slurry. Furthermore, the presence of these panicles inside an adsorbent decreases the effective diffusion of gold or silver cyanides into the adsorbent matrix. When fine suspended solids are present in the reactor, a decrease in the effective availability of the superficial surface of the pre-saturated adsorbent panicles for mass transfer from the liquid phase was observed. This newly defined surface availability factor was dependent on the concentration, panicle size, and the zeta potential of the fine particles in suspension.

Jan 1, 1993

By Z. Y. Hu

This paper reviews the past and presents the present state of industrial minerals in China. The resources, reserve and production of major non-metallic minerals are given. The mining and milling operations are reviewed. The future development and plans of Chinese non-metallic minerals industry are summarized.

Jan 1, 1990

By M. P. Roy, P. K. Singh, A. K. Mishra, Ashish K. Vishwakarma, Vivek K. Himanshu

Ground vibration is one of the major hazards produced by rock-blasting operation. The accurate prediction of vibration is necessary for designing controlled blasting parameters. The existing vibration predictors consider maximum explosive charge weight per delay and distance as the parameters responsible for ground vibration. These predictors are based on the assumption that the geometrical parameters of the blast will be constant for a site. However, the mining sites with bigger production targets have varying geometrical parameters to suit the excavator utility. Accordingly, the other blast design parameters will also have an impact on ground vibration intensity. A principal component analysis is a dimension reduction technique. This technique along with multivariate logarithmic regression has been used in this paper to predict the ground vibration. The technique has classified the blast design parameters into four principal components. The regression with the scores from these principal components has been carried out. The evaluation of the model performance of predictors along with the existing empirical predictors has been carried out using R2 and RMSE values. The evaluation suggests that the predictor with logarithmic regression followed by principal component analysis gives better performance with respect to the existing empirical predictors.

Jul 30, 2022

By J. Bilant, B. Carlson, N. Gow

"High-pressure grinding roll (HPGR) technology was evaluated to replace tertiary cone crushing at Coeur Rochester operations (Coeur Rochester Inc.) as an opportunity to improve silver recovery. In 2016 and 2017, onsite and third-party pilot programs were initiated to evaluate the impact on metallurgical recovery and heap leach performance of crushed product generated by an HPGR. In 2018, Forte Dynamics evaluated the HPGR laboratory metallurgical data from Coeur Rochester and all third parties to develop field-scale leach curves based on new crushing scenarios. The laboratory recovery test work data were consolidated and scaled to field conditions to determine projected heap leach performance. Based on the metallurgical testing conducted, the replacement of current tertiary cone crushers with HPGR technology has the potential to increase Coeur Rochester’s silver recovery rate by 8 percentage points, from 61 percent to 69 percent, and shorten the overall timing of silver recoveries from 20 years to just more than two years.The Rochester Mine, and associated valley fill heap leach facilities is an openpit silver and gold mine located in Pershing County, NV, approximately 42 km (26 miles) northeast of the city of Lovelock. In 2017, Rochester produced approximately 4.7 million oz silver (Ag) and 51,000 troy oz gold (Au). Ore mined at Rochester is either fed directly to the primary X-Pit crusher, crushed at an in-pit crusher system, or placed directly onto a heap leach pad as run-of-mine (ROM). Both crushing circuits are comprised of three stages of crushing to produce a nominal 3/8 in. ore. Primary crushing consists of jaw crushing while secondary and tertiary crushing are composed of varying cone crushers.Historical recovery rates of crushed Rochester ore averaged 61.4 percent Ag and 95.9 percent Au over a period of 20 years (Robinson et al., 2018). These rates were derived from third-party verification of in-house metallurgical test results, crusher production and heap leach production results from 1986 through 2004 in a private report for Rochester produced by KD Engineering Co., Inc. Recovery rates are regularly verified by compositing daily samples of ore delivered to each leach pad from the X-pit crusher, in-pit crusher and/ or ROM. A proportionate split of each sample is used to generate monthly composites for metallurgical analysis utilizing column leaching and bottle roll leaching. These tests are run in a manner analogous with production conditions and deliver test results that provide expected heap leach performance. As the Rochester oxide deposit has been mineralogically and metallurgically consistent, the gold and silver recovery trends have also been consistent over the life of the project."

Sep 1, 2019

By Savita Schlesinger, Mike Hanna, Nathan Scalla, James O’Shaughnessy, Steve Miller

Loudoun Water’s Quarry A (Milestone Reservoir) project involves conversion of a rock quarry to a billion-gallon raw water reservoir. The project includes a new 40 MGD pump station, deep intake shaft, and three drill and blast intake tunnels for accessing the reservoir. Due to concerns regarding constructability and construction risks, the project design was paused while a Construction Manager At-Risk (CMAR) contractor was procured. The CMAR contractor was engaged collaboratively with the design team to provide risk and constructability input for refining the design. Aspects of the original design, design modifications, and benefits of the CMAR collaboration will be presented.

Jun 13, 2023

By A. K. Martin

Adaptive management can be described as a structured, iterative process of robust decision making in the face of uncertainty, with a goal of reducing uncertainty over time through system monitoring. Adaptive management is a tool which can be applied to not only change a system, but learn about the system (Holling, 1978). Adaptive management has been used in ecosystem management for years and guidance is provided in a variety of handbooks and publications. Adaptive management can be applied to industrial facilities and mines through the use of an adaptive environmental management plan (AEMP) and associated practices. The goal of this paper is to provide an explanation of how the plans and practices support regulatory agency approvals and permitting, span the life-cycle of mines, manage uncertainty, and assist in addressing mining impact and legacy issues. AEMPs and associated practices are useful tools to address the uncertainties in identifying, evaluating, and managing impacts of proposed new and modified mining facilities undergoing environmental review. Once a proposed project is approved, the AEMP continues as a living document, being informed, revised, and adapted by the operations. The AEMP can serve as an ongoing management tool for describing and evaluating environmental impacts, continuing in operations into post reclamation. If initiated during planning and environmental review of a project (and in some locations such as the United States [U.S.], the preparation of an Environmental Impact Statement (EIS)), the AEMP becomes a basis to identify, monitor, and manage potential project environmental impacts. Development of an AEMP for an operating mine is also beneficial since there are generally developing and ongoing environmental issues at those facilities as well. Over time, the AEMP is adapted to changing requirements and conditions including those anticipated and unanticipated. Ever increasing scrutiny of mining projects and the complexities of the EIS process highlight the uncertainties inherent in impact predictions. In making the momentous decision of initial project approval, these uncertainties can discourage the regulatory agencies? actions and create stakeholder anxiety and controversy about a project. A well-designed AEMP can support the decision to approve an EIS and enable a project to move forward. Additionally, an AEMP can inform financial assurance estimates and revisions over the life of a mine providing all parties including the citizens of the surrounding communities with greater confidence that potential environmental impacts and risks will be well managed.

Feb 23, 2014

By D. Wenstrup, K. Perry, J. Hatfield, P. Sainato, B. Lusk

Concrete-infused cloth is used in several civil and mining surface applications whose circumstances are similar to some of those in underground mining. A feature of this material is that it cannot be overhydrated. In underground conditions, however, the excess supply of water to the cloth for hydration could lead to muddy and potentially unsafe working conditions, as well as resource wastage by supplying more water to the construction site than is needed. The objective of this study is to verify the water-to-cloth ratio and study the effect of hydration level on the strength of the Concrete Cloth product. We found that the strength increases with increased hydration up to a 1:2 water-to-cloth ratio by weight, after which the strength holds steady regardless of additional hydration. This confirms the 1:2 water-tocloth ratio by weight for hydration and confirms that strength is retained even if the cloth is excessively hydrated.

Jan 1, 2014

By Juan J. Monsalve, AMAN SONI, ALEX PFREUNDSCHUH, Nino Ripepi

Ground control failures are one of the main causes of accidents in the underground stone mining industry. Some of the fundamental tools for rockfall hazard identification are related to rock mass characterization and geotechnical discontinuity mapping. Recent technological advances in these methods are related to remote sensing techniques and point cloud processing software for automated discontinuity mapping. Remote sensing techniques, such as LiDAR and photogrammetry, generate multimillion point clouds with millimetric precision, capturing the structure of the rock mass. The automated point cloud processing tools offer alternative algorithm-based methods to characterize and map these discontinuities. However, their applicability is constrained by multiple factors such as site specific conditions of the rock mass and the parameters used within the mapping algorithms. This paper evaluates the performance of automated discontinuity extraction software compared with manual virtual discontinuity mapping. Sampling windows from laser-scanned sections in an underground limestone mine are defined and mapped using discontinuity set extractor (DSE). Results from the virtual discontinuity software are compared with manually extracted fractures from I-Site based on reviewing orientation, trace length, spacing, number of extracted discontinuities, and processing time. The analysis determined that the automated mapping algorithm was able to identify the same discontinuity sets that had been manually mapped. The automated mapping software mapped an excessive amount of smaller fractures, which caused the comparison of both mapping techniques to be unsuccessful in terms of trace length and spacing.

Mar 19, 2021

By Andrea Brickey, JUDITH BUABA, RICHARD AMOAKO

The global mining industry has recorded significant declines in accident and injury rates attributed to the advancement in technology, increased enforcement, and safety consciousness. A goal of the mining industry is to achieve zero injury and occupational illness on all mine sites, prompting increased research into ways to further reduce mine accidents. A machine learning technique known as multiclass logistic regression is applied on a 10-year injury dataset from the Mine Safety and Health Administration (MSHA) to determine a miner’s susceptibility to a class of injury and to help identify significant risk factors associated with different classes of injury. The data is aggregated based on injury classification to provide statistically relevant results. The analysis identifies specific risk factors that influence a mine worker’s susceptibility to a given class of injury, i.e., non-fatal with no days lost or restricted activity, non-fatal with days lost and/or days of restricted work activity, and fatal and total permanent or partial permanent disability. These factors include miner’s age, mine type (coal vs. non-coal), experience on the current job (years), shift start time, employment type (operator vs. contractor), mining district, and type of accident. The results of the analysis indicate that a miner’s experience on the job, i.e., the number of years worked in a current job, is a significant risk to injury occurrence, even for those with decades of total mining experience. We further show the differences and similarities between the surface and underground mine incidents.

Nov 3, 2020

By Manoj Khandelwal, Jian Zhou, Yingui Qiu, Peixi Yang, Pingan Peng

Rockburst prediction is crucial in deep hard rock mines and tunnels to make safer working conditions. Due to the complex interaction of many factors involved in rockburst prediction, such as multi-variable and multi-interference factors, three hybrid support vector machine (SVM) models optimized by particle swarm optimization (PSO), Harris hawk optimization (HHO), and moth flame optimization (MFO) are proposed to predict rockburst hazard level (RHL). The RHL is determined according to four kinds of microseismic characteristic parameters including angular frequency ratio, total energy, apparent stress, and convexity radius. Then, six types of microseismic characteristic parameters are taken as input variables in 343 sets of data, including angular frequency ratio and total energy, etc.. And the RHL is taken as the output target of rockburst prediction. The classification performance of PSO-SVM, HHO-SVM, and MFO-SVM hybrid models is evaluated by accuracy (ACC), precision (PRE), and kappa coefficient. Findings reveal that the MFO-SVM model performs best in terms of accuracy, with ACC, PRE, and kappa coefficients reaching 0.9559, 0.9063, and 0.9094 respectively, while PSO-SVM and HHO-SVM have similar performances. However, the PSO-SVM, HHO-SVM, and MFO-SVM all perform better than the unoptimized SVM model. This confirms that the three optimization algorithms significantly enhance the rockburst prediction capacity of the SVM model to help mine practitioners apply machine learning methods to rockburst prediction problems appropriately.

Feb 3, 2023

By VASU GANGRADE, Marcia Harris, Kumar Vaibhav Raj, Jim Addis, Khaled Mohamed, Snigdha Sarkar

The National Institute for Occupational Safety and Health (NIOSH) conducted a ventilation assessment for a recently established underground room-and-pillar stone mine implementing split-mine ventilation. The primary objective was to examine the impact of the length of the in-place stone stoppings on face ventilation efficiency. These stone stoppings serve to separate the intake and exhaust entries and align with the mining direction. To achieve this, computational fluid dynamics (CFD) modeling was utilized. The appropriate turbulence model was selected, and a mesh convergence analysis was conducted for the CFD model. Following that, the CFD model was validated using the conducted ventilation surveys. Two configurations of in-place stone stoppings, designated as Layout-I and Layout-II, were simulated using the validated CFD models. Layout-I featured a shorter in-place stone stopping, while Layout-II had a longer one. The results obtained from the CFD models demonstrated that the increased length of the in-place stone stopping in Layout-II resulted in a notable enhancement in ventilation efficiency at the advanced faces (last stopping), elevating it from 4% in Layout-I to 8.4% in Layout-II. However, no significant impact of the in-place stopping layouts was observed at other faces. In general, Layout-II exhibited a greater circulation of air at the outby stoppings.

Feb 1, 2024

By Ihsan Berk Tulu, Haochen Zhao, Deniz Tuncay

This paper proposes a new method to estimate the percentage of load carried by the gob in underground coal mines using a new parameter that introduces the site-specific overburden geology. The new parameter was defined as the total strong layer thickness (tstr) that represents the strength and stiffness of the overburden with a single value. Twelve field measurement case studies from 11 different U.S. longwall mines with different overburden geologies were used to develop the new methodology. 2D numerical models of these case studies (and additional parametric runs with different panel widths) were verified against field measurements such as surface subsidence and stress. Statistical analyses using the model results were conducted for a loading model with the new tstr parameter as one of the variables. The new methodology was found to have a coefficient of determination (R2) of 85% when compared to the field measurements and the parametric models. The method was then tested for practical implementation for pillar design. The percentages of load carried by the gob as estimated by the new method were implemented into the LaModel program, that is commonly used in the coal industry. The results obtained from LaModel were compared to the available field stress measurements, and the new method implemented into LaModel was found to give successful results.

Jul 18, 2022

By E. Siami-Irdemoosa, S. R. Dindarloo

Ease of excavation or rippability, also called diggability or excavatibility, is a critical decision-making parameter in the selection of both the overburden removal method and the required equipment in surface mining and geotechnical engineering projects. The most widely used method of estimating rippability is rock mass classification. Although there are different classification schemes in the literature, all of them have the two major limitations of sharp transitions at class boundaries and subjective uncertainties in decision making. In this study, the decision trees method was employed as a classification tool for estimating ground rippability, using the four rock mass parameters of weathering degree, uniaxial compressive strength, joint spacing and bedding spacing. The results were compared with those of the widely used method of diggability index rating (DIR) and a fuzzy-based DIR. The problem of subjective uncertainty was resolved in the proposed decision trees method, as the tree rules were derived automatically from the training data sets. Compared with fuzzy-DIR, a decision tree classifier is simpler, needs less computational time and is more appreciable by industry practitioners. Nevertheless, the proposed method is not flawless and, similar to both the conventional and fuzzy DIR methods, yielded poor estimations in particular instances. The limitations of the three methods are discussed.

Jan 1, 2015

By Wen Tao Liu, Tong Tian, Fu Sheng Niu, Xiu Man Liang

In order to address the difficulty of accurate segmentation of froth images of different sizes, a method of froth image segmentation based on highlight correction and parameter adaptation is proposed. First, a machine vision system on a single-cell flotation machine is built to collect froth images. Homomorphic filtering is used to improve the uneven brightness and shadow of the images. Fuzzy c-means (FCM) clustering is then utilized to classify similar highlights that belong to the same froth. After Otsu threshold segmentation, a parameter-adaptive morphological operation is used to extract the marker points and edge bands and correct the froth edges in the original image. Finally, the modified image is filtered by morphological reconstruction, and the highlight mark is used as the local minimum point for watershed segmentation. Three sizes of froth images are segmented in comparative experiments. The results show that the proposed method is suitable for the segmentation of froth images of different sizes. The position of the extracted segmentation line is close to reality, with average over-segmentation and under-segmentation rates for froth images of 2.6% and 6.8%, respectively. The froth image segmentation performance is stronger than that of the other methods examined.

By M. Mustafa Kahraman, Sean Dessureault, W. Pratt Rogers

Most contemporary mines have considerable amounts of data. Structured and unstructured large data sets are colloquially named big data. Much of the data in mining operations come from a variety of systems, each with different databases and reporting environments. Standard technology deployments create a Bsilo-ification^ of data leading to poor system benefit. Through modern server monitoring and systematic approach, data utilization and value can quantifiably be measured. The Data Utilization and Value Index (DUVI) can quantify business intelligence best practices and user interaction. This study seeks to provide a data management tool to measure data utilization across the process of converting data into action.