Search Documents

By S K. Michelic, M Schickbichler, A Kharicha, E Karimi-Sibaki

The requirements for the controllability of metallurgical processes are increasingly becoming the focus of both industry and research. Advances in this field of research not only impact the stability of processes but often also influence the quality of the final product. One important way to examine processes in-depth, and thus show potential for improvement, is to describe them using physicsdriven models. In metallurgy, thermodynamic and kinetic descriptions of interactions between individual components of a system are often used to describe and analyse important metallurgical phenomena across the entire process. However, for the creation of physics-based models, boundary conditions and process variables must be implemented to enable a description that is as realistic as possible. The collection and generalisation of boundary conditions and process variables is, therefore, an important step towards functional models. The focus of this study is the determination of mass transfer coefficients between all components in a steel/slag/refractory system. For this purpose, experimental and theoretical methods are applied. Laboratory scale experiments are carried out in an induction furnace, and the mass transfer coefficients of the defined steel/slag/refractory system are calculated from changes in the chemical composition of the various components. Additionally, a calculation of the mass transfer coefficients based on dimensionless quantities is carried out. By comparing the values of the mass transfer coefficients determined theoretically and those determined experimentally in the trials, the suitability of the calculation is examined. The collection of mass transfer coefficients provides essential findings for future kinetic descriptions of inclusion modification based on the effective equilibrium reaction zone (EERZ) approach.

Aug 21, 2024

By A Kleinitz, J Halilovic, K Trappitt

Mine operators use grade control to determine the destination of each block of material in the mine. In polymetallic mines, grades are best expressed in dollars: the Net Smelter Return, NSR, per tonne. To estimate NSRs, geologists working on grade control develop models for each geometallurgical domain in the mine. These models may incorporate observations on the mineralogy and grain sizes of the material being examined. The site’s mill operators contribute to the models by providing geologists with statistical analyses that relate assay results and mineralogical compositions to metallurgical parameters, such as the rates of recovery of each economic metal to each of the concentrates produced, and the compositions of those concentrates. The team responsible for sales and marketing of the site’s products contributes to the NSR models by providing details of the costs of shipping concentrates to smelters and refineries; and by providing figures that are specified in the smelter contracts, such as the payability of the metals in each concentrate and the fees charged by the smelter. The mill operators also provide, for the NSR models, equations to estimate the rates of recovery of deleterious materials to each concentrate. Deleterious materials comprise mostly halogens and amphoteric elements, both of which reduce the efficiency of smelters. Furthermore, deleterious materials such as antimony and arsenic may be poisonous to people and to the environment. The sales and marketing team provide specifics of the penalties that smelters impose upon deleterious materials. These penalties may reduce NSRs by tens of percent, possibly to levels below the cut-off grade. Thus, in the blocks that are subject to grade control, mine geologists monitor not only the concentrations of economic metals, but also the presence and abundance of deleterious materials. The preparation and maintenance of models, to estimate NSRs and to assess changes in the levels of potentially toxic materials to be mined, requires close and continuing consultation between corporate departments. There must be strong communication of mine geologists with the mill operators; with the people who market the mine’s concentrates; and, should there be a risk of encountering toxic levels of deleterious materials, with the mine’s health, safety and environmental officers. This co-operation could require radical changes in the structure of many organisations. However, experience suggests that such changes can significantly improve the profitability of a mine.

Mar 22, 2022

By A Purwodihardjo

Evaluation of the construction method used for the pedestrian underpass construction at Ipswich Road, Brisbane, Australia is presented in this paper. The pedestrian underpass was constructed through the existing railway embankment between Harrogate and O’Keefe Streets on the eastern side of Ipswich Road. This underpass construction is part of the CLEM7 tunnel project (formerly known as the North-South Bypass Tunnel) which is the longest toll road in Australia at a total length of 6.8 km. The jacked box construction technique was initially identified as a preferred option during the tender and concept design phases. However at the final design stage, the cut and cover technique was selected as this method can reduce the construction time and cost significantly. The design and construction teams effectively managed the challenges, complexities and risks associated with undertaking cut and cover tunnel through the existing heavily utilised rail embankment. The on-site construction time for the underpass using the cut and cover technique was reduced to less than 42 hours.

Mar 8, 2011

By D Wimpenny

Underground infrastructure is often a critical component of transportation and utility schemes. It is characterised by long design lives with limited access for inspection and maintenance. The exposure environment can be difficult to assess since it will often vary substantially between different locations in the same facility and with time during construction and in service. In addition, the specific demands placed upon underground infrastructure are not well covered by the exposure classes and other guidance given within current codes of practice. When problems occur they can be difficult to rectify and involve significant disruption.Given these substantial risks the prudent designer may adopt a systematic ‘durability planning’ approach which:· defines the environment and principal deterioration mechanisms for the various elements and construction materials,· predicts the design life for alternative durability enhancement options, and· recommends associated measures to be adopted during construction and in service.This paper describes the development of durability planning within Halcrow, giving examples of its use from its first implementation on tunnels under the Suez Canal in 1993 to recent projects in the Middle East and Australia. It seeks to demystify the process, identify shortcomings and speculate on its future development within the civil and mining sectors.

Mar 8, 2011

By R Miller

The enrichment of magnetite to haematite and haematite-goethite leads to a coincident magnetic low and gravity high within the banded iron formation. Palaeochannel deposits of pisolitic limonite can be expected to provide a relative magnetic high and gravity low in a sinuous geometry. Detrital iron deposits of conglomerate, scree or ‘canga’ might have indistinct magnetic response but will usually have a relative gravity high.These signatures provide clear discriminators detectable by a joint gravity and magnetic survey.The combination of airborne gravity gradiometry and magnetometry is particularly powerful in detecting and discriminating targets, as well as mapping lithologies and structure, across a wide variety of iron ore deposit styles. It provides detection capabilities in a platform capable of rapid, complete coverage with minimal access issues. This approach has been used in FALCON™ airborne surveys for iron ore exploration in the Great Lakes, USA; the Middleback Ranges, South Australia; and the Hamersley Basin, Western Australia.The complex magnetic properties of iron formations (particularly remanence, anisotropy and depth of weathering) prevent this approach from being simple. The use of vector residual magnetic intensity (VRMI), calculated from the measured total magnetic intensity (TMI), assists by reducing the complexity due to the different directions of the remanent and induced magnetic fields.Estimations of the density to magnetisation ratio via the pseudo-lithology calculated from the VRMI and gravity gradients provide a useful method of capturing the discriminatory power of joint magnetic and gravity gradient data.

Jul 11, 2011

By K Whelan

The Land Access Branch of the Mines Division of the Northern Territory Department of Mines and Energy is responsible for Aboriginal Liaison and cross-cultural matters that affect the Department. In essence, it exists to provide a basis for communication between the Department, industry. Aboriginal organisations and Traditional Owners. The paper outlines the various ways in which this is accomplished including the preparation of detriment submissions for pending land claim hearings, the use of promotional material to support access to Aboriginal Land for NTGS Mapping Programs and field work, and advice/assistance on exploration and mining issues.

Jan 1, 1994

By T Gready

Stawell Gold Mines operates the Magdala underground mine in western Victoria, Australia. Several orebodies are extracted by longhole open stoping at a depth of 900 m below the town of Stawell. Some stopes are backfilled with cemented slurry rock fill (CSRF) to ensure stability, increase recovery of ore reserves, minimise dilution of ore grades, and add value to the project. StawellÆs simple CSRF system is described, including the novel equipment used to minimise capital costs. Design criteria, operating procedures, monitoring systems and results are discussed in detail. Practical aspects are considered, including lessons learnt about barricades, overbreak and segregation. The economics of CSRF are discussed, including capital costs, operating costs and the total cost per ounce of gold poured. Options for mining with and without CSRF are compared in terms of return on investment and net cash flows. Examples demonstrate the method used to calculate æbreak-evenÆ stope ore grades which determine whether or not CSRF will add value in different circumstances.

Jan 1, 2002

By H G. Poulos

Prediction of ground deformation caused by soft ground tunnelling is an important problem facing design engineers. The ground deformations are caused by the closure of the gap formed around the tunnel due to the tunnelling procedure and soil intrusion via the tunnel face into the tunnel. There are three different approaches that are commonly used in practice to estimate the ground deformations due to tunnelling, namely, empirical methods, analytical methods and finite element methods. One of the important issues of tunnelling in urban areas is the assessment of the likely impact on adjacent pile foundations of ground movements arising from tunnel construction. The main objectives of this paper are two-fold: first, to assess the available methods to estimate the tunnelling-induced ground deformations, and second, to examine the effect of such ground deformations on adjacent piles. Analytical solutions to predict the tunnelling-induced ground deformation developed by the authors are used in this study. These estimated ground deformations are imposed on the pile in simplified boundary element analyses to compute pile responses. The influence of various factors such as tunnel geometry, ground loss ratio, pile diameter and ratio of pile length to tunnel depth are examined in this study.

Jan 1, 1999

By A Mcquillan, N Bar

Geotechnical models developed during the open pit mine planning stage are generally three-dimensional (3D) in component to capture the spatial variation in geological, structural, hydrogeological and geomechanical conditions. Yet when geotechnical analysis is completed, often the 3D geological, hydrogeological and structural models are simplified to two-dimensions (2D). This paper demonstrates this simplification, through referenced case studies, can lead to the wrong failure mechanism being analysed and/or a conservative Factor of Safety (FOS), or Strength Reduction Factor (SRF), being calculated, leading to a false sense of stability. There exists a paradigm that the FOS calculated using 2D limit equilibrium (LE), or the Strength Reduction Factor (SRF) calculated using 2D finite element (FE), modelling methods is generally conservative, ie lower, than the true FOS. However, this assumption that 3D FOS, or 3D SRF, is always higher than 2D FOS, or 2D SRF, is not always correct (Chen and Chameau, 1983; Bromhead and Martin, 2004; Herza et al, 2017; Pyke, 2017; Dana et al, 2018).

Nov 29, 2022

By N Udugampola, d A. Seneviratne, X Ai, B Li

With the evolution of mining technology, wireless mesh networks using low-power, long-range technologies such as LoRa are increasingly utilised in underground mining operations. Efficient deployment of wireless nodes in such mesh networks necessitates understanding radio wave propagation behaviour in underground mines. While existing propagation models either remain theoretical or apply only to basic geometric shapes, we propose a practical approach to analyse radio wave propagation behaviour in underground mines using ray tracing simulations with reconstructed 3D models of targeted environments. Our method validated using a set of corridors as a substitute for underground mine environments, involves constructing a 3D model using SolidWorks from LiDAR scans of the environment and performing wireless transmission simulations using the MATLAB ray tracing toolkit. Our simulation model is also fine-tuned by calibrating the raytracing parameters based on real-world LoRa transmission experiments in the actual environment corresponding to the 3D model. This method offers a practical solution for optimising wireless node placement in underground mines, facilitating efficient network deployment while reducing the need for extensive physical testing of radio wave transmissions.

Sep 1, 2024

By A Murphy, D Lauder, J Miranda

Minera Alumbrera Limited operates the Alumbrera concentrator, treating a nominal 80 000 tpd of porphyry gold/copper ore. It is located in Argentina, 1200 km north-west of Buenos Aires in Catamarca Province, at an elevation of 2550 m above sea level. Treatment facilities consist of crushing, SAG and primary ball mill grinding circuits, rougher flotation, ball mill regrinding, gravity recovery and cleaner flotation. It is one of only a small number of concentrators in the world, which uses Jameson Cells alone for cleaner circuit flotation. Plant design was started in June 1995, with commissioning commencing in July 1997. Following a successful ramping up to design tonnages and recoveries, a number of options were reviewed to improve gold and copper recoveries. This paper concentrates on a detailed size by size flotation recovery project, commenced in May 1999. Utilising optical microscopy, scanning electron microscopy and analysis of surface chemistry it has allowed losses by size fraction to be quantified and options for enhanced recoveries to be developed. Coupled with extensive circuit surveys it has also provided an insight into previously unknown properties of Jameson Cell operation. Among these are unique residence time and bubble formation reactions to reagent and pulp flow variations, which has permitted a number of novel changes to the operation to maximise capacity and recovery.

Jan 1, 2000

By F Sahlström, E M. Jolis, V R Troll, E Jonsson, K Högdahl, C Harris

"An EXTENDED ABSTRACT is available for download. A full-length paper was not prepared for this presentation. The Bastnäs-type magnetite-skarn-hosted rare earth element (REE) mineralisations are located in the Palaeoproterozoic Bergslagen ore province, central Sweden, and occur along a ca 100 km long belt of 1.90–1.87 Ga metavolcanosedimentary rocks. Ten different Bastnäs-type deposits have been sampled in order to assess the origin of ore-forming fluids in these systems. Magnetite and quartz have d18O values ranging from -2.3 to +1.1‰ and +7.2 to +8.3‰ respectively. Mineralised carbonates have d18O values between +5.8 and +7.2‰ and d13C values between -5.4 and -3.3‰. Temperature calculations based on the O-isotope composition of mineral pairs, combined with available fluid inclusion data, suggest primary mineralisation at ca 650–400°C. For these temperatures, calculated equilibrium fluids have d18O values that range from those typical of magmatic fluids (+6 to +8‰) to lower values (down to +3‰). Variation in carbonate O and C isotope data are consistent with interaction between local Palaeoproterozoic carbonate rocks (d18O = +12.5 to +19.6‰ and d13C = -1.8 to +1.7‰) and fluids of a magmatic origin. It is suggested that the Bastnäs-type REE-magnetite mineralisations formed as a result of reactions between local carbonate units and high-temperature, magmatic-dominated hydrothermal fluids during 1.90–1.87 Ga (Svecofennian) syn-volcanic activity.CITATION:Sahlström, F, Jonsson, E, Högdahl, K, Harris, C, Troll, V R and Jolis, E M, 2015. O and C isotope study of Bastnäs-type rare earth element mineralisation, Bergslagen, Sweden, in Proceedings PACRIM 2015 Congress, pp 439–444 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Mar 18, 2015

By S Versace, D Arnott, D Bojcevs, A Shaw

The George Fisher deposit is a significant sediment hosted silver-leadzinc resource located 2 km north of the Hilton Mine in NW Queensland. The George Fisher feasibility project involved the completion of underground and surface drilling programs to delineate Measured and Indicated Resource which could be converted to an Ore Reserve through mining and commercial studies. The geological information which was collected and used for the feasibility study included a major program of diamond drilling, predominantly from underground sites, but with some drilling also completed from surface. All drillcore was geologically and geotechnically logged, sampled and assayed. Data was also collected from underground cross-cut and drive development which was mapped for rocktype, ore distribution, structure and geotechnical condition. This new geological data, generated during the Pre-Feasibility and Feasibility stages, was combined with results of all previous drilling campaigns in the George Fisher area to produce a comprehensive database on which geological modelling and Resource estimation could be based. To allow fast and accurate collection and utilisation of data from the drilling program, digital collection processes were used where possible. This resulted in rapid data entry into the project database, significantly enhanced data quality, 100 per cent data ownership within the project team and increased productivity levels. Processes used during the project data collection program are described, lessons learned are related and suggestions for ænext timeÆ are listed using the benefit of hindsight.

Jan 1, 1998

The process of mine planning at AnacondaÆs nickel and cobalt laterite operation located at Murrin-Murrin in the Northern Goldfields of Western Australia is carried out in a number of stages in an endeavour to determine the optimum mining sequence in order to maintain supply to the 4 Mtpa plant subject to operational constraints. The 296 Mt @ 0.99 per cent Ni and 0.064 per cent Co ore reserve (based on a cut-off grade of 0.8 per cent Nickel) is spread geographically widely over three regions comprising Murrin North (15 km + 15 km), Murrin South (7 km + 16 km) and Murrin East (5 km + 13 km) (refer Figure 2). The nickel mineralisation has been broken up further within each region into 18 separate manageable block models representing the 32 different deposits. The models are based initially on the 50 m + 50 m resource drilling for long term planning and updated with 12.5 m + 12.5 m grade control drilling prior to mining. Each of the individual block models are optimised using Whittle 4X software to provide the shells used as the basis for each of the 126 pit designs. The pits are generally nested with starter pits targeting the higher value shells with subsequent pits incrementally cutting back ultimately to the life of mine shells. A series of steps including: the coding of the individual pits into the block model; data export; TCL scripting (to calculate additional economic and tracking information); importing; and re-blocking; completes the transfer of the data into a MineMax (mixed integer linear programming schedule optimising software) model. Using MineMax and the application of operational and production constraints allows the optimisation, assessment and economic evaluation of alternative scenarios in order to determine the optimum life of mine plan and schedule.

Jan 1, 2003

In the past few years the Rietveld method emerged as a routine tool for quantitative phase analysis (QPA) from X-ray diffraction data. Fast and reliable results became possible by combining modern computer technology and optimised mathematical algorithms with the fundamental parameters approach in the Bruker AXS TOPAS software. Here the routine analysis of bauxite raw material and of aluminium bath electrolyte is presented. The accuracy of bauxite quantification was tested by analysing the IUCr round robin sample. An agreement of better than one per cent was obtained for minor constituents and a maximum deviation of 2.5 per cent for the major phases. This is excellent agreement with expected results from weighting. Ten different phases were quantified in natural samples from Turkey with a precision better 0.5 per cent for the major phases and one per cent for the minor phases. Additionally, crystallite sizes were obtained from the peak profiles that give valuable information for the processability of the material. XRD data from solidified aluminium electrolytes were rapidly measured using silicon strip detector technology. With the LynxEyeTM detector full patterns were collected in 90 seconds and analysed with TOPAS. It is shown how to derive well-established measures such as bath ratio and excess AlF3 from the Rietveld results. These measures are widely used in aluminium production and readily available with very high precision. The excellent agreement with ALCAN reference data demonstrates the outstanding accuracy of the method. The mean deviation between here presented results and reference data is below 0.5 per cent for total CaF2, below 0.25 per cent for excess AlF3 and 0.02 for the bath ratio. The precision of the method was evaluated by repeated measurements.

Jan 1, 2008

By C J. Stanley

Reflected light optical microscopy, or epimicroscopy, is one of the oldest techniques of modern mineralogy. At a relatively low capital cost, it is also very resourceful, and the analytical choice for the identification of most ore minerals. In ore mineralogy, reflected light optical images have the potential to overcome the main limitation of backscattered electron images from scanning electron microscopes, namely contrast of mean atomic number  below the spectral resolution of the backscattered electrons detector. This is the case for relevant ores, like iron (haematite-magnetite) and copper-zinc ores (sphalerite-bornite), but for both cases the pairs of minerals are easily discriminated in reflected light. The improvements in optics and electronics also made microscopy a powerful source of digital images, suitable for automated analysis for minerals processing, as the determination of liberation spectra. The drawback, however, has always been the impossibility to recognise the transparent minerals, which account for most of the gangue phases in ores, from the embedding resin, usually epoxy. In order to determine if there was any possibility to separate quartz from epoxy resins, reflectance spectra have been acquired for quartz and some commercial epoxy resins (Araldite, BuehlerÆs Epothin and Epocolor, Araldite spiked with fluorochrome from Struers), from 380 to 720 nm in 5 nm intervals. Reflectance of quartz and epoxy is very similar over the whole visible light range, and varies from 4.5 to five per cent. Epocolor, a red-dyed epoxy, reflects slightly more above 560 nm, as does Araldite spiked with the fluorochrome from 460 to 570, but for both the reflectance is still very close to that of quartz, under 5.1 per cent. This data set is final, and precludes the application of reflectance in light optical image analysis for assessment of liberation, phase quantification, or any other signal that requires separation of resin from transparent minerals.

Jan 1, 2008

Many mining companies, by their remoteness of location from source of power, have to generate their own power and must experience the same problem that had to be met when deciding to increase the capacity of the power station. At present the Company is treating approximately 54,000 tons of ore mined per month, and the present shift average load. is approximately 8,500 kW. at 0.8 power factor, generated at the power plant, the observed peak load being 10,500 kW.It is proposed to increase the tonnage of ore treated to include 36,000 tons of copper ore, in addition to the present 54,000 tons of lead ore. The average load is estimated to be approximately' 16,000 kW. with a peak load of 17,500 kW. The estimate provides for power of 1,000 kW. to be supplied to the north end leases in the next 12 months, also for increased ventilation in the mines.There are installed in the main power station three turbo alternator sets each of 5,000 kW.; normally two sets are run in parallel and one set is a standby unit. A 12,500 kW. set is being installed and proposed loading with the increased tonnage will require the 12,500 kW. set and one 5,000 kW. set, or alternatively, the three 5,000 kW. sets When the 12,500 kW. set is down for service. When the original plant was installed some 25 years ago, the switches selected and installed in the main 3,300 V. power plant switchboard were rated at 150 MVA and the substation distributing centres located at the surface of the mine, in the mill, and in the smelter, were purchased as having a rupturing capacity of 100 MVA, and the stator...

Jan 1, 1953

By G R Ryan

Dissatisfied with conventional wet processing methods for alluvial deposits, Resource Trend Pty Ltd of Cairns set out to develop a better process. After comprehensive investigation of existing dry techniques the principals have now developed a rotary dry concentrator that can handle the fine-grained fraction of alluvial deposits as well as the coarse. Four of these units have been mounted on an integrated towable treatment plant which has been in successful commercial operation for four years in northern Queensland. A second plant is now under construction for use in the United States. Grades of less than 0.2 g/lcm have been profitably mined at throughputs of about 80 cubic metres per hour and 85 per cent availability. The operation runs round the clock with an establishment of four. Major benefits, apart from lower capital and operating costs, are environmental. Ore is picked up, treated, and replaced in its original mixed condition within 25 m of its initial location. Rehabilitation is completed almost immediately behind the plant as it advances, leaving no slimes dams, coarse stockpiles, or haul roads. In 1993 the company won a Premier's Award for Environmental Excellence in the Queensland Mining Industry. The principal disadvantage is moisture, and the company is now actively seeking deposits in the deserts of the world. In Queensland mining is normally possible only for six months of the year.

Jan 1, 1994

By M Sandy, A Vakili, J Albrecht

Although rock strength anisotropy is a well-known phenomenon in rock mechanics, its impact on geotechnical design is often ignored. No widely accepted guideline currently exists for its characterisation. Anisotropy can significantly control the failure mechanism and progression of damage into the rock mass, particularly in high-stress conditions. As such, it can play a key role in the stability of underground excavations and subsequent geotechnical design.This paper introduces the concept of anisotropy at both intact and rock mass scales. It then presents guidelines for measuring anisotropy and assigning rock mass strength properties. An improved unified constitutive model (IUCM), which can account for more complex failure mechanisms, is then briefly described. This IUCM is used to better understand the typical responses of anisotropic rocks to underground mining and to develop an improved damage classification scheme for these conditions.The application of conventional design methods in anisotropic conditions is shown to lead to significant errors. Two case histories are then presented, illustrating how the proposed methodology can improve the reliability and accuracy of the geotechnical analysis when compared with conventional design methods.CITATION:Vakili, A, Albrecht, J and Sandy, M, 2014. Rock strength anisotropy and its importance in underground geotechnical design, in Proceedings AusRock 2014: Third Australasian Ground Control in Mining Conference , pp 167–180 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Nov 5, 2014

By R Marchant, D Willingham

"Predictive maintenance (also known as PHM or equipment ‘health monitoring’) refers to the intelligent monitoring of equipment to avoid future equipment failures. In contrast to conventional preventive maintenance, the maintenance schedule is not determined by a prescribed timeline; instead, it is determined by analytic algorithms, such as machine learning, using data collected from equipment sensors and/or via simulation.Predictive maintenance offers the following benefits for operators and equipment manufacturers:reduction of equipment downtime by identifying issues before failure, thereby enabling convenient scheduling of equipment service and extending equipment lifetimeautomatic determination of the root cause of the failure, enabling appropriate service to be performed without utilising resources to determine a diagnosis avoidance of costs of unnecessary maintenance and unexpected failures improved safety and product quality.Algorithms and data are critical to predictive maintenance success. Sensor data preprocessing is performed using advanced statistical and signal processing techniques. In the case that data isn’t available for the full range of operating modes, operating scenarios can be simulated. Machine learning techniques are then used to estimate equipment health. Once tested, predictive maintenance algorithms may be operationalised in an IT environment such as a server or cloud. Alternatively, algorithms may be implemented in an embedded system directly on the equipment, allowing for faster response times and significantly reducing the amount of data sent over the network.In this paper, we use both historical and simulated data of the plant under various modes of operation including run to failure, and we then leverage machine learning techniques in MATLAB to estimate degradation and remaining useful life. This technique, of combining both simulation models and machine learning, in the areas of predictive maintenance and equipment health monitoring has been adopted by Safran, makers of aircraft jet engines, since 2007. They now have over 160 modules developed (Lacaille and Aurelie, 2015).Citation:Willingham, D and Marchant, R, 2016. Predictive Maintenance Using Simulation and Machine Learning, in Proceedings 13th AusIMM Mill Operators’ Conference 2016, pp 279–284 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Oct 10, 2016