Search Documents

By J. E. Gebhardt, B. Temel Mckenna, W. Lee, C. S. Macomber

X-ray diffraction (XRD) data was extracted from various sources to develop qualitative ternary and tetrahedral plots differentiating mineralogy, bond work index (BWi) and hardness of ore bodies at different mine sites. A large number of historic reports and compiled characterization laboratory data were used to create a searchable "data lake." The data lake provides a means to locate, consolidate, and visually represent XRD from disparate sources. Visualizations with large amounts of mineral ore XRD characterization data provide a qualitative assessment of ore properties, including comminution qualities such as material hardness. The visual map can be employed to quickly estimate expected ore character and behavior, given XRD analysis of samples from newly characterized and unfamiliar ore. Keywords: Mineralogy, Characterization, Comminution, Database, Ternary, Tetrahedral

Jan 1, 2020

By L. Makua, K. Langa, Ndlovu. S., C. Saguru

"Global demand for the three platinum group metals (PGMs) Pt, Pd, and Rh has been steadily growing due to their widespread use in emission control, industrial catalysis, and numerous other applications. The primary supply of PGMs is currently the mining industry. However, legislative, operational, and environmental challenges faced by many mining operations result in erratic supply patterns and deficits for these three metals. Naturally, recycling scrap material to recover Pt, Pd, and Rh has therefore aroused research interest in the scientific and engineering communities. Given that the majority of the global demand for these three metals is driven by emission control devices, autocatalytic converters are therefore a significant source of already processed and beneficiated PGMs for recycling.Although pyrometallurgical processes dominate the recycling industry, hydrometallurgical processes may offer certain advantages, chief among these being lower emissions and reduced energy consumption. In this investigation, scrap converter material was leached in acidic chloride media and the leach liquor subjected to solvent extraction and cloud point extraction (CPE) to recover the PGMs. The recoveries for Pt and Pd using Alamine 308® dissolved in kerosene with decanol as a modifier were 95% and 81%, respectively. The maximum recoveries using CPE after complexation with 2-mercaptobenzothiazole (2-MBT) in the presence of Triton X-100 and tin (II) chloride dihydrate as a reductant were 97% for Pd, 96% for Pt, and 91% for Rh. This demonstrates that CPE, although relatively new, may have some potential as a breakthrough PGM recovery technology. IntroductionPlatinum group metals (PGMs) have found a wide variety of applications in different industries due to their chemical, catalytic, and physical properties. PGMs are essential in automobile emission abatement, petroleum refining, and the pharmaceutical and electrical industries (Carabias-Martinez et al., 2000). However, the abundance of PGMs in the Earth’s crust is low and their primary sources are fast depleting (Crundwell et al., 2011).The high demand for PGMs, together with social, economic, environmental, and political aspects related to their production, has led to concerns about their future supply. This has resulted in renewed interest in recycling end-of-life material. PGM supply from recycling has doubled over the last decade, and currently contributes 22% to global supply (Johnson Matthey, 2016). This is in part due to the environmental, social, and operational challenges associated with mining of PGMs. For example, labour unrest, energy cuts, declining commodity prices, and declining ore grades have collectively made the mining landscape economically challenging (KPMG, 2015). On the other hand, the high content of PGMs in secondary sources makes their recovery from the increasing quantities of waste products important from a resource conservation viewpoint. Moreover, PGMs obtained through recycling have been demonstrated to have a 1% environmental cost from a life-cycle perspective, whereas PGMs obtained from mining contribute the remaining 99% of environmental cost (Bossi and Gediga, 2017). Sustainable resource recovery and the economic incentive of recycling have therefore been major drivers to justify investment in PGM recycling. The autocatalytic converter industry accounts for about 70% of the global consumption of these metals (Johnson Matthey, 2016) and therefore recycling spent converters has become a major source of Pt, Pd, and Rh (Figure 1)."

May 1, 2019

By J. Pelders, F. Magweregwede, S. M. Rupprecht

Increased depths of conventional gold and platinum mines, longer travelling times as working places move further from the shaft, and ancillary activities taking place in the mining cycle reduce the useable time spent at them workface. Current shift lengths of 8 hours 20 minutes may no longer be adequate ton complete required mining activities.The impact of mineworker commuting times on shift work is also not well understood. The aim of this research was to draft a framework to optimize shift cycles in order to maximize productivity, health, safety, and wellness in the South African mining sector. The framework was informed by a review of the literature, case studies at a local gold mine and platinum mine, and a workshop with industry experts. The findings indicate potential advantages of extended shift lengths and continuous operations, such as improved productivity, asset utilization, and employee morale. However, concerns included fatigue and the associated safety hazards, particularly when working longer shifts, night shifts, and numerous consecutive shifts. Job demands, personal factors, and commuting times are further considerations when scheduling shifts. The ideal shift system for the mining sector should holistically consider and balance operational requirements, health and safety, and employees’ and their families’ requirements, and suit the unique needs of each operation. Changes in shift cycles will require a structured change management process, which involves all stakeholders, and could help to enhance the viability of the South African mining sector.

Aug 1, 2021

By Z. Nzimande

The Constitution of the Republic of South Africa advocates the importance of sustainable economic development and justifiable environmental consciousness by business. The government needs to ensure that every citizen of the Republic has access to an environment that is protected, pollution free, and sustainable by enacting certain regulations. However, there are more than 5 700 derelict and unrehabilitated mines of all types in South Africa. Former asbestos operations were among the first to be targeted for clean-up under the programme instituted by the Department of Mineral Resources (DMR), owing to the proven direct impact of asbestos pollution on health. This paper seeks to investigate the challenges faced by the coal sector as far as mine rehabilitation and closure is concerned. For the purpose of this paper rehabilitation is defined as per the Chamber of Mines Rehabilitation Guidelines publication, which defines rehabilitation as putting the land impacted by mining activities back to a sustainable and usable condition. Some of the current rehabilitation challenges are technical skills (know-how), leadership focus, poor planning, cost saving initiatives, and the government's lack of capacity to enforcement rehabilitation requirements. It is imperative that mining companies identify rehabilitation as a critical strategic pillar that directly influences license to operate. The case study evidence indicates that relevant policies, appointment of accountable people, sufficient leadership support, and the correct choice of rehabilitation equipment can assist to improve the rehabilitation and land management challenge.

Jan 1, 2012

By A. Brodt, I. Mezhibovsky

The traditional vertical transportation systems deliver both gangue and useful mineral. The extraction of the desired minerals requires the construction of mineral processing and waste management plants, driving production costs, and often creating a negative environmental impact. The proposed technology is an integration of mineral processing within the transportation system. The mined rock is crushed and then loaded into a vertical lifting system filled with heavy media, with an intermediate density between the mineral and the waste rock. Driven by gravity separation, the desired mineral floats to the earth's surface, while the waste sinks. Delivered minerals and sunk waste is extracted from the heavy media and is then regenerated to a dry state. The useful mineral should be suitable for further use, and the waste used for backfilling. Remained residues of the heavy media may be recycled and reused in the vertical transportation system. Trials of the proposed process in a pilot format have confirmed economic and environmental advantages over traditional methods of transportation and mineral processing technologies. Keywords: Gravitational processes of mineral processing, separation in heavy media, vertical transportation to earth's surface by floating up

Jan 1, 2020

By A. Drumond, J. F. C. L. Costa, M. G. Lemos, A. L. Rodrigues, F. G. Niquini

The past decade has seen a renewed possibility of using machine learning algorithms to solve a large collection of problems in several fields. Data acquisition for mining operations has increased with the growth in sensor-based technologies, and therefore the amount of information available for mining applications has dramatically increased. Ore sorting equipment is available for separating ore from waste based on differences in physical properties detected by a real-time analyser. The separation efficiency depends on the contrast in these properties. In this study we investigate the application of machine learning models trained using data from the output of a dual-energy X-ray ore sorting apparatus at a gold mine. The particles were first hand-sorted into ore and gangue classes based on their mineralogical composition. Classification models were then used to help decide the balance between the number of true and false positives for ore in the concentrate, with a view to economic parameters, using their receiver operator characteristic (ROC) curves. The results showed AUC (area under the ROC curve) scores of up to 0.85 for the classification models and a maximum reward condition Fpr/Tpr around 0.5/0.9 for a simplified economic model.

Aug 8, 2024

By G. Segaetsho

"Conventional blasting rules of thumb used to develop blast designs are based on parametric ratios, with insufficient consideration of the rock mass factors that influence the achievability of final wall designs. At a hard-rock mine in Botswana, catchment berm designs were frequently unachievable, which exposed the mining operation to safety hazards such as local wallrock failure from damaged crests, frozen toes, and rolling rockfalls from higher mining levels. Increased standoff distances from the highwall reduced the manoeuvring area on the pit floor and the extraction factor that was safely achievable. Application of rock mass classification and the Blastability Index (BI) as a means to improve wall control was investigated. Zones were defined according to rock types forming the western highwall rock mass, and distinguishing rock mass classification factors were used to establish the suitable wall control designs. The approach combined rock mass classification methodologies such as the Geological Strength Index and the Rock Mass Rating, and related them to the BI and discontinuities of the rock mass to produce a design input tool that can be used to develop objective wall control designs. The designs driven by the tool inherently take into account the rock mass characteristic factors at the centre of the rock mass classification methods mentioned above, and significantly reduce the dependence on rules of thumb. It was found that this approach produces designs with explosive energy measures that are consistent with the required rock-breaking effort and the behaviour of discontinuities, while preserving perimeter walls.IntroductionBlasting is the first step in the comminution process. Various coordinated inputs contribute to its success, and in turn to the efficient execution of processes that lie downstream from the blasting step. Primary to meeting production and operational objectives of a mine, as well as the protection of human life and the mineral resource, is the achievement of highwall design specifications and competence. To this end, this study investigated the use of existing tools and knowledge for the achievement of highwall control goals at a hard-rock mine in Botswana."

Jan 1, 2018

By J. van der Walt, W. Spiteri

Flyrock remains a significant threat to the health and safety of mine employees and integrity of infrastructure, as well as to the safety of the neighbouring communities and their property. This investigation was motivated by the general lack of fundamental research and mathematically quantifiable data in the literature regarding the relationship between blast design parameters and their impact on flyrock. The focus was to develop a concept that can be used to mathematically quantify the trajectory of flyrock resulting from a blast, which can be used for future research. The ultimate goal for this technique, once it has been fully developed, is to: ➤ Enable mining operations to generate a database with accurate historical flyrock measurements resulting from their blasting operations ➤ Allow research teams to conduct scientific investigations into flyrock and the impact of various blast design parameters ➤ Generate point-cloud data to visualize blasts and flyrock in a virtual reality environment for training and education purposes. This paper summarizes a conceptual technique and preliminary fieldwork that was carried out to determine the technique’s feasibility and motivate further development. The results show conclusively that a modified photogrammetric technique is capable of capturing flyrock data for further processing and analysis. The data acquisition procedure can, at this point, be used to meet the first aim of the project, namely to gather a field database of historical flyrock generation. Further development of the technique is ongoing and it is envisioned that the scientific-based technique will provide a method whereby future flyrock studies will be comparable and that assumptions will be limited.

Apr 5, 2023

By G-L. Wu, S-W. Wu

"The hot deformation behaviour of Nb-Ti microalloyed high-strength steel was investigated. Hot compression tests were conducted in the temperature range 900 to 1100°C under strain rates of 0.1, 1, and 5 s-1. Dynamic recrystallization (DRX) occurs as the main flow softening mechanism at high temperature and low strain rate. The hot deformation activation energy was calculated to be about 404 699 J/mol. The constitutive equation was developed to describe the relationship between peak stress, strain rate, and deformation temperature. The characteristics of DRX at different deformation conditions were extracted from the stressstrain curves using the work hardening parameter. The Cingara-McQueen equation was developed to predict the flow curves up to the peak strain. The processing maps were obtained on the basis of a dynamic materials model. The results predict an instability region in the temperature range 1010 to 1100°C when the strain rate exceeds 0.78 s-1. IntroductionThe 700 MPa grade HSLA steel is widely used in engineering machinery, automotive beams, carriages, and axle tubes, etc. (Pan et al., 2017 ). Generally, such grades contain a moderately high amount of Mn (approx. 1.4% and above), and microalloying elements like Nb, Ti, V, and Mo to impart the desired strength and toughness through solid-solution strengthening, precipitation hardening, and grain refinement dislocation strengthening (Chen and Yu, 2012; Opiela, 2014). However, the production costs can be greatly reduced by replacing part of the Nb, V, or Mo with inexpensive Ti and adopting the compact strip production CSP process (Opiela, 2014; Chen et al., 2015). Furthermore, the microalloying technology coupled with new-generation thermomechanical control processing (NG-TMCP) has proved efficient for achieving the proper balance between strength, toughness, ductility, and formability by means of a suitable combination of chemical composition and thermomechanical treatment parameters (Shukla et al., 2012; Wu, Zhou, and Liu, 2017).In hot forming processes, the complex microstructural evolutions are often induced by multiplicative hot deformation mechanisms, such as work hardening (WH), dynamic recovery (DRV), and dynamic recrystallization (DRX) (Zhang et al., 2014; Liang et al., 2015). Dynamic softening behaviour during hot processing has generated considerable interest because component properties are influenced significantly by its corresponding microstructural evolution (Wu et al., 2010). During deformation in the DRX process, deformed grains are replaced with substructures and newly formed fine and uniformly distributed grains. This occurs only when a critical strain for the onset of DRX is reached, and at the same time, the minimum rate of energy dissipating is reached (Ferdowsi et al., 2014). DRV occurs at a high strain rate and low temperature, reducing the stored energy greatly and making DRX difficult (Liang et al., 2015). The microstructural changes during DRX are sensitive to the processing parameters, such as strain rate, deformation temperature, and strain (Zhang et al., 2014; Ferdowsi et al., 2014). Therefore, in order to optimize the hot processing parameters, it is important to understand the behaviour of hot deformation visà- vis control of microstructural evolution."

May 1, 2019

By V. K. Risinggård, M. Sparta

We report on the development of a finite-element method model for a pilot furnace for the production of manganese alloys. The model is a multiphysics model that addresses material flow, electrical conditions, heat transfer, and physical and chemical transformations. It is capable of studying both quasi-steady and transient states in time-dependent simulations. The model includes common charge materials and fluxes and can simulate production of both ferromanganese and silicomanganese alloys with acid and basic slags, as well as changing charge compositions. The model output provides access to the material distribution in the furnace during furnace runs, temperature profiles, current paths, energy balances, and alloy and slag production rates and compositions.

Apr 16, 2024

By H. M. Friede, R. H. Steel

Notes on Iron Age copper-smelting technology in the Transvaal by H. M. FRIEDE, Ph.D. and R. H. STEEL (Visitors) Earlier reports on Iron Age copper metallurgy and copper-smelting techniques in the Transvaal are surveyed, and a description and tentative classification of the copper furnaces are given. The analyses of furnace slags and sherds of glazed crucibles from archaeological sites of the Transvaal and the neighbouring Orange Free State pro. vide evidence of copper smelting there in Iron Age times. . An investigation conducted by the Department of Archaeology of the University ofthe Witwatersrand provided information on the details of furnace construction and smelting processes, on the composition of the materials used and produced, and on the making and handling of tools and accessories, such as bellows and tongs, needed by Iron Age smelters. Three models (the KaondejVenda furnace, the Rooiberg crucible furnace, and the Uitkomst furnace) were constructed and operated as a demonstration of Iron Age copper smelting as it was practised in the Transvaal.

Jan 11, 1975

By N. Saldía, C. Riveros, R. Hills, S. Barrera

The transport of tailings composites provided by different sources is a field of study where a limited amount of research has been conducted. Nevertheless, such systems are important sources of operational difficulties, especially in the case of high clay content tailings. The case presented in the present paper consists of a free surface flow pipeline transporting a composite of two different tailings with high clay content. It has presented operational difficulties such as partial blockages and upstream box and air intake overtopping events. In the present paper, the causes of these difficulties are identified. These include lack of complete mixing of the different tailings, multi-layered flow with low velocity and high yield values with high frictional losses. The pipeline characteristics and performance are analysed in three stages: design, initial operation and enhanced operation, the latter accomplished by means of increasing turbulence in the box located upstream from the pipeline. The last section of the pipeline and another distribution pipeline system located downstream from the pipeline have performed well. The cause of different behaviour of both systems is also assessed.

Jan 1, 2007

By N. Naude, R. Foisy, F. Bornman

Spiral separators have been widely accepted as one of the most flexible gravity separation devices for several decades. The International Journal of Mineral Processing, 84, pp. 118 – 132 mentioned that spirals are for treating material too coarse for flotation and too fine for dense-media separation. Powder Technology V 102, pp 244 – 252, 1999 stated that there exists a genuine need for extending the performance envelope of spirals – whether to treat finer or coarser material than the traditional size ranges. In recent times there has been an upsurge in interest, particularly in the development of newer fine gravity separators. Spiral separators for the recovery of ultra-fine particles have a unique profile, pitch and features to ensure efficient performance. The flow on the spiral trough must be controlled to minimise turbulence that will entrain fine particles in the outer section of the trough. The experimental test work showed a movement of mass from the outer region towards the centre column of the spiral, i.e., from the fine tailings band towards the concentrate. As recovery on the spiral trough is a function of mass yield and grade, the ultra-fine 7 spiral had a better recovery than the HX5. This makes the UF7 an ideal rougher spiral. Keywords: Ultra-fine particles, spiral, design, recovery

Jan 1, 2020

By I. Kaabachi, F. Meunier, N. Morales

In open pit mining, ore and waste are hauled outside of the excavation area by trucks that move along a system of ramps. The design of these ramps must be carefully addressed because they have to comply with geomechanical constraints to ensure the stability of the pit walls, provide access to the different levels and phases, but also maximise the value of the extracted ore and reduce the extraction of waste. Because an optimisation approach able to deal with the design of the full ramp system seems to be out of reach at the moment, this paper addresses the problem of designing one ramp providing access to a single pushback, which has been determined beforehand. The optimisation objective is therefore to find a ramp that gives access to one given potential volume, while minimising its impact on the economic value of the volume. Two versions of the problem are formalised. One version allows the extraction of ore and waste only if this extraction is necessary for the ramp system. This version somehow minimises the intrinsic value of the ramp system. In the second version, it is possible to extract more than is needed by the ramp system. For instance, this takes into account the possibility of attaining ore on the wall opposite to the ramp as soon as the ramp reaches its level. In the setting mentioned above, the contribution of this work is three-fold. First, the computational complexity of the two different versions of the problem is presented and discussed; in particular, they are shown to be NP-hard. Second, compact integer programs modelling these two versions are proposed. Third, an efficient GRASP algorithm able to cope with the large instances of the problem is proposed. To assess the proposed approaches, the models and algorithms are applied to real instances with an off-the-shelf solver, illustrating and discussing their potential and relevance for the two versions of the problem. They are also compared with other approaches from the literature in terms of value and resulting designs.

Sep 1, 2021

By W. R. Matizamhuka

"The consolidation of nano-sized composite materials presents a challenge using conventional hot pressing methods. Spark plasma sintering (SPS) technology has shown great promise in the successful sintering of nanoreinforced composite materials. This qualitative review seeks to impart knowledge gathered, and progress made over the years on the consolidation of nanocomposite materials using SPS technology. The review is aimed at introducing this technology to the South African science and engineering community. Emphasis is on improving the mechanical properties of structural ceramic nanocomposite materials, which over the years have shown great promise in a wide range of applications, including transport, energy, mining, and the environment. Although success has been achieved within the laboratory for research purposes, there are still great opportunities to commercialize the technology for the production of larger components with more complex shapes.IntroductionSince the pioneering work of Niihara and Nakahira (1991) over a decade ago there have been extensive attempts to harness the potential of nanostructural metals, ceramics, and composites in a number of applications (Niihara and Nakahira, 1991; Selaho et al., 1997; Sekino and Niihara, 1995; Khalil, 2012; Aalund, 2008). It is generally realized that reducing the grain size of materials to nanoscale offers a significant improvement in properties. Attempts to synthesize nanostructured compacts by conventional sintering methods have not succeeded owing to the uncontrollable high rates of grain growth driven by long dwelling times at the sintering temperatures and large powder surface areas (Sergueeva et al., 2009; Gua, Khora, and Chieng, 2004; Tang et al., 2009). Following the development of spark plasma sintering (SPS) technology, it is now possible to process nanocrystalline materials with controlled grain growth. SPS, also referred to as the field-assisted sintering technique (FAST) or pulsed electric current sintering (PECS), was developed with the aim of improving on the well-established hot pressing (HP) technology (Kessel and Hennicke, 2007;"

Jan 1, 2016

By C. Karageorgos, J. Sakala, A. Prinsloo, B. Ngambi

The sulphide flotation circuit at First Quantum Minerals’ Kansanshi mine in Zambia produced over 100,000 t of copper in 2019. For this circuit, mineralogical analysis has shown that the majority of the copper lost is hosted in fine liberated chalcopyrite, which is a paramagnetic mineral. The objective of this work was therefore to improve fine chalcopyrite recovery in the sulphide flotation circuit at Kansanshi, using a magnetic conditioning technology to agglomerate fine paramagnetic minerals. This theoretically increases the probability of attachment during collision and therefore improves recovery. A four-month paired ‘t’ test plant trial was carried out and comprised of consecutive ON-OFF periods with and without magnetic conditioning in the rougher flotation bank of the sulphide circuit. The experimental design involved assessment of recovery by size based on daily and weekly composite samples of feed and tails, sized using both wet-screening and cyclosizer. Both the daily plant data and the sized samples showed an increase in Cu recovery with magnetic conditioning ON. A 0.56% copper recovery improvement was measured with magnetic conditioning at a 99.4% confidence level. Keywords: Flotation, fine mineral, chalcopyrite, magnetic aggregation

Jan 1, 2020

By T. Nghipulile, M. Moys, M. Bwalya, H. Simonsen

The quest for efficiency in comminution is an ongoing concern as comminution usually constitutes a major cost component in the metal production industry. Such improvements can be made by circuit optimization or development of more efficient equipment. A novel crusher, known as the rotary offset crusher (ROC), promises to deliver in this space. The ROC was invented in 2002 by Michael Hunt, Henry Simonsen, and Ian Sinclair, but failed to garner enough support to progress to production. The original design concept was recently rekindled, and a laboratory version of the crusher has been built and commissioned at the University of the Witwatersrand. The crusher is simple in design, with two cylindrical discs that are parallel to each other, and, as the name implies, there is an offset between the vertical axes of the discs. The top disc has a conical section on its lower face, and this creates a crushing zone between the opposite faces of the two spinning discs. Centrifugal motion transports particles through the crushing zone. Batch experiments have been conducted with quartz at various crusher settings (discs offset, rotational speed, and vertical exit gap) for various feed size distributions. The indications so far suggest that the disc speed is a key factor affecting the performance. Size reduction ratios as high as 11 were recorded from experiments with quartz at a speed of 830 r/min.

Jan 1, 2021

By R. T. Rudd

DISCUSSION R. T. RUDD I have the following comments on Mr Bosman's paper. Before giving the company permission to discharge neutralized mine drainage containing 1800 mg/l of dissolved solids into a public stream, my Department had to consider the matter from both the legal and the practical viewpoint.

Jan 4, 1974

By C. M. van der Walt, J. F. van Rensburg, H. J. Groenewald

The South African platinum group metals mining industry faces considerable operational costs, with compressed air networks’ annual costs accounting for up to 35% of total electricity consumption. Amidst escalating electricity tariffs and volatile commodity prices, enhancing energy efficiency has become critical for economic sustainability. This study addresses the prevalent issues of mismanagement and inefficient use of compressed air on the demand side, such as leakages and unauthorised use for ventilation. While previous research has identified these inefficiencies, a gap exists in the continual monitoring and reporting of network performance to drive sustained improvements. This paper presents a practical solution developed and applied within a major South African platinum group metals mining group. The methodology focuses on a continual monitoring and reporting framework to improve demand-side management. The implementation of this solution has demonstrated significant financial and energy-saving potential. Key findings from case studies include: 1) the mitigation of R150,000 in costs over five days by rectifying a single instrumentation fault, 2) a potential annual energy saving of up to 5.6 GWh (R10.6 million) by enforcing valve closures during non-productive periods, and 3) an annual reduction of 3.7 GWh (R7.2 million) through improved underground ventilation controls. These outcomes underscore the value of a systematic, data-driven approach to managing compressed air consumption, offering a viable strategy for cost reduction and enhanced efficiency across the platinum group metals industry.

Mar 6, 2026

By E. J. Y., G. J. McLachlan, E. Amini, Koha

Inferring individual component flotation rates from recovery-time data of ore complexes is important in optimising and designing minerals processing plants. However, existing two-component first-order flotation models are computationally intensive to solve using conventional non-linear least squares regression. In this paper, a Convolutional Neural Network (CNN) is used to approximate the inverse function which predicts the two-component first-order model parameters using recovery-time data. This paper compares the accuracy and computation speed of the proposed CNN against traditional non-linear least squares regression on 1 million generated data based on a known two-component firstorder kinetic model. It is shown that using a CNN is possible to approximate the inverse function for the non-invertible two-component model with recovery-time as an input matrix for convolution operations. The CNN method is 450 times faster to compute than the Trust-Region (TR) non-linear least squares regression algorithm. However, the CNN model is less accurate compared to the TR algorithm overall. Keywords: Flotation kinetics, convolutional neural network, inverse problem, modelling and simulations

Jan 1, 2020