Search Documents

By Abegail Endraca, Allan Sebastian, Andrew Raine, Allan Patdu

The project involves the construction of a new aqueduct tunnel by an Earth Pressure Balance TBM tunnel for the Novaliches-Balara Aqueduct No 4 (NBAQ4) project in Metro Manila. It comprises a 7.3 km long and 3.1 m internal diameter tunnel that can deliver up to 1,000 MLD of raw water and the tunnel passes under urban residential and urban populated areas adjacent to and along Commonwealth Avenue. A new reservoir intake structure was constructed in the La Mesa reservoir by a cofferdam and the TBM breakthrough connected the reservoir to the outlet surge shaft structure and the downstream pipe network system connecting to the Balara Water Treatment Plant. The TBM incorporated a double articulated head configuration to allow tight 80 m radius curves to navigate some of the difficult alignment considerations. The alignment passed very close to some existing foundations for MRT7 and needed to clear several tight curves to remain within government land ownership. The project excavated through the local Guadalupe weak rock formations and there was minimal ground movements observed as a result of the work.

Jun 13, 2023

By Yuan Le, Dominic Reda, Vojtech Ernst Gall, Kurt Zeidler, Tomasz Kecerski

High Speed 2 (HS2) mandated that Building Information Modelling (BIM) processes be implemented during design and construction. Gall Zeidler Consultants (GZ) was responsible for developing the BIM Models for the portals, tunnels, and cross passages of the of the 16 km-long Chiltern twin-bore Tunnel. In addition, GZ developed the GBR for the Chiltern Tunnels and incorporated the relevant information into the Project’s BIM framework. This paper presents the implemented BIM framework, describes the modelling approach, and discusses the advantages and challenges of implementing BIM, particularly how BIM improved interface coordination and how BIM was used in feasibility assessments of different construction options.

Jun 13, 2023

By Xiaochao Shu, Kun Wang, Fanwei Meng, Rui Tao

Rapidly searching for carbonatite-related rare earth element (REE) mineralized systems is of paramount importance to explorers, because these systems provide the world’s most significant supply of REE. Biotite and barite are suitable indicator minerals that can offer reliable elemental geochemical information used for REE exploration. In this study, we provided an elemental geochemical dataset of biotite and barite from Cenozoic REE deposits in the eastern Tibetan Plateau, and compared the obtained data to those of biotite and barite forming in other geological settings. The F (i.e., fluorine) contents in carbonatite-hosted biotites are highly variable, with biotites from mineralized carbonatite complexes having much higher values (1.05–2.37 apfu, where apfu = atoms per formula unit) than their counterparts from barren carbonatite complexes (≤ 1 apfu). It is therefore believed that the presence of high-F biotites can be regarded as a sign for predicting REE reservoirs. Barites in REE mineralized systems contain much higher (even one or to orders of magnitude) total REE contents (ΣREE >100 μg/g) relative to those species forming in carbonate-hosted fluorite-barite deposits and open marine environments. This means that the high ΣREE concentration of barite can serve as an effective index for REE exploration. The above information is integrated into a REE exploration program in which the areas with strong local tectonism along cratonic edges are priority exploration targets, and high-F biotites and REE-rich barites can serve as direct indices for rapidly identifying carbonatiterelated REE mineralized systems at a strategic distance from other geological settings.

Jun 9, 2023

By M. Z. Emad, N. Abbas, Y. Majeed

Room-and-pillar mining is commonly employed for the extraction of rock salt in undergroundmines. Pillar stress is a major concern in these mines as it is directly related to stability and mineralrecovery. In this study a flat jack method was used to measure pillar stresses in three undergroundrock salt mines in Pakistan. The field work included determination of in-situ stress, in-situ elastic modulus, recording of field variables (pillar length and width, height and width of opening, opening width to height ratio, extraction ratio, and overburden height) and collection of salt block samples. The geomechanical properties of rock salt (uniaxial compressive strength, Young’s modulus, Brazilian tensile strength, and density) were also determined to estimate overburden stress, pillar strength, and factor of safety (both estimated and actual). It was found that the measured pillar stresses are proportional to the overburden stress values, with their magnitude ranging from 6.05 MPa to 11.97 Mpa, and the pillars were found to be stable. Regression analysis was performed to develop statistical models for in-situ stress and in-situ elastic modulus. Finally a quick guideline chart was developed to determine the suitable length of pillar for a given span and required level of safety.

Jun 5, 2023

By K. Woodward, Y. Potvin, B. McFadyen, M. Grenon

Open stoping has become a popular mining method in hard rock mines, not only due to the safety of the method as a non-entry approach, but also because of the high extraction rate and low costs. At mine sites, stope performance is evaluated by calculating stope overbreak using the stability chart. However, limitations of the stability chart regarding the precision of the predictions, nonconsideration of factors such as the influence of blasting, and the exclusion of underbreak have led to non-optimal designs. The capabilities of today's computers have increased the amount of data being collected and the power of models being built. This article presents a step towards a new stope design approach where stope overbreak and underbreak are measured and georeferenced using octrees at an approximately cubic metre resolution and predicted using multivariate statistical models (partial least square, linear discriminant analysis, and random forest). Results show that overbreak and underbreak location along the design surface and their magnitude are predicted with good precision using a random forest model. These predictions are used to build the expected geometry of the open stope. The resolution of the data and the use of multivariate analysis has enabled the prediction of variation in stope performance along the design surface, going well beyond the simple qualitative per stope face prediction provided by a traditional stability chart approach.

Jun 5, 2023

By Anup Tiwari, Khanindra Pathak, BIBHUTI BHUSAN MANDAL

Failure of in-pit overburden dumps in open-pit coal mines causes debris to flow toward the active working face, threatening the safety of people and equipment. The evaluation of the potential mobility of failing mass will aid in hazard mitigation associated with unwarranted dump failure. The potential mobility is shown by mobility ratio (ratio of total drop between debris flow's initial and final deposition points to total travel distance) and runout characteristics. In light of above, a laboratoryscale debris flow flume was developed to investigate the effect of material gradation and slope angle on runout characteristics and mobility ratio. The total mass of experimental debris mix (Q) is fixed at 30 kg with 20% water content. Experiments at three different slope angles (30°, 35°, and 40°) demonstrate that increasing the proportion of fines in the experimental mix increases runout characteristics while decreasing the mobility ratio. The length and area of the runout decrease as the slope angle increases, while the mobility ratio increases. There is a positive correlation between d50 and runout characteristics at a fines content of 0.1Q, but a negative correlation at a fines content of 0.2Q and 0.3Q. Conversely, there is a negative correlation between d50 and mobility ratio for fines content of 0.1Q, but a positive correlation exists for fines content of 0.2Q and 0.3Q. A new index called the fine-to-coarse (F/C) ratio is used to identify the critical value of fines and coarse proportion that causes a transition from dry granular flow to fluidized debris flow.

May 29, 2023

By D Hope, D K. Mukhopadhyay, J D. Harvey

South32 (S32), a globally diversified mining and metals company, is listed on securities exchanges around the world (ASX, JSE, LSE), with its primary listing being on the Australian Securities Exchange (ASX). Chapter 5 of the ASX Listing Rules (Australian Securities Exchange (ASX), 2019b) requires a mining entity to provide a summary of governance arrangements and internal controls with respect to its estimation processes, estimates and reporting of Mineral Resources and Ore Reserves annually. As a global company, it is also important to design and implement all governance processes and internal controls which can be used consistently across the organisation. The three lines model (previously known as the ‘three lines of defense’ model) is employed across South32 to manage risk where the first line (Practitioners) designs, implements and executes processes and controls to manage risk; the second line (Stewardship) identifies material gaps and improvement opportunities in the first line by monitoring conformance with the group requirements, legislative and regulatory obligations. Second line also assists with the development and improvement of core fundamentals based on industry good practise. The third line (Group Assurance) provides independent and objective assurance over the Group’s system of risk management and control. The estimation of resources and reserves for most of the operations within South32 is managed by the Planning function. The estimation process is part of the annual Life of Operation Plan (LoOP). The LoOP identifies and assesses the strategic alternatives for the development of an operation and recommends the preferred pathway based on value and risk. The LoOP starts with opportunity framing and the updated resources as an input and ends with the short-term plan and annual budget (the outputs). Ore Reserves estimates are one of the outputs from the LoOP. All the inputs and outputs follow internal standards and procedures which includes peer review and performance reconciliation. Stewardship (Second line) which is a centralised function has standards in place to ensure compliance to internal controls and external regulatory requirements. This includes assessment of the competence of Competent Persons, technical reviews, independent audits and training in the relevant chapters of the ASX Listing Rules, Guidance Notes and Appendices. Group Assurance (Third line) which reports to the Risk and Audit Committee of the Board of Directors ensures the design and operating effectiveness of the processes, standards and procedures associated with the estimation and reporting of resources and reserves. While the level of scrutiny has a different intent for each line in the three lines model, the overall purpose is to achieve a consistent outcome across the organisation

May 24, 2023

By D A. Sims

This paper outlines the contributing factors to a series of erroneous Mineral Resource estimates which led to considerable loss, including significant reduction of mine life and consequently a large write-down of asset value. The error prompted divestment of the mineral asset in the short-term by the owners, a major mining company. There were multiple and complex contributions to the result: • The mine was undergoing a transition in the deposit geology with increasing depth that was not accommodated in the models. Early indications of the geological transition in initial drilling were generally unrecognised in resource modelling. The shortcomings of the models became apparent with increasing infill drilling and subsequent production reconciliation. • There was a lack of recognition of, and confidence in, site-based input and skills by corporate technical management. The site had a reputation internally for over-delivery to plan early in its life and that supported the anticipation of ongoing metal delivery into the mine plan by management. • A corporate lack of confidence in site being able to adequately domain the mineralisation led to the use of a CIK domaining process, rather than one which was geologically based. This domaining process led to gross over-statement of mineralisation trends reflected in the subsequent OK estimate. • Timelines on the outsourced estimation process were so short that validation was not possible. Obvious errors in the estimate versus data were not able to be used to correct the issues and the site’s Competent Person sign-off occurred without adequate checks. This case study is presented to reinforce the concept that Mineral Resource estimates are not solely based on the ability of the Competent Person to satisfactorily guide the process. There are usually multiple complex issues in the estimation process which need to be recognised and considered in judging reconciliations of model to actual.

May 24, 2023

By L Bertoss, D Carvalho

In the last decade, the use of advanced implicit modelling software/algorithms in mineral resource workflows has become a best practice in the mining industry. In most cases, these workflows can easily replicate the level of detail of explicitly modelled geometries, even for very complex deposits. These techniques are flexible and can produce fast results since software is responsible for generating 3D surfaces and solids based on geological and interpretation data. Nevertheless, depending on how unique and complex some deposits are, intense manual editing and input are required to honour the geological context and produce the desired outcome. The current geological modelling workflow at George Fisher Mine (GFM) is based on the semi-automatic built-in tool that generates stratigraphic sequences (stacked lithology layers) based on logging and mapping data. This tool (stratigraphic sequence from Leapfrog Geo™) works for the majority of areas in the mine but fails to capture observed mineralisation pinch-outs in operational areas and at extrapolated boundaries of the deposit. These pinch-outs have the potential to negatively impact grade forecasts if not resolved manually. Using built-in software tools only, the alternative for a more accurate model is to generate each individual layer and adding tens of thousands of manual interpretation points to honour pinch-outs (based on the amount of existing drilling in the mine and number of layers). This approach would require an estimated minimum of two to four years of a full-time employee (FTE) to be exhaustively completed. This study presents an automated approach to generate pinch-out points using a set of Python scripts that only take a few minutes to run. The newly generated points are then combined into the commercial software workflow as interpretation points, honouring observed pinch-outs. The remarkable time difference between approaches removes chance of manual errors and allows mine geologists to spend valuable time in validation and testing of scenarios, ensuring they are more representative of the deposit’s geology.

May 24, 2023

By I Sucholutsky, D M. First, D Mogilny, F Yusufali

Machine learning is creating value in all facets of the mining industry, from exploration to production. The authors provide an accessible, high-level introduction to artificial intelligence (AI), machine learning (ML), and deep learning (DL); the latter being widely recognised as one of the most powerful forms of ML. In particular, the authors will introduce deep learning models known as convolutional neural networks (CNNs), how they are applied, and the economic considerations necessary for determining when DL may be the right solution to de-risking complex block modelling problems. The authors present preliminary results from the mineral resource modelling study of the Jundee orogenic gold deposit, Yandal belt/gold province, Western Australia. The primary goal was to identify the direction and location of the narrow gold veins more accurately and demonstrate how non-linearly correlated elements are used as direct inputs to the resource model to assist with the target element’s grade prediction. This demonstrates that: (1) existing techniques for finding correlations between assayed elements do not adequately reflect the complex geology of the asset, (2) nonlinear correlations that are difficult to model as simple mathematical functions are representative of geological patterns in a deposit, and (3) non-linearly correlated assayed data, fed as inputs, increase the performance of the resource model as reconciled through blind tests. To conclude, the authors hypothesise that the patterns represented by the DL block models may be revealing the results of overprinting geological processes that generated mineral deposits. For example, the primary hydrothermal processes that deposited metals created depositional patterns that become particularly complex as a result of being overprinted, in part or in whole, by secondary physicochemical processes. This may explain why non-linear geochemical relationships have the capacity to generate more accurate block models of mineral deposits.

May 24, 2023

By D Clarke, I Minniakhmetov

This paper describes the application of the SBRE framework to model the Olympic Dam deposit, one of the largest copper and uranium deposits in the world. Geostatistical simulations are the best practice for quantifying uncertainty in the mineral value chain and estimating resources. However, these simulations are currently undertaken on an ad hoc basis in the mining industry due to the high requirements in computing resources and capabilities in advanced geostatistics. The SBRE project provides a standard framework to test, build, and run conditional simulation workflows, which has been applied to the Olympic Dam deposit. Conventional geostatistical methods face challenges when modelling the Olympic Dam deposit, such as non-stationarity, non-linear correlations, and a large number of grid blocks to simulate. To address these challenges, a combination of methods was used, including projection pursuit multivariate transform, trend-residual decorrelation, pluri-Gaussian simulations, and turning-bands simulations. Various tools and applications were used to build the model, including in-house developed applications, Autovariogram software (Varify), and the RMSP python library. All computations were accomplished on the AWS cloud using the EC2-Batch service. The final set of simulations was validated using various methods, such as grade-tonnage curves, histograms, swath plots, and variogram reproductions, as well as validation using historical samples back-testing. The study highlights the importance of an automated, modular, and scalable framework in the development of conditional simulation workflows and describes the learning gained from trials of different combinations of methods and software

May 24, 2023

By C Artica

Two quantitative methods for Mineral Resource classification have been applied to a copper skarn deposit beneath a large open pit that is mining a world-class porphyry complex. A drill hole spacing study (DHSS) using the single block kriging method (SBK) and a conditional simulation method (CS) were applied to the skarn deposit and the results compared. Inputs to both processes included the proposed mining rate and stope designs to estimate the likelihood of achieving grade and metal production targets. Mineral Resource classification of the deposit considers the relative precision of tons, grade and metal predictions over quarterly and annual production periods. These relative precision estimates are calculated at 90 per cent confidence interval (CI). The SBK method represented the production period as a single large block. Kriging estimates were performed in the large block for various synthetic drill hole grids, and the estimation errors derived. The error was assumed to be normally distributed due to the large block size and quantity of samples, allowing CIs to be deduced. The CS method followed a conventional sequential Gaussian simulation workflow where grades were simulated with a 5 ft × 5 ft × 5 ft grid node spacing inside mineralisation domains. Each realisation was then averaged up to monthly production volumes represented by a combination of designed stopes, and the coefficient of variation (CV) for the averaged grade was calculated. CI on the relative precision of grade predictions were then deduced from the CVs. The two methods produced similar results; despite being calculated independently. CS results were used to report uncertainty in the proposed life-of-mine plan and highlight areas for additional drilling. SBK results were used as the basis for Mineral Resource classification as this method has been previously applied to the skarn deposit.

May 24, 2023

By M Bond, R R. Hargreaves, G W. Booth

There are numerous causes of speculative mineral resource and reserve inflation. Traditionally, these are linked to issues of data accuracy or misinterpretation, the use of overly optimistic estimation parameters or assumptions, an absence of independent expert verification, or the simple pressure to increase company value, covert or otherwise. Owing to its subjective nature, classification of resources and reserves remains an opaque process. Of necessity, Competent Persons rely on personal heuristic interpretations, ideally underpinned by appropriate estimation and classification experience across commodity and deposit types. Whereas independent verification of individual resource and reserve statements remains impractical, publicly available data can be interrogated for potential category inflation, particularly when viewed with exploration expenditure statistics included in annual company reports. Abrupt changes in category tonnages and market capitalisation without concomitant expenditure can aid in outlier detection. Consequently, a comparison of common exploration and resource reporting parameters offers a basis for risk assessing classification robustness, over time. In this introductory study, an analysis of globally listed companies was undertaken over a multi-year period, examining base and precious metal projects in both preproduction and operational asset classes. From these, a series of exploratory decision tree trigger points were generated against which target companies were anonymously identified and risk-ranked.

May 24, 2023

By P Dowd, A Adeli, C Xu, X Emery

Geometallurgical modelling is increasingly being incorporated into mineral resource modelling and estimation as a means of increasing efficiency, decreasing operating costs and reducing risk in mining operations. Traditional geostatistical workflows for geometallurgical modelling face several difficulties, in particular, related to the non-additivity of process response variables, to highly heterotopic data sets and/or to preferential sampling designs, all of which may explain why most attempts to estimate geometallurgical response variables from assay data and mineralogy are still based on statistics and machine learning. The aim of the work presented here is to demonstrate the applicability of geostatistics to estimate copper recovery from copper sulfide ores at the Prominent Hill Iron Oxide Copper-Gold (IOCG) deposit in Australia. As recovery is non-additive, the preferred workflow is the joint estimation of the masses of metal in the feed and in the concentrate, both of which are additive variables. While the mass of metal in the feed can be estimated from abundant online assay analyses, the mass of metal in the concentrate can only be estimated from a very limited number of laboratory-scale batch flotation tests. Traditional approaches to estimating the masses of metal in the feed and in the concentrate, such as simple and ordinary co-kriging, are described and discussed. A modified version of co-kriging is introduced, which incorporates linear relationships between the mean values of the input variables, in addition to a spatial correlation model. Co-kriging with related means is shown to outperform traditional simple and ordinary co-kriging in terms of precision, accuracy and consistency of the estimates, and offers a practical and efficient tool to deal with highly heterotopic and preferential sampling designs.

May 24, 2023

By A Jewbali, L Allen

At Newmont Corporation drill hole spacing studies are done to support the business in understanding the cost of collecting additional information (with a specific focus on drill hole sampling density) versus the value of additional drilling in terms of resource risk reduction. For the last 20 years drill hole spacing studies have been executed in an effort to answer the following question: What spacing should the deposit be drilled at to achieve a certain level of resource confidence so that when mining occurs the resource model delivers as predicted ie what is the optimal sampling density? The optimal sampling density supports a resource model that provides a sound foundation for mine planning purposes and resource/reserve reporting. At Newmont Corporation drill hole spacing studies are now a requisite for understanding drill data density needs for new deposits and near mine expansions. This paper details the evolution of drill hole spacing studies at Newmont Corporation in terms of methodology and usage.

May 24, 2023

By M P. Murphy, C M. D Barton

When developing a new underground mine, the geological interpretation that guides the mineral resource is crucial to the preparation of a reliable ore reserve. In preparing a robust geological model to underpin a resource estimate, practitioners must weigh the comparative risk of accepting a relatively wide-spaced drill hole pattern, versus a more close-spaced pattern that ensures a high local geological confidence for mine planning but may have an exponentially increased time and monetary cost. This paper details the authors’ investigations into the geological uncertainty of IGO’s Odysseus Deposit, which is approximately 645 km north-east of Perth, Western Australia. At Odysseus, the komatiitic nickel sulfide mineralisation is irregularly cross-cut by nickel-barren pegmatites that have intruded and offset its thick ultramafic orebodies. These pegmatites generate significant uncertainty in the precision of Odysseus’ resource volume and tonnage estimates, as well as the subsequent quantification of pegmatite mining dilution in its ore reserve. To quantify the geological uncertainty in the pegmatite interpretations, IGO’s mineral resource practitioners prepared several geological risk studies over the Odysseus North lode, which is the lode most affected by the pegmatites. These studies included categorical conditional simulation of the pegmatites, preparing implicit geological models with alternative algorithms, trialling a machine learning application to prepare a maximum likelihood geological model, and finally assessing the early results of the pre-production close-spaced drilling to these different models. To assess the precision of the different single-outcome models, the authors’ compared the estimated pegmatite content of each model to the range of possibilities modelled by categorical conditional simulation within the planned stopes at Odysseus North. An estimation confidence score for each modelling method was then prepared for each alternative single-outcome modelling method. From these studies IGO concluded that a close-spaced drill pattern is essential at Odysseus, supporting the view of the Competent Person in 2017 who proposed a 25 m drill spacing in areas affected by pegmatite which had been partially classified as Inferred.

May 24, 2023

By Vhutali Carol Madanda, FHATUWANI SENGANI, François Mulenga

The first introduction of fuzzy theory in the nineteenth century created room for continuous research and application in various fields. Fuzzy set theory has been globally applied in geotechnical engineering, and research in this field continues to date. The fuzzy inference system is considered to be one of the most popular techniques adopted to resolve some of the geomechanical challenges faced in both surface and underground excavations. This paper unpacks fuzzy theory-based approaches in mine geomechanics with the aim of expanding the innovative application of the same approach specifically in tunnel geomechanics. This aim was achieved by conducting a review of recent successful and unsuccessful applications of fuzzy inference systems in underground excavations/tunnelling geomechanics. Indeed, this review has outlined some cardinal points associated with the ability of the technique to solve complex geomechanics problems. However, the success of the technique was accompanied by a few limitations associated with the methodology. Finally, a future outlook associated with the technique has been established.

May 15, 2023

By Carla Da Corte, Kagisego Letsoalo, Ashma Singh

Banded Iron Formations (BIF) are sedimentary rock formations ranging in age from 0.8 to 3.8 billion years and consist of alternating layers of silica and iron. The thickness of the alternating layers varies between and within deposits, with this lithology forming approximately two-thirds of South Africa’s future low-grade hematite resources. The production costs for South African iron ore producers are approximately double that of the largest iron ore producers, namely, Brazil and Australia. This in conjunction with volatile commodity prices, necessitated a cost-sensitive beneficiation strategy for low-grade hematite to sustain the industry and extend life of mine. A BIF sample grading at 44% Fe and comprising predominantly of hematite and quartz with minor amounts of magnetite and goethite was subjected to three fines gravity processing routes to establish the amenability of this sample to beneficiation. To provide flexibility for iron ore producers who still have high-grade resources available, two product grades were considered, namely a 60% Fe product for further blending or a 63% Fe product for direct sales.

May 12, 2023

By Ayokunle Adewale Akinlalu, Sunday Bayode, Sherif Olumide Sanusi, Joshua Oluwagbenga Adeboye

Gold occurrences have been reported in Alagbede, southwestern Nigeria, but a mineral potential map (MPM) to guide academics and investors in the area is still needed. As a result, geophysical methods (aeromagnetics and aero-radiometry) have been used to assess the potential for gold minerals in the area. Several enhancement filters, such as reduction to the equator, upward continuation, analytical signal, second vertical derivative, and power spectrum analysis, were applied to the aeromagnetic data to understand the subsurface geology better. The enhancement filters applied to airborne radiometry data are K/eTh, ternary color composite, F parameter, and deviation from the ideal K values (Kd). Geophysical data analysis was used for structural mapping and geological reconstruction, while aero-radiometric data was used for hydrothermal alteration mapping. The primary trend observed in the area’s magnetically inferred structural framework map is NE-SW, while a few are in the NW–SE and E-W trends. These observed trends show that the study area suffered at least three deformation episodes. Geological evidence of gold mineralization, such as favorable lithology, geological structure, and hydrothermal alterations, has been fused to produce a reliable MPM of the area. The geographical location of the existing mineral sites in the investigated area agrees with the geological structures and the MPM produced there. Thus, the systematic approach adopted in this study can be extended to other supracrustal belts of a typical Precambrian basement complex worldwide to ensure the reliability of orogenic gold mapping and resource management.

May 9, 2023

By A. Jahedsaravani, M. Massinaei, M. Zarie

Deep learning is a subset of machine learning that uses artificial neural networks for extracting high-level features from image data. In the present study, a soft sensor is proposed for the prediction of the flotation performance through froth features generated by the use of pre-trained convolutional neural networks. Several state-of-the-art convolutional neural networks (AlexNet, GoogLeNet, VGGNet, ResNet, and SqueezeNet) pre-trained on the ImageNet database are used to predict the metallurgical performance of two flotation systems. The first case study is a batch copper flotation system video-captured over a wide range of process conditions. The second case study is an industrial coal flotation column equipped with a continuous video recording system. The pre-trained networks are used to extract features from the froth images, and these features are subsequently used to predict the flotation conditions and performance. The prediction results by the pre-trained algorithms were compared with the traditional image processing algorithms. This demonstrates the ability of the pre-trained structures to generalize to images outside the ImageNet database. GoogLeNet outperforms other network architectures and provides more accurate predictions of the flotation process behavior and performance.

May 5, 2023