Search Documents

By E. Shavartz, N. B. Strydom

The incorporation of individual cooling in a compressed-oxygen closed-circuit breathing apparatus by E. SHVARTZ, M.Sc. (U.C.L.A.), Ph.D. (U.S.C.) (Visitor) and N. B. STRYDOM, M.Sc., Ph.D. (Illinois) (Fellow) A conventional compressed-oxygen breathing apparatus, which did not include provisions for dehumidification of the inspired air at high environmental temperatures, was tested at these temperatures with and without conductive cooling in the form of 2 kg of pre-frozen ice placed inside the breathing bag of the apparatus. The pre-frozen ice provided conductive cooling of the soda lime and of the chest and abdomen of the subject, who performed moderate work at 50,1 "c. Without cooling, the subject was exhausted after 35 minutes because of a wet-bulb temperature of the inspired air of 46"c. With cooling, the subject finished 2 hours of work. This was possible by keeping the soda lime at a relatively Iow temperature, which resulted in a wet-bulb temperature of the inspired air of only 42 °C after 2 hours, and by conductive cooling of the chest, which resulted in the maintenance of a relatively Iow heart rate and rectal temperature.

Jan 7, 1975

By W. Soetaert, P. Dhar, H. R. Kota, M. Thornhill, S. Roelants, I. V. Chernyshova

Yeast-derived bola-amphiphiles have attracted considerable attention for their applications in various industrial sectors in recent years. However, only a few studies on this class of surfactant were reported to be relevant to mineral processing applications. In this paper, one of the novel surfactants, acidic glucolipid obtained from Candida bombicola sophorolipids and modified by using Penicillium decumbens naringinase substrate has been evaluated for its interaction with chalcocite and calcite minerals because of a new Cu-ore Nussir deposit in Norway containing calcite impurity. The interaction of glucolipid biosurfactant with copper sulphide and carbonate minerals was investigated with zeta potential, adsorption and FTIR studies, and also by Hallimond tube and bench scale flotation tests using pure minerals and Nussir copper ore, respectively. The results illustrate collector adsorption and flotation of copper sulfides at neutral pH. The bench-scale flotation results demonstrate that copper sulphides can be selectively floated from carbonate and silicate gangue minerals. This study underlines the glycolipid’s high potential for its use as collector for flotation of valuable copper sulphide minerals. Keywords: Flotation, biosurfactants, adsorption

Jan 1, 2020

By T. Copland

"The decreasing availability of resources amenable to surface operations has led to increasing numbers of underground mines, with trends indicating this will continue into the future. As a result, there is a need for additional optimization processes and techniques for underground mines, with many analogous methods having already been developed for surface mining. Current methods for design and optimization of stope boundary selection and scheduling mainly involve heuristic methods which focus on a single lever. Individual optimality may be approached, but globally optimal results can be obtained only by an integrated, rigorous approach. In this paper we review previous methodologies for stope boundary selection and medium- to long-term scheduling and highlight the need for an integrated approach. Previous integrated approaches are reviewed and an improved modelling system proposed for shorter solution times and greater applicability to mining situations. Randomly generated data-sets for gold-copper mineralization are used to investigate the model performance, describing solution time as a function of data complexity.IntroductionThe increasing need for mineral resources is driving an increase in underground mines. Lower grade mineralization with larger amounts of overburden is becoming economically viable due to technological advances; however, the software and tools available for strategic underground mine planning are not well developed. Advances in the methods used to determine underground layouts and scheduling must occur to ensure underground mining is as optimized as open pit operations, as underground mining involves many more technical restrictions.The process of determining stope boundaries and scheduling is an example of an aspect of underground mining amenable to optimization (Topal and Sens, 2010). The current industry standard for medium- and long-term planning for sublevel stoping (SLS) is to exclusively determine stope outlines and then determine an appropriate sequence and schedule accordingly. This process violates the concept of optimality as integrating the constraints imposed by pre-determining stope outlines does not allow for considerations in scheduling to influence boundary planning (Ataee-Pour, 2005). An integrated planning process that combines both stope outlines and scheduling would approach the optimal solution and hence generate more value for operations. This investigation specifically deals with the underground sublevel stoping (SLS). Other underground mining methods such as block caving, sublevel caving, and room and pillar mining have unique characteristics and therefore require specific stope boundary/production scheduling considerations."

Jan 1, 2016

By M. Asghari, R. Amiri, A. Haratian, S. Haji

The aim of this investigation is the evaluation of optimising the Shahroud copper ore beneficiation plant near the Iranian city of Shahroud, by means of a sensor-based ore sorter applying X-ray transmission technology. Currently, this plant’s feed capacity of 52t/h produces 0.5t/h copper concentrate with a grade of 30% and copper recovery of 85% from a feed grade of 0.36%. By applying an X-ray transmission-based (XRT) sorter, it is possible to preconcentrate the feed and remove the gangue materials before entering the plant, enabling the production rate of concentrate to be increased. In this study, the obtained representative sample from the plant was preconcentrated in particle size of - 75+10mm by using the X-ray sorter, thus the concentrate with Cu grade of 0.85% was obtained. Therefore, by using of X-ray sorter the Cu grade of plant feed was increased to 0.48%. By increasing the feed grade from 0.36% to 0.48%, and considering a Cu recovery of 85%, the production rate will be increased from 0.48t/h to 0.61t/h. Therefore, the preconcentration by using the XRT sorter increases the production rate by 27%. Keywords: Optimisation, preconcentration, copper, X-ray, sensor-based ore sorting

Jan 1, 2020

"Chairman: Mr R. A. PLUMBRIDGE Rapporteur: Dr D. M. HAWKINSPapers:The relevance of computer methods to the economics of the mineral industry by R: A. PerlmanDynamic control of a mining enterprise by R. G. CoyleAn economic model of the mineral sands industry by G. P. A. HoweMr M. Splaine, in opening the discussion on Mr Perlman's paper, asked whether the model, as fitted by data up to 1963, predicted the rise in the price of copper in 1967, and whether the model could be used to capitalize on short-term price fluctuations.Answering the second question first, Mr Perlman said that the horizon used is six months to one year. In the very short term the activities of speculators obscured the effect of the fundamental econometric variables. This effect, however, was removed if one moved to a longer term, say, quarterly. In 1963 the model had predicted a price rise in 1964 and 1965 and a drop in price in 1966. The rise in 1967 had been caused by a strike, and imponderables such as large strikes were difficult to include in the model since they were unpredictable. Model simulation can be used to show the effect of strikes on price and the effect of small strikes is small.Mr B. R. van Rooyen said that because models are both calibrated and tested on historical data a bias was introduced which gave rise to an overoptimistic estimate of the accuracy of the forecasts. To this Mr Perlman replied that there seemed to be no alternative to the use of historical data for calibrating and testing models, and thus little hope of avoiding the bias. A second point made by Mr. van Rooyen was that manage¬ment tended to be suspicious of complex models and that frequently more heuristic models were sufficiently accurate and preferable for investment decisions. He added that if management were not involved in the model building the econometrician might easily go astray, Mr Perlman replied that symbiosis between data analysts and users of the model was essential and that the experience of the practitioner must be reflected in the model.Mr M. R. Fuller-Good remarked that a clear understanding of future price trends was essential for effective capital planning, and asked, first, how one went from the compiled data on supply and demand to the determination of their effect on price, record, whether necessary data, for example, capacities, could be obtained timeously, and, third, when strikes restricted supply, whether stockpiling by consumers induced large price fluctuations."

Jan 1, 2014

Geological mapping makes an important contribution to orebody knowledge during the evaluation of structurally controlled gold veins. Orebody knowledge comprises an understanding of mineralization characteristics relevant to evaluation, mining, processing and environmental issues and allows project expectations to be realistically set. Structural interpretation to define continuity and mineralization controls is a key part of geological risk reduction and the reporting mineral resources using the JORC and other codes. The Dolgellau gold belt is a small British field that produced an estimated 150 000 oz from narrow quartz veins. Historical records, recent exploration and production data, published material, and accessible surface and underground exposure provide a valuable case study. Previous mapping has shown the general geometry of vein systems, but tends to accentuate gross geological continuity. Recent work has attempted to determine internal vein architecture and examine the significance of the historical views of ore shoot controls. The work resulted in the definition of vein continuity scenarios for the gold belt and evaluation expectations associated with each. This has, in turn, led to a realistic view of what can be achieved from an evaluation and project development perspective.

Jan 1, 2009

[Consider the situation where we wish to estimate the value of a block of ore W from the values of n samples wt (i = 1, 2.... n). The samples can be located anywhere inside or outside W. The blocks and the samples can have any size or shape (Fig. 8.1). We define ws as the set of all the samples wi: WS = Iw1; W2; W3.. . wn and we wish to estimate the block W using the samples ws. Let xi be the value of the ith sample and µw the unknown average value of the block. We can estimate µw from the average value of all the samples. Let µw be the estimator of µw. As the samples need not be of equal size, the sample average is: µw = wi xi/~ wi. (8.1) The mean squared error made when estimating µw by µw is known as the variance of estimation of W by ws. It is the error made when giving the value of the sample set ws to the block W and is written o2E (WS to W). By definition: o2E (ws to W) = E [(µw - µw)2]. (8.2) If n = 1, this error is known as the extension variance. Since the sum of the weights given to the sample values is equal to 1,0, the estimator µw is unbiased (the question of the absence of bias is studied in more detail in Chapter 9): E [( µw - µw)1 = 0. (8.3) The error (µw - µw) has zero mean and a variance o2E = E (W8 to W). If we assume that this error is normally distributed, we can define confidence limits for µw. Let tP be the value of the standardized normal variance t such that the probability that t is less than tP is p: (t,) = .\/27T f exp (- t2/2) dt = p (8.4) The probability that µw is larger than µw + t1-P oE is p. The probability that µw is smaller than µw- t1-P oE is p. The following approximation formulae are often used to calculate 2p central confidence limits for the block value: 68% central confidence limits (p = 16%): µw - o2E, and µw + o2E. 95 % central confidence limits (p = 2,5 %): µw - 2 oE, and µw + 2 oE. Tables of the function 0 can be found in any textbook on statistics (for example, Fraser, 1958, p. 388) (see Table 7.2). [ ] The last line of Table 2.2, corresponding to f = 00, also contains the value of tP for p = 80, 90, 95 and 97,5 %.]

Jan 1, 1978

Financial Times Mining International Year Book 1979. London, The Financial Times Limited, 1979. 712 pp. Price: airmail, U .S. $60,00; surface mail, U .S. $42,00. International Wrought Copper Council. Glossary of terms applicable to wrought products in copper and copper alloys. London, the Council (6 Bathurst Street, Sussex Square, London W2 2SD), 1978. 170 pp. 80 Swiss francs (approximately £25). Council of Mining and Metallurgical Institutions At a meeting of the Council of Commonwealth Mining and Metallurgical Institutions held on 15th January, 1979, it was unanimously agreed that the name of the Council should be changed.. Assaying and analytical techniques This year sees the Diamond Jubilee of the South African Institute of Assayers and Analysts, which held its first meeting on the 3rd of May, 1919.

Jan 1, 1979

By R. J. Davidson

The chemistry related to the adsorption of gold, uranium, and transition-metal ions onto algal biomass (activated carbon) is related to the genesis of the Witwatersrand. Detrital gold being washed into the early basin, together with cyanide generated in the atmosphere, would have solubilized as the stable aurocyanide complex, the necessary oxygen being produced from the photosynthesis of carbon dioxide by primitive algae. Pebble-type conglomerates, while providing for the free movement of solutions containing the vital nutrients for prolific algal growth, would have screened of the sunlight, which would otherwise have degraded any free cyanide in solution. With the subsequent decomposition of the algal deposits, it is surmised that carbon-rich layers having adsorptive properties similar to those of activated carbon formed in the conglomerates. Under these conditions, gold (silver) in solution would have been adsorbed selectively as the cyanide complex, together with uranium as the carbonate complex. Any transition-metal ions present would also have been adsorbed onto such a substrate. The subsequent burial and compression of the gold-rich conglomerate with temperatures rising to about 400DC would then have reduced the adsorbed gold to the metal in a single segregated gold-silver metal phase (95 to 99 per cent of the contained gold), while leaving behind a sulphide phase rich in iron, base metals, and arsenic and containing some gold and silver. The recrystalization of this later phase may explain the presence of the rather consistent contents of secondary pyrite in the Witwatersrand conglomerates. Similarly, uranium minerals, some rich in titanium and carbon, may also have formed. An adsorption model would explain the very consistent trends in the gold-to-silver ratios of individual reefs in the Witwatersrand, which suggest an extensive hydrothermal system approaching isothermal equilibrium. Also, as gold grades increase, so silver grades generally decrease, indicating the sequential displacement of silver by gold as classically obtained with activated carbon.

Jan 1, 1990

By N. Hanief

This research involves the investigation of phase transformations in the platinum-chromium coated system. Single-layer 0.1 µm platinum coatings were deposited via electron beam deposition on 99.98 percent pure chromium substrates. Specimens were subjected to systematic heat treatment in a vacuum furnace at 900°C for up to 20 hours. Phase formation and the changes in surface morphology were investigated by X-ray diffraction (XRD) and scanning electron microscopy (SEM).Both CrPt and Cr3Pt phases are formed during heat treatment for different times at 900°C. Significant changes in the morphology of this coated system were detected after heat treatment at 900°C for 20 hours.

Jan 1, 2012

By A. G. Royle

The reasons for constructing a model of an orebody for which both the parent population and the sampling distribution are known are discussed and details of the model are given. A brief summary of Matheron's theory of regionalized variables is included, with particular reference to his kriging estimators and their variances. Using the model, a comparison is then made between these kriging estimators and other commonly-used estimators. These are compared to find the one with the minimum variance, and an analysis is included to investigate whether any of the estimators is biased. Also included is a comparison between theoretical and experimental variances for some of the estimators.

Jan 1, 2014

By Peter Smith

The construction of one of the world's largest goldrecovery plants to treat run-of-mine ore is progressing on schedule at the President Brand Gold Mine in the Orange Free State. Designed to treat 390 kt per month, the plant will recover 96 per cent of the gold from the ore at a capital cost of 160 million rands in terms of January 1983 money. It will replace the existing gold-treatment installation, as well as provide a 30 per cent increase in capacity. Mintek reports Report M161 Improved recoveries of gold from auriferous calcines and pyrites by fine milling. Report M171 The development of a versatile computer programme for the evaluation of batchflotation results. Report M178 The reduction of chromite in a transferred-arc plasma furnace. Report M179 Optimization of an inductively coupled plasma by the simplex method.

Jan 1, 1985

By A. J. Hofmann, G. P. R. van der Merwe, J. E. W. Holm

"A new approach is proposed to perform relativistic comparisons between alternative operational risk management solutions by taking into account the impact of each operational activity on overall system performance. A specific case study, to which this new approach is applied, involves the deployment of safety systems in underground mining operations. Conflicting objectives to be satisfied are the minimization of risk to human lives and the minimization of production losses. As the focus in this case is primarily on the mitigation of risk, the approach that was applied is referred to as activity-based risk (ABR) analysis. Existing development process and risk management methods used in the South African mining environment were analysed by means of observations, a case study, technical documentation, and literature review. It was evident from this analysis that a discontinuity existed between the acquisition and operational phases in terms of the management of safety risk in the acquisition of electronic safety equipment when viewed from a full lifecycle perspective. This discontinuity could be addressed by defining a risk perspective in the system development phase by employing ABR in the preliminary design phase of a system’s engineering life-cycle. The focus of the ABR system development process is to find the functional definition and configuration of safety equipment that addresses both safety and productivity when taking into account human performance variability. In doing so, a balance between productivity and safety is found in a relativistic sense. IntroductionIn any system life-cycle, two major phases exist, namely system acquisition and operation (including maintenance). A distinction is made between acquisition and procurement, where acquisition includes system development and integration as specific engineering activities. In the development phase of a new system, conceptual design, preliminary design, and detail design phases follow in this order to define a complete system, after which the system is put into production and implemented in an operational environment—these activities chronologically define system acquisition in the context of this paper. It is not uncommon that differences exist between the risk management perspective during acquisition of a system and risk management perspective during operation, where nontechnical aspects are often ignored during acquisition, but are then encountered and found to be problematic during operation (Leveson, 2012). These differences also exist in the mining industry."

Jan 1, 2017

By B. Kenealy

A typical deep shaft is President Steyn No. 2 in the Free State, where 9 tonnes of ore are hoisted at about 15 metres per second from 2378 metres below surface. The skips and attachments each weigh 7 tonnes and they are connected by 43 tonnes of rope, so that to hoist the 9 tonnes of payload, a total of 66 tonnes is accelerated from stand still to 55 km/h for each cycle, using an average of 3185 kilowatts of power in the process. The cycle time for the hoisting is 3.22 minutes. The peak power consumption is 6954 kilowatts, which determines the size of the motor used. Is this the right approach? Are larger skips moving at higher speeds the answer? Is there another way?

Jan 1, 1996

By D. Borman

The location of underground positions in mines has usually fallen to their survey department's. Their usual tasks include: ? installation of a high-precision peg network like the National Survey grid as beacons ? offset measurements to the sidewalls, and sometimes hangingwall and footwalls, of development tunnels and excavations ? offsetting of stoping panels for the calculation of face ? advance and the square meterage of area removed. Other departments build their observations into the plans produced by the surveyors. If more precision is required, they ask the surveyors to `elevate' their points with a theodolite. Apart from the survey peg network and `elevations' these measurements are usually planer measurements suitable for producing plans, sections and projection sheets. When the only representation medium was a sheet of paper or transparency, this was perfectly suitable. However the development of CAD models of the workings has changed all this. Full 3D representation is not properly catered for in the tool sets in current use, and needless hours are spent converting analogue-type observations into digital form. The basic survey models need to be augmented by the observations of other disciplines that are also required to locate positions underground. These include: ? the need for geologists to plott their mapping and ? borehole logs into 3D space ? the need for samplers to position their sample points accurately because the geostatistical models are biased and inaccurate ? the need for stoping width recorders to position their thickness observations to prevent errant evaluation and bonuses ? the need for rock engineers to place their mappings into 3D to build true geotechnical models to manage geotechnical stresses ? the need for production officials to receive updated face ? positions during the month so that they can manage the ? production and utilize their resources properly. This paper covers a new method of positioning profiling points to a suitable degree of accuracy. I believe the method is sufficiently simple and cheap for all to use. Historical methods Platinum and gold orebodies, especially in South Africa, are generally narrow tabular deposits. This made them suitable for depicting on a 2D medium like paper. The determination of stoping or face widths was not a problem, as the ore is removed in a single stoping process. Such 2D representations could be easily positioned using tape offsetting between survey pegs or points tied in from survey pegs. Problems of dip were handled by using 'Stope Sheets' which chose a best fit projection for the whole area depicted or by using true dip section sheets for inclined tunnels. Rolling reef and potholes were the common areas of difficulty. Most mines now model their orebody and plan the extraction in computer graphics. This means that the representation of the current workings has to change to support this trend. It now becomes a truly 3D problem. Mining officials find it inconvenient to have their actual workings in single-line depictions while their orebody is depicted with top and bottom contacts and the planned tunnels in 3D shapes. Geological models which form the basis for the resource model and planning process are often out of date, as the updating process is slow. The geological mapping has to be plotted onto sections and plans. These are then digitized into graphics by a draughtsman and checked by the geologist. Only then does the interpretation and model update take place. Potential methods to create 3D 'Actuals' Global positioning systems (GPS) Surface mines have been blessed by the advent of GPS technology. These simple-to-operate pieces of equipment and compatible software make it possible for all types of mine employees to locate themselves, and therefore to locate their observations. GPS are often inexpensive and give an acceptable degree of accuracy. Only in deep pits or close to the highwalls are observations hindered. Such technology cannot however, work underground. Ground penetrating radar (GPR) GPR is reported to be very useful for estimating the positions of potholes and faults. However it is still considered as providing an estimate, not a definite measurement. GPR is good for seeing into solid rock, not into open spaces. Inertia reading devices Experiments with inertia reading devices have been conducted on the mines. They were the forerunners of GPS for military guidance systems, and were even used for city navigation in the early 70s. They do however work best with heavy or fast-spinning gyros. Anglogold Ashanti's attempt to use them were discontinued in the mid-90s when the developers asked for an additional few million rand for a device that would weigh more than 12 kg and have a limited operational life.

Jan 1, 2006

By J. Cilliers, R. Seitz, D. Drinkwater

Mineral processing produces a saleable product from high-cost ore. The Mineral Processing Engineer must constantly improve the separation to create the most value from the ore and reduce the associated costs. Graduate Metallurgists (or Chemical Engineers) have had the university theoretical training required, but often are illprepared to perform their plant roles. The in-work Metcelerate programme was designed specifically to develop the practical skills that Mineral Process Engineers require, by combining three key elements: 1. Knowledge transfer through self-paced, on-line training; 2. Practical skills acquisition through assessed, practical plant exercises; 3. Skills development through online tutorials. A final process improvement project adds significant value to the operation that far exceeds the training cost. Experience from Metcelerate clients has indicated improved staff retention, greater confidence, and pro-active process intervention.

Jan 1, 2023

By A. L. Hinde, A. A. Bradley, P. J. Lloyd

The results of slow crushing tests in a stiff testing machine for both small and large step reductions of particle size are given. The energy consumption required to produce a given weight of minus 74 um material was determined when both single-crystal quartz and Witwatersrand reef were crushed. For comparison the two materials tested were also comminuted in a ball mill under optimum conditions. There are indications that slow crushing under stiff conditions is the most efficient method of breakage that can be devised. The comparison with ball milling results thus yields a value for the efficiency of ball milling of approximately 80 per cent. These results confirm that the best current estimates of milling efficiency, which are based on the free boundary surface energy of the material being milled, are probably too low by at least one order of magnitude.

By G. Akdogan, I. Mwandawande, S. M. Bradshaw, M. Karimi

The mixing characteristics of industrial flotation columns were investigated using computational fluid dynamics (CFD). Particular emphasis was placed on the clarification of the relationship between the liquid and solids mixing parameters such as the mean residence time and axial dispersion coefficients. The effects of particle size and bubble size on liquid dispersion in the column were also studied. An Eulerian-Eulerian method was applied to simulate the multiphase flow, while additional scalar transport equations were introduced to predict the liquid residence time distribution (RTD) and particle age distribution inside the column. The results obtained show that particle residence time decreases with increasing particle size. The residence time of the coarser particles (112.5 μm) was found to be at least 60% of the liquid residence time, while the finer particles (19 μm) had a residence time similar to the liquid. The results also show that an increase in the particle size of the solids results in a decrease in the liquid vessel dispersion number, while a decrease in the bubble size increases liquid axial mixing. Finally, the simulated axial velocity profiles confirm the similarity between the liquid and solids axial dispersion coefficients in column flotation.

May 2, 2022

By M. Asghari, R. Amiri, A. Haratian, M. Noue Parast, S. Haji

Today the roller screen has a wide range of applications in the steel-making industry. It is used for screening of green pellets before using the kiln. Since the appropriate size of a green pellet is -16+9 mm, there are different gaps between rollers that make green pellets classified in three categories: -9 mm (undersize), -16+9 mm (onsize) and +16mm (oversize). The efficiency of a roller screen is specified according to the weight percent of undersize in onsize as a fine material, and weight percent of onsize in oversize (loss). This efficiency is influenced by different operational parameters such as roller diameter, roller speed, and roller gap, material type of rollers and inclination of roller screen. This study investigates the effect of different material types of rollers in efficiency of Ardakan roller screens, located in the Yazd province of Iran. The rollers of the existing roller screens in this pelletising plant are made of polyurethane which according to this investigation, has a maximum lifetime of about six months. Operating the polyurethane rollers beyond its lifetime generates serious problems such as high wear of rollers, and consequently, material buildup on the roller surface which then significantly decreases the roller screen efficiency. So, after examining different roller materials, stainless steel 304 with higher surface roughness to help pellets move properly on the roller screen surface was selected as a solution to this problem. The new roller screen was constructed by Fakoor Meghnatis Spadana (FMS) and replaced the previous one. In this way, the maximum capacity of the roller screen was increased about 17% and the roller screen efficiency was increased about 15%. Keywords: Roller screen, green pellets, efficiency, onsize, operational parameters

Jan 1, 2020

By A. Navarra, A. Quelopana

The mine production scheduling problem (MPSP) has been studied since the 1960s, and remains an active area of computational research. In extending the concepts of the MPSP, the automated mine may now be regarded as a hierarchical intelligent agent in which the bottom layer consists of distributed robotic equipment, while strategic functionality occupies the higher layers. Here we present a disambiguation of artificial intelligence, machine learning, computational optimization, and automation within the mining context. Specifically, the Q-learning algorithm has been adapted to generate the initial solutions for a high-performing strategic mine planning algorithm, originally developed by Lamghari, Dimitrakopoulos and Ferland, based on the variable neighbourhood descent (VND) metaheuristic. The hierarchical intelligent agent is presented as an integrative conceptual platform, defining the interaction between our new Q-learning adaptation and Lamghari’s VND, and potentially other hierarchically controlled components of an artificially intelligent mine, having various degrees of automation. Sample computations involving Q-learning and VND are presented.

Dec 1, 2021