Search Documents

By A. Jeffkins

Visibility is restricted when operating load haul dump vehicles resulting in a number of serious accidents in the Ontario Mining Industry. One of the leading causes of these accidents is the inability of the equipment operator to see clearly people, objects or hazards around the machine. Previous line of sight testing by the research team found specific machine characteristics were responsible for blind spots and impaired visibility. In order to identify feasible design modifications a computer simulation program, Classic JACK 3.1, was utilized. Program features include human factors analysis, which allows evaluation of line of sight and operator posture in order to decrease risk of musculoskeletal injury. Research within the virtual computer environment consisted of a Visibility Audit and a Target Audit in order to quantitatively determine how certain components of the LHD design affected the line of sight around the vehicle. Results indicate that modifying the LHD light brackets, engine profile, cab posts and other components will enhance visibility. The addition of cameras located on the front and rear of the vehicle were able to enhance the operator?s sight lines to previously obstructed areas. Modifications to seat height and the operators orientation both improved sightlines and decreased risk factors associated with back and neck musculoskeletal disorders.

May 1, 2003

By Jan E. Nesset, L. Paul Staples

"High Gradient Magnetic Separation (HGMS) technology, although developed over 2 decades ago, has not been widely applied to the separation of sulphide minerals. Under conditions of strong magnetic field gradients, weakly magnetic minerals such as chalcopyrite (CuFeS2) and marmatite (Zn(Fe)S, sphalerite with iron in solid solution) behave paramagnetically and can be effectively separated from diamagnetic minerals such as galena (PbS). The application of this technology to the separation of Cu-Pb and Zn-Pb bearing streams in the treatment of fine grained complex sulphides may in some cases be more effective than separation by flotation. A 2 TPH Sala HGMS pilot plant was operated at Brunswick for a nine month period, ending in March 1995. The testing demonstrated the mechanical reliability of the technology, the consistency of operating results and the scale up from laboratory testing. HGMS is seen as a complimentary technology to flotation, best suited to performing those separations of galena (and other diamagnetics) which flotation does not do as well.IntroductionBackgroundSince the turn of the century, the magnetic character or magnetic susceptibilities of minerals have been determined with increasing precision and accuracy. Figure 1 illustrates specific magnetic susceptibilities of some common minerals. As long as susceptibility ranges do not overlap, separation is possible.In 1937, the principle of using a magnetizable matrix material in a magnetic field to increase both magnetic flux density gradients and number of capture sites for susceptible minerals was first applied (Frantz). It was not until the 1970's, however, that the genuine development of wet high gradient magnetic separation began with the introduction of very fine matrix materials to the magnetized volume of large solenoid magnets. Today, dozens of HGMS units purify, filter and separate minerals, primarily for the removal of iron stained minerals from clays used in the paper coating and china clay industries and for the recovery of fine titanium and iron oxides in the iron ore industry. Only the Garpenburg mill in Sweden is currently applying a continuous HGMS machine to separate complex sulphide minerals; upgrading a lead concentrate since 1988."

Jan 1, 1996

By Jürgen Antrekowitsch, Gerardo R. F. Alvear Flores, Mehmet Ayhan, Christoph Zschiesche

Synergies between copper and lead extractive metallurgical processes enable the processing of a broad range of polymetallic materials. However, this complexity also brings some challenges expressed in terms of complex intermediates and final products. For instance, based on the limited solubility of Cu and Ni in crude lead bullion additional phases will appear during the crystallization of the melt. Beyond the need for continuous optimization of metallurgy the control of phase solidification is a further important pillar to achieve a more efficient process by minimizing the amount and cycles of reverts. This paper describes the microscopy study of one of the most relevant intermediate in the Cu and Pb metallurgy, the Cu based alloy and highlights the importance of applying a well-controlled cooling sequence to improve the overall process efficiency. INTRODUCTION One of the key aspects in Aurubis’s 2025 vision is to move towards the implementation of a multi metal recovery strategy. The implementation of this new multi metal vision is supported by the long tradition of the company, founded in 1866 as Norddeutsche Affinerie, and further developed by adopting modern copper smelting and lead smelting technologies for the processing of primary and secondary materials. The combination of these assets have already build the basis for processing of complex materials in the copper and lead circuits implemented in Aurubis’s facilities. The addition of a new smelting facility, will enhance these capabilities. Aurubis current flowsheet combines Cu, Pb and Zn metallurgy. This includes primary smelting of copper concentrate, processing of secondaries (residues, slimes, slags) and recycling materials (scrap, shredder material, e-scrap). These broad range of materials contain not only the mentioned base metals but also a number of minor metals that requires to be properly managed to ensure efficient recoveries and quality of the targeted metals.

Jan 1, 2019

By X. Shi

Magnesium, the lightest structural metal, has not yet been considered as a serious contestant for automotive use due to its weaknesses in corrosion. Electroless nickel-boron alloys are well known for their corrosion resistance and hardness. An electroless nickel-boron layer was successfully deposited first on the chemical conversion pre-treated AZ31 alloy and also on the Ni-P coating which was deposited on the conversion coating. The electroless bath contained nickel sulphate and dimethylamine borane (DMAB) as main salts and the samples were activated by a 5 g/L AgNO3 solution before the electroless plating process. The presence of the conversion coating between the nickel coating and the AZ31 substrate acted as a barrier and prevented corrosion of the alloy. The morphology of the nickel-boron layer was studied using SEM. The crystal structure and the composition were examined by EDS and the hardness was measured. The corrosion behaviour of the nickel-boron layer deposited on the conversion coating and on the Ni-P coating was studied using potentiodynamic polarization in a 0.5M NaC1 solution. A saturated standard calomel electrode was used as a reference electrode. The results show that the nickel-boron coatings had a significantly better corrosion resistance than the AZ31.

Jan 1, 2006

By M. J. Davie, D. S. Ross

"The successful design of a new mine water pumping system is in part dependent upon the accuracy with which the operating conditions can be forecast. This paper outlines the data which should be obtained on water quantity and quality. Methods of modifying the quality are also discussed. Some pumping systems for disposal of sludge are described, citing operating examples. The various types of mine dewatering pumps are described in terms of design characteristics as they affect operating efficiency and installation and maintenance costs. Piping system parameters are outlined. Finally, a hypothetical case study of pumping from a depth of 3,000 ft is assessed, with particular reference to capital costs.IntroductionMany mine operators would agree that the pumping system usually receives a low engineering priority during the design stage, and as a consequence causes some of the most frustrating problems during production. For a ""dry"" mine (up to 200 gpm), design of the pumping system may indeed be simple, but outside of the potash industry such mines are not common. For ""wet"" mines, the pumping system is important because it significantly affects the initial capital and on-going energy costs of the mine and, in the area of sludge disposal, the working conditions and production costs. Indeed, a failure in the pumping system usually has serious, and sometimes disastrous, consequences.The intent of this paper is to outline the factors which should be considered in the design of a pumping system and to describe the types of pumps used in mine dewatering and relate them to practical operating systems."

Jan 1, 1980

By Mario E. Rossi

The full economic evaluation of a mining project requires a block model that provides an estimate of the tons and grades of available resources. The model must be representative of the mineralization to be found at the time of mining for specified extraction periods and within acceptable error margins. In an operating mine, there may be a reasonable understanding and estimates of actual dilution and ore loss. This paper discusses the issue from the perspective of a project at a feasibility or preproduction level of development. Three types of dilution are discussed. Internal dilution (or change of support) is function of the spatial distribution of the mineralization and its relation to the operation?s selectivity. Geologic contact dilution is the unavoidable mixture at contacts or boundaries of material with different geologic characteristics, grades, or metallurgical performance. Operational planned and unplanned dilution should also be considered, sometimes incorporated by factoring the resource model, but more accurately by mimicking the grade control process. The resource estimation process always carries uncertainty, which is sometimes significant, and usually caused by several factors. These include quantity and quality of drill hole information; quantity and quality of geologic data; grade estimation methodology; dilution and mining recovery factors applied; etc. A key decision is to whether estimate as accurately as possible the in-situ geologic resource or to estimate the tons and grade of the material to be fed to the processing plant. The geologic modeling and grade estimation methods used are conditioned by this decision.

May 1, 2009

By C. Groccia

As the search for new ore bodies drives mines to be developed at greater depths, the associated high stress environments present challenges for rock support design. Excavations in highly stressed brittle rock are often subject to large volume increases due to rock failure, a phenomenon known as rock mass bulking, which can result in significant wall convergence. Support systems need to be designed to minimize the amount of bulking and to accommodate large wall convergences. In order to design such a support system, empirical guidelines are often used to predict the amount of bulking. However, the empirical guidelines that are currently available are based on a limited number of case studies and consider few input parameters, which may result in an inaccurate bulking assessment. This paper describes methods of collecting quantitative field data at Creighton mine in Canada to better understand rock mass bulking and to further develop the empirical guidelines for bulking assessment for tunnels in highly stressed grounds. Measuring

Aug 1, 2013

By Charles Camsell

If it were necessary to preface a discussion of the mineral position of the Empire by justifying one's interest in that subject, there are two points that at once suggest themselves by way of vindication. Tremendous Growth of MINERAL Consumption The first of these points has to do with the general question of the world's mineral consumption. Most thinking persons appreciate in a more or less vague way the vital rôle that has been, and is being, played by mineral products in building up the material side of our modern civilization. But, apart from that casual and almost subconscious appreciation, very few have any precise knowledge of the extent to which the growth and the operation of our vast present-day industrial structure has been made possible by, and only by, a tremendous increase in the consumption of mineral products of all kinds. The increasing use of minerals confronts us today at almost every turn. It does not matter in what direction we look-at the expansion and the change in transportation facilities, in the air as well as on land and on sea; at the increasing mechanization, not only in factory and mill but even in our domestic life; or at the constantly widening use of machinery for all phases of farm production-everywhere we meet the same phenomena of rapidly growing uses of equipment produced mainly from minerals. Without resorting to any tiresome statistics, a few figures may suffice to indicate with what enormous strides the world's mineral consumption has been advancing. The figures for recent years may be open to objection on the plea that, ever since the outbreak of the world war, conditions have hardly been sufficiently normal to give us trustworthy data-we have been living under extremes either of depression or of abnormal stimulation. During the last decade before the war, however, from 1903 to 1913, the world was moving along in a quietly prosperous manner; and we have figures, or at least reasonably reliable estimates, as to the growth in mineral consumption during that decade.

Jan 1, 1932

By Eduardo A. Pérez, Alejandro R. Alonso, Rosa María Luna-Sánchez, Gretchen T. Lapidus

Rare earth elements have been widely used in various sectors, from the aerospace and steel industries, to electronic applications, particularly in displays and batteries for portable devices. The high demand for newer and better equipment, such as cell phones, tablets and lap tops, has increased the consumption of the rare earth elements and at the same time the need for its recovery from electronic wastes. For that reason, the recycling of batteries is important, principally the Ni-HM batteries, due to their elevated content of rare earths elements, in addition to the high concentrations of cobalt and nickel. The current processes are based on dissolution in strong acid solutions (sulfuric acid concentrations from 2 to 4 mol/L), and temperatures from 30 to 90°C. In the present work, electrodes from spent Ni-HM batteries were leached using 1 mol/L H2SO4, in the presence of ozone as the oxidant, where recoveries of 96% for La, Ce and Nd were obtained at room temperature. The separation of Ni and Co from the leach solutions was performed using an electrochemical reactor, after which rare earth elements were precipitated, obtaining a mixture of its hydroxides with impurities below 1%, according to EDS analysis.

Jan 1, 2014

By I. Westermann, K. Marthinsen, M. S. Remøe

"Al-Mg-Si alloys often add small additions of e.g. Mn or Cr, to form dispersoids, which may act as nucleation sites for Mg2Si particles after homogenization. The purpose is to ensure a high density of uniformly distributed small ?’-particles, which can be dissolved during further processing prior to the final age hardening step. However, their density and spatial distribution are critically dependent on the homogenization procedure. It is therefore important to have a robust and reliable method for assessing their spatial distribution. In the present work an existing methodology for assessing spatial uniformity, the Global Shannon Entropy (GSE), has been implemented and evaluated for different dispersoid structures characterized by scanning electron microscopy. This metric is highly dependent on the parameters used, but by careful selection of adequate parameters, it can be effective in detecting non-uniformity. An important weakness with the GSE was identified, and a modification to improve on the ability to differentiate degrees of non-uniformity is suggested. To evaluate the proposed methodology, the effect of heating rate on dispersoid precipitation behaviour during homogenisation of four Al-Mg-Si alloys with different Mn/Cr-content has been investigated. The metric with the new term has demonstrated promising results, and improved the ability to differentiate degrees of spatial uniformity.INTRODUCTION Al-Mg-Si series alloys are the most common aluminium extrusion alloys and are attractive for applications in a range of sectors (e.g. construction, automotive and recently also in consumer electronics), due to their generally good combination of strength, ductility and corrosion resistance. However, their extrudability and end properties depend critically on the alloy chemistry as well as prior processing conditions. Coarse ß-AlFeSi or Mg2Si-particles typically have a detrimental effect on extrudability, while small dispersoid particles may affect recrystallization, grain growth and precipitation of Mg and Si. The strengthening potential in the final age hardening step depends strongly on the amount of Mg and Si in solid solution after extrusion. The manner in which these particles are spatially distributed will decide whether the final product will exhibit uniform properties, and the number density and sizes will determine the extent of the effect. As such, these are important characteristics."

Jan 1, 2018

By José J. Suárez

Abstract: Globally, the mining industry is expected to face the following challenges through 2020: 1. Sustaining growth amidst fierce competition 2. Containing cost increases and managing through the cycle 3. Attracting and retaining talent 4. Managing environmental concerns and improving sustainability 5. Managing volatility risks in commodity markets Our experience and research reveals that the higher performing global miners are adopting many of the following strategies: (1) Adopt a Global, Agile Operating Model (2) Be the Developer of Choice (3) Drive Capital Efficiency (4) Be the Employer of Choice (5) Integrate the End-to-End Business Model (6) Move to the Virtual Mining Value Chain This paper/presentation will provide data obtained through research on five (5) challenges facing the mining industry, and on the six (6) strategies that high performing global miners are adopting.

May 1, 2013

By N. Hwang

There has been increasing interest in the use of robotic machines, and several prototype robotic machines have been developed to automate the grit-blasting process for the purpose of steel bridge maintenance. To utilize such a robotic grit-blast machine effectively, the first consideration is automating the determination of the rust surface area to blast, on the basis of standards of practice, in a rapid manner. This study aims to propose a method to rapidly and accurately determine the rust surface area on steel bridges to blast, with consideration for the standards of practice, from images acquired via a blasting machine. The first step is to perform a color space conversion to transform the input image from a red/green/blue (RGB) color space to a hue/saturation/intensity (HSI) color space. The next step is to detect the presence of rust, using pixel-level classification via the C4.5 decision tree algorithm. Then it is necessary to confirm the blasting area by verifying whether the rust detection result satisfies the specified criteria on the basis of standards of practice. The proposed method was validated on 39 test images with various characteristics with respect to the degree of rusting and rust distribution type. The experimental results showed that the average accuracy rate of rust area classification was about 97.63%, and the success rate of the final decision of blasting area determination was 100.00% for 39 test examples. The whole processing time took an average of only 0.86 seconds per image. The preliminary results demonstrated that the proposed method not only determined whether rust was present in an image and the amount of rust but also indicated whether blasting was necessary, and, if necessary, it rapidly specified the rust surface area that should be blasted on the basis of standards of practice. The proposed method could be successfully incorporated into a robotic grit-blast machine.

Aug 1, 2013

By Don Peel, Jeremy Richards

Abstract - Aggregates (sand, gravel, and crushed stone) are low unit-cost products extracted in very large volumes for the construction of buildings, roads, and other infrastructure essential to modern society. Because of their low unit value, transportation costs are a key factor in resource economics, and deposits are commonly developed close to market (i.e., close to towns and cities, or along low-cost transportation corridors). This proximity results in potential conflict with residents over land use, disturbance, and pollution. Management of aggregate resources in Alberta is examined in the light of resource geology and distribution, and governance. A case history of development of the Calahoo-Villeneuve deposit is described, and the conflicts between residents and developers that led to establishment of an Area Structure Plan (ASP) are explored. The plan sets limits to, but at the same time safeguards, resource extraction, and defines terms for compensation to residents through a voluntary levy on production (Community Enhancement Fund). This fund is used to support community activities and to pay for a groundwater monitoring program. The ASP is examined within the context of the "Seven Questions to Sustainability" as set out by Mining,Minerals and Sustainable Development-North America (2002). It is concluded that the ASP, for the most part, provides a good model for conflict resolution and sustainable resource development, which could usefully be applied in other jurisdictions. The ASP was developed at a municipal level, and adoption at a provincial level would aid sustainable development of aggregate resources across the province.

Jan 1, 2003

By T. Gerritsen, R. MacRosty, R. Pula, P. Gebski, W. L. Ying

Furnace run-outs can cause extended furnace downtime for repair, while leaks or more severe failures in the cooling system can lead to brick hydration or in severe cases, steam explosions. These incidents can result in lost production, damage to equipment, injuries and casualties. To prevent such incidents, reliable and accurate techniques to monitor the critical components of the furnace such as refractory lining, furnace structure, taphole integrity and main water circuits are required. This paper describes several advanced methods that have been developed to assess the condition of furnace integrity, refractory lining, tapholes and cooling water circuits.

Jan 1, 2015

By S. B. Mishra

Ni-20Cr metallic coating was deposited on a Ni-based Superalloy (3Fe-19.5Cr¬0.3Ti-Balance Ni) by a shrouded plasma spray process; NiCrA1Y was used as a bond coat. Erosion studies were conducted on uncoated and plasma-spray coated superalloy specimens using an air-jet erosion test rig at a velocity of 40 m/s and impingement angles of 30° and 90°. The coating has been characterized for porosity, microhardness and microstructure and X-Ray Diffraction (XRD). An electron probe micro analyzer (EPMA) was used to obtain X-ray elemental mappings of the coating along the cross-section. Scanning electron microscope (SEM) with EDAX attachment was used to analyze the eroded surfaces.

Jan 1, 2005

By M. Marchese

It is no secret that scarcity of fresh water is an issue that at a global level in the years to come will have a major impact on the business landscape. A number of projects, beyond the mining sector, could remain on paper only due to this. At the same time, this situation is seeing the rise of new business opportunities, such as development of technologies for more efficient usage of water, water recycling, and desalinization of sea water. Despite that most of Chilean mining facilities are located in the driest area of the world, business has developed strongly and actively for more than a century. However, the negative effect on the water reservoirs and the environment is, lately, resulting in the reduction of the authorized water rights. Holding Water Rights for any given volume does not guarantee that the resource will be available when needed. A recent report from the United Nations on global climate change indicates that global warming can be directly related to changes in the natural and human environment. Chile would not be an exception. The reduction in snow levels in the high Andes and reduced rainfall during the so called "Bolivian winter", have directly affected the replenishing of the underground water reservoirs in the lower parts of the valleys, where most of the extraction of the resource takes place. Mining facilities shall be designed to reduce potential environmental effects, using proven technologies, and considering the best practices available. These measures shall constitute a complete structural framework for the environmental impact assessment (EIA) of the Project. The measures to prevent and mitigate the impacts on the water resources shall be considered during the design stage of a mining project. Current and future mining projects in Chile are conscious that the increasing pressure on the limited water resources is becoming unsustainable, and are already facing the water scarcity and social pressure by implementing sea water desalination plants, including long pressurized pipelines to the mine sites (e.g. Escondida, Candelaria, El Morro, Regalito). This paper presents, in summary, an analysis of the present and potential future scenarios.

Jan 1, 2007

By K. Fumimura, T. Nishimura, M. Kohno

When applying numerical techniques to problems of deformation of rocks, the body to be analyzed is divided into small portions and is represented by a system of points linked together with the neighboring points. In the so-called distinct element modeling, the particles in the system are directly connected by springs and a contact law is used to specify forces on the particles to simulate the mechanical behavior of the body. The relation between the spring stiffness and commonly measured material properties, such as the Young’s modulus and the Poisson’s ratio, should be known a priori. For the general case of a random packing of particles, the relation is found by means of a process in which a system of particles and set of parameters are prepared to simulate a set of specimen-size test and then the input parameters are chosen to match the measured material properties. The validity of the numerical result is only demonstrated by comparison model behaviors with the measured responses. The process includes trial-and-error manner, therefore, no model is complete to reproduce the mechanical properties. In this paper, a relation between the spring stiffness and the elastic constants; the Young’s modulus and the Poisson’s ratio, is introduced to a three-dimensional distinct lattice spring method. Two simple numerical examples will be presented to demonstrate the performance of the method with the procedure for the determination of the spring stiffness.

Jan 1, 2015

By J. C. Farge, G. G. Jacox

"The effect of composition and process variables on the properties of Marmet and modified Ni-Hard slugs will be discussed. The effect of shape on the over-all performance of grinding media and its relationship to the end product has been investigated and these results will be reviewed. The cost effectiveness of slugs versus balls has been well documented under various operating conditions and this will be presented in detail. IntroductionThe selection of grinding media is based on the cost-to-wear ratio combined with the consideration that it must stand repeated impacts without breaking. The specific consumption of grinding balls and slugs depend s primarily on their microstructure, which, in turn, is controlled by chemical composition and by the processing condition s to which they are subjected during manufacture.The first part of the paper deals with the optimization of alloy content to produce cast iron slugs with microstructures consisting essentially of marten site and carbide and with hardnesses of 650 B.H.N. and higher. The second part deals with the use of cast iron slugs to replace forged steel balls in milling operations. Tests indicate that the shape of the media has little if any effect on results and that the hardness and microstructure of grinding media will determine its relative performance. Where price is equal under similar milling conditions, the cost effectiveness of cast iron slugs is superior to that of forged steel balls.In order to understand the role of alloying elements in cast irons, it is judicious to consider the microstructural changes which occur during solidification and subsequent cooling, particularly from above the eutectoid temperature. Solidification starts with the formation and growth of dendrites of austenite. As temperature decreases, an eutectic nucleates and grows between the primary austenite dendrites. Immediately after solidification, the structure consists of proeutectic austenite and of the eutectic of primary carbides and austenite. On cooling to room temperature, austenite can be retained or transformed to pearlite, bainite, martensite or mixtures thereof. It is necessary to prevent decomposition of austenite into pearlite by adjusting the alloy content. For best abrasion resistance, the microstructure at room temperature should consist essentially of martensite and carbide. These types of irons are known as ""martensitic irons "". Depending on the carbon content of the austenite and cooling rate, "" as-cast"" martensitic irons will contain different proportions of martensite and retained austenite. The more carbon in solution in the austenite, the lower is the temperature at which the martensitic transfoemation takes place. By the time room temperature is reached ., the transformation is seldom complete, and the end product is generally a mixture of martensite and retained austenite."

Jan 1, 1980

By Jr. Carmichael

"THE MAYO AREA was prospected as early as 1887. The first major activity started in 1898, when the Stewart River and its tributaries were examined for placer deposits, and in succeeding years the district became a small producer of placer gold. The first discovery of the lead-zinc-silver mineralization which has become the main interest of the district occurred in 1906, when a vein was found in the canyon of Galena Creek on the northwest slope of Galena Hill. This deposit was later known as the Silver King mine. In 1919 further discoveries were made on Keno Hill, approximately 15 miles east of the Silver King, the most important being the No.9 vein. Directly or indirectly, these finds are attributable to the search for placer gold, as galena was frequently found in the stream gravels.The 1919 Keno Hill discoveries were acquired by Yukon Gold Co. and operated through a subsidiary, Keno Hill Ltd., from 1920 to 1923. Most of the production came from No.9 vein. In 1921 Treadwell Yukon Corporation entered the field and acquired the Ladue mine. This company continued to operate for 21 years. It acquired in succession the Ladue, Sadie, Friendship, Lucky Queen, Elsa, Silver King, and Calumet mines. Its record of successful operations is very largely the achievement of the late Livingston Wernecke. Under his direction, the Treadwell Yukon Corp. produced metals with a gross value in excess of $21,000,000, in the face of greater transportation problems than exist today and with considerably lower metal prices.Treadwell Yukon ceased operations in 1942. Its entire assets were acquired in 1946 by United Keno Hill Mines Ltd., which has substantially increased the original holdings. It has drawn the bulk of its production from the Hector mine, adjacent to the Calumet. The Hector was not developed by Treadwell Yukon because of legal disputes among the vendors. It has proven to be the largest deposit yet discovered in the district."

Jan 1, 1949

By B. Samanta

Abstract - Ore reserve estimation, based on sparse drill hole data, was conducted for a placer gold property in Nome, Alaska. A problem with sparse data is that random subdivision of the data into modelling and evaluation subsets (as is commonly done) becomes a problem, as random selection may result in biased/skewed subsets. Therefore, a technique that combined data segmentation with genetic algorithms (GA) was applied to divide the samples into three equivalent subsets: training, validation and testing. Data segmentation was done on the basis of the distribution of gold values. Neural network and a variety of kriging techniques were used to estimate gold grades. A multi-layer feed forward neural network along with "early/quick stop" training was used for neural network modelling. A comparative evaluation of kriging and neural network methods was then performed. The results revealed that neural network was generally superior to the kriging techniques for gold grade estimation in the Nome deposit.

Jan 1, 2002