Search Documents

By D M. Silva, J C. Alves

According to the literature, material transportation represents 50 per cent of the operating costs for an open pit mine. In this context, this paper proposes a multistage approach for dynamic truck dispatching in real open pit mine environments, implemented in the commercial package SmartMine®, marketed by Devex SA. The first stage of this approach defines the optimal number of trucks that maximises the tonnage production by means of a robust linear programming model, which considers the operational constraints of a real mining process. The second stage uses a dynamic dispatching heuristic joining computational simulation and multicriterion optimisation techniques for decision making for truck dispatching. Another relevant contribution of this work is the publication of realistic instances collected from a dispatching system managing an iron mine, containing information about the hauling and loading fleet, the equipment situation when the working shift starts, cycle times, the time line of special occurrences (such as equipment stoppages and loading equipment reallocation in order to satisfy the mine planning) and the tonnage produced. These instances were generated with the purpose of submitting the method to the test of a real situation that considers the uncertainties existing in the process studied. The proposed approach was validated by means of a discrete event simulation model applied to the previously designated instances. Using this multistage approach as a mechanism for dispatch decision making, it is shown that the haulage fleet productivity increased when compared with the real values reported from the instances. These results are important because they show that the proposed approach generates efficient dispatch decisions for trucks operating in a real environment, reducing operating costs, increasing production and making the mine more competitive.

Sep 26, 2011

By D R. Seaman, B Adamson, P Sharman, M McMahon

"The Telfer processing plant commissioned its pyrite regrind and flotation circuit in August 2012. The circuit was designed to regrind pyrite concentrate to a p80 of <30µm then float a gold and copper rich concentrate before tails from the flotation circuit fed the carbon-in-leach (CIL) circuit downstream. Expected benefits were: improved CIL performance that would result from the finer grind and a reduction in cyanide soluble copper to the CIL circuit, as well as a small increase in overall flotation circuit recovery. While the benefits of a finer grind were soon realised, recovery in the post-regrind flotation circuit (named the ‘pyrite recleaner circuit’) was consistently and significantly lower than that expected based on laboratory test work. Selectivity in the pyrite recleaner circuit was virtually nil and copper reporting to the CIL circuit did not change as a result of the pyrite recleaner circuit operation.A pulp chemistry survey of the plant and comparison with the lab showed that the dissolved oxygen (DO) demand in the plant was much higher than that in the lab. Lab flotation tests conducted using nitrogen gas instead of air resulted in recoveries similar to those from the plant. It was identified that the freshly ground pyrite surfaces exiting the regrind mill were consuming oxygen in the slurry and there was insufficient oxygen available for collector adsorption and pyrite depression to occur. Test work, using a pilot regrind mill, showed that a reduction in grind size resulted in an increase in DO demand.A range of oxidising agents were tested in the laboratory and using a pilot flotation rig set-up in the plant. Oxygen was found to be the most reliable and effective agent and options for increasing oxygen delivery to the plant were explored. Scale-up from the lab oxygen requirement to the plant is difficult and efforts to implement a permanent solution for meeting the DO demand in the plant are ongoing.Citation:McMahon, M, Seaman, D R, Sharman, P, Adamson, B and Seaman, B A, 2016. Optimising the Telfer Pyrite Regrind Circuit - Effect of Dissolved Oxygen Demand, in Proceedings 13th AusIMM Mill Operators’ Conference 2016, pp 51–58 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Oct 10, 2016

By L Lorenzen, H Muller

"Every year a large number of projects are evaluated by small listed and unlisted mining companies that are hoping to find the ideal project, which will catapult them from a mining junior status to that of a mid-tier mining company. Usually this includes finding the æidealÆ or ærightÆ orebody and then developing a process which will allow cost-effective recovery of the valuable metals and the production of a saleable product. These dreams are seldom realised and there are a number of good and obvious reasons for this. Issues that are generally high up on the agenda for the smaller companies are: cost of developing a project before the feasibility study stage finding a suitable, or optimum processing technology financing of the project dealing with risk.The most expensive part of the development process for the small miner is often the exploration side of the business and finding the æidealÆ orebody. However, finding the right orebody will not be discussed in this paper. The æidealÆ orebody does not necessarily solve the problems of the mining junior, as much of the uncertainty lies in the process required to recover and produce the final metal product. Once a mineralised deposit has been identified and the grade at least reasonably qualified, the development of a suitable process becomes the driver to convert the deposit into an orebody. This paper proposes that a small exploration company has a very limited opportunity to succeed if it does not do sufficient homework before it identifies the æidealÆ orebody. The risk profile for the small mining company, by its very nature, has to be different to that of a major company and as a result the opportunities often lie in managing different and often new process options, which may be the key to bring such projects on line successfully.CITATION:Muller, H and Lorenzen, L, 2012. Project selection and process development for mining juniors, in Proceedings Project Evaluation 2012, pp 149-158 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

May 24, 2012

By D Reid, A Fourie

The in-pipe treatment of slurries with polymer addition shortly prior to deposition is a noteworthy emerging technology of increasing popularity. Although polymer treatment has been shown to substantially modify and improve depositional and dewatering behaviour in a significant number of cases, the impacts of polymer treatment on geotechnical performance of tailings are less well understood. For example, certain combinations of polymer and slurry type have been shown to result in lower final densities at a given vertical effective stress. Despite these lower densities, polymer-treated tailings often exhibit peak undrained shear strengths consistent with untreated material. However, the sensitivity and/or brittleness of the material may be negatively influenced by the looser state created. Although these changes have been studied, most testing available in the literature was undertaken on relatively ‘fresh’ samples of polymer-treated material. However, significant shear may occur following treatment and prior to the commencement of settling and self-weight consolidation as the material moves down the beach.To study the effects of shearing on the subsequent performance of polymer-treated tailings, a test program consisting of consolidation, triaxial and direct simple shear tests was undertaken on presheared polymer-treated material. Materials used were identical to those used in previously published studies on the impacts of polymer treatment in a ‘fresh’ condition. Shearing of the polymer-treated material generally appeared to lessen the impacts of the polymer treatment process. However, the behaviour of the material when sheared indicated that the polymer was still impacting the behaviour of the material in some respects. The results indicate the importance of the consideration of shearing on material behaviour when planning and designing a tailings deposit where polymer treatment is to be implemented.CITATION:Reid, D and Fourie, A, 2015. Effects of shear on the behaviour of polymer-treated slurries, in Proceedings Tailings and Mine Waste Management for the 21st Century , pp 215–224 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 27, 2015

By R J. Hardy

The aim of this study is to examine the volumetric and mass movement characteristics of load and haul operations using statistical modelling of relatively large samples of bucket loads that are transported as small samples in the form of truck payloads. Generally, the factors influencing bucket load variability are random, difficult to predict and to control. In the process of loading trucks the underlying variability of individual bucket loads will determine the variability of truck payloads. Bucket loads of material prepared by drilling and blasting for loading into trucks are fundamental quantities in open pit mine production. A study of payload data from a large surface mining operation indicates that bucket loads and truck payloads that are a small sample of bucket loads are normally distributed. Truck payloads have a reduced dispersion compared with bucket loads that is an inverse 0.5 power function of the number of passes per truck payload. Comparison of statistical modelling results with the æ10/10/20Æ policy promoted by Caterpillar Global Mining Inc, indicate that compliance with the æ10/10Æ part of the policy, applying to truck overloading is facilitated, as the coefficient of variation of truck payloads decreases, as a result of the increasing number of loading passes. Compliance with the more stringent æ20Æ part of the policy, relating to safe steering and braking is also facilitated, albeit at lower coefficient of variation for similar reasons.

Sep 26, 2011

By I Canbulat, J Oh, A Mcquillan, D Payne

This paper presents a new risk assessment tool for coal mine excavated slopes. This new empirical-statistical Slope Stability Assessment Methodology (SSAM) is intended for use by geotechnical engineers at both the design review and operational stages of a mine’s life to categorise the risk of an excavated coal mine slope. A likelihood of failure is determined using a new slope stability classification system for excavated coal mine slopes developed using a database of 119 intact and failed case studies sourced from open cut coal mines in Australia. Consequence of failure is based on slope height and stand-off distance at the toe of the excavated slope. Results are presented in a new risk matrix, with slope risk being divided into low, medium and high categories. The SSAM is put forward as a new risk assessment tool to assess the potential for, and consequence of, excavated coal mine slope failure. Unlike existing classification systems, assumptions about the likely failure mode or mechanism are not required. Instead, the SSAM applies an approach which compares the conditions present within the excavated slope face, with the known past performance of slopes with similar geotechnical and geometrical conditions, to estimate the slope’s propensity for failure. The SSAM is novel in that it considers the depositional history of strata in an excavated slope and how this sequence affects slope stability. It is further novel in that it does not require explicit measurements of intact rock, rock mass and/or defect strength to rapidly calculate a slope’s likelihood of failure and overall risk. Ratings can be determined entirely from visual observations of the excavated slope face. The new SSAM is designed to be used in conjunction with existing slope stability assessment tools. CITATION:Mcquillan, A, Canbulat, I, Payne, D and Oh, J, 2018. New risk assessment method for coal mine excavated slopes, in Proceedings The Fourth Australasian Ground Control in Mining Conference (AusRock), pp 473–495 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Nov 30, 2018

Discovered in 1896, the Sons of Gwalia orebody is located in a ductile mylonite zone within a sequence of Archaean pillow metabasalts and minor metasediments of greenschist facies which are variably sheared.The ore zone has good continuity, being 110 m wide and 500 m long, dipping 45 degrees east and plunging 70 degrees to the south to a depth of 1500 m downplunge. A strongly-developed foliation is present together with a prominent lineation paralleling the plunge. The mylonite zone consists of unmineralised chlorite schist and a 'U' shaped mineralised zone of chlorite-sericite schist with varying amounts of quartz-carbonate as veins parallel to foliation, boudins, and locally as massive quartz-carbonate. Pyrite is the dominant sulphide present.Grade control utilises RC holes on a 10 m x 10 m pattern, with infill blast rig holes 5 m deep where necessary.Some visual control of ore boundaries is present and, combined with good ore continuity and a knowledge of the structure of the orebody, enables cost-effective grade control to be achieved. To-date, over three million ounces of gold have been produced from the orebody.

Jan 1, 1993

By E Jak, P Hayes, J Chen

The paper provides an overview of the various analytical and microanalytical techniques currently in use to characterise the outcomes of pyrometallurgical processes, examining the advantages and limitations of these approaches. Specific focus with be given to quantitative microanalysis techniques including electron probe microanalysis and laser ablation, covering general principles, capabilities and limitations and recent development to address specific challenges associated with analysing molten slag, matte, and alloys, highlighting the necessity of embracing the application of these and other innovative analytical methodologies.

Jun 19, 2024

By D Henderson, M Germain

The beneficiation of iron ore deposits to yield haematite and magnetite concentrates for steel making processes typically require the use of one or a combination of wet processing techniques based on gravity, magnetic or froth flotation processes. With the need for more cost-effective technologies with a lower water demand, a re-examination of dry processing techniques has been initiated. For example, a dry processing capability may offer an advantage where suitable quality and quantity of process water hinders the development of a particular resource. This paper describes recent laboratory test work for the production of high grade concentrates using dry electrostatic techniques for -300 ¦m haematite and magnetite ores and compares them with magnetic separation techniques.

Jan 1, 2009

By C Rizos

Many of the ‘new paradigms in mining’ and notions of ‘sustainable mining’ have at their core the requirement for reliable, continuous centimetre-level positioning accuracy to enable increased automation of mining operations. The deployment of precision systems for navigating, controlling and monitoring machinery such as drills, dozers, draglines and shovels with real time position information increase their operational efficiency, and reduce the need for humans to be exposed to hazardous conditions. The Global Positioning System (GPS) is the best known, and only currently fully operational, Global Navigation Satellite System (GNSS) providing positioning capability anywhere in the globe, on a continuous 24/7 basis, with accuracies ranging from the dekametre-level to the sub-centimetre-level depending on hardware and operational configuration. Despite this versatility, GNSS cannot satisfy the high accuracy positioning requirements for many applications in mine surveying, and mine machine guidance and control. The reason is that increasingly open cut mines are getting deeper, resulting in a reduction of the ‘sky-view’ necessary for GNSS systems to operate satisfactorily. Yet, to date there have been no viable alternatives to GNSS that can be deployed in mine environments that can meet the challenging requirements in open cut mines.Locata Corporation, a Canberra-based company, has invented a terrestrial high accuracy positioning system known as ‘Locata’ that can augment GNSS with extra terrestrial signals to permit cm-level positioning accuracy even when there are insufficient GNSS satellite signals for reliable positioning and navigation. Locata relies on a network of synchronised ground-based transceivers that transmit positioning signals that can be tracked by suitably equipped user receivers. Hence Locata can be considered a new type of ‘local constellation’, able to provide high accuracy positioning coverage where GNSS fails. This paper introduces some of the technical aspects of this Australian technology and describes tests conducted by Leica Geosystems over the last few years at Newmont Boddington Gold in Western Australia. A recent news announcement by Leica Geosystems (12 January 2011) has confirmed that their new mine management system will have combined GNSS + Locata positioning capability – the first commercial product that integrates GNSS and Locata capabilities into a single high accuracy and high availability navigation device for open cut mine machine automation applications.

Nov 22, 2011

By P Kappen, R N. Collins, K M. Spiers

X-ray absorption spectroscopy (XAS) is a synchrotron-only technique used to determine chemical speciation, providing a powerful alternative to most traditional ‘wet chemistry’ and lab-based speciation methods. XAS is an element specific method that can be used to address a variety of systems, ranging from heterogeneous to homogeneous, polycrystalline to amorphous, and solid to liquid. The strength of XAS in identifying and managing chemical species in tailings and mine waste is demonstrated, with the presentation of highly relevant studies into lead, uranium, chromium and arsenic speciation. In each example, waste samples are compared with known standards, allowing an assessment to be made of the quantity of particular chemical species in each.CITATION:Spiers, K M, Collins, R N and Kappen, P, 2015. ‘Forget the wet chemistry’ – how the Australian Synchrotron can help with tailings and mine waste management, in Proceedings Tailings and Mine Waste Management for the 21st Century , pp 145–148 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 27, 2015

Transformations of minerals to processed mineral products fundamentally involve wholesale chemical change, and therefore have a high potential for the release of chemicals and wastes. In this regard minerals processing contrasts with downstream production operations, which involve mainly physical changes. The contrast with mining, which must take place where the minerals are found, is that mineral processing allows choices as to location, processes, fuels and reductants. These choices provide a foundation for dealing with issues of resource stewardship. This paper locates the mineral processing industry in the global perspective by quantifying the masses of major material inputs and outputs, based on current processing choices. Estimates for recycling have also been collated, revealing figures that differ surprisingly from commonly held impressions. The paper draws on a variety of current sources, mainly those available through the Internet, to rank the major transformed virgin mineral products by production, price and value. The figures demonstrate the dominance of Portland cement and steel in the global environmental impacts of mineral processing. Aluminium comes a distant third in the list, and the metals particularly associated with localised environmental impacts have relatively small global effects compared with those of the staple materials of our built environment. This global macro input/output perspective, with materials flows expressed per unit of virgin product, provides a benchmark for grasping sustainability challenges within specific operating businesses. Because of the global scope and pervasive impact of the minerals processing industry, the issue of resource stewardship is rising as a matter for public concern. There appears to be a developing view that the mining and mineral processing sector should take responsibility for these products throughout their various life cycles. However, in a future of stabilising consumption, dematerialisation and intensive recycling, the mining industry would only need to provide the top-up to a stock of recirculating materials. The question of responsibility for stewardship over SocietyÆs stock of materials remains open.

Jan 1, 2002

By K Fiedler, A Newell, P D. Munro

Test work is the foundation upon which the success of projects and subsequent operations is laid, reflected in Professor Arthur Taggart’s pithy observation: ‘Make your mistakes on the small scale and your profits on the larger scale’. Indeed, Professor AllanTrench has succinctly noted that ‘Get the metallurgical characteristics wrong and you don’t have a project’.With deposits becoming lower grade, more structurally and mineralogically complex, final products requiring lower levels of impurities and tailings management demanding more attention, test work now assumes even greater significance in the acceptance and successful execution of a project. This paper is the first in a series aiming to stimulate thought on the metallurgical test work process by getting back to the fundamental basics through exploring and providing some guidelines for the metallurgical testing world, noting preferred practices as well as precautions and mitigations. This covers the key characteristics of metallurgical test work programs, including what needs to be done, sample selection, quality control and associated drivers, and most importantly, selecting, assessing and managing test work facilities. CITATION:Newell, A, Munro, P D and Fiedler, K, 2018. Metallurgical test work – between a rock and a hard place, in Proceedings 14th AusIMM Mill Operators' Conference 2018, pp 15–32 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Aug 29, 2018

By J Field

Many aspects of water use in mining are driven by the technical requirements for water. There has been little consideration given to both the safety and the health requirements. Workers in the mining industry are exposed to water from a range of treated and untreated sources. The intended use of this water dictates the required quality of the water, sometimes with limited consideration for contact with miners. Particularly for underground workers, there is exposure while working in and walking through groundwater possibly contaminated by hazardous substances. Where controls are inadequate the outcomes of this exposure can result in disease, illness and injury û the costs of which can be significant. The situation could also arise where, due to the lack of human exposure, the controls are unwarranted and the financial cost unjustified from a health perspective but warranted from an equipment management standpoint. In addition to the health aspects, water can impact on a range of safety issues resulting from high pressure usage, dust suppression, fire fighting and other processes. The protocols and procedures in place need to consider the safety issues in addition to managing water usage. The current state of water management in mines from an occupational health and safety perspective has been ascertained from a survey targeting underground and surface coal and metalliferous mines. This survey considered the health and safety issues associated with water use, the types of surveillance, control protocols and the strategies that the mines have in place to manage the health and safety risks associated with water systems. The results assisted in the identification of potential occupational health and safety risks associated with water systems and the management processes that may be appropriate from a risk management perspective. Health and safety issues are often neglected but remain critical issues affecting the value of water to the mining industry.

Jan 1, 2006

By R Wilson, S Luke, R Williams, B Freeburn

"In 2010, two McLanahan RSS14×50 scrubber screens were installed at Fortescue Metals Group’s (Fortescue) Christmas Creek site. By 2015, the trommel (screen) section had effectively reached the end of their serviceable life. This was determined by regular measurement of structural components over the previous 18 months that tracked wear life. At the same time, numerous trials and optimisations had taken place on screen panel design and material composition. During 2015, a new set of trommels were designed, manufactured and installed that incorporated many new features: increased open area to facilitate high throughput, improved wear protection for structural members, simplified trommel panels and realigned discharge ports to reduce wear on exit. Numerous other upgrades have taken place on the drive system, feed chutes, liner and weir configurations and park brake, to name a few. This paper will highlight how regular measurement drove design changes and how the site and the original equipment manufacturer (OEM) managed a replacement program that has delivered improved performance.Citation:Wilson, R, Luke, S, Freeburn, B and Williams, R, 2016. Regular Measurement Defines Upgrades on Scrubber Screens, in Proceedings 13th AusIMM Mill Operators’ Conference 2016, pp 285–290 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Oct 10, 2016

The eastern third of Australia contains an unrivalled Phanerozoic rock record generated by the regional interaction of Gondwanaland with the Pacific and by the global effect of the 400 m.y. Pangaea - Panthalassa cycle. Between the latest Proterozoic (600 Ma) breakup of Proto-Pangaea and the mid-Carboniferous coalescence of the dispersed continents in Pangaea, the Lachlan and Thomson Foldbelts accreted to the craton by Mariana-type (backarc basin) and Chilean-type (continental margin) subduction from eastward jumps of the Palaeo- Pacific rim. Further jumps of the rim of the Permian and Mesozoic Pacific, now expanded to Panthalassa, accreted the New England Foldbelt to the craton. An Early Permian rift basin was succeeded by a Late Permian to mid-Triassic foreland basin which extended between the craton and the foldbelt behind the 10000 km Panthalassan rim, from the Bowen Basin of Queensland to South America, and was host to the productive coal measures of eastern Australia, as the succeeding Jurassic and Early Cretaceous foreland and epicratonic basins included the coal measures, hydrocarbon reservoirs, and aquifers of the Great Artesian Basin. The magmatic arc on the Australian margin ended after the mid-Cretaceous uplift along the Queensland coast that initiated southwestward drainage from the high Pacific rim. The Chilean-type subduction that had prevailed since the Devonian was superseded shortly afterwards by Mariana-type subduction with the successive generation of the back-arc basins of the Tasman Sea, Coral Sea, and other southwest Pacific basins by the migration of the island arc to its present position 2500 km eastward of Australia.

Jan 1, 1990

The underground storage of LPG and other hydrocarbons is in current commercial use in Northern Hemisphere countries in Europe, Asia and the USA.Elgas Pty Ltd, a 50 per cent joint venture between AGL and BOC, embarked on a worldwide feasibility investigation in 1989 to establish the viability of constructing an underground LPG storage facility in Sydney, Australia, the first of its kind in the country. Elgas recognised that with the limited 19 000 tonnes of storage capacity at Port Botany and the limitations imposed by use of small coastal ships (up to 10 000 tonnes capacity), a larger storage facility was required to utilise higher capacity ships from more remote sources such as the North West shelf and overseas. This would achieve security of supply in high demand periods and economies of scale. The underground option also provides improvements to safety and environmental standards.

Jan 1, 1999

Mining of the Martha Hill epithermal gold deposit via open pit methods will excavate a pit to 15 m below sea level. Regular geotechnical evaluations of pit slopes have taken place. Details of the various components of these evaluations, including geological structure, material strength, and groundwater, are covered. Pitwall geological structures are represented clearly on pit floor grade control maps with the dominant sets being steeply dipping strike fractures. Cross cutting shears are common. Material strength is reflected by the oxidation status of the hydrothermally altered host rocks, with weaker material occurring in partially oxidised ground. Regional groundwater is generally high, particularly on the north-eastern side of the pit, where it has been little affected by de-watering. Geological structures appear to control the flow of groundwater in the proximity of pitwalls and require draining by the introduction of horizontal drains. An overview of pit slope design is given. Slopes are designed for overall slope stability, allowing for the occurrence of minor interbench failures.

Jan 1, 1991

By N DavT

Pyritic tailings from the Quirke mine waste management area in Elliot Lake, Ontario were subjected to long-term column leaching experiments in two PVC columns measuring 122 cm in height and 15.2 cm in diameter. At the end of the leaching experiments, the columns were taken apart and sampled at 5 cm intervals for quantitative mineralogical and geochemical characterisation. Each column is represented by a total of ten samples. Polished sections, prepared from the samples, were studied by optical microscopy, scanning electron microscopy, electron microprobe and X-ray diffraction techniques. Mineral quantities were determined based on linear mixing models of whole rock and mineral compositions. Pyrite particle sizes were measured by image analysis interfaced to an electron microprobe. The tailings are coarse-grained (ie 96 per cent passing 75 ¦m) and composed of quartz, K-feldspar, muscovite and pyrite. Pyrite is homogenous and occurs as liberated particles displaying angular to subangular boundaries with strong dissolution features at the end of the leaching experiments. Based on up to 3518 particles measured in a sample, pyrite particle sizes range from 1.7 to 78.6 ¦m. Pyrite concentrations vary from 0.1 to 7.8 wt per cent, depending upon their location from the top of the columns. These correspond to pyrite losses of up to 99 per cent from their original level of 7.2 wt per cent in the upper half of the columns. Pyrite oxidation rates in terms of moles of pyrite oxidised per mole of pyrite per square metre per second were calculated from the effluent data and the measured pyrite particle sizes. The rates vary from 1.71+10-12 to 5.78+10-10 mole+m-2+s-1 within the 1.5 to 3.5 pH range for 10 ¦m particles. These results are comparable with the published oxidation rates at pH 2 where the dissolved oxygen is the only oxidant.

Jan 1, 2003

By B Laidens, D Souza, W Bielefeldt

The CaO-MgO-SiO2-Al2O3 system, characterised by its intricate phases and thermodynamic properties, plays a pivotal role in steel secondary refining processes, encompassing desulfurisation, non-metallic inclusion capture, and refractory protection. Accurate predictions for diverse industrial applications, including metallurgy, ceramics, and materials science, are imperative. To address this challenge, a combination of machine learning techniques will be specifically applied to model the liquid fraction of the slag and the solid fraction of MgO. The development of an artificial intelligence (AI) system, leveraging various machine learning techniques, has gained momentum in this project. The focus of this work is on constructing an AI model, based on machine learning techniques, within the CaO-MgO-SiO2-Al2O3 system, utilising simulation results from FactSage™, version 8.1 (by GTT Technologies). The primary objective is to train the AI model using these simulation outputs to predict the percentage of liquid fraction and MgO saturation based on chemical composition parameters. The AI model will undergo training with a comprehensive data set of simulations within the CaOMgO- SiO2-Al2O3 system, covering a diverse range of compositional at 1873 K. These simulations, conducted through FactSage™ 8.1 software, provide a robust foundation for AI model training, ensuring generalisability and precise predictions for the liquid fraction of the slag and the solid fraction of MgO, the solid fraction of MgO in this case is determined by the difference between the total MgO and the MgO in the liquid fraction, so it is not the objective of this study to determine which phase of MgO is in the solid state.. The predictive capabilities of this AI model hold significant implications for process optimisation, quality control, and decision-making in CaO-MgO-SiO2-Al2O3- dependent industries. Precise estimations of the liquid fraction and MgO saturation empower researchers and engineers to enhance operational efficiency and quality. This paper explores the methodologies employed for AI model creation and training, achieved results in terms of prediction accuracy, and potential applications in the field. The development of this AI system signifies a notable advancement in utilising machine learning for better comprehension and control of complex chemical systems. Furthermore, to align the study with real-world steel production, we introduce FeO and MnO at concentrations of 2 per cent and 1 per cent at 1873 K, respectively, following the validation of model results using the CaO-MgO-SiO2-Al2O3 system. This adjustment aims to bring the study closer to the observed reality in steel mills globally.

Jun 19, 2024