Search Documents

By A. Ochieng

Solids suspension influences the quality of mixing and energy requirement in a solid-liquid system, both of which determine the efficiency of industrial processes such as nickel precipitation. Nickel solids concentration distribution in a stirred tank was investigated using computational fluid dynamics (CFD) and experimental methods. The concentration distribution of the nickel solids was compared with that of sand and glass. The laser Doppler velocimetry (LDV) method was used to measure the velocity field for the liquid-only system and an optical technique was employed to determine the axial solids concentration distribution. Regions of in homogeneity in the tank were identified. It was found that, for a given solids loading, the solids concentration distribution depended on both particle size and particle size distribution. High solids loadings were investigated and a difference in the concentration distribution pattern was obtained with nickel, flint glass and sand particles. The CFD simulation results highlighted problems that could be associated with some conventional experimental methods of determining solids concentration distribution in a stirred tank. Keywords: nickel; CFD; simulation; mixing; solids suspension.

Jan 1, 2010

By L. Sahu, S. Bhattacharya, S. Dey

"An ideal procedure to determine the limits of flotation-based separation, as is the case with washability analysis for density separation, does not exist. Therefore, a procedure called release analysis, considered to be the counterpart of the washability process in density separation, was developed to evaluate the flotation characteristics of coal fines. Since flotation is a complex process it is necessary to know the maximum recoverable yield that could be achieved at a target ash level and what could be obtained by release analysis. Due to a number of limitations in the initial procedures, modifications were recommended by various researchers to generate an optimum separation curve. This paper presents a review of, and a discussion on, the chronological evolution of release analysis methodology over the decades. Notwithstanding the availability of a standardized release analysis procedure, such as BS 7530, the paper highlights the critical parameters involved in the procedures, such as coal type, feed characteristics, choice of reagents and dosage, operator bias, and design features of the flotation cell IntroductionCoal is a heterogeneous substance consisting of various combustible constituents (macerals) and associated mineral matter. The kind and abundance of the various macerals present in the coal, such as vitrinite, semivitrinite, exinite, and inertinite, determine the type of coal. As macerals are formed by biological degradation of different parts of the plant material, they have different properties based on their original composition. Coal cleaning processes are dependent on the differences in physical properties between the coal components (the macerals) and also between the macerals and the mineral matter. Thus the cleaning characteristics of the coal might vary from one type to the next. The cleaning processes influence the distribution and the concentration of macerals in the various size and density fractions of the cleaned product."

Jun 1, 2019

By Dolly Chakraborty, S. Ranganathan, S. N. Sinha

Pre-reduction of chromite outside the submerged-arc furnace (SAF) can significantly lower the specific power consumption in the SAF process. Conventional processes for the pre-reduction of the ore operate at relatively high temperatures, at 1400-1500°C. It is possible to enhance the rate of reduction at low temperatures by optimizing the flow rate of inert gas over the reaction site. The influence of the flow rate of inert gas on the rate of reduction of chromite ore was investigated. The rate of reduction initially decreased wit the flow rate of the gas. It increased subsequently at higher flow rates to be followed by a decrease again. There was an optimum flow rate at which maximum reduction could be obtained. It was possible to achieve high levels of reduction at 1200°C by optimising the flow rate of the gas. The degree of reduction obtained was comparable to that obtained at 1400-1500°C, by conventional process routes.

Jan 1, 2007

By P. K. Sahoo, C. R. Ray, S. S. Rao

This paper deals with various factors affecting the strength of chromite briquettes which plays a vital role in the smelting of charge chrome / ferro chrome production. Appropriate briquetting parameters like molasses and lime binder level, molasses quality, particle size distribution and segment condition etc. are essential to guarantee quality briquettes in the successful use of briquette and chromite ore fines. In developing a technology for briquetting of chromite ores, it is important not only to study the grain size characteristics of the chrome ore fines but also to make an informed choice of the type and quality of the binder and the condition for producing a physically and chemically competent green and cured briquette. This paper also describes the effect of strength of briquettes on various parameters of charge chrome production as the use of quality briquettes in the production of high carbon ferrochrome alloys has a number of operational, metallurgical and economic advantages. It is also a requirement for submerged arc furnace operation that the charge be adequately porous to allow gaseous products of the reduction reaction to escape from the furnace charge burden without hindrance. Otherwise, furnace material would erupt causing electrodes and furnace other equipments damage and risking the safety of the work force. The briquette, because it replaces lumpy charge but has an advantage of smaller size, allows for an uniform and porous charge so that the ascending gaseous products can escape freely. Finally this paper deals with furnace operational results with varying proportion of briquettes having same strength.

Jan 1, 2007

By J. C. Carrasco, M. Sánchez, R. Jara, F. Marquez, F. Parada, R. Parra, J. Palacios

In past years, Chile has been the largest copper producer in the world and for 2002 mining represented country average of 10 % of the GDP, accounting for 47 % of the total exportation. As copper sulphides are the main mining resources in the country, the metal is produced using the classical processes of flotation and pyrometallurgical extraction. Seven copper smelter plants, which extends from the northern Atacama desert to the central part of the country produced1,522,000 metric tons of fine copper in 2002, approximately one half of total copper concentrate production, with a notorious environmental impact due to the great amount of slag produced during these extraction steps. In this work, a global characterization of copper pyrometallurgical slags produced and disposed of in Chile and worldwide is done, and the concept of total project development is considered to explain the scopes of the study, recovering different compounds and generating new activities around mining. The presentation is completed with the proposal of various methods and techniques being developed today in a joint project between smelter plants and the University of Concepción, with the support of the Chilean government and mining companies, addressed to generate new materials from copper slag. Recovery of copper, molybdenum, precious metals, silica and iron, that is the most abundant component of the slag, are the goals for this research. Metals, commercial compounds, alloys and different forms of iron oxides for steel industry are proposed products.

Jan 1, 2004

By F. B. Samani, B. Stabel

The 1,000 MW Hydro Power Station Masjed-e-Soleiman (formerly called Godar-e-Landar) in Iran is under construction since 1992. The rock engineering aspects of the major underground structure, i.e. the powerhouse cavern shall be reported on in detail. The geotechnical investigations are described and results given. The results of several geotechnical analyses are presented. The designed and executed rock support is given. A description of the monitoring systems and typical measurement results obtained during and after excavation are presented. The lessons learnt during construction of the Stage-I powerhouse cavern were applied on the extension of the powerhouse cavern, which is to house an additional 1000 MW. Details regarding the unexpected behaviour of the Mudstones are given. Die 1000 MW Wasserkraftanlage Masjed-e-Soleiman (vormals Godar-e-Landar genannt) befindet sich seit 1992 in Bau. Dieser Artikel berichtet im Detail über die felsbaulichen Aspekte der Untertagebauwerke, insb. der Maschinenkaverne. Die geotechnischen Untersuchungen werden beschrieben und deren Ergebnisse wie die Ergebnisse verschiedener Berechnungen werden präsentiert. Die geplante und die ausgeführte Felssicherung wird angegeben. Die eingebauten Überwachungseinrichtungen werden beschrieben und typische Ergebnisse während des Aushubs und danach werden dargestellt. Die Erfahrungen beim Aushub der Kaverne der Stufe I wurden beim Entwurf der Kaverne der Erweiterungsstufe II, die weitere 1000 MW beherbergen wird, berücksichtigt. Details zum unerwarteten Verhalten des Schluff-/Tonsteins werden angegeben. La centrale hydroélectrique de Masjed-e-Soleiman (dénommée anciennement Godar-e-Landar), d’une puissance de 1.000 MW, est en construction depuis 1992. Un rapport détaillé sera présenté sur les aspects relatifs à la construction en enrochements de l’aménagement souterrain principal, à savoir la caverne abritant la salle des machines. Une description des investigations géotechniques réalisées y est fournie ainsi que les résultats correspondants. En outre sont présentés les résultats de plusieurs analyses géotechniques. L’ancrage dans la roche tel que projeté et réalisé est présenté. Une description des systèmes de contrôle ainsi que les résultats de mesures typiques obtenus au cours des travaux d’excavation sont donnés. Les leçons tirées lors de la construction de la Phase 1 de la caverne de la salle des machines furent appliquées à l’extension de la caverne de la salle des machines, qui doit abriter une unité supplémentaire d’une puissance de 1.000 MW. Par ailleurs, des détails sont donnés sur le comportement inattendu des argilites.

Jan 1, 2003

By K. M. Godiwalla, S. Ranganathan

The thermal state in submerged-arc furnaces (S.A.F.) producing ferro alloys is important for the conditions of both the grade of alloy produced as well as specific energy consumption. The temperature profile in the S.A.F. is affected by the endothermic chemical reactions and the rate of gas evolution. The gas evolution commences at about 900 C due to the reduction of iron in the ore. A first-principle-based 2-D model has been developed to predict the temperature profile in the furnace. In this study, four ores of different grades have been considered in order to simulate the thermal profile in the S.A.F. The influence of the composition of the ore on the thermal profile and its significance in rationalisation of charge distribution to optimise the process are discussed.

Jan 1, 2007

By R. J. Fruehan

Slags have many useful functions in iron and steel making. In particular, slags are used to remove impurities such as sulphur, phosphorus and inclusions from the metal, and a large amount of research has been done in this area. Slags also insulate the metal thermally and form reactions with the atmosphere such as reoxidation and nitrogen pick-up. However, slags serve other more unique functions, several of which are reviewed in this paper. The role of slags in new iron smelting processes with regards to reduction of ore and gaseous desulphurization are discussed. In iron smelting processes, much of the reduction occurs by the reaction of carbon in the char and the metal suspended in the slag with iron oxide dissolved in slags. The slags also react with the gas resulting in sulphur removal from the process. The mechanisms of these reactions and pilot plant data for these processes are given in this paper. Slag formation within ferrous burden materials affects the cohesive zone and the performance of the blast furnace. Recent theoretical and experimental findings on this topic are presented. In the electric arc furnace, foamed slags are used to allow for higher power operation and productivity. Of particular interest, foaming in stainless steel production is more difficult than for normal steels. The foam index, or the ability of the slag to foam, for stainless steelmaking is similar to that for carbon steelmaking slags. The poor foaming is due to the lack of gas generation for the foam. Methods to increase foaming in stainless steelmaking are discussed.

Jan 1, 2004

CSIRO Mineral has recently developed a new electron microprobe based system for characterizing zircon grains from heavy minerals sand deposits. The system acquires cathodoluminescence (CL) spectra, X-ray and backscattered electron (BSE) signals in parallel. By scanning over a specified target area, CL wavelength and X-ray element distribution maps of polished zircon grains can be acquired. Post-inspection of the combined dataset using in-house developed software enables correlations between chemistry and structure to be investigated. The new method offers significant benefits over traditional CL and BSE techniques in that direct comparison with the elemental concentrations over the same region is now achievable. By combining the electron microprobe results with data for the same mapped region obtained via a nuclear microprobe, significantly better detection limits (~ 1ppb) for elements with atomic numbers greater than iron are possible. The ability to measure spatially related analytical data and then investigate the correlation of the CL spectra with chemical data is an important advancement in the characterization of zircons. Key words: zircon, characterization, cathodoluminescence, backscattered electron, electron microprobe, nuclear microprobe, chimage, proton induced x-ray emission.

Jan 1, 2003

By A. Basçetin

Equipment selection in mining engineering is one of the most important decisions that affects the mine design, production planning and economic parameters in open pit and underground mining. Mine planning engineers generally use their intuition and experiences in decision making. Mostly, linguistic variables (the weather is raining, soil is wet, etc.) come into question and decision-makers may not know how these variables are computed. Since the advent of the fuzzy set theory, these uncertainties are easily interpreted in the decision-making process. The development of computer technology and programming of colloquial language with expert systems have considerably reduced decision-makers? burden. This paper reviews the development of a computer programme software called EQS (EQuipment Selection) that automates equipment selection in mining engineering using fuzzy set theory. The EQS with an introduction of the concepts and theories of multiple attribute decision-making, the fuzzy set theory, and EQS applications to mining industry problems with case studies are presented

Jan 1, 2006

By M. Shapiro, L. A. le Grange, B. Henning

Effective pyrometallurgical process vessel design requires accurate assessment of the heat fluxes through the walls of the furnace. This is particularly important for freeze lining operation which is designed to protect refractory materials exposed to chemically corrosive molten contents, or facilitate high temperature operation when the refractory materials are used at conditions close to their service limits. Numerical modelling of fluid flow and heat transfer in process vessels is often used to aid in the design of process vessels. Sophisticated models are used to analyse the three dimensional flow and heat transfer predicting the effects of electrical heating, magnetic stirring, buoyancy, shear forces, various cooling effects and ultimately heat fluxes at the walls of the furnace and refractory. Traditionally these models are applied to the separate single fluid systems in a vessel such as the freeboard region including the arc, the slag region and the metal bath. Boundary conditions such as shear forces and heat fluxes between connecting regions such as the slag and metal bath are either estimated or carried over from separate solutions. Shortcomings in these traditional approaches include the estimation of sometimes critical boundary conditions leading to unreliable heat flux calculations. Also when boundary conditions are carried over between solutions, the process is difficult to set up, time-consuming and finally not fully coupled. In this paper the definition and results of a fully integrated numerical model of a complete arc furnace are presented. The most important mechanisms acting in an arc furnace were considered, including the fields of electrical potential, current, magnetism, momentum, heat transfer and radiation. Temperature dependant properties included electrical conductivity, density, viscosity, and thermal conductivity. The geometry consists of the freeboard, the arc, slag, metal baths and different refractory regions. Although the combined model of air, slag and metal would be defined as a multi-phase problem it is not solved as such. Instead the different fluids are separated by sets of special solid baffles. These baffles allow the implicit transfer of current, magnetism, heat transfer and shear forces between the different fluids and disallow mixing of the separate fluids. The strengths of the integrated model are threefold: Firstly, it provides robustness in defining the geometry and boundary conditions for the overall model. Secondly, it provides the capability to switch on and off individual mechanisms such as buoyancy, magnetic stirring and shear forces in order to observe their individual importance. Finally, it provides a useful tool in the design process through its ability to obtain results of parameter changes in short time scales.

Jan 1, 2004

By F. T. Cawood

The distinction between real estate ownership and that of interests in the property is fundamental to the appraisal of mineral properties. This distinction affects the nature and understanding of security of tenure and, consequently, the perception of what constitutes fair value. Legal matters are a particular concern because of their influence on security of tenure, ownership definition and use restrictions. The dynamics of the market and the complex interrelationships between the factors of production define value at a specific point in time for the bundle of rights, interests and assets that constitute a mineral property. Because each mineral property is unique, physically immobile and of a wasting nature, its usefulness to its owner and society must be optimized. The US Appraisal Institute (2001) classified the forces that affect land use as the cultural, political and economic attitudes of society. These forces culminate in laws that often dictate the purposes for doing appraisals. Once the legal definition of the asset is understood, valuers can decide on the valuation process that will support the final valuation approach.

Jan 1, 2004

By C. Nexhip, S. Sun

Critical to understanding and controlling phase mixing and separation in metallurgical processes, is the development of reliable experimental techniques to measure interfacial properties of melt systems. A series of experiments has been carried out to determine the effect of oxygen potential on the surface tension of liquid copper. Using an electromagnetic levitation method, a surface tension-oxygen chemical potential adsorption isotherm was produced for the Cu-O system at T 1400 K. The surface tension results show good agreement with the literature values e.g. within 3 per cent for pure copper. The Belton `ideal' adsorption isotherm was applied, and the following equation derived to best fit the experimental data ? =1251-77.5 1n41+ (2.79x105 . pO1/2)](mN.m Using this equation, the surface tension of copper was calculated/predicted as a function of oxygen potential at 1400 K, and showed excellent agreement with the experimental values. This confirmed that the adsorption behaviour of oxygen in liquid copper is ideal. The saturation coverage of oxygen on the surface of liquid copper was determined to be T0 = 6.65 µmoles.m,-2 corresponding to an area per adsorbed oxygen atom of ao ? 25 Å2. These values agree well with those cited in the literature, and our experimental data cover a very wide range of oxygen potential (10-5 to 10-17 atm). Keywords: levitation melting, surface tension, Cu-O alloys, oxygen potential, adsorption isotherm, surface coverage.

Jan 1, 2004

By M. Bhandari, D. Norval

The bulk of plain carbon steel is produced through conventional Basic Oxygen or Electric Arc Furnace routes where the development of the AC Ladle Furnace has made it possible to also produce alloy steels. Smaller Ladle Furnaces have limitations such as lower efficiency; high electrode consumption and diminutive yields rendering them uneconomical to operate and making the processing of low carbon steel grades difficult due to carbon pick up. The demand for special steels and alloys with strict specifications is increasing while commodity prices remain competitive. The production of special steels and alloys have specific process control requirements and the development of the induction melting furnace (IMF) has made it possible to produce smaller batches economically. Refining and alloying of the melt in the IMF further enhance the efficiency. The INDUREF furnace offers increased productivity and flexibility through increased thermal efficiency and can be utilised for holding molten metal for further processing such as granulating, atomising, nitriding, alloy additions and desulphurisation of Ferro-alloys and steels. The system utilises a specially engineered ladle which is placed in an induction-heating assembly comprised of a stationary water-cooled copper coil and lamination packs. The addition of equipment for vacuum degassing and decarburisation of steels and alloys is also feasible. Benefits are: ? No electrode consumption or carbon pick-up ? Lower installation, operation and maintenance cost. ? No line-flicker facilitates operation on a weak power grid. ? Good power factor and balanced load ? No skull formation and reduced refractory consumption ? Higher yield of Fe-alloys ? Automatic controlled stirring

Jan 1, 2004

By R. J. Durrheim

The seismicity of the Witwatersrand Basin and Bushveld Complex has been analysed, revealing significant differences in source and damage mechanisms. A comparison of mining taking place at similar depths and extraction ratios indicates that the seismic energy release rate is considerably lower in the Bushveld Complex. Technologies introduced in the past decade to manage the risk of rockbursting are reviewed and assessed. These include geophysical methods to detect hazardous structures ahead of mining, new mining layouts and support systems, and the mechanization of in-stope processes. Despite important differences in geology, in situ stress, mining layouts and methods, there are many opportunities for the reciprocal transfer of knowledge, experience and technology between the gold and platinum mining sectors to improve the management of the rockburst risk.

Jan 1, 2005

By A. Normanton, B. Harris, V. Ludlow, S. Riaz

Why does a continuous casting mould powder, which works successfully on a particular caster with respect to semi quality, fail to perform on a caster of a similar design utilizing liquid steel from a similar route for an identical product without some tuning of its make-up and composition? In casting sequences of the same steel grade, why do some apparent random heats produce poor surface quality with respect to cracking when otherwise good surface quality is realized? The answer to these questions lies in the interaction of the mould powder, the casting hardware, and the casting process variables. Using, as examples, data collected from within Corus UK and during collaborative work on the assessment of mould powder performance and its effects on surface quality, the interaction of the mould powder, the casting hardware and the casting process variables is explored. The steelmaking route and its associated alumina load, unexpected changes to slag chemistry, infiltration of the slag into the mould strand gap, and the nature of the slag film are all shown to affect powder performance. Keywords: continuous casting, mould powders, alumina, slag films

Jan 1, 2004

A Seismic Hazard Scale (SHS) has been developed to provide a practical seismic hazard assessment tool applicable to mine site personnel. It has been applied to seismic data sets from numerous Western Australian mines. The SHS is applicable when quantifying seismic hazard on a mine wide scale, on a mining block scale, and on a local cluster-by-cluster scale. Spatial mapping of variations in seismic hazard is a particularly powerful application of the scale. The SHS is sensitive to temporal increases in seismic hazard. It has also been shown that the SHS can be applied to estimate seismic hazard when seismic monitoring data are not available. The SHS is a simple derivation of the Gutenberg-Richter relation. There are assumptions and limitations to the SHS that need to be considered when applying it to mine seismicity data.

Jan 1, 2004

By J. D. Steenkamp

"In July of 2016 and June 2017, major tap-hole repairs were carried out during the annual shutdown of two 63 MVA submerged arc furnaces producing ferrochromium in South Africa. The hot excavations of the tap-holes allowed for a study of the wear profiles. Subsequent thermodynamic calculations allowed for the quantification of the potential for chemical reaction between refractory and slag or alloy contributing to wear in the tap-hole area. Results from both wear profiling and thermodynamic calculations are reported here. IntroductionFerrochrome (FeCr) is an essential alloy in the production of stainless steel (Gasik, 2013). In 2017, 11.7 Mt of FeCr was produced (Pariser et al., 2018.). The main producers were China (39%), South Africa (29%), Kazakstan (12%), and India (8%).A number of grades of FeCr are available to producers of stainless steel, including high-carbon ferrochrome (HCFeCr) (Gasik, 2013). HCFeCr typically contains 60–70% Cr and 4–6% C (Basson and Daavittila, 2013). When the chromium content is lower (50–55% Cr) and the carbon content higher (6–8% C), it is referred to as charge chrome. Charge chrome is typically produced in South Africa due to the grades of ore available.FeCr is produced in submerged arc furnaces (SAFs) and in open arc furnaces (Mc Dougall, 2013) by carbothermic reduction of oxide raw materials. In a SAF the electrode tips are submerged in a porous charge mix. In FeCr production, the electrical energy is mainly liberated by resistive heating of the wet coke bed (Barker et al., 2007; Steenkamp et al., 2017). Thermally conductive lining design philosophies are typically applied in SAFs producing FeCr (Steenkamp, Denton, and Hayman, 2017; Coetzee, Duncanson, and Sylven, 2010; Coetzee et al., 2010).In July of 2016 and June of 2017, major tap-hole repairs were carried out during the annual shutdown of two 63 MVA SAFs producing FeCr in South Africa. The hot excavations of the tap-holes allowed for a study of the wear profiles. Both SAFs were operated on the same site, by two different operating crews, using the same raw materials. The major difference between them was that the SAF excavated in 2016 was an open SAF (referred to as Furnace A) and the one excavated in 2017 was a closed SAF (referred to as Furnace B). In an open SAF, a gap exists between the top of the steel shell and the roof, with the top of the burden being open to the atmosphere and the CO-rich off-gas being combusted as it escapes. In a closed SAF, the roof is attached to the steel shell and the CO-rich off-gas is collected from an offtake on the roof for further treatment and used in downstream processes.The paper presented here reports the macro-scale observations on refractory wear for the two SAFs, and studies the potential for chemical wear of refractory by slag and alloy as a potential contributing factor to the tap-hole wear observed."

Jun 1, 2019

By C. Birch

"A mineral resource royalty is payment to the holder of mineral rights for the utilization of the mineral resource. In South Africa, this payment is made to the State as holder of the mineral rights (The Mineral and Petroleum Resources Royalty Act of 2008). The principle purpose of this research paper is to identify if the State is benefitting from the mineral resource royalty by considering its impact on seven individual Witwatersrand gold mines.For this study, a simple financial optimiser model was created in Microsoft Excel that links the ore flow, block listing and the cash flow (excluding or including the cost of the mineral resource royalty). Mixed integer linear programing (the Excel Solver function) is utilised to optimise either profit or NPV (at 9% and 12%) by adjusting the cut-off grade.The impact on each of the seven mines mine was different but overall R7.9 billion is estimated to be paid in mineral resource royalty over their expected remaining lives. Due to the cost of the mineral resource royalty and increasing the cut-off grades, the total revenue decreases by R10 billion. A significant portion of this lost revenue would have been paid to the State in the forms of other taxation including company income tax which decreases by R2.8 billion. It is recommended that an industry wide investigation be conducted to determine if the resource royalty is adding to the State’s revenue, or destroying value including premature job losses. IntroductionTaxation of mining companies has become a very topical subject in the context of the postapartheid South African economy. There have been increasing calls for equitable re-distribution of mineral asset wealth for the benefit of all South African citizens and not just to an elite few. As part of the Mineral and Petroleum Resources Development Act (MRDPA) of 2002, the Mineral and Petroleum Resources Royalty Act of 2008 was introduced and came into effect in 2010 (South African Revenue Services, 2008). A mineral royalty is payment to the holder of mineral rights for the utilization of the mineral resource. In the case where the holder of the mineral right is the State, then this payment is made to the State (Cawood, 1999). Studies on the potential impact of the mineral resource royalty on the minerals industry have been conducted during the formulation of the Act and subesquently. These include Cawood and Macfarlane (2003), who suggested a cap of no more than 3% (Cawood and Macfarlane, 2003), as well as Cawood (2011), who predicted rising cut-off grades and thus reducing mineral reserves. In 2013, Grobler completed a Masters in the Faculty of Economic and Management Sciences at the University of Pretoria and concluded that the impact of the mineral resource royalty on the economy is positive. She stated that the royalty has caused operating expenses to increase, but this does not appear to be significant. Furthermore, she stated that the royalty has not affected the way the mining industry operates (Grobler, 2014)."

Jan 1, 2016

The relationship between neural network (NN) performance and the parameters that form the architecture of the neural network is complicated. This paper studies an issue that is still controversial—the effect of the number of neurons and number of hidden layers on NN performance. This paper tests if the above parameters affect network performance when the NN is trained according to the quick stop strategy. It was determined that the number of neurons did not have any effect on the NN performance for a single layer or a double layer network. It was also found that the training error and calibration error could be poor indicators of the prediction correlation coefficient.

Jan 1, 2003