Search Documents

By Xiaoxu Sun, Jianchao Yao, Jiancheng He, Shijie Lu, Hongxi Zhou

"The ball mill performance relies on impact grinding, but it has disadvantage of the lower efficiency when the ore is finer; while tower mill relies on friction shear affection with high energy efficiency, which is considered to be one of the most potential fine grinding equipment all over the world. Generated by the agitator device, the internal media movement is complex because of comprehensive interaction of screw mechanism, cylinder structure and adjacent media, which is the key factor of grinding process. But the kinematics parameter ,such as speed, acceleration, stress and so on, of media motion cannot be obtained through traditional laboratory test method, which restricts deeply research on finer grinding mechanism seriously. In order to solve this problem, characteristics of media motion in tower mill is studied via the discrete element method. Coefficient of restitution, coefficient of static friction and coefficient of rolling friction are the key parameters affecting the media movement, which were calibrated by stacking angle test firstly. A 3kW tower mill is established as the model for simulation. At last one appropriate simulation strategy is selected to increase simulation accuracy. The characteristic of media motion is obtained based on the computer simulation analysis: macroscopically, the media in tower mill is a dynamic equilibrium state generally accompanied by spiral up and down movement all the time. And it has been found that the maximum lifting height is proportional to the rotation speed of agitator shaft. The velocity of media at the edge of screw stirrer is biggest, while the velocity of media near the cylinder wall is smaller, so the grinding performance between the two ring areas is the best. The rotational speed of agitator shaft and media filling ratio are the two most important operating parameters in tower mill. The impact curve of two main operating parameters on the grinding intensity and energy efficiency are obtained. All these can provide theoretical basis and technical support for operating parameters setting of industrial tower mill."

Jan 1, 2018

The status quo of ecological rehabilitation in metal mine in China and progress in the technology for ecological rehabilitation are presented, including soil reconstruction, soil improvement, plant selection. The present and future research fields are suggested: basic theory of ecological rehabilitation, operative technology of ecological rehabilitation, new technology application research and ecological rehabilitation plan, management and policy.

Jan 1, 2014

By S. Banisi, O. Farshid, M. R. Rozebehi, A. Bahar, A. Arghavani, M. Mahdavi

At the rougher flotation circuit of the Miduk copper concentration plant (Kerman, Iran) five column cells (CISA) with the diameter of 4m and height of 12m using static mixer type (MicrocelTM) spargers have been installed. Based on the initial design, columns should accept a feed rate of 625 t/h with 80% passing size of 90 µm and solids concentration of 28% and produce 88% of the plant concentrate (i.e., 22 t/h) containing 32% copper. Due to mechanical and processing problems this objective was never realized and theses columns were remained out of operation from the commissioning time (2005). A new attempt with the aim of returning these cells into operation started in 2013. The results of an extensive study indicated that spargers plugging due to the entrance of small amount (2 kg) of coarse particles (up to 2.5 cm) because of usual problems at the plant environment was the main reason of columns non functionality. With a change in the recycle pump inlet design to the column, which prevented the entrance of coarse particles to the spargers, the operation of the column significantly improved. It was found that in order to have a stable operation of the columns at the rougher stage the feed rate for each column should be reduced from 125 (design) to 70 t/h. The air superficial rate had to be also reduced from 1.9 (design) to 0.6 cm/s. A period of 10 days of continuous operation showed that the carrying capacity was 0.23 (g/min/cm2) which was significantly lower that of the design value (i.e., 0.58). The gas hold up was found to be lower than 10% beyond which columns started to move to the turbulent state indicated by "boiling" froth. The average life time of spargers was determined to be 20 days which considered to be very short. The average recovery and concentrate grade of these columns were found to be 68% and 32%, respectively. The high wear rates of spargers, unusually high level of maintenance and supervision needed and instability of the operation made the plant managers not to use column cells as the roughers.

Jan 1, 2014

By S. H. Morar

Froth stability is widely recognized as a key driver of flotation selectivity. It is well known that froth stability is affected by the type and quantity of surface active reagents present (frothers), and the concentration and hydrophobicity of solid particles present. While some studies have been performed on the effect of frothers on froth stability in three-phase systems and the hydrophobicity of particles present, very little work has been performed on the effect of solids loading on froth stability. This may be due to insufficiently robust measurement techniques. This paper investigates the use of a new machine vision measurement to measure solids loading, and the relationship between this measurement, bubble size, and bubble burst rate on the froth surface. Keywords: froth flotation, machine vision, solids loading

Sep 1, 2012

By H. Sarvamangala

Selective separation of alumina, silica, calcite and apatite from hematite was achieved through microbiologically induced flotation and flocculation in presence of bacteria (B.subtilis) and that of hematite from apatite after interaction with yeast (Saccharomyces cerevisiae). Bacterial and yeast metabolites containing extracellular proteins were characterized from mineral-grown cell free extract. Bacteria and yeast can adhere to mineral surfaces and influence subsequent separation of the minerals. Bacteria functioned as a stronger depressant for hematite, while yeast cells depressed apatite at neutral pH. Selective affinity of the bacterial and yeast cells towards the mineral surface was observed through adsorption studies. Extracellular proteins (EP) were isolated from B.subtilis and yeast. The protein profile of the EP of bacterial and yeast cells grown in presence and absence of minerals was studied. This study has demonstrated the utility and amenability of microbially-induced mineral beneficiation of iron ores through bacterial and yeast cells and their metabolic by products.

Sep 1, 2012

By D. Z. Wang

A red copper plate, discovered in the ruins of Dachengshan in Hebei province, was recognized as a forged one rather than a cast one, which means it was probably made from natural copper during the Longshan Culture period (2200~2208 BC) in the Chinese history. The copperware, found in the Niangniang Tai relics in Wuwei city, Gansu province, contains 99.6% copper and 0.4% Sn, Pb, Sb and Ni, which was guessed to be made during the Qijia Culture about 2000~ 1900 BC in the Chinese history in the late Neolithic before Shang dynasty. This shows that Chinese ancestors were able to distinguish, sort and use some native metals and minerals more than 4000 years ago.

Jan 1, 2014

By Anuj Narang

Large-scale separation or flotation cells, used in the primary extraction in the oil sands industry, are integral parts of the overall process of bitumen extraction. Good regulation of the interface level between the bitumen froth and the middlings in these cells can result in a significant improvement in bitumen recovery and throughput, and heavily influence process economics. Automatic control of such industrial processes presents challenges such as multi-phase flow dynamics, variable process gain and time delays, poor quality of measurements and significant disturbances. This paper details a case study application of development of multiple models of the dynamics of the interface level and the design of model predictive controllers (MPC) for a separation cell process. A Model predictive controller (MPC) using linear models is designed and implemented in real time on an industrial separation cell. The industrial implementation results show that the MPC scheme provides significant benefits over the current operations which use a PID controller. The benefits include significant reduction in the variance of the interface level resulting in higher bitumen recovery and smoother downstream operation plus energy savings due to reduced underflow pump speed.

Sep 1, 2012

By John A. Herbst, Ming Song, Xiangjun Qiu

"It has been known for sometime that as wear occurs in tumbling mills there is an associated change in mill throughput. These changes have traditionally been simplistically, attributed to “mill volume effects”. New high fidelity simulation (HFS) tools (involving DEM, CFD and Breakage models) are now giving new “microscale” insights into the complex interactions that occur between evolving lifter/liner profiles and breakage. An illustration of this analysis is shown in Figure 1 below.Here we see that after a new lining is installed (Region I) the wearing process reduces the liner thickness resulting in a larger power draw and an associated higher throughput until Region II is reached. By this point the lifter height is reduced significantly changing charge motion (less cataracting) the power begins to decline, but the comminution efficiency increases with this type of “calmer” breakage environment therefore the throughput continues to increase. In Region III the lifter is no longer providing the minimum required charge lifting action, the power and the throughput both drop off significantly. In the last two stages the behavior is especially complex because throughput is not linearly related to power since grinding efficiency is changing.The study described here shows that these new HFS tools allow the design of wear part profiles which will maximize mill productivity over the entire life of liner/lifter systems. A simple example of such a design procedure is shown involving the selection of a sinusoidal profile for a 34 ft diameter SAG mill.The paper discusses how the principles exposed in this simple example can be applied to search for an optimal profile in which non-standard modifications are allowed to compensate for throughput or wear shortcomings of standard profiles."

Jan 1, 2003

By M. Kosugi, M. Kawata, J. V. Satur, K. Mitsuhashi, R. Kawarabuki, W. Kracht, Y. Ebisu

Copper concentration is becoming more difficult because remaining copper ores are more complex and of finer copper mineral grain size, making copper minerals harder to float because of the fine particle size required to liberate the valuable species. The purpose of this work was to study the flotation behavior of fine copper sulfide ores at different conditions of agitation and aeration. The experimental campaign was carried out in a laboratory Denvertype flotation cell of 1 L volume modified to be operated with forced air that allows decoupling air flow rate and agitation speed. Four ore samples from Chile were used, all of them containing copper sulfides such as chalcopyrite, bornite, chalcocite, and tennantite, but with varying grain sizes and compositions. Preliminary flotation tests for establishing the flotation conditions of grinding size and collector dosage were conducted before the kinetic flotation tests that were carried out at different agitation speeds varying from 900 to 1300 rpm for gas flow rate ranging from 1.6 to 7.2 L/min. The flotation products were analyzed by ICP-MS and MLA (Mineral Liberation Analyzer). The results showed that high agitation speeds with corresponding air flow rates resulted in better recovery than moderate agitation speed and air flow rate, and an excess in gas flow rate resulted in bad performances. The flotation rates of the fine copper minerals were improved despite the different improvement rates among the fine size fractions. The impact of these operational variables, however, was different when comparing the results for the four ore samples. While it was found that the order of floatability in the four samples was the same, that is, chalcocite > tennantite > bornite > chalcopyrite, the kinetic constants of the copper minerals in the samples were different, indicating that mineral composition in the sample affects the flotation kinetics.

Jan 1, 2018

By Felix M. Zhuravlev, Vitalij P. Lyalyuk

"While there is a large industry based on recovering platinum group metals (PGM) from complex sulphide ores containing Cu and Ni, there is little information on the thermodynamics of the matte phase formed on smelting the ore and in particular the behaviour of Pt in the matte.The equilibrium between metallic platinum and industrial mattes was studied in a series of experiments where a small quantity of matte (5g) and platinum foil of 150 µm thickness (0.5 g) were equilibrated in magnesia crucibles at 1400°C under conditions where the oxygen and sulphur partial pressures were controlled.The chemistries of the phases were determined from EDS analysis using a scanning electron microscope. Line scans were initially used to confirm that the foils had attained a uniform composition across their thickness. The composition of the matte was determined from analysis of an area of matte including the small metallic droplets and dendrites.The distribution of Pt in Cu-Fe-Ni mattes (Pt: 1.5 – 3%) and solid Pt alloys (Pt: 54 – 72%) was studied. For a matte of base composition 45%Fe, 11%Ni, 8% Cu, at a base temperature 1400°C, the following behaviour was observed for the Pt distribution ratio:Under the range of sulphur and oxygen pressure of this study (log pO2 from -15 to –12.2, log pS2 from – 4.6 to –2.2), the distribution ratio of Pt between matte and alloy was independent of the sulphur and oxygen pressure, having a value of 0.04.The Pt distribution ratio increased from 0.02 to 0.08 with temperature from 1340 to 1450 oC.For mattes where the proportions of Cu and Ni were kept constant, a slight decreasing trend was shown for the distribution ratio of Pt versus the iron content (37 to 53%) in the matte but was not confirmed because of experimental uncertainty."

Jan 1, 2003

By Naoki Hiroyoshi, Hajime Miki, Tsuyoshi Hirajima, Masami Tsunekawa

"Acidic solutions for chalcopyrite leaching contain cupric, ferrous and ferric ions, and the oxidizing power of the solutions is indicated by a redox potential, determined by the concentration ratio of ferric to ferrous ions. This paper reviews our previous studies on the redox potential dependence of chalcopyrite leaching in sulfuric acid solutions. Leaching experiments indicated that copper extraction rate was accelerated by cupric and ferrous ions , and was higher at potentials below a critical value (critical potential) in the presence of these ions. This was in good agreement with the results of electrochemical measurements, i.e. in the anodic polarization curves for a chalcopyrite electrode, active-passive behavior was observed when cupric and ferrous ions co-exist, but the activation at low potential did not occur without these ions (Figure 1). The analysis of the AC impedance spectra for chalcopyrite electrode indicated that a high-resistance passive layer grows on the chalcopyrite surface without cupric and/or ferrous ions, and that coexistence of these ions causes a formation of another product layer and inhibits the passive layer growth at low potentials.These results are explained by a reaction model assuming the formation of intermediate Cu2S due to chalcopyrite reduction and the subsequent oxidation of the Cu2S. The critical potential corresponds to the redox potential of the Cu2S formation and the predicted values matched with the experimental results. Catalytic effect of silver ions on chalcopyrite leaching was also discussed based on experimental results and the above model."

Jan 1, 2003

By Tomasz Niedoba

Coals occurring in nature are characterized by various properties. According to Polish norms, the classification of coals taking into consideration their calorific value contains coals from type 31 (flaming coal) until type 43 (meta-anthracite). The samples of coal of type 31 were taken for investigation. To this purpose, the approximations of ash contents and density distribution functions were done for this coal type (determination of marginal distribution functions). They were the basis for application of so-called Morgenstern distribution functions to approximate the function Z=L (?), where Z is ash contents and ? - coal density. Then, the comparison between obtained results was performed and the results were statistically evaluated. They are the basis for the further research of other types of coals.

Sep 1, 2012

By B. K. Gorain

Mining of low grade deposits along with the necessity to design and operate flotation plants with high throughput presents unique metallurgical and environmental challenges that need to be addressed to reduce project risks, improve project economics and to sustain the profitability of operations over the life of a mine. Some of the key challenges include poor recovery of valuables and concentrate quality issues due to complex mineralogy, the need to use poor quality water such as brackish or sea water, reduce environmental impact from the process, integrate flotation with hydrometallurgy to maximize precious metals recovery, escalation of capital and operating costs, use of unproven technology and constant use of larger equipment, high ore variability, worldwide constraints on resource availability and an ever increasing need for reliable metallurgical input to financial models to evaluate economic viability of projects. The need to develop effective solutions to these problems in a short time frame is becoming a key to the success of any new project and for sustaining the profitability of a mining operation. An integrated multi-disciplinary approach to problem solving is crucial with the need for a more lateral thinking along with strategic partnerships and collaboration involving the right players. This paper presents some of the key findings based on experiences from a large number of challenging projects and operations focused on solving complex flotation problems Keywords: mineral processing, flotation, flotation problem solving, flotation optimization, plant design, innovation

Sep 1, 2012

By J. Yvon, Inna V. Filippova

"The aim of this work is to seek the inhibitors of the meteoric and bacterial dissolution of sulphides and gangue minerals to stop the undesirable chemical reactions during conservation of the flotation wastes. The approach of passivation of surfaces by chemical treatment of the solid phase is applied for this objective.The samples taken from different depths of an old French waste dump revealed the capacity of the flotation tailings to produce acid waters (pH 1.8-2.4) and to release heavy metals. Mineralogical studies show not only the product of sulphide oxidation, i.e. sulphates, but also the complex transformations of aluminosilicates in acidic liquid phase. The detection by XRD of aluminium hydroxides (gibbsite, boehmite) allows supposing the recrystallisation phenomena during tailings conservation.Comparative tests of the passivation of the surface of sulphide minerals and waste of flotation with using of conventional reagents (CaO, NaOH, phosphates) and original reagents for this purpose (alkyl dithiocarbamates) allow to identify the optimal treatment conditions and the efficient chemicals.Leach tests were carried out in percolation columns during 68 weeks. The normalised leaching tests according to French legislation were run to confirm the selected treatment conditions. The results obtained show that a single treatment with carbamate inhibits the oxidation of the pyrite and the other sulphides, and totally prevents the formation of acid waters (the stabilised pH was 5.3-5.8). Treatment of in situ drainage water allows to obtaining a total precipitation of heavy metals: the residual concentrations of Fe, Cu and Zn are lower than 0,1 mg/l.The passivation of sulphides is the result of the formation with carbamate (studied by IR spectroscopy and XPS) of organometallic compounds, which are stable in acid medium. The presence of thiuramdisulphide (product of alkylcarbamate oxidation) at the mineral surface stabilises the mixed adsorption layer and leads to a considerable reduction in the hydratation rate of surface by avoiding the corrosion of the pyrite. No aluminium was detected in leach solution with this treatment."

Jan 1, 2003

By Remmerswaal, U. Boin, M. B. G. Castro

"To design sustainable products that can be recycled with high resource efficiency, low environmental impact and economic feasibility, the choice of materials and materials combinations, made in the design stage, is fundamental. The products we design, manufacture and use now will be the resources of the future. Designers are able to select materials for a product according to the many functional requirements they must fulfil. But they have a limited knowledge of the recycling processes and its requirements regarding quality of the secondary material streams. Resource Engineers have to manage the processing of these streams, that are becoming more complex with the increasing variety of materials and decreasing size of components. After mechanical separation of the materials streams resulting from shredding of EOL (endof- life) products, there is always a degree of contamination, from two possible causes:Incomplete liberation: the bonds between different materials combined in a component are not completely destroyed by shredding, resulting in some particles containing two or more materials attached;Separation efficiency: the mechanical separation processes are not able to separate perfectly the many material particles; there are always a number of foreign particles in the recovered streams.Sometimes, those contaminants cannot be removed by the industrial metallurgic recycling processes, and a more serious problem occurs when the contamination levels compromise the recycling of the material stream by lowering its quality (i.e. the properties of the recycled material will be lower due to the contamination). As a consequence, the material must be diluted in virgin raw material and/or used in a less demanding application (downgrading), causing resource depletion and increased energy use, waste production and recycling costs. In order to make the best choice of materials combinations for a product, a systematic approach is necessary, that can close the gap between the knowledge areas of Product Design and Recycling Technology."

Jan 1, 2003

By Erico Tabosa, Kym Runge, Peter Holtham

"The distribution of turbulence in an industrial scale mechanical flotation cell and its effect on flotation kinetics was studied using a fully instrumented 3m³ cell. The cell was operated at a copper concentrator in Australia with different combinations of airflow rates, impeller speeds and sizes and cell aspect ratio providing a wide range of hydrodynamic conditions. An analysis of the overall flotation cell performance showed that the overall copper recoveries were very similar for the conditions tested. However, by decoupling pulp effects from froth effects it was possible to evaluate whether the changes made affected the pulp zone and/or froth zone responses. The analysis showed that the overall recovery has the potential to be up to 7% higher, if not limited by froth recovery. The cell hydrodynamics were characterised by the overall energy dissipation rate and, to understand the distribution of turbulence within the cell, localised measurements were made using a piezoelectric vibration sensor. By comparing the metallurgical performance of the cell with the different hydrodynamic conditions it was found that the collection zone flotation rate constant was not directly related to overall energy dissipation, as is commonly observed at laboratory scale, where energy is usually only changed by varying impeller speed. In this study, energy dissipation rate was varied using not only impeller speed, but also the size of the impeller and the cell aspect ratio. In these circumstances, the best correlation was found to be between the collection zone flotation rate constant and the distribution of turbulence, i.e. the size of the turbulent zone."

Jan 1, 2014

By Vishal Shukla, Ashok Kumar, Manas Ranjan, D. Chakraborty, Narayan Sharma

Jigging has a very important role in mineral processing Industry. Upgrading of Iron Ore by jigging has been an emerging trend. A detailed investigation is carried out to understand the influence of Jig feed granulometry and bed height during jigging operation. Noamundi jig plant data shows that variation in jig feed granulometry, feed quality and bed height are major contributors to fluctuation in jigging performance. At Noamundi the feed size (-10.0+0.5mm) fraction is used for fines jigging operation. To understand the effect of granulometrey on jig plant performance such as yield, separation efficiency and Fe recovery. In this context The performance of jigging was evaluated by daily average data from jig operation was used to study the influence of feed distribution on jigging performance .Coarser fraction (+6mm) has a positive influence , whereas fines fraction (-0.5mm) tends to lower performance . During Jigging rearrangements of Particles takes place due to an alternate expansion and compaction of Jig Bed .These particles are arranged by increasing density from top to bottom. During the particle stratification, Jig bed physically cut at desired horizontal particle density plant to separate the desired product. Investigation shows that optimum bed height is required at different Jig feed quality to achieve desired product quality, maximum separation efficiency and Fe recovery. This Paper will illustrate role of granulometry and Bed height control on Jigging plant performance.

Jan 1, 2014

By P. Prakash

A dual-drive planetary mill, which has a rotating shaft that sweeps a circle of diameter 750 mm, has been designed. The planetary mill is powered by a 5 hp motor to rotate the main shaft and a 3 hp motor to rotate the jars. The charge dynamics inside the horizontal-axis planetary ball mill was established using three-dimensional DEM simulations. The simulation results provided data to determine the impact energy distribution and the effect of process parameters such as mill speed and filling. It has been observed that the mean impact energy per unit time increases with rotation-to-revolution ratio, whereas the average number of inter-particle impacts per unit time decreases. The mill was also used to synthesize a variety of powders. Here three case studies of reaction milling are briefly presented: (i) cementite and silicon carbide, (ii) oxide dispersed strengthened (ODS) steel, and (iii) magnetite from blue dust. In each case, the powder was produced by mixing and then milling the corresponding pure components. The phase evolution, particle size distribution, and morphology of particles during milling were studied for various samples collected at different milling times using laser size analyzer, SEM, TEM, and Mössbauerspectroscopy. The results established a convenient way to produce powders of high technological and commercial value.

Sep 1, 2012

By V. G. Prikhodko, G. I. Sukhinin, I. V. Yarygin, A. V. Fedoseev, S. A. Novopashin

"The first experiments on the vacuum drying of spherical clay sample are presented and the theoretical model of the process is considered. The model is based on the solution of the heat and the moisture transfer equations with the effective thermal conductivity and water diffusion coefficients for wet porous clay-like medium. The time and radial dependence of the temperature and the moisture were calculated for different initial conditions. The results obtained for the time dependence of the moisture content are in good agreement with the experimental results obtained in the initial period, when all the moisture in the sample did not freeze to form an ice crust. INTRODUCTION Capillary-porous materials very often occur in nature and in industry. A porous medium is a solid matrix with voids, or pores, which are continuously connected. These pores are usually filled with fluids or moisture, water vapor and air that can pass through the medium because the voids are interconnected. The void fraction in the solid matrix is referred to as the porosity. Porosity or void fraction is a measure of the void (i.e. ""empty"") spaces in a material, and is a fraction of the volume of voids over the total volume. The moisture content in porous media determines the properties of the porous body, its mechanical and thermo-physical properties, such as density, plasticity, viscoelasticity, swelling, cracking, and so on. Complex processes of heat and mass transfer occur in porous bodies when they are heated or cooled, during drying or freezing (Luikov,1966). The course of these processes depends essentially on the physical-chemical composition of the solid matrix of the porous body, on its fractal dimension, porosity and morphology. The clay and clay minerals are the most important porous materials in the history of the mankind (Mukherjee, 2013). Clay is a very fine grained, unconsolidated rock matter, which is plastic when wet, but becomes hard and stony when heated. It has its origin in natural processes, mostly complex weathering, transported and deposited by sedimentation within geological periods. Clay is composed of silica {SiO2), Alumina (Al2O3) and water (H2O) plus appreciable concentrations of oxides of iron, alkali and alkaline earth, and contains groups of crystalline substances such as quartz, feldspar, and mica. Building materials, bricks, and tiles, pottery, porcelain and faience are made from clay. Clay is used in the food and medical industry, and, not least, in the mining industry as a carrier containing aluminum, silicon and other valuable elements, as well as metals (copper, gold) as constituents, contained in the pores in the form of micro- and nano-particles or grains."

Jan 1, 2018

By Wieslaw Wszolek, Kazimierz Trybalski, Ryszard Tadeusiewicz

"The present work is an attempt of neural networks application to the description of complex technological processes of useful minerals enrichment. Neural networks are among the most convenient tools that have been added recently to the professional toolbox of modelling specialists, and they are particularly useful in realisation of multiple practical tasks, characterised by great complexity and relatively low amount of available a priori knowledge about the nature of the modelled processes. They are successfully applied in a wide variety of problems related to data processing and analysis, their prediction, classification or process control. The object of the study was the technological site for copper ore enrichment by floatation, being a part of technological line in the Ore Enrichment Plant ZG „Polkowice”, KGHM „Polska Miedz” S.A.The main floatation is described by parameters measured by the supervision and control system, which can be grouped with respect to the functions performed for the object:a) input function: aFG - copper contents in the feed material for the main floatation [% Cu]b) control: LFG I - level in the first section of the floatation unit [%], LFG II - level in the second section of the flotation unit [%], LFG III - level in the third section of the floatation unit [%], LFG IV - level in the fourth section of the floatation machine [%]. These quantities compose the five elements long input vector.c) output function: ? - copper contents in the waste from main flotation (final waste) [% Cu]The measurement data, containing the above-mentioned parameters, have been collected during the normal operation of the plant. The data contain momentary values of the parameters, registered every 10 minutes, covering the period of 196 hours of the plant’s operation (1176 measurements for each quantity).For construction of the model used in the study classical multi-layer perceptron-type neural network has been used, with one hidden neuron layer, trained by the error back propagation method."

Jan 1, 2003