Search Documents

By D Joshi, J Rostami, M Karakus, A Eustes

The first target of mining activities on the surface of the moon is to find and extract water from the icy regolith on the moon. A test drilling unit was designed and fabricated under a NASA Early Stage Innovation (ESI) grant. A high-frequency data acquisition system was used to record drilling responses at 1000 Hz. Parameters like weight on bit (WOB), torque, rev/min, rate of penetration (ROP), mechanical specific energy (MSE), field penetration index (FPI), and the uniaxial compressive strength (UCS) were recorded for 40 boreholes in the analog samples made of regolith simulant and specialised cement. Development of the AI system and machine learning (ML) algorithms for analysis of data to evaluate strength and hence water content of icy regolith required a large data set. In this case, the data set comprising of more than one billion data points recorded while drilling into various analogue samples and cryogenic lunar formations to optimise power consumption and make bit wear adjustment during drilling operations. The tests were also repeated in the samples of icy regolith at various water content at -190C to verify the ability of the algorithms to analyse the data and to estimate the strength of the frozen formation and hence water content. The paper will discuss the objectives and methodologies used in the project and reviews the testing program and the machine learning (ML) algorithms ability to identify various formations along the exploration boreholes.

Sep 1, 2024

By N Arrys, A Jani, S Shahin

Optimising pit slope stability and reducing strip ratio of a mining operation are two key tasks in geotechnical engineering. With a growing demand for minerals and an increasing cost associated with extraction, companies are constantly re-evaluating the viability of mineral deposits and challenging their geological understanding. Within Rio Tinto Iron Ore (RTIO), the Structural Geology (SG) team investigate and collect critical data, such as point based orientations, mapping and geological inferences from adjacent pits to remodel deposits where previous interpretations have failed to account for structurally controlled slope failures. This work outlines the key methods utilised by the Structural Geology team which form the foundations of informed orebody knowledge and subsequent geotechnical design recommendations. This publication utilises the results from a recent analysis to highlight the benefits of this methodology and how it has impacted the economics of an operation through optimisation of a pit wall ‘cutback’ and crest relocation.

Sep 1, 2024

By S F. Wang, J J. Yin

Dust pollution poses a persistent challenge within mining processes, giving rise to a spectrum of concerns, including occupational diseases, mechanical degradation, diminished visibility, and the potential for dust explosion incidents. Existing dust detection and monitoring methodologies face limitations, including insufficient measurement accuracy and intricate processing procedures. Consequently, a comprehensive identification and evaluation system rooted in image processing technology is proposed to facilitate real-time measurements of dust pollution in mining worksites. The study primarily employs grey scale average and fractal dimensions to characterise particle features evident in collected dust images. As a result, the data processing platform can dynamically process data and present dust pollution conditions. Notably, this research integrates the monitoring and assessment of dust pollution with the systematic adjustment of mining parameters, ventilation parameters, and strategies for dust reduction. Through statistical analysis of dust concentration and particle size during mining processes, rock properties such as components and cuttability can inform mining parameters. This information, in turn, guides detailed excavation strategies, including cutterhead speeds, torque, and excavation speed. Similarly, analysing dust characteristics derived from images is a valuable resource for gaining deeper insights into the efficacy of implemented ventilation strategies. By harnessing vision-based information detailing dust concentration and distribution, a wealth of direct guidance becomes available for refining ventilation parameters. This encompasses crucial aspects such as the selection of appropriate ventilation systems tailored to the specific mining environment and the optimisation of operational conditions for ventilation fans. Additionally, the detailed information derived from the visual data allows for strategic decisions on factors like the spatial arrangement of ventilation outlets and the calibration of airflow rates. Moreover, precise choices for dust reduction measures and parameters can be made based on the prevailing dust conditions. Upon real-time monitoring of dust pollution using the proposed method, corresponding measures such as spraying and foaming can be promptly implemented. Crucial parameters, such as spray angles and volume, are integral to these application processes. In essence, the proposed method assumes a pivotal role in not only dust monitoring but also the formulation of preventative and control measures within mining processes.

Sep 1, 2024

By D Brown, Z Tabor

Projects must be flexible to account for the rapid development of new technologies and changing stakeholder expectations. Coupled with calls for bleeding-edge solutions, customers, shareholders, and regulators demand robust, safe products and systems-of-systems. Developing and integrating these solutions is becoming increasingly complex and maintaining the flexibility required to ‘pivot’ to effective solutions can be a serious challenge. The necessary flexibility is fundamental to the Agile ethos, and this family of methodologies therefore offers a potential solution to this challenge (Beedle et al, 2001). These have traditionally been delivered with systems engineering applied through a Waterfall methodology. Agile Systems Engineering combines both approaches and presents a means to achieve these goals without compromising flexibility, quality or safety. A robust methodology for the application of Agile Systems Engineering is required to enhance practical outcomes and reduce risk for real-world mining projects.

Sep 1, 2024

By B Gyngell, P Culvenor

Large language models (LLMs) have generated a lot of hype since ChatGPT was released in early 2023. In essence, they allow people to interact with computer systems through natural language and have the ability to generate highly complex text, images and videos (Patil and Gudivada, 2024). It is clear that this technology has significant potential, however most mining companies have not yet found practical applications for it within their operations. In this paper, we present a range of such applications along with the tactical considerations associated with developing and implementing them. We have identified use cases across a variety of operational and functional areas within the mining industry and evaluated them based on their potential business value and ease of implementation. Firstly, we provide an overview of how LLMs work and a review of how LLMs are being applied in other industries to provide best practice inspiration for mining. Next, we present a list of possible applications in mining and a critical assessment of each use case. This section also includes a technical deep dive into the different methodologies for developing the technologies as well as an analysis of barriers to adoption within mining organisations. Finally, we share a discussion of the potential path forward for LLMs in mining and the impact they could have on the industry. We analyse the potential differences between early adopters and laggards in the artificial intelligence (AI) space. This research draws on interviews and surveys with artificial intelligence experts as well as mining subject matter experts to connect cutting edge thought leadership with the specific problems faced by our industry.

Sep 1, 2024

By T Zhao, K Wang, Z Zhang

Tailings pond safety monitoring is vital for preventing dam failures and ensuring environmental safety. Unmanned Aerial Vehicles (UAVs) can enhance tailings pond monitoring with flexible operational cycles and the ability to collect remote sensing data from inaccessible areas. While many mining operations have adopted UAVs for tailings pond management, their full potential in data acquisition and subsequent analytical processing remains largely untapped. This paper explores various case studies where UAVs have been utilised for monitoring key aspects of tailings ponds such as beach line indicators, dam displacement and erosion, slurry discharge processes, and tailings pond capacity. We also present examples where data derived from UAVs have been instrumental in slope stability analysis, seepage modelling, Tailings Dam Breach Analysis (TDBA), and risk prediction. By integrating UAV technology with traditional ground-based sensor techniques, this approach significantly enhances the precision and reliability of hazard prevention and management in tailings pond operations.

Sep 1, 2024

By V Salamakha, K Tang, G Si, J Oh, X Wu, Z Yu

The development of machine learning (ML) algorithms has led to promising advances in lithology classification from geophysical logs, which is indispensable in various underground engineering applications. Due to the resolution and availability of logging data, ML models can recognise lithology change in a definitive form at a fine scale (0.01 m). While the results from previous models indicated promising performance in the classification, the robust capability of generalising lithology prediction to unseen data may not be true for those models due to: (1) data bias caused by borehole selections, and (2) logging data mismatches among boreholes. To this end, this paper aims to investigate the generalisability of ML models and seek potential improvements. Four ML models were selected to be trained on single reference boreholes to test the other (as unseen) in the same region, which includes Support Vector Classifier (SVC), Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and Residual Neural Network (ResNet10). The data set involves 11 boreholes from a coalmine in north-western Bowen Basin (Queensland, Australia): density, gamma ray, neutron, and sonic logs are selected as inputs. Additionally, a data adaptation method is applied for better generalisability. The results show that there is an accuracy trade-off between the same borehole and unseen boreholes across the models. It also indicates a 16–43 per cent reduction in model performance when generalising the predictions (in marco-F1 score), while the adapted data sets can contribute to a around 12 per cent improvement. This study provides a fundamental understanding of the model generalisability when using a single borehole, essential for further correlating boreholes for regional lithology classification; the adaptation method can improve the generalised accuracy, and reduces the labour to label lithology, which facilitates the identification of gas storage mechanisms, geological/geophysical modelling, and stratigraphic analysis.

Sep 1, 2024

By L Mackinlay

The Apeketon Business Hub in Lihir, Papua New Guinea, emerged in 2019 through a partnership between Australian Business Volunteers (ABV) and Lihir Gold Limited (LGL), a subsidiary of Newmont Corporation. This development was driven by a shared vision for the Lihir gold mining operation to further enhance opportunities for the local community and strengthen the economy’s resilience post-mine. At its core, the business hub serves as the epicentre of ABV’s operations in the region. It includes a drop-in resource centre which provides the community with mentoring and consulting services, and access to a range of impactful workshops facilitated by ABV’s local staff and skilled volunteers. These workshops focus on local Lihirians but are open to the entire community, including Newmont employees. We design and continually refine Apeketon Business Hub support programs and offerings driven by community priorities, building trust through long-term relationships, and working side-by-side on real-time challenges. We offer three core programs to different levels of the community, from individuals and families to start-ups, large corporations, and landowner groups. There is significant demand for the support services provided by ABV, with over 350 Lihirians participating in our workshops over the 2023 calendar year. One of the hub’s core offerings is the Family Money Management Program, which addresses crucial challenges faced by Lihir households, particularly in terms of financial resilience. The program takes a comprehensive approach, assisting families in long-term planning and developing skills to effectively manage the income they derive from their employment with LGL and other enterprises. Significantly, the program also addresses financial stress, a factor often associated with domestic violence (Fox et al, 2002). By empowering women and promoting joint financial decision-making, the Family Money Management Program fosters a culture of savings and improved financial management, ultimately enhancing economic resilience within the community.

Sep 1, 2024

By H Utama, R Heryadi

The demand for environmentally friendly commercial explosives has increased globally due to concerns regarding environmentally friendly mining activities. Ammonium nitrate fuel oil (ANFO) and bulk emulsion explosives (BEE) are two kinds of civil explosives primarily used in coal and mineral mining in Indonesia. Indonesia is one of the leading countries in coal and mineral mining production and export, with abundant resources; therefore, the consumption of civil explosives such as ANFO and BEE is enormous. The selection and evaluation of commercial explosives are mostly done on the commercial and technical side, and no assessment is made based on environmental aspects. This preliminary study evaluates the economic value and environmental burden of greenhouse gas emissions produced by ANFO and BEE and determines which type of explosives is more environmentally friendly. The combination of environmental and economic indicators, eco-efficiency (E/E), was selected to investigate BEE’s economic and environmental performance compared to ANFO. The life cycle of greenhouse gas emissions of BEE and AN was determined using previously available studies and simple calculations. The cost of the product or explosives was used to represent the economic value. The E/E results showed that environmental and economic sustainability could be enhanced using BEE.

Sep 1, 2024

By A Krishnan, C Garcia, I Luna-Berbesi

The discovery and exploration of deposits are progressively shifting to extremely remote regions and greater depths. As a result, exploration costs and the economic risk of a bad investment increase. Current megatrends in the exploration and mining sector indicate a growing demand for the implementation of automation, digitalisation, and machine learning techniques. The implementation of a multi-sensor-based core logging device (DMT, 2024) was done on 400 m of drill cores to optimise interdisciplinary processes in terms of time and quality, by using interlinked and consistent data in real-time, to obtain reliable predictions that support and speed up decision-making. The results are consistent with the laboratory data previously obtained by the mining company, highlighting the benefits of introducing ANCORELOG into their core logging procedures.

Sep 1, 2024

By A Innis, A Bye, B McCarthy, S Glover

Technology adoption in the mining industry has been steadily increasing over the past decade, driven by the need to improve operational efficiency, safety, sustainability, and profitability. As mining companies wish to implement solutions to improve mining safety and productivity, various technologies are being integrated into mining operations to enhance processes, reduce risks, and optimise resource utilisation. Adoption of new technologies such as autonomous trucks requires a strong focus on foundational operational technology (OT) and a systems-thinking approach. OT support is critical however, OT is traditionally not considered or integrated into standard maintenance activities. Consequently, sourcing and applying service support to OT systems in real-time has posed significant challenges to date. Neglecting the monitoring and upkeep of these operational technologies and equipment can lead to a host of adverse consequences. Operating instability becomes more prevalent, necessitating reactive measures, and the vulnerability to cybersecurity threats increases significantly. To address OT monitoring and maintenance challenges, a systems wide mindset and remote support discipline must be utilised. Remote operations support refers to real-time, 24/7 monitoring, control and support of site OT: network, production systems, maintenance systems, enterprise systems and mobile and fixed plant through a single interface remote from site. The presence of a disciplined team, grounded in a systems-oriented approach, is of the utmost importance to remote monitoring, given the intricate interdependencies of OT systems. The ability to understand the relationships among multiple systems, coupled with the capacity to distinguish between symptoms and root causes, assumes a pivotal role in operations. Through diligent monitoring and the astute understanding of system thresholds, remote operations support can actively identify and alleviate constraints, in turn, serving as the enabler for transformative advancements in technology output.

Sep 1, 2024

By M Rea, E O’Connell

Decarbonising explosives manufacturing and catalysing low-carbon mining supply is a significant global challenge. Low-carbon manufacturing precincts – clusters of geographically close businesses across multiple industries that share a goal of adopting firmed renewable energy and decarbonising process emissions – offer one potential solution. In an Australian first, Orica commissioned tertiary catalyst abatement technology in 2023 to mitigate greenhouse gas (GHG) emissions at its Kooragang Island (KI) facility in New South Wales (NSW), Australia. The EnviNOx® technology (ThyssenKrupp Industrial Solutions AG, Dortmund, Germany) used reduces nitrous oxide (N2O), a potent greenhouse gas arising as a by-product of nitric acid manufacture. As a result, mining customers in NSW are now benefitting from ammonium nitrate (AN) products that are almost 50 per cent less emissions-intensive than those Orica previously offered. The $37 million project is a private-public partnership that has involved partners across Federal and State government, global engineering and technology vendors, local community groups and local carbon advisors to overcome financial barriers.

Sep 1, 2024

By D Brown, K Markovic, Z Tabor

From ancient times to the modern world, the mining industry has played a pivotal role in shaping the society that we live in today. It remains an integral part of everyday life and is a catalyst for both technological and economic growth. With finite resources on Earth, and growing pressures surrounding climate change and the environment, space mining opportunities have become of increasing interest. Recent discoveries have shown celestial bodies including the Moon and surrounding asteroids, contain an abundance of critical minerals, as well as resources necessary to sustain human life. These discoveries coupled with a transition into the digital and autonomous age, offer an innovative solution to solving some of the mining challenges currently being faced on Earth. Similarly, they also offer a pathway to enabling deep space exploration and off Earth exploratory missions. However, like with mining operations on Earth, space remains and immensely challenging and complex operational environment. The inhospitable nature of space poses new challenges, including communication barriers, lunar dust, cosmic radiation, and gravity. The challenges and risks are not just technological, as Environmental, Social, and Governance (ESG) factors must also be considered to prevent unintended consequences and hazards. Furthermore, future workforce, law, financial, and security systems must evolve to enable space mining to take place. These are all known aspects to begin with, but as the complexity of the space grows it becomes apparent that a holistic approach to assess and manage these factors will be required.

Sep 1, 2024

By K Rau

The overall success of a mining operation is directly impacted by the reliability and availability of mining equipment. Heavy-duty vehicles such as excavators and haul trucks are used for conveying of bulk material and improving such assets’ availability helps reduce costs, increase throughputs and improve safety (Ravande, 2022). If a mining operation’s key performance indicators (KPIs) are tied to operational performance, then overall equipment effectiveness (OEE) is an essential metric to track progress and to identify areas of improvement.

Sep 1, 2024

By P Mugebe, M Yahyaei, M S. Kizil, R Low

This paper seeks to establish an empirical relationship between the impact of mining technological innovation implementation and a company’s market value. The company’s market value is represented by its stock price. In a bid to ascertain the relationship, a stock price prediction model is sought to be established using the firm-specific factors impacted by the implementation of innovative technology. This work is performed under the watch of the prevailing macroeconomic factors. The background anchors in the understanding that the difference between the economic status of a mineral deposit and its uneconomic status lies in the level of mining technological innovation most prevalent at a given time (Hartwick, Olewiler and Preuss, 1986; Wellmer and Scholz, 2017; Wright and Czelusta, 2003). This is derived from productivity improvement, resulting in sustainable profitability due to technological innovation. Unfortunately, there is not an adequately established relationship that links this technological innovation impact to the share price performance of the mineral commodity company.

Sep 1, 2024

By D Brown, K Markovic

The world is becoming an increasingly complex environment to operate within. Adoption and evolution of technology is occurring at a rapid pace and operating spaces are growing in interconnectedness and interdependency. In mining this is evidenced by the large-scale adoption of autonomous machinery, intelligent systems, Internet of Things (IoT) devices, and robotics to realise benefits in optimisation, productivity, and safety. To enable continual delivery and growth in operational performance, and to realise the aforementioned benefits, a new approach for managing mining and metals is required (Mining Review Africa, 2023). This means that an already talent constrained workforce must learn to manage the complexity inherent, evolving, and growing in the environment (Abenov et al, 2023). A key skill that needs to be further developed and deployed to combat these challenges and to enable robust problem solving is that of systems thinking, which is already practiced in pockets within the mining industry. Experience and learning can be leveraged from other industries and their application of systems thinking to ensure that focus is maintained on areas where the benefits from which will be optimised. With targeted application, a workforce capable of effective systems thinking can be the catalyst to optimisation across mining organisations.

Sep 1, 2024

By A Seneviratne, Y Li, N Udugampola, X Ai, B Li

LoRa (Long Range) is a low-power, long-range wireless communication technology that has gained significant research interest for its potential use in multi-hop linear wireless sensor networks (LWSNs) for underground mines. These networks deploy LoRa-enabled sensor nodes in underground mines, together with LoRa repeaters placed along mine tunnels to relay sensor data to a LoRa gateway, which connects to a backend network for application-level processing. Since the packets generated by sensor nodes farthest from the gateway have to hop through many repeaters, their probability of successfully reaching the gateway is significantly lower due to the higher chance of packet collisions compared to sensor nodes closer to the gateway, resulting in a lack of network fairness for the sensor nodes. In this paper, we first present an algorithm to improve the fairness of a LoRa LWSN by grouping neighbouring nodes and adjusting the number of packet re-transmissions and transmission intervals for each group. Then, we demonstrate that the fairness of a simulated LoRa LWSN can be improved by approximately 500 per cent by applying our algorithm. We verify our algorithm with network simulations under different network traffic levels and grouping strategies, obtaining fairness improvements in each scenario. Our algorithm and results will pave the way towards developing highly fair LWSNs for underground mining applications.

Sep 1, 2024

By Y Tang, G Si

The analysis of rock fragment sizes plays a pivotal role in various stages of geotechnical and mining engineering. Traditional case-based methods often falter in addressing the variability in rock fragment images due to fluctuating geological conditions and imaging environments. To counter this challenge, AI-based models necessitate training on expansive and diverse data sets, encompassing a wide range of conditions and fragment types. However, the creation of such data sets is often hampered by financial and environmental constraints. This paper introduces a novel approach for rock fragment recognition, which leverages the power of AI for data augmentation, automated annotation and prediction. The methodology integrates three key components: Style-Based Generator Architecture for Generative Adversarial Networks (StyleGAN) for data augmentation, the Segment Anything Model (SAM) for automated annotation, and the multiscale version of you only look once (YOLO-MS) real-time instance segmentation model. The proposed method begins by training a new StyleGAN model using the original data set. It then delves into exploring the latent vectors of different rock fragment images to generate specific ‘style representations’. These latent vectors form the foundational elements of each image in a high-dimensional space, encapsulating critical features such as size, shape, texture, and colour variations. The next step involves conducting quality checks on the generated images to ensure their realism and suitability as training data. Subsequently, the augmented image set is annotated using modified SAM module, followed by training the YOLO-MS real-time instance segmentation model. The performance of this model, trained on the augmented data set, is compared with a model trained on the original data set, particularly in terms of generalisation abilities in new scenarios. The results exhibit a significant enhancement in accuracy, robustness, and generalisability of the model trained on the augmented data set, underscoring the potential of StyleGAN as a powerful tool for data augmentation in geotechnical engineering image analysis.

Sep 1, 2024

By R Daiyan, G Burge, M Haider Ali Khan

Australia’s mineral and metal exports have a substantial carbon footprint, twice that of its domestic emissions, mainly due to fossil-fuel-dependent downstream processes like processing into secondary metals and their transport. The country’s vast renewable energy and low-carbon hydrogen potential offer a promising alternative to mitigate this impact. These resources can be leveraged to displace fossil fuel use and become embedded into the metals value chain. Ultimately, it will yield ‘Green Metals’ that can be scaled to reduce the environmental footprint and provide an avenue for Australia’s vast green resources to be embedded (incorporated during production and supply) in green metals that can be exported. One potential green metal is copper, which is in great demand and likely to drive global decarbonisation through renewable electrification due to its role as an energy conductor. Given that Australia is a large producer and exporter of copper, this paper provides a techno-economic model of the copper value and applies it to Queensland (a hub of Australia’s copper production) as a case study. The results show that under incumbent hydrogen (A$8/kg) and renewable energy costs, the cost of green copper would be A$9704/t (~10 per cent higher than current copper costs). Further analysis revealed that the cost of hydrogen is a major cost driver; therefore, if the cost of hydrogen can be reduced to A$2/kg (a 2030 target of the Australian government), the cost of green copper would become competitive. Furthermore, if a carbon pricing regime ($54–79/kgCO2) is introduced, green copper would become competitive at a hydrogen cost of A$3/kg. Altogether, these findings provide insights for a future green copper export opportunity in Australia. Additionally, as the next step, the model can be extended to include other metals and released as an open-source resource for assessing global green metal opportunities.

Sep 1, 2024

By M Dalm

More and more mining companies are becoming aware of the potential benefits of sensor-based ore sorting and process optimisation. This is reflected by a growing number of analysers that are available for drill hole logging, conveyor belt scanning, ore sorting, slurry analysis, etc. These tools all rely on a specific sensor technology that can be used to detect a material property such as colour, density, mineralogy, or chemical elements. However, all sensors have restrictions on the minerals and/or elements that can be detected or inferred. This is caused by the physical mechanisms behind the technology and depends on mineral concentration and compositional heterogeneity of the ore. Since nearly every ore deposit is unique in composition and characterised by different geological features that drive heterogeneity, no one-size-fits-all sensor solution is available. This makes it difficult for mining professionals to find suitable sensing technologies that can help them solve problems and improve processes for their specific ore types.

Sep 1, 2024