Search Documents

By V. Arslan

In this study, effects of the inert constituents, such as ash, and the effect of blending coals with differing rank and composition on the plasticity of coal blends were investigated. The reference coal originated from the Zonguldak region, in the north-west part of Turkey. Firstly, the effect of coal ash on the plasticity of Zonguldak coal was determined. Secondly, the relationship between the plastic properties of the individual coals and those of the blended coals were identified. Some important relations were found, related to the characteristics of the individual coals. Ultimately, the manner in which the plasticity of Zonguldak coal was affected by blending with low volatile coals was investigated. Keywords: coal blending, coal plasticity, coke, fluidity, rank.

Jan 1, 2006

By I. Jones

Geologists, engineers, technicians and surveyors have successfully utilized technical software in the mining industry for over 30 years. Software for processing survey, geology, mine engineering and planning information make these functions more efficient by automating repetitive tasks and reducing data processing errors. While these systems have been improved incrementally overtime, new systems that represent giant leaps in technology have been introduced to help mining operations increase productivity and reduce costs. However, their widespread use within the industry has left individual companies without a competitive advantage. Additionally, the ability of these applications to provide the productivity improvements required in today’s uncertain market conditions has since peaked. The next wave of technology—integration of independent software applications—is just starting to emerge and will have a significant effect on the productivity of mining operations. To reap the productivity gains required to remain competitive, mining companies must exploit the collective knowledge and experience of every employee in the organization. Integration of independent software application allows companies to leverage information from all activities, enabling staff to make better decisions to improve productivity. This paper outlines the importance of integration as productivity enabler. Key performance indicators, strategic mine planning, resources management and mine-to-mill integration are discussed as processes that enable productivity. The Gemcom Enterprise Mining System (GEMS)is introduced as the industry’s first integrated solution that enables these productive processes. The paper concludes with a comment on the level of change required to realize the benefits of integration.

Jan 1, 2003

By M. -O. Suk, S. -K. Jo, S. -C. Shim, J. T. Kim, S. -H. Kim, C. -W. Seo, J. -S. Kim

An equilibrium study was carried out at 1873 K to ascertain the effect of carbon in CaO-SiO2-Al2O3-MgO-MnO-FetO slag systems on their FetO and MnO activity coefficients, representing the slag?s thermodynamic potential for steel reoxidation. Both ?FetOand ?MnO showed not only a sharp increment, but also a simultaneous slow decrement by increasing carbon content in slag, suggesting opposite roles of the carbon according to its stable forms. XPS (X-ray photoelectron spectroscopy) was introduced to clarify the stable forms of carbon in slag. XPS results prove that carbon dissolves in slag as carbonate, and carbide ions under oxidizing and reducing atmospheres, respectively. It was concluded that carbonate ions increase ?FetOand ?MnO, and that carbide decreases them. This paper suggests an application method of the present results to actual ladle refining processes, in order to enhance steel cleanliness without decreasing (FetO + MnO) content in slag. Keywords: carbon, slag, activity coefficient, FetO, MnO, carbonate, carbide, XPS, reoxidation, cleanliness

Jan 1, 2004

By R. J. Kendall

As we enter the new millennium, the South African mining industry has to ensure that it becomes more competitive if it is to survive in the ever more demanding global environment. Traditionally, mechanization in narrow stopes has been limited to the use of scraper winches, and numerous mechanization attempts have been restricted to pilot projects operated on an extremely limited scale (with varying degrees of success). The benefits of hydropower are well documented, and Northam Platinum has shown these benefits to be achievable on a mine-wide basis. However, the equipment originally developed for hydropower systems has followed the traditional labour-intensive approach commonly used in deep level narrow stoping operations. The problems experienced with the hydropower system are discussed and the rationale for developing alternate technologies is explored. The hydropower system has shown to be a versatile powering medium which can be harnessed for a diversity of uses. It (hydropower) enables the mining engineer to change traditional paradigms and to design an entirely new approach for optimizing the mining operation based on explosive techniques. The system developed for Northam consists of the following: ?Purpose-built stope drill rig operated off the hydropower system with special features to ensure accurate drilling patterns throughout the length of the blast hole ?Purpose-built high rate cleaning system for rapid transfer of fractured ore to the stope orepass ?Redesigned stope layout to facilitate in-stope water control and to recover fines from the run-off water ?Purpose-built drill rig for rapid establishment of reef raises and advanced strike gullies ?Purpose-built drill rig for flat end development. On both types of development end rig, emphasis is placed on ensuring accurate drilling patterns throughout the length of the hole to maximize linear advance per blast. The paper discusses the implementation of the Northam system on a large scale as well as current initiatives to further improve on the efficiencies of mining operations. It concludes by emphasizing that mechanized hydropowered stope technologies are in their infancy and thus offer unlimited scope in progressing beyond today?s paradigms to present as yet unthought of solutions for optimizing deep level ore extraction.

Jan 1, 2000

By P. H. S. W. Kulatilake, B. Malama

To simulate brittle rocks, a mixture of glastone, sand and water was used as a model material. Thin galvanized sheets were used to create joints in blocks made out of the model material. To investigate the failure modes and strength, both the intact material blocks as well as jointed model material blocks of size 35.6 × 17.8 × 2.5 cm having different joint geometry configurations were subjected to uniaxial and biaxial compressive loadings. Results obtained from the intact model material blocks are used to validate a new intact rock failure criterion for biaxial loading. Results obtained from both the intact and jointed model material blocks are used to develop a strongly non-linear new rock mass failure criterion for biaxial loading. In this failure criterion, the fracture tensor component is used to incorporate the directional effect of fracture geometry system on jointed block strength. The failure criterion shows the important role the intermediate principal stress plays on rock mass strength. Zur Simulation spröder Gesteinsarten wurde ein Modellmaterial aus Dentalgips, Sand und Wasser hergestellt. Daraus wurden Blöcke gegossen, in denen mittels dünnen, galvanisierten Blechen Trennflächen erzeugt wurden. Die Blöcke mit Abmessungen von 35.6 × 17.8 × 2.5 cm wurden in einaxialen und biaxialen Druckversuchen belastet. Es wurde das Versagensverhalten und die Festigkeit von intakten Blöcken sowie durchtrennten Blöcken mit unterschiedlicher Trennflächengeometrie untersucht. Aus den Ergebnissen der Versuche an intaktem Material wurde ein neues Versagenskriterium für biaxiale Belastungen validiert. Die Ergebnisse der Versuche an intakten und durchtrennten Blöcken wurden verwendet, um ein neues stark nicht-lineares Versagenskriterium für geklüftetes Gebirge unter biaxialer Belastung abzuleiten. Darin wird der Bruchtensor verwendet, um den Einfluss der Trennflächengeometrie auf die Festigkeit zu erfassen. Das Versagenskriterium stellt heraus, welche Bedeutung die mittlere Hauptspannung für die Gebirgsfestigkeit hat. Un mélange de platre dentaire, de sable et d’eau a été utilisé pour développer un matériau analogue des roches fragiles. De fines feuilles galvanisées permettent de créer des discontinuités représentatives des discontinuités naturelles dans des bloques fabriqués avec ce matériau analogue. Les modes de rupture et la résistance, tant pour le matériau intact que pour le matériau avec ses discontinuités, ont été étudiés sur des blocs de 35.6 × 17.8 × 2.5 cm soumis à des efforts de compression uniaxiaux et biaxiaux. Différentes configurations de géométrie de discontinuités ont été considérées. Les résultats obtenus à partir des blocs intacts permettent de vérifier un nouveau critère de rupture pour les roches intactes soumises à des efforts biaxiaux. Les résultats obtenus, tant avec les blocs intacts qu’avec les blocs avec discontinuités, sont utilisés pour développer un nouveau critère de rupture, fortement non linéaire, pour les massifs rocheux soumis à des chargements biaxiaux. Dans ce critère de rupture, un tenseur de fractures est introduit pour caractériser les effets directionnels de la géométrie des systèmes de discontinuité sur la résistance des blocs avec discontinuités. Ce critère de rupture démontre le rôle important de la contrainte principale intermédiaire sur la résistance des massifs rocheux.

Jan 1, 2003

A number of impending and actual pit wall failures have been observed and documented, which have been interpreted to initiate on newly generated structural features. This infers failure through intact rock. Failure mechanisms have been postulated resulting from circumferential stress, extensional strain and brittle flexure. These will be discussed in the context of the failures and the associated monitoring. The implications of failure initiating on ?unknown? features has a significant impact for deep open pit mines where designs are based on the expected structural regime. Being able to anticipate such failures is important for design. Equally important is management of such changes as they arise. In this context, monitoring using high resolution microseismic techniques will be discussed as a means of providing early warning of such failures.

Jan 1, 2006

By J. V. Simmons

Composite rock mass failures involve intact rock material as well as fracture and shear on existing defects. Experiences from open-cut coalmining in the Bowen Basin of central Queensland are that failures of this nature occur suddenly with little warning, and are much more common than classical structurally controlled failures. Geological conditions and mining practices in the Bowen Basin are described. The circumstances of a sample of composite failures are described in detail in the paper. From this experience it appears that several aspects of conventional geotechnical investigation and design practice have not contributed significantly to either predicting or controlling the risks associated with sudden failures. These practices are described as myths for reasons outlined in the paper. On the other hand, the reality seems to be that high initial stresses and stress changes caused by excavation lead by a process of extensional deformation to a critical stress condition within the rock mass, and that sudden collapse follows when that critical stress condition can no longer be sustained. It is concluded that learnings gained from underground excavations in rock may be more applicable to open pit excavations than previously thought, and that the processes of prefailure deformation require more careful study if we are to develop more reliable risk management controls.

Jan 1, 2006

By P. J. D. Lloyd

The widely employed IPCC models for the release of methane from underground coalmining operations are reviewed, and put in the context of the South African National Communication on greenhouse gas emissions. Then attempts to calibrate the model via measurements on South African coalmines are described. These attempts failed because it rapidly became clear that the IPCC model, involving methane adsorbed by the coal and released (a) by the depressurization of the strata caused by mining, (b) from the broken coal and (c) from coal remaining in roof, floor, pillars or goaf after mining, was not valid. Instead, measurements showed that the methane release was very variable, sporadically falling to zero. Carbon dioxide concentrations were monitored at the same time as methane, and followed methane concentrations. An alternative model was developed, in which methane was largely displaced from the coal and held in fissures, cleats and pores, which, when intersected by mining, released methane into the ventilation stream. In a key test of this hypothesis, methane concentrations around a continuous miner were monitored both during operation and after shutdown. Even during operation, methane became undetectable. It is hypothesized that heating of the South African coal-seams during the emplacement of the igneous dykes that cut so many of the seams caused displacement of the methane from the coal into the pores. This fissure-held methane, or free methane, is released rapidly once a pathway through the coal into the mine atmosphere is established. In contrast, methane adsorbed in the coal, and measured as the seam gas, desorbs relatively slowly. Measurements suggest that on average about 50%of the adsorbed methane is lost one day after mining. By that time, the coal will have left the mine, so that the remaining seam gas will be released to the atmosphere outside the mine. Attempts to measure methane emissions from surface coal-mining operations showed very little detectable methane. Coal from surface operations, which was milled and exposed to atmosphere, adsorbed gas from the air. It is concluded that methane release from surface operations is probably less than 3Gg/a. It is estimated that the total methane release from the coalmining industry amounts to about 72 Gg/a, as opposed to the National Communication estimates of 323 Gg/a in 1990 and 317 Gg/a in 1994. However, there are large errors associated with these estimates, and it is recommended that the methodology outlined in this report be extended to as many mines as possible to reduce the errors that are inherent in the physical processes underlying the release of methane from South African coalmines.

Jan 1, 2005

By J. Eriksson

Slag from stainless steelmaking is known to disintegrate, which is an environmental problem and prevents the cooled slag from being utilized. This disintegration is due to the transformation from the ßto the ? polymorph of di-calcium silicate. The transformation is accompanied by an increase in volume of about 11% and a total disintegration of the slag. AOD slag from stainless steelmaking was re-melted in a laboratory induction furnace, together with olivine and calcinated dolomite, to investigate the prevention of disintegration by increased MgO content of the slag with small changes in CaO to SiO2ratio. The modified slag was examined with X-ray diffraction and scanning electron microscopy. The trials showed that an increased MgO content can change the mineral composition towards formation of more Merwinite and Bredigite, which prevents disintegration of the slag. Keywords: slag, disintegration, di-calcium silicate

Jan 1, 2004

By Luthie Els, Chris Coetzee, Roedolf Koekemoer, Casper Els, Olof Vorster, Frank Fereday

Three electric arc furnaces (EAFs) were constructed by Union Carbide at Tubatse Ferrochrome (TFC) in1975. This plant was expanded to four furnaces at the East Plant in 1985 and the gas cleaning system was enlarged without taking flow dynamics into consideration. In order to improve competitiveness, TFC has increased furnace capacity, partially substituted coal for coke, and changed the charge mix. These changes increase the heat and dust load into the air pollution control (APC) system. TFC embarked on a project to improve the APC capacity by: ?Quantifying the required off-gas capacity ?Optimising the aerodynamic flow through the system by means of Computational Fluid Dynamics (CFD) ?Converting the old Brandt Koyo top entry baghouses to bottom entry ?Upgrading the cleaning system ?Installing Gore-tex® ePTFE membrane filter bags The estimation of required off-gas capacity is traditionally done by rule-of-thumb methods such as specific extraction. A more elegant evaluation method was developed for simulating the effects of changes in charge mix on the furnace reaction gas volume and the APC system. Reaction gases are calculated by modelling the reactions taking place in the furnace and off-gas volumes are compared to both fan and baghouse capacity. This enables identification of bottle-necks in the off-gas system. CFD techniques were utilized to evaluate geometric imbalances and propose solutions to ensure optimal use of off-gas capacity. The system modifications were completed over several months and the modified equipment went into service in May2006.

Jan 1, 2007

By M. D. Budeba

Determining the efficiency of a surface coal mine operation is an essential activity, which can help in deciding on the optimal use of input resources, including effective capital allocation, in generating a desired quantity of coal of a specific quality. Mines operate today in challenging conditions, with diminishing reserves of high-quality coal, remote location of new coal deposits, infrastructure problems, environmental legislation, and the effects of climate. All these have an impact on the performance of a mine. Given such challenges, a company has to be technically efficient compared to other existing coal producers in order to generate profits. It can use the measurement of its efficiency to evaluate its productivity, benchmarking this against the best-performing mines and determining optimal variables in order to minimize slack and achieve the desired outputs. This paper discusses the use of Data Envelopment Analysis (DEA) in evaluating the efficiency of a surface coal mine supply chain for the coal export market. The supply chain is considered to be composed of subprocesses that are modelled as a multistage system. Numeric examples will be used to illustrate the application of DEA.

Jan 1, 2014

By J. H. Zietsman, S. Maharajh, J. Muller

In the chlorination process for TiO2 pigment production, blends of titania feedstocks such as ilmenite, synthetic rutile (SR), natural rutile, upgraded slag, and chloride-grade slag are reacted with coke and chlorine at a temperature of around 1000°C to form TiCl4 (the main product) and other waste metal chlorides. The TiCl4 is the main feed material for the TiO2 pigment-making process. Feeding different titania materials to the chlorinator affects the amount of coke and chlorine required for the process, the amount of waste generated, waste disposal costs, the amount of TiCl4 produced, and bed build-up rates. These factors influence the value of the feedstock. Generally, a higher TiO2 feedstock is more valued since less waste is generated and less reagents are consumed. To quantify the impact of different feedstocks on the chlorinator, a techno-economic model was developed to describe the chlorination process and estimate process variables at steady state. This paper describes the development of the model and studies in which the model has been used to quantify effects of using different feedstocks.

Jan 1, 2015

By G. R. Lane

A large opencast gold mining company in Africa had just completed a feasibility study for an expansion of the operations. A traditional net present value project valuation methodology had been used that showed a very positive net present value (NPV). The project team had conducted a qualitative risk assessment that identified and logged all potential project risks and had subjectively incorporated 'risk' via the discount rate and other assumption contingencies around gold price expectations, operating parameters, etc. Management requested that an independent quantitative risk modelling approach be adopted to obtain a better understanding of the impact of risk on the overall project valuation and confidence level in the final valuation. A detailed project valuation model was configured in the Cyest Carbon Modelling Technology platform, and the stochastic modelling module used to perform the Monte Carlo simulations. Analysis of historical operational performance data relating to actual achievements versus planned and budget determined the historical variability of the underlying parameters as well as variance to budget. This was done at a detailed level for mining rates and costs, processing rate, costs and recovery, and other operational efficiency measures. External market assumptions relating to gold price, exchange rate, and inflation were modelled and the dependency between them modelled using a copula. This case study will demonstrate the approach taken to building and populating the quantitative risk model and the overall results of the Monte Carlo simulation. The final valuation demonstrated that the project had a 44 percent probability of an NPV less than zero i.e. a 44 percent chance of project finance loss.

Jan 1, 2013

By A. N. Clay

In recent times, there has been criticism of the minerals industry over the lack of quantifiable boundaries between inferred, indicated, and Measured resources. A recent initiative through the United Nations aims to try to converge the mineral resource classification systems. Since the oil and gas industry uses a probabilistic approach to defining reserve boundaries, it is appropriate to introduce a similar statistical methodology for minerals. The Venmyn Variance Tower has been developed based upon traditional statistics to utilize historical and ongoing information in order to quantify variance of geological and chemical parameters and the boundaries and logic for quantitative mineral resource classification. It is proposed that a less than 50% variance from the mean of all sample parameters is required to achieve the classification threshold to define an inferred Resource whereas between 20-10% is needed for an indicated Resource and less than 10% variance from the mean is needed to declare a Measured Resource. These limits are similar to those used by the oil and gas industry, and it is suggested that these thresholds be adopted as an industry standard to ensure consistent quantitative reporting. While this process is intended to use statistics of an orebody to provide quantifiable and defendable boundaries, it cannot be carried out unless the geology of the mineral deposit is understood and the borehole samples can be categorized into appropriate populations for which the statistics are valid. This means that competent geologists are always required to work with and understand the implications of the Variance Tower results. This paper is intended to form the basis of a series of publications that establish a process to take mineral projects along a quantifiable and logical development path. Hence, no specific field example of the practical application of this process is given here.

Jan 1, 2012

By A. Nkolele

Paper written on project work carried out in partial fulfilment of B. Tech (Metallurgical Engineering) degree Fine coal of the Goedehoop Colliery is dewatered by centrifuging before being sold. Full-scale plant tests were carried out to reduce residual cake moisture by the addition of surfactants. It is believed that by modifying the interface between the coal surface and the adherent surface water, as well as the water occluded in the cake voids, drainage is improved. Two anionic surfactants at concentrations up to 150 g/t were tested on coal of <0.5 mm size. The results demonstrate that quite high additions of surfactant (80 g/t)were needed to reduce moisture from 20 to about 17?18%. It was observed that when increasing surfactant additions at low levels, within a very narrow concentration range, the retained moisture first increased sharply only to decrease sharply immediately thereafter; this effect points to a critical surfactant concentration. Based on the obtained results, the use of surfactants cannot be recommended at this stage; further investigations under more controlled conditions are required.

Jan 1, 2004

By L. A. Cornish, S. N. Prins, R. Süss

The work is being done using the Thermo-CalcTM software, and the database is being built up by obtaining good thermodynamic descriptions of all of the possible phases in the system. The database supplied did not cover all of the phases, and these had to be gleaned from literature, or modelled using experimental data. Similarly, not all of the experimental data were known, and where there were gaps or inconsistencies, experiments had to be undertaken. A preliminary version of the database was constructed from assessed thermodynamic data-sets for the binary systems only. The binary descriptions were combined allowing extrapolation into the ternary systems, and experimental phase equilibrium data were compared with calculated results. Very good agreement was obtained for the Pt-Al-Ru and Pt-Cr-Ru systems, which was encouraging and confirmed that the higher-order systems could be calculated from the binary systems with confidence. Since some of the phase models in databases were different, these phases had to be remodelled. However, more work is ongoing for information concerning the ternary phases present in the Al-Cr-Ru, Pt-Al-Ru (two ternary compounds in each) and Pt-Al-Cr (possibly more than three ternary compounds) systems. At later stage of the work, problems with the thermodynamic descriptions of the Cr-Ru and Pt-Cr binary systems were found. A programme of experimental work to overcome these has been devised, and is being undertaken. Keywords: Pt-based alloys, phase diagram calculations.

Jan 1, 2006

By R. Hope, C. van Heerden

In any process or organization inefficiencies are costly. In times of abundance this reality often does not receive much attention. During such times the focus is rather on increasing capacity to increase production. However, there is a growing awareness in the world of tougher economic, social as well as environmental conditions, and enterprises find themselves facing greater demands for accountability towards shareholders, the environment and the public, as well as growing competition for market share and limited global resources. This reality is no different in ensuring a sustainable mineral sands operation. In order to achieve this, any operation needs to be stripped of all process as well as operational inefficiencies. In this context it has become essential for any Mineral Separation Plant (MSP) to have the necessary process monitoring and control systems in place to continually monitor and optimize the production of on-spec products and maximize operational efficiency and consistency. The MSP Grade Control Solution developed by Crusader Systems and running on top of the CSense platform contributes towards these goals by improving the consistent production of on-grade product. This allows the process to operate closer to the maximum allowable product grade constraint, which in turn maximizes production.

Jan 1, 2003

By W. Stumpf

Mill log analyses and complementary hot deformation studies were carried out on the as-cast structure and on a hot rolled structure of the same low carbon steel (SAE 1006) that had been processed according to the direct or hot charge route in a compact strip plant. The main softening mechanisms during hot rolling were found to be complete dynamic recrystallization during each pass above about 1000°C for the as-cast structure with an austenite grain size of 277µm and, secondly, incomplete static recrystallization after each pass with a finer austenite grain size of about 26 µm and tested below 1000°C. A two-stage hot working mechanism has also been found by others on a similar steel also processed by the hot charge route and this may appear to be a characteristic of this type of material. Constitutive constants determined from hot working studies were combined with other constants from the literature and incorporated into a grain size development model that correctly predicts the final ferrite grain size in the hot rolled strip steel. The predicted incomplete static recrystallization during the last three finishing passes in the plant appears to result in some retained strain in the hot rolled austenite as it transforms to ferrite on the run-out table. Analyses with the model predict relatively little sensitivity of the final ferrite grain size to process and product variables such as temperature and strain per pass for the last three passes and also the starting austenite grain size in the slab. Keywords: Low carbon steel, hot rolling of strip steel, rolling mill log analyses, austenite grain size, ferrite grain size, grain size modelling.

Jan 1, 2003

By S. Kamalpour

It has been observed that the productivity of ferromanganese furnaces, and the stability of metal and slag compositions, vary considerably according to the type of coke used as reductant. However, the desired properties of coke for optimum furnace performance are not well understood. In this investigation, the behaviour of four cokes, which exhibited a wide range of performance in ferromanganese production, was investigated by means of laboratory simulations of reducing conditions in the furnace. The Stationary Charge in Controlled Environment (SCICE) technique was used to simulate the conditions in the furnace shaft. Batches of raw materials, mixed in the same proportions as used in practice, were heated at fixed rates to 900, 1100 and 1300°C then cooled. The mass loss was used as a measure of the degree of reduction. Conditions in the lower part of the furnace were simulated by means of melt-reduction experiments in which lumps of coke were drilled out to form crucibles in which enriched ferromanganese slags were reduced at 1500 and 1550°C then cooled. An examination of the raw materials and the cooled, reacted charges using a variety of analytical and characterization techniques enabled the sequence of reaction and changes in morphology of the raw materials to be followed. This enabled an understanding of the behaviour of the cokes during reduction to be developed, which was then used to explain the observed performance of the cokes in practice. By relating the observed behaviour of the cokes in the laboratory tests to measurable properties of the unreacted cokes and to their observed performance in practice, it was shown that to achieve high productivity and good furnace performance, cokes should be selected to have moderately high reactivity towards CO2 (Boudouard reactivity) relative to conventional iron blast furnace cokes.

Jan 1, 2004

By T. Ertekin, X. Dong

This paper identifies the need for the development of specialized inverse solution techniques for the analysis of pressure transient data for the characterization of the transport and sorption properties of coal seams. Central to the proposed inverse solution technique is a specially structured artificial neural network (ANN). The most important transport and sorption characteristics of coal seams are butt and face cleat permeabilities, macropore porosity, Langmuir volume constant, Langmuir pressure constant, and sorption time constant. Conventional methods, such as type curve matching techniques and laboratory-derived measurements are handicapped in terms of being representative over the entire domain of interest. In this paper, we utilize analytical forward solution techniques for various combinations of characteristics of coal seams to generate training and testing patterns. These training patterns are shown to an ANN structured to learn the ubiquitous non-linear relationships that exist between coal seam properties, input conditions and the pressure transients measured. The trained networks are then extensively tested to ensure that they have effectively learned the training patterns. In the final stage of the development, the networks are run in the prediction mode. The responses of the networks are found to be in agreement with the input data. The developed networks are able to generate results generally within 5% error margin for permeability and porosity and 20% error margin for the sorption characteristics of coal seams. A number of examples highlighting the capabilities and degree of effectiveness of the network in characterizing the coal seams areincluded. Keywords: artificial neural networks (ANNs); coal seam characteristics; pressure transient analysis

Jan 1, 2003