Search Documents

By A J. Clough

There has been an unprecedented rise in the fatality rate in the Australian mining industry over the last few years. The factors behind this rise are not clear; however, it is noted that the increase in fatalities has occurred during a fall in commodity prices.This paper examines prevention methods and systems to deal with hazards that have the potential to result in either single or multiple fatalities. Managing the risks associated with mine ventilation is used to illustrate the principals behind the approach.The paper also touches on the broad science of human error and proposes a multifaceted approach to controlling and preventing fatal risks.A summary of the steps involved in developing an effective principal hazard management plan is provided.CITATION:Clough, A J, 2015. Ensuring an effective principal hazard management plan, in Proceedings The Australian Mine Ventilation Conference, pp 3–8 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Aug 31, 2015

By I Jabou, D G. Blazak, L C. S Hogarth

The R70 test is a good indicator of coal reactivity to oxygen and is commonly used to provide a rating of propensity for self-heating. Tests performed by The University of Queensland Spontaneous Combustion Testing Laboratory have resulted in the development of a large database that shows the impact of coal quality on this parameter. From these results it is possible to infer an R70 value, which can be used to gain an appreciation of the intrinsic coal reactivity before it is even tested. However, any interpretation of R70 values must consider the influences of coal rank, mineral matter and moisture content to provide a better understanding of the spontaneous combustion risk of a particular coal.

Jan 1, 2005

By J Balzary, A Mohais

Dynamic market and operating conditions, coupled with an environment in which multiple objectives and trade-offs are common, pose major challenges for planners and schedulers working in any mining entity. Many mining companies recognise the need to shift from a siloed mining-focused push model to an integrated value chain, demand-driven approach, but there are still fundamental barriers in business process and the supporting technology preventing a consideration of end-to-end optimality.This paper presents some elements of experiences working with companies to adopt such advanced approaches. In addition to algorithmic elements, an approach to phased and gradual deployment of progressively more sophisticated optimisation models is described. From a practical software adoption perspective, it is believed that this last concern is also of primary importance. Next generation approaches to the optimisation of complex bulk commodity demand chains, namely iron ore and coal are presented, with case studies in the world’s largest integrated operations in Western Australia and Queensland from the raw material mined through to market. Utilising accurate simulation models supported by metaheuristic optimisation techniques, a range of ways to engineer a dynamic decision support framework that can adapt and change with the inevitable changes in commodity markets is explored. Objectives such as total revenue, margin, cost, NPV, throughput, asset utilisation, contractual penalties and bonuses, and energy consumption can be managed simultaneously across the mine, plant, logistics network, port operation, shipping and sales domains.CITATION:Balzary, J and Mohais, A, 2014. Consideration for multiobjective metaheuristic optimisation of large iron ore and coal supply chains, from resource to market, in Proceedings Orebody Modelling and Strategic Mine Planning Symposium 2014, pp 213–222 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Nov 24, 2014

By T Baumgartl, L Zhou, D Mulligan, L Huang

The rapid production and accumulation of mineral processing wastes in the environment can present serious threats to environmental quality and human health. Phytostabilisation with native plant ecosystems is, in many cases, a preferred option for rehabilitation of mine waste storage facilities. However, much of the literature has focused on species selection in short-term experiments to test their suitability under the often extreme chemical conditions in the wastes without addressing the fundamental requirements – ie hydrogeochemical stabilisation and functional root zones. As a result, successful examples of phytostabilisation of mine wastes such as base metal tailings have been rare, especially if success is defined as meeting the completion criteria of non-polluting and sustainable land system at rehabilitated sites. Conventional capping options to isolate reactive tailings/wastes by using physical break and/or sealing layers are often not reliable in the long term (particularly under semi-arid climatic conditions) and, in many cases, they may not be feasible in the field due to the large areas to be covered and the lack of adequate suitable materials at mine sites. By using sulfidic tailings as an example, we have proposed a new paradigm for phytostabilising mine wastes – ecologically engineered pedogenesis in tailings involving accelerated physical, chemical and biological weathering of tailings minerals to achieve hydrogeochemical stabilisation and the development of soil functions, soil horizons and functional root zones.Ecologically engineering functional root zones firstly requires controlling geochemical reactivity in the wastes (ie hydrogeochemical stabilisation), which can cause polluting effects in the root zone and plant toxicity. By means of ecological engineering, in situ weathering of primary minerals (eg pyrites) in tailings may be accelerated by adding functional materials (eg functionalised biochars and organic matter) in the waste slurry during the process of deposition. This will remove or diminish key risk factors (eg potential acidity in tailings and elevated soluble heavy metals) in the solid phase, before placing growth media for reconstructing root zones and transplanting/sowing target plant species. However, much of the acidity, soluble metals/metalloids and other salts would be transported out of the solid phase into the wastewater, which can be addressed by on-site water treatment facilities during mine operation. The trajectory and state of engineered pedogenesis in the weathered tailings may be manipulated to provide specific soil horizons within future root zones that are dynamically evolved toward fully functional soil subsystem within rehabilitated plant ecosystems.CITATION:Huang, L, Baumgartl, T, Zhou, L and Mulligan, D, 2014. The new paradigm for phytostabilising mine wastes – ecologically engineered pedogenesis and functional root zones, in Proceedings Life-of-Mine 2014 , pp 663–674 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 16, 2014

By H Askari-Nasab, E Torkamani, M M. Badiozamani, S P. Upadhyay, M Tabesh

"Decision-making in mining is a challenging task. Optimal decisions regarding shovel and truck allocations, aligned with the optimal short-term production schedules, are crucial in keeping the operations in line with the company’s long-term objectives. In this paper, we present two main modelling components as the means to achieve near-optimal operational plans: a mixed integer linear goal programming model to allocate trucks and shovels to mining faces over a shift-by-shift basis so that operating costs are minimised and resource utilisations are maximised through the planning horizon a discrete-event simulation model to investigate the behaviour of a truck-and-shovel haulage system in the presence of uncertainty within mining operations. The goals integrated into the mathematical model are to: maximise production minimise deviations from the target head grade minimise deviations in tonnage feed to the processing plants from the desired feed minimise operating cost.The mathematical model provides shovel assignments and the target productions as an input to the discrete event simulation model while meeting the desired goals and constraints of the mining operation. We illustrate the applications of the discrete event simulation model by presenting a large-scale oil sands case study. The main contribution of this work thus far is the development, implementation and verification of a simulation model with a link to optimal short-term mine schedule and extraction sequence of mining faces, which assists in achieving a high level of mine plan compliance across short-term planning and operational planning time horizons.CITATION:Askari-Nasab, H, Upadhyay, S P, Torkamani, E, Tabesh, M and Badiozamani, M M, 2014. Simulation optimisation of mine operational plans, in Proceedings Orebody Modelling and Strategic Mine Planning Symposium 2014, pp 299–312 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Nov 24, 2014

By P Moser, P Schimek, F Ouchterlony

This paper summarises the findings of 27 model-scale bench blasts in magnetic mortar, which were conducted from 2011 to 2014 at the blasting site of the Montanuniversitaet Leoben.The aim of the study was the investigation of the influence of blasthole delay times in small-scale bench blasts on the face characteristics and cracking damage created in the surrounding rock, which affects the fragmentation in subsequent rows.The test specimens or blocks, which were produced out of magnetite concrete, were roughly 1:100 in scale to normal bench blasts. The confinement of the testing blocks at the sides and back ensured the similarity to normal bench blasts with regard to the wave transmission into the surrounding rock. The specimen contained three or four rows with five blastholes each and were shot row by row, with virgin (undamaged) material in row 1 and increasingly damaged or preconditioned material in the following rows.The tested delay times varied between 0, 28, 73 and 140 µs, which corresponds to 0, 0.4, 1.0 and 2.0 ms/m of burden.The evaluation of the material properties showed that the use of magnetite concrete eliminated the inhomogeneous behaviour of rock, but some unexpected differences of the individual production cycles were still detected.The characteristics of the bench after each blast was evaluated along three horizontal lines out of a 3D model of the bench face. The tested delay time sequences of the virgin (first row) and single preconditioned blasts (second row) produced more overbreak for longer delays, while the third-row shots resulted in a smoothened surface independent of the chosen delay.The introduced damage after every blast was evaluated by an observation of irregularities on the newly blasted bench face. The visible cracks at the top of the testing blocks were documented and divided into several crack families according to their angle, length and origin. The remaining block was broken out of the blasting site after blasting, cut into several horizontal and vertical slices and dye penetrant spray was used to visualise the cracks created. Some of the detected crack families showed an influence of the delay time. The calculated mean crack density and mean crack intersection density showed that longer delays resulted in a higher degree of damage.The fragmentation results were well reproduced by the basic three-parameter Swebrec function. The observed improvement of fragmentation in the second- and third-row blasts was linked to the preconditioning of the burden for the following row while blasting the actual row. With the exception of the simultaneously initiated blastholes, the blasts showed coarser fragmentation for the shortest delays, while the longest delays generated the finest fragmentation.CITATION:Schimek, P, Ouchterlony, F and Moser, P, 2015. Influence of blasthole delay times on fragmentation as well as characteristics of and blast damage behind a remaining bench face through model-scale blasting, in Proceedings 11th International Symposium on Rock Fragmentation by Blasting, pp 257–266 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Aug 24, 2015

By J J. Hanhiniemi, M S. Powell

A ‘Variable Blend and Rates’ model is developed for SAG mills which extends upon the JKSimMet® Variable Rates Model. Similarly, a ‘Variable Blend Residence Constrained Perfect Mixing’ Ball Mill model is also introduced, also extending upon the existing JKSimMet® model. These models are used in conjunction with JKSimMet® while employing external technical programs. The technical model is then used to inform an economic model described elsewhere in Hanhiniemi and Powell (2022), which calculate operating and unit costs based on operating conditions, design, and ore characterisation. The SAG and ball mill models include constraints beyond those in the JKSimMet® models. The SAG model constraints include Size Specific Energy (SSE) verification, charge weight limit, and assessment of the impact of media to ore composition in the charge using the SAG Charge SSE Model developed in this paper. The ball mill model includes residence time, volumetric capacity, and SSE verification constraints. These models are applied to Cortez Gold Mine in the processing of two very different ore types and their blends; ‘Horse Canyon’ which is softer in coarser sizes and competent is fine sizes, and ‘Wenban’ which is competent at coarser sizes but softer in fine sizes than Horse Canyon. Horse Canyon also has a finer run-of-mine size distribution then Wenban. The application of the model at this site included undertaking five surveys at varying blends. The behaviours of the blends and individual components is then studied in the SABC circuit. A nonlinearity is observed with throughputs increasing with blending. The newly developed modelling approach captures these responses. Controlled blending based on ore competence-by-size and size distribution was implemented by the site, which then realised significant improvements in throughput without any capital cost (Ntiamoah et al, 2020). The modelling developed in this paper is then compared to existing practice, and the new method was found to provide improved fidelity and utility. A three-dimensional surface is then developed using the model describing the SAG mill throughput capacity at varying conditions (speed-filling) versus varying blend. The change in throughput as a function of only the changing charge composition is presented. The result is nonlinear, and explanations are provided to describe this behaviour.

Aug 24, 2022

By C Simpson, J Market

The process of sampling blasthole cones utilising personnel to manually shovel material into sample bags is a long-standing industry accepted process. However, this method has several drawbacks, including the safety issues around having personnel performing manual sampling in a harsh environment and the variability involved in getting a human to repeatedly get a ‘shovel full of dirt’, and make it always representative. Geophysical blasthole sampling, or utilising a Downhole Assaying Tool (DHAT) has been tested and has now begun implementation at many iron ore sites throughout the Pilbara region, Western Australia. This method uses a geophysical tool to capture data within blastholes, and together with a semi-autonomous logging platform to minimise risks around manual handling, delivers a multielement proxy-assay which can be utilised by the mine geology team to accurately domain the orebodies. Logistically, the combination of a specially designed tool and semi-autonomous truck are the way forward for a safer and more data-robust blasthole sampling practice. The method utilises a neutrongenerating geophysical tool and linked elemental spectroscopy sensor, which measures the response of the material surrounding an open hole. This delivers results at submetre intervals. These results are then utilised, similar to blasthole sample results, to map out areas within the blast pattern that are ‘ore’, ‘waste’, or ‘other suitable grade’. This paper outlines a project that has been in ‘proof of concept’ at selected Fortescue sites over the last few years with testing of these tools carried out on reverse circulation (RC), diamond drill and blastholes. The method is now being implemented at operational hematite mine sites. Fundamentally, the method adds more than enough value to justify its implementation. The aim is that these learnings will enable the greater industry to adapt, implement and improve their mining practices. Ultimately, the outcome will be greater value in mining for the industry by having a larger volume of good quality data to make reliable decisions on material movements, minimising ore-loss and dilution, and maximising the value of our current and future orebodies.

Nov 8, 2021

By P Christen, D R. Ashley, G R. Power

The Ernest Henry Mine is currently a copper-gold open pit operation situated in north-west Queensland, Australia. It is owned and operated by Xstrata Copper with a current throughput of 11 million tonnes per annum; however, open pit operations are scheduled to cease in late 2011. The deposit dips at approximately 45¦ and extends for at least another 400 vertical metres below the final 530 m deep pit design. Resource drilling from 2002 until mid 2008 has enabled an Indicated Mineral Resource to be established to 1000 m below surface. Scoping and prefeasibility studies (PFS) have been completed toward determining if this resource is suitable for underground mining and a feasibility study is currently progressing with a sublevel caving (SLC) concept. This paper briefly describes the process by which the SLC method was selected, conclusions regarding the non-selected methods, and then discusses the optimisation process used to derive the mining plan. The key optimisation parameters include the production drive spacing, level spacing, draw strategy, cut-off grade and production rate. Key risks will then be assessed and economic sensitivities studied. Final sensitivities will use Monte Carlo simulations to improve the transparency of the projectÆs risk profile. The feasibility study (FS) began in March 2008 and this paper describes the main optimisation steps at the time of writing and outlines the plan for study completion through to March 2009.

Jan 1, 2009

My purpose here today is to introduce an element of democracy into this seminar. In my experience, the mines of Australia can be divided into two categories; those that pay and those that don't. As far as I can ascertain, every other paper being delivered at this seminar concerns mines which come into the first category, or at any rate are close enough to it for the promoters to be able to afford an expert's valuation.

Jan 1, 1989

By G R Ryan

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

Jan 1, 1994

By J Pan

In this paper, the technology of producing fluxed pellets by using hydrated lime as binder instead of bentonite was carried out. The properties of the two types green balls (0.8 per cent bentonite and 2.0 per cent hydrated lime) were as follows: drop numbers of 4.8 - 5.0 times/0.5 m, compressive strength of 19.7 - 24.2 N/pellet and thermal shock temperature of 280° - 385°, respectively, under the same conditions of 1.5 per cent coke, 1.45 basicity and balling at 8.5 per cent moisture for 13 min in disc pelletiser. Comparing with bentonite as binder, the compressive strength of fired pellets with hydrated lime is elevated by 13.8 per cent and climbs up to 3113 N/pellet under the following conditions: preheating at 1050°C for ten minutes and fi ring at 1300°C for 15 min. In the mean time, the hydrated lime also improves the metallurgical performance of fired pellets. The reduction index was enhanced from 68.6 - 70.6 per cent, RDI+3.15+ increased from 90.1 to 98.8 per cent and reduction swelling index dropped from 22.4 - 7.4 per cent, respectively. The mineral compositions and microstructure of fi red pellets shows that the fired pellets containing 2.0 per cent possess more calcium ferrite and magnesium ferrite and compact microstructure, leading to the higher compressive strength.

Jul 11, 2011

By K Hooper

Over the past 20 to 30 years statistics as a science has grown in significance. Not a day passes without reference to the latest statistics by the print, audio and audio-visual media. The Northern Territory Government has been part of this growth and like other public and private sector organisations collects a broad range of statistics. The Northern Territory Department of Mines and Energy participates in the government's statistics collection process. Statistics collected and published by the Department of Mines and Energy include geoscientific; mining and exploration tenure; environmental (e.g. mine site waste water management); production of minerals, oil and gas; mining sector employment; and occupational health and safety. The importance of statistics collection to the Northern Territory Government is discussed in the paper.

Jan 1, 1994

By M Grigorescu, J H. Hodgkinson, H Alehossein

A new framework that collates and interprets pre-existing data to assess vulnerability and ultimately plan to avoid or minimise flood-related risk to infrastructure, people, downtime, environment and revenue has been developed. The æClimate Related Adaptation from Terrain Evaluation ResultsÆ (CRATER) method tested at a coal mine in Queensland, provides semi-quantitative information to assist decision makers when designating investment for minimising vulnerability of mining operations to climate. Here we present the processes involved in this three-step approach that uses pre-existing spatial data of the mine site and local knowledge to build a set of visual tools to assist decision-making. The first step of the process is performing multi-criteria evaluation (MCE) within a geographic information system (GIS) on ranked natural conditions at the mine, such as elevation, slope, drainage, soil and vegetation, which is performed to identify critical flood areas. Secondly, a fault-tree analysis identifies how impact can occur and what options there are for impact reduction. Finally, a resource assessment of the mineÆs capacity to adapt reduces the adaptation options to those most suited to the mine. The results are confidential, but for the purpose of introducing the methodology, we present simplified results, particularly of steps 2 and 3. CRATER can also be used for future æwhat-ifÆ flooding scenarios to identify the most suitable locations for roads, buildings or other critical infrastructure. The methodology is transferable to any mine, series of mines or locations along the mining value chain that have sufficient data, providing a practical decision-making tool to identify æno-regretsÆ actions that not only could reduce downtime after or during an event, but in some cases may enhance production between extreme events. We now plan to test this method at a broader scale, to encompass more than one mine in the analysis.CITATION:Hodgkinson, J H, Grigorescu, M and Alehossein, H, 2013. Climate Related Adaptation from Terrain Evaluation Results (CRATER) - interpretation of pre-existing data for mine site flood vulnerability and management, in Proceedings Water in Mining 2013 , pp 259-266 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Nov 26, 2013

By C McCamley

"The requisite for maintaining optimal carbon concentration levels in a carbon-in-leach (CIL) circuit is of paramount importance in the prevention of gold losses. The process’s ability to recover gold from the aqueous phase is primarily dependent on the carbon loading profile of the CIL train.Newmont Boddington Gold (NBG) have over 2015 tested the Mintek online carbon concentration wmeter (C2 Meter) suitability for effective carbon concentration measurements in their CIL circuit compared to the standard method where the readings are taken twice a shift by the operations staff. The C2 meter works by passing a 1MHz ultrasonic signal through a slurry containing carbon where there is a relationship between the carbon concentration and the attenuation of that signal.It also highlighted another area where the C2 meter could be implemented at NBG whereby the instrument can be as a cautionary device for carbon losses in place of carbon safety screens.Citation:McCamley, C, 2016. Continuous Carbon Concentration Measurement at Newmont Boddington Gold, in Proceedings 13th AusIMM Mill Operators’ Conference 2016, pp 207–212 (The Australasian Institute of Mining and Metallurgy: Melbourne)."

Oct 10, 2016

By J O. Watson, V S. Vutukuri

This paper presents results of an investigation on acoustic emission characteristics of granite, sandstone and rock-like material in the unconfined compression and tensile tests. Both the acoustic emission signature and stress-stain curve are analysed in the experiments.The experimental results show that different acoustic emission characteristics are observed at different stress and deformation stages in unconfined compression and tensile testing. Extensive and unstable acoustic emission changes may be interpreted as indicating failure of the rock.

Jan 1, 1999

In spite of the efforts done in the past to implement in Codelco best practice guidelines and standards on several important sampling, assaying and variability issues, many people, particularly top managers and operators, are still not aware of the relevance of the use of the principles and practice of geostatistics, sampling theory, analytical chemistry and the understanding of processes variability from rock to cathodes. As a result, an important challenge for the sampling community is to find out the causes of this lack of awareness and to develop communication skills to influence the organisation, particularly the top management level. This situation is not affecting only Codelco; it is a common characteristic of the copper mining industry. The main cause is cultural. Judeo-Christian and occidental sciences are deterministic. This implies a disregard of process variation and the assumption that homogeneity is omnipresent. Another important aspect of the cultural challenge is education. Education is the most efficient way to transfer a system of ideas, traditions and practices. To implement proper courses of sampling theory and geostatistics and support to multidisciplinary education at universities, mining companies will improve teamwork between geologists, mining engineers, metallurgists and chemists. The improvements will imply a more sustainable and efficient mining business.

Mar 1, 2010

By X L. Liu, W Huang, J M. Zhu, S L. Wu

The shape, position and thickness of the cohesive zone have a great influence on the operational performance of the blast furnace. Many researchers have found that the high temperature properties of iron ores determine the formation of the cohesive zone. The results of this work show that sinter of high basicity interacts with lump ores and acid pellets due to the difference in chemical compositions. The softening and melting properties and the primary slag formation behaviours in the cohesive zone are improved by the high temperature interactions. The high temperature interaction is mainly influenced by the chemical compositions, porosity, interfaces and so on. Although the softening and melting properties and primary slag formation behaviours of lump ore A (a typical limonite lump ore from Australia) is the poorest of the iron ores studied, the high temperature properties of integrated burden A (consisting of sinter and lump ore A) is no worse than the other integrated burdens due to the high interaction between the sinter and lump ore A. It is useful to apply the results in the optimisation of blast furnace burden.CITATION:Liu, X L, Wu, S L, Huang, W and Zhu, J M, 2015. High temperature interactivity of iron ores in the cohesive zone of the blast furnace, in Proceedings Iron Ore 2015, pp 363–366 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Jul 13, 2015

By G Lane, M Bueno

In a recent publication (Bueno and Lane, 2011) the authors presented the analysis of a consolidated dataset composed by 137 autogenous/semi-autogenous grinding (AG/SAG) mill pilot trials. By comparing the measured data against theoretical specific energy consumption, the analysis indicated which circuit configurations were more or less energy efficient. However, the analysis has also indicated that the energy efficiency of each of the types of circuits vary significantly.There are numerous factors that contribute to the variations of energy efficiency of AG/SAG mill-based circuits, such as feed size distribution, recycle ratios and ore characteristics. In view of this, the present work accesses these factors individually and discusses what may lead a particular circuit configuration to be more or less efficient in terms of energy and costs.CITATION:Bueno, M and Lane, G, 2012. Key drivers of energy and cost efficiency in autogenous/semi-autogenous grinding circuits, in Proceedings 11th AusIMM Mill OperatorsÆ Conference, pp 113-118 (The Australasian Institute of Mining and Metallurgy: Melbourne).

Oct 29, 2012

By M Balamurali

In mining, grade control generally focuses on blasthole sampling and the estimation of ore control block models with little or no attention given to how the materials are being excavated from the ground. In the process of loading trucks, the underlying variability of the individual bucket load will determine the variability of truck payload. Hence, accurate material movement demands a good knowledge of the excavation process and the buckets’ interaction with the environment. However, equipment frequently goes into off-nominal states due to unexpected delays, disturbances or faults. The large amount of such disturbances causes information loss that reduces the statistical power and biases estimates, leading to increased uncertainty in the production. A reliable method that inferences the missing knowledge about the interaction between the machine and the environment from the available data sources, is vital to accurately model the material movement. In this study, a twostep method was implemented that performed unsupervised clustering and then predicted the missing information. The first method is Density-based spatial clustering of applications with noise (DBSCAN) based spatial clustering which divides the diggers’ and buckets’ positional data into connected loading segments. Clear patterns of segmented bucket dig positions were observed. The second model utilised Gaussian process regression which was trained with the clustered data and the model was then used to infer the mean locations of the test clusters. Bucket dig locations were then simulated at the inferred mean locations for different durations and compared against the known bucket dig locations. This method was tested at an open pit mine in the Pilbara region of Western Australia. The experimental results demonstrate the advantage of the proposed method in inferencing the missing information of bucket-environment interactions and therefore enables miners to continuously track the material movement.

Jun 22, 2022