Search Documents

By P J. Terbrugge

Many ore deposits have considerable vertical extent which is not always known at the time of commencement of mining. In many of these cases, initial mining is by opencast methods, and as ore reserves are proved to greater depths, the pits are often planned to go deeper than had been originally envisaged. In such cases, surface plants and critical underground facilities such as conveyer tunnels, access ramps, ore passes, hoisting shafts and ventilation shafts are often located much closer to the pit rim and the orebody than is desirable for the deeper mining situation. This usually raises the question of the stability of such underground excavations, which may be critical for the viable longer-term mass underground operation of the mine. In this paper the key considerations in the evaluation of the stability of the overall mining environment for ædeepened minesÆ are defined. Aspects which are dealt with are: open pit stability, shaft stability, dilution, mudrushes and airblasts, and selection of mining method. The necessary stability evaluations are put into the appropriate context by considering two case histories. Critical parameters and considerations which need to be addressed during the evaluation of excavation interaction are also discussed.

Jan 1, 2000

By Bluhm S. J, Feio L, Ramsden R

A new mining area at the Vaal Reefs gold mine is to have a shaft. system which will extend to a depth of 4 200 m and will require 130 MW of cooling. A novel feature of the proposed cooling system is a large underground air cooling installation in which an ice slurry is sprayed into the ventilation air. The design of the ice slurry bulk air cooler, in the form of counter.flow cooling towers, is discussed. Comparative thermal tests with cold water and ice slurries (with ice mass fractions up to 22 per cent), were carried out in a 5 m high test tower. The presence of the ice in the water spray increases the resistance to heat flow and reduces the overall thermal characteristics of the air cooler by 8 per cent. Notwithstanding this, the use of ice slurries is indeed beneficial in terms of overall costs. It is concluded that a 25 MW air cooler should use 410 kg/s of ice slurry with a 10 per cent ice mass fraction to cool 550 kg/s of air which is 75 per cent of the total air flow rate.

Jan 1, 1988

By S Grobler, T Fares

Understanding the real utilisation of the available volumetric capacity of a conveyor is key to unlocking latent capacity or ‘debottlenecking’ existing plant. Conveyors are typically designed on the basis of conservative density and ore surcharge angle specifications, and consequently there is often latent volumetric capacity available.Laser scanning measurements of conveyor ore profiles has been undertaken on iron ore conveyors to gain an understanding of the actual surcharge angle and the available edge clearances. Iron ore producers seeking to extract maximum production from their assets have used these measurements to debottleneck existing plant and to revise the design criteria for future plant. The benefit is that latent capacity of existing plant can be unlocked and smaller and cheaper conveyors can be designed for future plant, maximising the return on capital. This paper describes the measurements and results.CITATION:Fares, T and Grobler, S, 2015. Laser scanning of conveyor ore profiles, in Proceedings Iron Ore 2015, pp 549–554 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 13, 2015

By H Han, W Wang, E Zhou, D Duan

"In this study, physical, chemical and microscopic characteristics of high phosphorus oolitic hematite were studied firstly. Based on which, the new methods of high phosphorus hematite used in the æsolid state reduction by rotary hearth furnace - magnetic separationÆ and iron nugget by rotary hearth furnace direct reduction processes were discussed. The results showed that high temperature, low basicity and high carbon content is conducive for the apatite in iron ore to reduce into molten iron, but not conducive to the removal of phosphorus. Through optimisation of process parameters, dephosphorisation rate of high phosphorus hematite is more than 60 per cent by æsolid state reduction roasting-magnetic separationÆ process while that is up to 80 per cent by iron nugget process. This study can provide theoretical and technical basis on economical and rational use of high phosphorus oolitic hematite.CITATION:Han, H, Duan, D, Zhou, E and Wang, W, 2013. New methods for high phosphorus oolitic hematite dephosphorisation by direct reduction process, in Proceedings Iron Ore 2013, pp 391-396 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Aug 12, 2013

By W Newton, J Price

This paper outlines the design, justification and performance of a gravity circuit upgrade at the Marvel Loch treatment plant. The design of the upgrade was simple but effective. The key components of the upgrade were the addition of a sluice and a second Knelson Concentrator. The sluice was installed as a pre-concentration step. The upgrade also included the purchase of a Mineral Cone to treat the increased quantity of gravity concentrate. The cost was low because of the use of mostly second-hand equipment. The result was that for a cost of $75 000 the gravity recovery doubled and the overall recovery increased by over one per cent. This paper shows that you do not need to spend millions of dollars to be innovative and successful.

Jan 1, 2000

Hydraulic mining shovels can be successively used at open-pit mining operation in severe climatic zone with air temperature interval from -700C to +450C typical for some northern region of the world particularly of Russia, Canada and Sweden, if they would be equipped by special preheating facilities for their diesel engine, water, hydraulic oil and lubrication systems. All shovels manufactured by the Komatsu Mining Germany GmbH for operation at ambient air temperatures down to -50¦C have cast and forged structural design elements, bolted connections made of special steel grades, electric cables with special insulation, flexible high-pressure hoses manufactured by ICE-Champion with connectors made of special steel grades.Generally at the temperatures below -25¦C the ordinary machine has to be stopped, the attachment should be placed in the parking position, the generator should be switched on, or the external electrical power supply connected, for the preheating equipment. For rapid start-up in winter after a long shutdown of a hydraulic shovel, there is a procedure for preheating of the main systems. It is applied for the following systems: engine cooling system, engine oil, hydraulic oil, pumps and drive motors of the propel gears, electric cabinets, machinery house, especially near the ventilation inlets and outlets.Start-up of the main drive engine is permitted at a hydraulic oil temperature of -20¦C, when it has a viscosity of 1000 cSt. In this case the rotation speed of the diesel engine crankshaft is lower by two times than the nominal value and this is the most favourable condition of start-up of the engine and hydraulic pumps and motors, which work with half of their rated rotation speed until the hydraulic oil reaches a viscosity from 100 to 10 cSt. After that the hydraulic system and the entire shovel begin to operate under normal conditions.

Dec 6, 2010

By B K. Hebblewhite, G Sharrock

The strength and deformation properties of a rock mass are important parameters influencing the design of civil and mining excavations or structures. The mechanical behaviour of jointed rock masses are controlled by the characteristics of discontinuities and the strength of intact rock bridges between discontinuities. To date, analytical, empirical and experimental methods have not captured the key mechanisms controlling the mechanical properties of actual rock masses with non-persistent joints. The emergence of the synthetic rock mass (SRM) in 2007 provides a promising approach for this purpose. In this paper a rock mass with non-persistent joints is analysed with the SRM model based on PFC3D. The influence of joint geometrical parameters on the uniaxial compressive strength (UCS), rock mass deformation modulus (Em) and failure mode is studied. Joint parameters include joint orientation, persistency, spacing and step angle. Prismatic numerical samples with dimensions 300 mm × 150 mm × 50 mm were generated and a sensitivity analysis of each joint parameter on UCS and Em was undertaken. The results show that of the parameters tested, joint orientation has the greatest influence on UCS. Minimum UCS occurs when the angle between the major principal stress and joint surface is approximately 60°. The joint step angle was found to have a significant effect on failure mode and a joint step angle of 90° is the most favourable joint orientation for step-path failure. The importance of joint step angle is highlighted in the discovery of a failure mode bifurcation point at joint step angles of 60° and 90° for joint orientations of 75° and 90°, respectively. For these parameters the failure mode transitions from block rotation to a new failure mode where the coalescence of cracks results in the formation of new small regularised blocks.

Sep 26, 2011

The extractive industry has been faced with a situation where there has been no systematic and formalised training and education structure available. Previous structures which were available, e.g. the quarrying diploma and the mining papers as a part of an engineering degree, have suffered the same fate as the Dodo. They are now extinct.   In providing for a training strategy, the past strategies need to be examined and reasons behind their demise examined. This paper examines the reasons for past failures in education and training in the extractives industry, the factors that need to be taken into account in creating an education and training culture, the strategies required, the Government regulations and trans-Tasman agreements, and the quality management which must surround the entire training programme.

Jan 1, 1997

By M Grigorescu, J H. Hodgkinson

The expansive, open cut iron-ore mines in Western Australia typically experience few days of rain per annum, often amounting to less than 250 mm. Unlike mines where rainfall is frequent, they may be less prepared for extreme rainfall events. Such events can cause erosion, flooding and sedimentation, drainage alteration, spoil and stock heaps wetting and effect slope stability. Such impacts may threaten personnel safety, infrastructure, and production. The CRATER (‘Climate Related Adaptation from Terrain Evaluation Results’) framework collates and interprets a mine’s pre-existing data and semi-quantitative information to assess vulnerability to, and ultimately plan to avoid or minimise, flood-related hazard to infrastructure, people, downtime, environment and revenue. Outputs assist decision makers to design investment strategies for minimising mining operations’ vulnerability to climate. Previously developed for smaller, wetter mines in Queensland’s coal region, the outputs provide a hot-spot map, fault tree analysis and an assessment of the mine’s capacity to adapt. The multicriteria evaluation (MCE) within a geographic information system (GIS), equally suits iron-ore mines’ siteconditions (elevation, slope, drainage, soil and vegetation) to identify critical inundation areas. Hotspot results provide target zones for in-depth fault-tree analysis that, in turn, present a range of sitespecific adaptation options. Rainfall-intensity and the number of rain days since the 1970s have increased over central and eastern parts of the Pilbara Region. While tropical cyclones may become less frequent, they are projected to increase in intensity. Although some parts of the Hamersley Ranges receive more than 500 mm per annum, rainfall in the Pilbara is generally very low. Therefore, experience of the impacts of extreme rainfall events in the constantly changing topography of Western Australia’s iron ore region may be sparse. Minimising potential effects can be proactively assisted using CRATER.

Nov 8, 2021

How many of you have felt tired and light-headed after standing or working in the sun or by the oppressive, hot, muggy conditions of an Australian summer? For those of you who have, you've experienced the minor effects of heat stress. Heat

Jan 1, 1994

By B C. Sarkar, D Ray, V Sarkar, P K. Sinha, R K. Singh, A Kumar

Estimation of iron ore grade distribution has been attempted using geostatistics and artificial neural network (ANN) based models for a banded iron formation (BIF) type iron ore deposit of East India. Geologically, it is a supergene iron ore formation through an enrichment process of parent material (BIFs) by gradual leaching of impurities, namely SiO2 and Al2O3. As the degree of leaching differs spatially, distribution of Fe varies depending on local controls of ore formation. While geostatistical methods work on models based on spatial correlations of mineralisation parameters, ANN models a non-linear distribution and is widely used as a global approximator. Spatial distribution modelling of Fe values has been carried out employing ordinary kriging (OK) and sequential Gaussian simulation (SGS). Non-linear modelling has been performed using hybrid neural networks (HNN) that provided an alternative option for grade estimation. Classical statistical modelling revealed a negatively skewed 3-parameter lognormal Fe population having a mean of 60.49 per cent with a skewness of -0.08 and a kurtosis of 2.60. Semi-variography and geostatistical estimation employing OK procedure led to block-by-block kriged estimates with associated kriging variance, which provided an overall mean kriged estimate and kriging variance of Fe as 60.29 per cent and 7.76 (per cent)2 respectively. SGS procedure revealed a mean of 60.71 per cent and a standard deviation of 5.89 per cent with minimum and maximum values as 45.12 per cent and 68.70 per cent respectively in respect of Fe. HNN model provided values of mean squared error (MSE) and correlation coefficient (R2) as 12.33 and 0.61 respectively, thereby exhibiting the robustness of the model to sustain maximum heterogeneity within the target domain. A comparison of Fe grade estimates obtained by kriging, simulation and HNN models more or less maintain similar distribution patterns that are close to the sample data. It is thus opined to carry out the grade prediction exercise employing all these three modelling approaches to obtain alternative scenarios for improved mine planning and design exercises. The techniques provide a foundation for cogent grade modelling leading to improved iron ore reserve estimation procedures.CITATION:Sarkar, B C, Singh, R K, Ray, D, Kumar, A, Sinha, P K and Sarkar, V, 2017. Iron ore grade modelling using geostatistics and artificial neural networks, in Proceedings Iron Ore 2017, pp 431–438 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 24, 2017

By P M. Ashley, M T. Costelloe

The Mary Kathleen tailings storage facility (TSF) contains 7.1 Mt of uranium mill tailings. This waste repository was rehabilitated in the mid-1980s using a multibarrier dry cover. At the time of mine closure, it was predicted that acid mine drainage (AMD) generation would not eventuate and that uranium, heavy metals and radionuclides would be adsorbed within the tailings and not seep from the TSF into the environment. This study reports on the environmental status of the TSF. Gamma-ray measurements indicate an intact dry cover of the waste repository. However, seepage (~0.5 L s-1) of acid (pH 5.71), saline (0.31 per cent), high conductivity (8.8 mS cm-1), slightly oxygenated (DO 2.6 mg L-1), radioactive waters occurs from the toe of the tailings dam into the former evaporation ponds and local drainage system. Seepage waters are calcium-magnesium-sulfate rich with elevated Fe, Mn, Ni, U and Zn values. Oxygenation of tailings seepages causes the precipitation of Fe and coprecipitation and adsorption of other metals (Pb, U, Y), metalloids (As), rare earth elements (Ce, La) and radionuclides (U-235, U-238, Th-227). In contrast, Ba, Ni, Sr, Mn, P, S, Ca, Mg, Na and K as well as Ra nuclides (Ra-226 and Ra-228) remain in solution until pH neutralisation and evaporation lead to their precipitation in efflorescences and sulfate-rich evaporative sediments further downstream. Dry capping of Mary Kathleen uranium mill tailings has resulted in physical containment of the wastes. The dry cover shows no signs of erosion and radiation levels are within acceptable limits. However, the flow rate of surface seepage from the TSF occurs at a much higher rate than predicted. Also, the neutralising potential and adsorption capacity of the tailings and underlying aquifer were overestimated at the time of mine closure. AMD has developed mobilising metals, metalloids, rare earth elements, alkalis, radionuclides and sulfate from the waste repository into surface water seepages.

Jan 1, 2003

By R J. In, C Moore, P J. Moffitt, T Hansen

Telfer Gold Mine combines a world-class gold and copper resource and longevity of operation as a major gold and copper producer. Telfer Gold Mine has undergone a series of transformations since mining commenced as a high-grade narrow-vein oxide open pit operation in 1977. In 1986, the open pit operation converted from a narrow-vein, high-grade operation, to a low-grade high-volume oxide mining operation utilising dump leach processing technology. Mechanised underground mining of the high-grade narrow-veins commenced in 1990. Total recovered gold production between 1977 to 1999 has totalled 5.7 million ounces. The Telfer Extension Project consists of two pre-feasibility studies, the Surface Extension Project (SEP) and the I-Series Project (ISP). The combined studies represent one of the more significant resource evaluations undertaken in the gold industry in recent times. Geological activities for the SEP pre-feasibility study have included the drill definition of a large low-grade resource within an area of 25 km2 . The surface drilling program has completed 15 000 metres of HQ3 diamond drilling and over 30 000 metres of RC between last quarter of 1998 and late-1999. The ISP pre-feasibility study is currently evaluating the resource potential of both a high-grade low-volume and a lower grade bulk mining scenario, 800 m to 1200 m below the surface of Main Dome. 15 000 metres of underground diamond drilling have been completed between last quarter of 1998 and August 1999 as part of this study. Systems and cultures have been developed to maximise safety, monitor the quality assurance/quality control (QA/QC) on all aspects of the operation, and minimise impact on the environment. All data are stored in database systems, specifically designed for Telfer operations. 3D geostatistical resource estimation using ordinary kriging has been carried out for over 220 geological domains within the 25 km3 of mineralised system. Non-linear geostatistical techniques are being investigated as part of the pre-feasibility study.

Jan 1, 2000

Ore from the Hill 50 Gold Mine, consists essentially of pyrrhotite, with minor amounts of pyrite, chalcopyrite, galena and gold, replacing "jaspilite." The gold is associated with the sulphides as shotty particles. About 8 per cent. of the particles are less than '0.010'mm.The Hill 50 Gold Mine, at Boogardie in the Murchison goldfield, about 300 miles north-west of Kalgoorlie, was first operated in 1898. From 1898 to 1917 it yielded 20,000 short tons of ore for a recovery of 6,225' fine oz. gold, equivalent to a recovery grade of 6.22 dwt. gold per ton.The present company since the beginning of its operations in September 1936 to June 30, 1954, produced 811,081 short tons of ore for a recovery of 242,554 fine oz. of gold, equivalent to a recovery grade of 5.98 dwt. gold per ton.The grade of ore (recovery grade) has shown a remarkable variation with depth. From the 120 ft. Ievel to the 300 ft. level, it averaged about 7.5 dwt. Au per ton. Below the 300 ft. level it declined, and from 300 ft. to 400 ft. averaged 4.9 dwt. per ton, falling further with increasing depth to about 4.5 dwt. per ton at the '600 ft. level.On the 820 ft. level the grade improved sharply to about 14 dwt: per ton, and this grade has persisted down to and on the 1060 ft. level.The orebody has been described by Finucane (1953) as a series of lenses of finely banded jaspilite conformably enclosed by greenstones. The jaspilite is tightly folded and faulted and intruded by dykes of felspar porpnyry.Mineralization is practically restricted to the jaspilite.

Jan 1, 1955

This paper contends that optimisation of energy resources through active control and predictive simulation modelling is possible, and that such monitoring leads to large savings in the electricity costs of hot mines (where refrigeration has to be employed). In addition, active monitoring and control can positively affect the establishment of a safe, healthy and productive working environment. In the entire optimisation process certain guidelines were set to ensure that the requirements of the Mine Health and Safety Act were met (South Africa). Varying the quantity of air supplied underground by means of variable speed drive (VSD) fans is one of the crucial factors in the interactive approach towards the optimisation of ventilation, as is refrigeration and the pumping requirements associated with refrigeration. This article highlights the interaction between the amount of air supplied and the effect it has on refrigeration requirements underground. This article also considers the effect that this would have on contaminant control. Various tools are available for ventilation and cooling design for mining. A lot of these tools are based on the assumption of steady state conditions and do not take into account instantaneous changes in conditions, day-to-day, or hour-to-hour (such as for temperature and contaminants). They also do not take into account the optimisation of energy resources related to the creation of the acceptable underground conditions. With these tools worst-case and best-case scenarios are identified, and strategic decisions are made accordingly. Currently, the amount of the fresh air, the velocity of the air, and its general temperature in the mine are only changed when one production phase changes into another (or when unacceptable conditions occur as a result of poor design or neglect). This means that during a specific production phase (which can last for several months), there can be an oversupply, or undersupply, of energy resources, which will obviously affect the concentration levels of the various contaminants (through under or oversupply of air).

Jan 1, 2005

By A B. Jahed, Ö Aydan, T Ito

In this study, the authors compiled some case history data and present some typical examples of rock slope stability issues in Afghanistan with a special emphasis on Kandahar region and categorise rock slope failures according to the principles of modern rock slope engineering. The slopes considered involve rock-cut, natural rock slopes mainly. The effect of structural geology and discontinuous nature of rock mass on both slope-cuts and natural rock slopes is taken into account and some preliminary assessments on the stable and unstable rock slopes are presented. Furthermore, the seismic effect on their stability is also considered. It is also pointed out that similar issues could be observed in open pit mines, which may be exploited in years to come.

Nov 29, 2022

By J Ledgerwood

Namakwa Sands is a mineral processing company based on the West Coast of South Africa and is solely owned by Exxaro Resources Limited. Mineral ore is mined and processed, concentrated and both chemical and mechanically upgraded before being sent for electrostatic and magnetic separation units. The final high value mineral products report as Zircon, Rutile and Ilmenite.The recovery of non-magnetic material is largely dependent upon a number of factors, including but not limited to dew point, ambient temperature, feed rate, mineral size distribution, specific gravity and mineral content in head feed. One important limiting factor to recovery in typical dry mill operations is the particle size distribution of the feed. Variance in the particle size has catastrophic consequences for recovery. This is the reason for this study. Until recently large variances in non-magnetic production were viewed to be a function of machine operation. This view was later rejected with the feed size distribution determined as the major driver of low recoveries, for Namakwa Sands orebody 50 per cent variance in particle size distribution can be noticed within one day. This is because of the successive mining blending techniques employed.The predicament is that the two modes were so closely placed together that recovery of a single mode is almost impossible without the consequence of greatly reducing recovery. The second mode was found at 125 µm while the first was at 90 µm. Interestingly, for the mentioned feed type a cumulative size distribution of a unimodal feed type is almost exactly the same as for a bimodal size distribution. Thus a plot of cumulative size distribution will show no difference due to the modes being so close together. This is the reason why this phenomenon was not noticed before.The study also found that, using an high tension roll (HTR) or rare earth roll, a fine stream with a single mode at 90 µm versus a coarse stream with a single mode at 150 µm would yield completely different results interms of yields. Larger conductive particles are thrown from the roll while small particles loose charge faster (entrainment). Results in terms of the bimodal size distribution show that even though 25 per cent of the feed type is greater than 150 µm the yields followed a similar pattern to that of the coarse particles rather than that of the majority (75 per cent) fine particles. This confirms what was published by M Ziemski and P N Holtham in 2005 on charge decay rates; they mentioned that particle bed effects played a major role in recovery.

Oct 5, 2011

By D Baas, J Le, R Braun, R Chandramohan, K Hollis, G Lane

The Phu Kham Copper-Gold Operation (Phu Kham) is located in northern Laos, approximately 140 kilometres from the capital, Vientiane. The operation is a producing asset for Australian-based copper and gold producer, PanAust Limited (PanAust) and is operated by Lao-registered company, Phu Bia Mining Limited (Phu Bia Mining). PanAust holds a 90 % interest in Phu Bia Mining. The Government of Laos owns the remaining 10 %.The Phu Kham Operation has recently undergone a series of process improvements to treat the anticipated competent ores scheduled for 2017 and 2018. The operation’s comminution circuit, which comprises a semi-autogenous (SAG) mill and two ball mills, each with 13 megawatts (MW) of installed power, was expected to be SAG mill limited when treating competent basement rock. Ausenco Services Pty Ltd (Ausenco), was engaged to help optimise and enhance the productivity of the Phu Kham comminution circuit over an eight-month period. The work involved participating in and overseeing the redesign of the SAG mill liner systems and developing operational strategies for maximising throughput through to the end of mine life. Ausenco’s comminution optimisation tool, Ausgrind, was used to benchmark and analyse plant data with empirical models, predict circuit performance for varying ore characteristics and evaluate liner wear and predict the life for varying operating parameters. Variances between the actual and the predicted values were assessed in detail to identify missed opportunities, and guiding operating parameters were redefined to maximise throughput and productivity. In combination with the redesigned liner system, optimised process controls for varying ore competencies, and improved operational practices and troubleshooting strategies, increased Phu Kham overall production, exceeding the milling capacity when treating competent ores. CITATION:Chandramohan, R, Braun, R, Lane, G, Hollis, K, Le, J and Baas, D, 2018. SAG mill optimisation and increasing throughput at the Phu Kham Copper-Gold Operation – a success story, in Proceedings 14th AusIMM Mill Operators' Conference 2018, pp 113–128 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Aug 29, 2018

By G Hill, D Grant, M Tyler

Located approximately 570km NNW of Adelaide in South Australia, the Olympic Dam mine (OD) is the world’s fourth largest remaining copper and gold resource and the largest uranium resource. Discovered in 1975 and going into production in 1988, the operation consists of a fully vertically integrated underground mine, mineral processing plant, copper smelter and refinery, as well as associated infrastructure. BHP achieved production of 203,000 tonnes of copper cathode plus associated by-products in financial year 2016. The immense size and high-grades of the Olympic Dam resource offer a range of growth pathways, making closure timing estimation and planning a challenge. Current estimates put the OD resource at approximately 79 million tonnes of copper. Major factors influencing the closure timing estimation, as a result of the large resource and grade tonnage profile, include the mining method that may be used and the downstream processing method, ultimately influencing such things as the total disturbance area and the extent of infrastructure to be demolished at the end of mine life. In addition, factors such as the mining and processing method and production rate have a direct impact on larger rehabilitation items such as the total number of tailings cells required.CITATION:Grant, D, Tyler, M and Hill, G, 2018. Olympic Dam mine closure planning process, in Proceedings Life-of-Mine 2018, pp 43–45 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 25, 2018

By Clarici E, Marsden J. R, Calderbank P. A

Evaluation of previous studies of multi-layer perceptron type artificial neural networks in the modelling of the deformability behaviour of rock have suggested that a deviation from the standard method of laboratory testing of rock under triaxial loading at constant confining stresses and constant axial strain rates may be inappropriate when the data produced are used to train an artificial neural network. In this paper, preliminary results of adopting such a strategy are reported. Of specific concern is the establishment of a suitable schedule for the stress path during testing. Furthermore, the training element of back propagation optimisation was directed towards prediction of new stresses given old stresses and old strain increments. Adoption of this method of supervisation in artificial neural network training facilitates the integration of the trained neural network within existing numerical methods used in rock mechanics. The target code was a finite difference Lagrangian formulation for the analysis of continua. Sandstone rock taken from a quarry in the UK was used in the study which showed that the method has great potential.

Jan 1, 1995