Search Documents

By Nico Sutmoller, Rich Palladino

Underground voids present a unique geotechnical engineering challenge. This paper will address materials and transportation mediums that are typically used for backfilling underground voids with native material. After reviewing traditional backfill and transportation methods, this paper will explore the advancing technology of foam transportation and the advantages of using this technology for transporting fill materials into underground voids to backfill them with Liquid-Sand. The paper will also review the benefits that Liquid-Sand brings to these applications and highlight specific case studies in which foam transportation has proven effective and provided cost-effective, environmental benefits.

Feb 1, 2025

By John J. Simmons

There is considerable interest in the iron and steel industry in the development of technologies that can reduce carbon dioxide emissions, as the iron and steel industry is the third largest producer of carbon emissions in the world, after automobiles and the power generation industry. The E-Iron Iron Nugget Making Process, invented by Dr. Komar Kawatra and Dr. Tim Eisele, provided a major breakthrough in the iron making process as the process uses biomass in the form of hard wood or soft wood as the reductant in the place of coal. Dr. Kawatra recognized that biomass is rich in both carbon monoxide and hydrogen, two important reducing agents. This resulted in initial experiments conducted by Dr. Kawatra and Dr. Eisele in the laboratories of the Chemical Engineering Department of Michigan Technological University (Michigan Tech) that prepared self-reducing pellets with wheat flour as the reductant and limestone/dolomite as the flux. Initial results were encouraging so they extended their work to include hardwood, which is in huge supply in the forests of Michigan and Minnesota, as the reductant. Dr. Kawatra has also applied the E-Iron Technology to other iron bearing minerals to produce pig iron grade iron nuggets. He used the E-Iron Process to convert red mud, a high iron waste product of the aluminum industry, into pig iron nuggets with the rare earth elements reporting to the slag. This work resulted in a patent with Dr. Kawatra and Dr. Michael Archambeau named as the inventors. Dr. Kawatra then extracted the rare earth elements as a separate high value bi-product using oxalic acid, which he produced from carbon dioxide. Dr. Kawatra also conducted a test program that produced pig iron nuggets from New Zealand beach sands. The vanadium in the beach sands was retained in the iron nuggets, recoverable as a valuable bi- product in a separate process. The titanium dioxide in the beach sands reported to the slag. This demonstrates the potential use of the E-Iron Process to convert the large ilmenite reserves in Northern Minnesota into pig iron and titanium dioxide. Another use of the E-Iron Process discovered by Dr. Kawatra was its ability to produce iron nuggets from manganiferous ores. Dr. Kawatra was able to direct the manganese into either the metal or slag by adjusting process temperature. The above discoveries are included in several patents that were assigned to Carbontec Energy. This presentation will only address the use of the E-Iron Process to produce pig iron nuggets from steel mill waste and un-pelletized, mid-grade iron ore. Carbontec Energy Corporation agreed to sponsor additional research directed at improving this new technology that would later be trade named, The E-Iron Process. Carbontec Energy conducted further work that proved that the E-Iron technology could also convert steel mill waste into metallurgically acceptable iron nuggets. Carbontec also collaborated with the Lawrence Livermore National Laboratory and Purdue University Northwest to conduct a Department of Energy (DOE) sponsored program that would use their high performance computer capability to both verify and model the E-Iron Process. Purdue University Northwest reported that the E-Iron Process can produce pig iron nuggets with 85% less carbon emissions than a blast furnace. The E-Iron Process is similar to the ITmK3 process, developed by Kobe Steel, that also produces iron nuggets but uses coal as the reductant.

Feb 1, 2025

By Boyd Eisenbraun, Dennis Murr, Milton Rojas

Approximately since 1925, the phenomena of grinding and classification of minerals with screens have been studied. In the U.S. iron ore mining operations located in the so-called “Mesabi Iron range,” magnetite processing plants have made progress in the application of high-frequency screens that have allowed them to process low-grade Taconite ores and successfully achieve the economic benefit of these minerals. In the particular case of magnetite minerals disseminated in the siliceous matrix, the main objective is to reduce the generation of particles called “middlings” with high silica contents. Commonly the primary challenge of the metallurgical task is to achieve high recoveries and iron concentrates with low impurities. To achieve this, several studies and industrial applications have shown success in this regard and not only in iron ores, but also in other minerals around the world. The study described in this paper attempts to describe some key aspects that helped develop an effective solution and list the benefits associated with this modern process design by using industry-proven technologies for minerals in Chile that have similar characteristics to the minerals of the iron belt in the United States.

Feb 1, 2025

By Liming Yuan, Wei Tang, RICHARD THOMAS, DAVOOD BAHRAMI

The location and orientation of fire suppression nozzles is critical in suppressing mobile mine equipment fires. To effectively suppress such fires, optimization needs to be considered for the suppression nozzle locations and discharge angle. Detailed experiments were conducted to study the effectiveness of fire suppression agents with different nozzle configurations. A variety of fire suppression systems including dry chemical, wet chemical, dual agent (dry and wet chemical), carbon dioxide, and water mist were used. Six types of nozzle locations were studied, and their fire suppression effectiveness were compared. Results from this work highlight potential considerations when determining effective fire suppression designs.

Feb 1, 2025

By Sean Hunter

Artificial Intelligence has a long history but is currently coming strongly into focus with new advancements. This leads to questions many people are asking: what exactly is AI, how can it be used effectively in mining operations, and what foundation is required to make AI implementations successful? In mining, many AI applications exist, from drill pattern optimization to predictive maintenance. However, many implementations struggle due to data integration challenges. Mining operations generate large amounts of data from many sources, such as fleet management systems, drill sensors, process control systems, and laboratory results. Unfortunately, this data often exists in silos where it’s difficult to get it out, making AI applications unable to leverage it. Worse still, tools that use AI don’t always provide their data back to the system, creating even further data silos. All these problems make it hard to take advantage of the data at the mine, slowing down and reducing the effectiveness of AI. This paper presents a comprehensive approach to organizing mining data using an AI-ready knowledge graph system. We will first explore the evolution of AI in mining, from early expert systems to modern machine learning applications. Then, we will detail how a knowledge graph can integrate business context, operational data, and AI models into a cohesive system that enables more effective AI implementations across mining operations. The proposed method has been developed considering both the unique data challenges faced by the mining industry, while also considering best practices learned from the AI field at large. By following this approach, it’s possible to better utilize existing data, getting higher quality and more complete results faster, and in a way that’s reusable and composable.

Feb 1, 2025

By Jeffrey W. Lin, Larry B. Weston, Jonathan D. Abbott, Jordan L. Arthur

Hydrocarbon fuel oils are one of the main components of ammonium nitrate-based explosives, including ANFO (Ammonium Nitrate-Fuel Oil) and emulsions. While a wide variety of fuels can, and have, been used in the manufacture of ANFO and emulsion products, No. 2 diesel, particularly dyed, off-road diesel, is widely used due to its ready availability and use in fueling mining equipment. However, a number of alternatives to standard diesel have been introduced over recent years, namely, biofuels, ‘high-performance’ diesels, and renewable diesels. The pressure to adopt these alternative fuels come from a variety of sources, such as initiatives to reduce carbon footprints, increased lifetime of equipment, and cost-advantages from tax credits. While these factors may provide a very real benefit to the mine site, a consideration that is often missed is how the use of these fuels can impact the formulation and characteristics of the ammonium nitrate-based explosives. Herein will be presented a discussion of these alternative fuels from a chemical perspective as well as the results of several studies focused on how the inclusion of various alternative diesels influences the production and performance of ammonium nitrate explosives. ANFO and emulsion were manufactured using representative fuel sources and studying in terms of the manufacturing parameters, shelf-life, interaction with other chemicals using in mining explosives. Detonation data was then collected for these products and compared to the behavior of products made with standard diesel fuels.

Jan 21, 2025

By Jorge Alvarez

In a large-scale open-pit mining operation, continuous efforts are made to control damage to the slope walls. An essential tool in this effort is determining the PPVc (critical peak particle velocity) in areas of interest. By knowing this value and generating criteria, drilling and blasting designs can be established to reduce vibrations that affect wall construction. It is crucial to understand that the PPVc changes as different mining phases develop, especially due to exploitation on the benches, which leads to vertical inherited damage. Therefore, it is imperative to regularly update the PPVc based on field tests that provide accurate data. With this information, vibration damage criteria can be established, and drilling and blasting techniques can be designed to minimize the impact on the remaining rock mass. This document presents a methodology for generating scaled criteria that best represent the reality of the rock mass.

Jan 21, 2025

By Visitor Makiyi, Chris Batten

Poor coal recovery due to coal damage or loss caused by blasting can have a significant impact on a mining operation. Increasing coal recovery by reducing blast damage can provide a significant opportunity for coal mines to maximise their revenue and reduce their operating costs. This paper provides details on advanced drilling and blasting techniques used throughout the coal industry globally to prevent coal damage and movement during blasting. Typical coal loss and damage mechanisms are explained, along with how each of the applied techniques works to minimise the impact of each mechanism. Key requirements for a coal loss reduction program are detailed with typical design parameters used for each of the methods discussed. The positives and negatives of each method are also provided to enable comparisons and help determine suitability for a particular coal mining operation.

Jan 21, 2025

By Aris Tambunan, Nella Lubis, Nurafrianti Saala, Komang Widhiayanto, Herry Saputra, Rudolf Sitorus

Maximizing mining recovery rates and minimizing ore loss are pivotal objectives for economic efficiency and operational effectiveness. This study explores methods to address these imperatives by enhancing ore production and recovery through improved blasting techniques and spillage control in the Martabe Gold Mine Project in North Sumatra Province, Indonesia. Between 2018 and 2021, the average mining recovery rate stood at 93%, resulting in a potential annual ore loss of 7% and a potential quarterly financial impact of close to $2 million. Maintaining and enhancing mining recovery became crucial, with a planned 30% increase in total material movement for 2022. The mining recovery target for 2022 was set at 96% based on best achievement historical data from 2021 to increase ore tonnage by 203 KTon per annum. To achieve the primary objective of increasing ore production by improving mining recovery, the study focused on predicting and controlling the movement of blasted ore to reduce spillage and enhancing the grade control model to reflect actual conditions post-blasting. Several alternative solutions were explored, primarily emphasizing drilling and blasting activities. Essential methods included capturing the actual blasting movement to adjust the ore block based on blasting design data and post-blasting muckpile topography. This approach minimizes ore loss by providing output as ore block adjustment based on post-blast movement data. In addition, the tie-up design was adjusted to control ore spillage outside the pit ridge. The implementation of these methods yielded significant improvements. Adjusting the ore block based on actual blasting movement contributed $1,545,764 in benefits. Controlling ore spillage outside the pit ridge achieved a 10% reduction in spillage, contributing $79,184 in benefits. These enhancements successfully met the 2022 mining recovery target of 96%, marking a 3% increase from 2021. Consequently, ore loss was reduced by 178 KTon throughout 2022, resulting in a financial impact of $7.3 million. The study underscores the significance of precise blasting techniques and effective spillage control in enhancing mining recovery rates.

Jan 21, 2025

By Campbell Robertson

The evolution of electronic detonators in commercial mining, construction and demolition has been a transformative journey, characterized by technological innovation, enhanced safety measures and improved precision. This abstract explores the historical progression and key advancements in electronic detonator technology highlighting its impact on the industry as well as the challenges in deploying these types of technologies. Electronic detonators represent a significant departure from traditional initiation systems offering precise timing capabilities and improved reliability and safety. The early development of electronic detonators can be traced back to the late 20th century with the introduction of basic electronic initiation systems. These early iterations provided a glimpse into the potential for greater control and accuracy in blasting operations. As technology progressed, electronic detonators underwent significant refinement incorporating advanced features such as programmable delay times, multiple firing sequences, expanded blast size and enhanced communication capabilities. These advancements revolutionized the way explosives are deployed in mining and demolition applications enabling engineers to tailor blasts to specific geological or environmental conditions and structural requirements. One of the most notable developments in electronic detonator technology is the integration of microprocessor-based control systems. These systems allow for precise calibration of detonation parameters, including timing, sequence, and energy distribution. By leveraging microprocessor technology electronic detonators have become increasingly sophisticated offering unprecedented levels of precision and safety in blasting operations. The advent of wireless communication technologies has further augmented the capabilities of electronic detonators. Wireless detonation systems enable remote initiation and real-time monitoring of blasting operations enhancing safety by reducing the need for personnel in hazardous environments. The evolution of electronic detonators has also been driven by a growing emphasis on sustainability and environmental stewardship. Modern electronic detonation systems are designed, amongst other objectives, to minimize environmental impact, achieve optimal fragmentation outcomes and reduced misfire rates during blasting. These advancements not only improve safety for workers and surrounding communities but also contribute to a more sustainable approach to mining and/or demolition activities. In conclusion, the evolution of electronic detonators has transformed the landscape of commercial mining and demolition offering unprecedented levels of data integration, precision, safety, and environmental responsibility. As technology continues to advance, electronic detonators are poised to play an even greater role in shaping the future of blasting and explosives engineering.

Jan 21, 2025

By Emmett J. Ientilucci, Martin Held, Xuesong Liu

Mining is crucial for advancing technology and science by providing essential resources and materials. Quarry blasting, a necessary process in mining, releases these resources and chemicals, driving research and engineering improvements. However, NOx (nitrogen oxides) is an undesired contaminant produced during quarry blasts, posing a significant negative impact on mining activities. Therefore, detecting and quantifying NOx emissions is essential for designing effective blasts, analyzing their dynamics, and reducing contaminant production. Image processing and machine learning, including deep learning methods, have been applied to solve smoke plume detection and segmentation tasks. Most research has focused on smoke from campfires or forest fires, which are important for early fire and smoke detection. However, there is limited research on quarry blast smoke using machine learning methods, which presents challenges for recognizing the smoke plume from complex background scenarios and objects, including collapsed rocks, scattered soil dust and dirt, and the dynamic movement of the scene due to blast vibrations. Detecting NOx within the smoke plumes is further challenging because NOx must be distinguished from the overall smoke plume, as they share many common spatial features. To resolve this issue, we propose an ensemble method for NOx detection that combines smoke plume segmentation with NOx fume detection. First, we apply a smoke plume segmentation model to identify the smoke plume regions. Then, we use these masked-out smoke plume regions to detect NOx based on its unique color features. The first stage of the ensemble method helps block out complicated confusers in the background, such as reddish and brownish dirt. Next, we specifically design a color classifier for NOx to further improve its sensitivity. We evaluate the overall video-wise performance using accuracy, false alarm, and miss rates based on sampled image frames from videos. Additionally, we assess the mean Intersection over Union (mIoU) for smoke plume segmentation and the mean Average Precision (mAP) for image-wise performance from an algorithmic perspective. In summary, this paper represents the first attempt to apply machine learning approaches to NOx detection in a memory-efficient and time-efficient manner.

Jan 21, 2025

By Guo Ziqing, Tang Qiuming, Liu Yuanyuan

The channel-type non-mechanical stirring production process is a new developed technology for emulsion explosives in recent years. It removes traditional equipment such as mechanical-mixing emulsification, mechanical-mixing sensitization, matrix pumping, and explosive pumping, and has been applied in China. This technique achieves a fusion of higher intrinsic safety and lower cost, as well as the excellent quality of products and high efficiency of production. The emulsion particle diameter is about 0.5μm. The storage period of emulsion explosive produced with span-80 emulsifier is more than 7 months.

Jan 21, 2025

By Jorge Cárdenas, Alejandro Luna

In mining simulation for fragmentation results prediction is of utmost importance to study feasibility, ensure safety, and estimate the correct use of resources in drilling an explosive to meet requirements and avoid excessive usage. One critical case is fragmentation prediction, developed through models. Developing a fragmentation model in a mining unit aims to control blasting results to align theoretical and real data and improve correlation. Therefore, it is essential to collect post-blast fragmentation data, organize it, and systematically process it to develop a suitable model that meets variable requirements. Using a robust system of equations, this model should generate the required results with minimal variability between simulation and actual results. Additionally, this model must be adaptive to reduce this variability. Studying the most known and used models in mining resulted in our work correlating Cunningham 2006, Swebrec, and CZM models. Thus, the Simfrag model was created, presenting a robust foundation and combining the most notable advantages of the aforementioned models.

Jan 21, 2025

By Alejandro Berrios, Matheus DaSilva, Erick Siqueira

Vazante mine is an underground polymetallic mine that produces zinc, lead, and silver, which belongs to Nexa Resources in Minas Gerais, Brazil. The mine, a sublevel stope underground mine, mainly applies two subvariants: VRM – Vertical Retreat Mining and Open Stope. In a specific place of the mine, the geology allowed the design of a production stope with larger dimensions than the standard stopes, commonly called Super Stope. At this place, the plan was to apply both sublevel variants simultaneously. This mining block comprises rings in two different levels, with access by two ore drives on each level; the dimensions would be approximately 50 meters high, 50 meters long, and 35 meters wide. Opening the Free Face to mine the whole Stope was a challenge due to operational issues, such as hazard risks from loading over void space, exposure to uncontained places, and the impossibility of implementing the optimal blast sequence. Wireless blasting initiators have gained popularity recently due to their convenience, safety, and efficiency. This initiation system was applied to preload all the rings required to open the Free Face, ensuring a safe and optimal blast sequence. Wireless initiation prevented hazard risks, enhanced the blast sequence to guarantee the required void space, and optimized the equipment's operational cycle. The blast crew carried out the activity without exposure to the risk of loading over void space. The wireless detonators also avoided after-blast activities, which were required to provide secure access to the blast crew, optimizing the operational cycle.

Jan 21, 2025

By Scott G. Giltner, Alex Schwenk

An iron operation sought to extend the life of the mine by conducting a major pit pushback in an area close to several public structures and the neighboring town. The result of the pushback would make millions of tonnes of ore available for mining allowing many additional years of taconite mining. This paper discusses the initial development blasts conducted for the pit pushback. For the development blasts, it was determined that no fly rock should leave the mine site and that the blast vibrations should be as low as possible, but specifically under 19 mm/s (0.75 in/s) at a nearby sewage treatment plant. One issue complicating the blast design was the variation in hole depth within any given blast. For the initial sinking shot, the hole depths varied from 6.4 m (21 ft) to 12.5 m (41 ft). In the subsequent blasts the hole depths within each blast could vary up to 5.8 m (19 ft). Various tools were employed to design the blasts to ensure there was no fly rock and that the blast vibrations were as low as possible. UAV surveys of the blast areas were conducted to provide a 3-D representation of the free faces and bench surface. The 3-D point cloud produced from this was used to measure the shape of the free faces. Once the shape of the free faces was quantified, it was possible to establish proper placement of the crest holes and develop a custom explosive load for each blast hole. In addition, signature hole analysis was performed for each blast to determine the optimum delay time that balanced the need for minimal vibration, prevent fly rock, and a well fragmented muck pile. Electronic detonators were applied to achieve the necessary control of the blast that balances these three concerns. The results of the seven blasts conducted to date provided the desired results. The peak vibration level at the sewage treatment plant for the seven blasts was 10 mm/s (0.40 in/s). The only fly rock occurred when there was a miscommunication in the blast design resulting in under burdened holes on the front row. To date, the mine has been able to safely expand the pit into an area that will add many years to the mine life. The muck piles have been well fragmented with reports from the shovel that they have all dug well.

Jan 21, 2025

By J. P. Remi Proulx, Areli Rodriguez, Ruilin Yang

Historically, presplitting has been considered effective in reducing the impact of blast vibrations on highwalls. However, it remains a debated topic: how significantly can it protect highwalls, and is it worth the cost and effort to implement presplit blasting techniques? In hard rock, presplit blasting can leave half-barrels on the highwalls, clearly demonstrating its usefulness. However, in a fractured rock mass, the half-barrels from presplit blasting may not appear in most cases, leading to questions about its role in protecting highwalls. Previous studies in the literature used geophones to measure blast vibrations at far distances and could not ascertain the significant benefit of presplit blasting in reducing the impact of blast vibrations on highwalls. Additionally, no studies in the literature address the role of presplitting in alleviating blasting-released gas pressure that could penetrate joints and open new fractures in highwalls. Yang & Proulx (2019) and Yang et al. (2022) using near-field blast vibration monitoring of signature hole blasts have revealed that the peak particle velocity (PPV) of blast vibrations at a scaled distance of 1 m/kg^0.5 can be reduced by 50% or more for presplit-filtered vibrations. These results have been confirmed for both hard rock and fractured ground. In addition to summarizing the reduction in blast vibrations due to presplitting for both hard rock and a fractured rock mass, this paper demonstrates the relief of subsequent blasting gases after the detonation of blastholes. This is shown through video recordings of gas ejections from a row of empty previously fired presplit blastholes located 6 to 9 meters away from the detonation edge or final buffer row of a blasthole pattern. The results clearly show that presplitting not only lowers blast vibration PPV’s but also reduces the entry of the gases produced by the detonation process into rock fractures and or open joints.

Jan 21, 2025

By Mario Alvarez

Drilling with tricone drill bits is widely used in the mining industry with a direct impact on drilling safety and costs, however it can be challenging to implement a new supplier of tricone drill bits, choosing a new model of this accessory due to the normal variations of the rock mass or even due to the acquisition of new and modern drilling equipment for open pit blasting operations. This article identifies the most common mechanisms of failure in productive drill holes of tricone drill bits, both in open-pit coal and metal mines, in two South American countries. It also emphasizes the important issues that must be addressed for the optimization of the performance of these accessories, such as the correct identification of the rock mass, the drilling parameters, and the impact of autonomous drilling on new equipment with this technology. The article presents some of the successful actions to economically improve the performance of drill bits considering the close relationship in the field with the supplier's technical representatives and factory designers, as well as the commercial interrelationship between their respective business areas. The article concludes by discussing the future of tricone drill bit design development, its environmental management, and possible new advances in its manufacture.

Jan 21, 2025

By Jorge Blázquez, Paulo Couceiro, Patricio Vergara, Luis Martínez, Juan Navarro

This study introduces the X-2Mill solution, a refined two-step methodology aimed at optimizing blast designs by aligning explosive energy with rock properties. The approach employs the X-4Traits Model, which uses drill-monitoring data from both autonomous and manual drilling modes to develop two critical indexes: the Drilling Rock Factor (DRF) and the Drilling SAG Power Index (DSPI). The DRF integrates the Size-Energy Fan Model with rock fragmentation results and blast design parameters, while the DSPI adjusts Specific SAG Energy (SESAG) based on Bond’s theory, incorporating ore X80 results, SAG mill capacity (TPH), and power draw to estimate milling difficulty. To enhance prediction accuracy, the X-2Mill solution incorporates, to a Principal Component Analysis of the normalized drilling data, a Meta Machine Learning model with a 3D spatial function, accounting for information from surrounding drill holes. This integration improves the precision of the DRF and DSPI estimates. The methodology unfolds in two main steps: Step 1: Bench-Scale Pattern Design, involves defining the target P80 size for ore based on the SESAG and the DSPI. It also establishes target X80 sizes for waste and oxide materials and iterates to determine the optimal Burden x Spacing (BxS) using the Size-Energy Fan Model and the DRF. Step 2: Blast-Scale Selective Explosive Density/Energy focuses on refining explosive density on a hole-by-hole basis to achieve the specified X80 values for ore, waste, and oxide materials. The X-2Mill Solution was developed at Minera Escondida Limitada (MEL) using data from 162,761 blastholes across 356 blasts conducted over three mine expansions. This solution addresses the challenges of blasting harder and more difficult rock, particularly in the lower levels of the mine. By adapting the blast pattern and explosive density to the specific rock properties and ore/waste designation, the X-2Mill Solution aims to achieve precise size distributions and improve overall blasting performance. The results demonstrate that the X-2Mill Solution balances ore fragmentation to meet SAG mill throughput requirements while optimizing powder factor costs for waste material and maintaining digging efficiency. By efficiently distributing explosive energy, the solution not only enhances throughput but also improves blasting efficiency while ensuring stable slopes and minimizing fault activation.

Jan 21, 2025

By J. Rafael Otaíza, Francisco Mardones

This work has addressed the problem of creating a predictive model of the maximum particle velocities in the rock mass (PPV). The model designed specifically can model the subsequent vibrations of blasting based on geometric parameters, explosive loading, and the blasting process itself. Models based on artificial intelligence (AI) algorithms can find useful non-linear patterns to solve classification, regression, clustering, among other problems. They are flexible mathematical transformations adaptable to various objectives and types of data. With their different levels of abstraction, they can find a function that relates the input variables to the sought-after response. These models have been successfully used in similar contexts (Prashanth, (2018)) and have achieved state-of-the-art results in the field (Lawal, (2021)). The main challenge is to adapt them to the context of Chilean mines, in addition to including the geometric information of the blasting and the heuristic to obtain the set of optimal parameters, it is proposed to follow the work of (Simonyan, (2013)) and obtain "saliency maps" adapting it to tabular variables. We implemented an Artificial Neural Network (ANN) with a large number of neurons in the hidden layers. Models based on neural networks can find useful non-linear patterns to solve classification, regression, clustering, among other problems. They are flexible mathematical transformations adaptable to various objectives and types of data. With their different levels of abstraction, they can find a function that relates the input variables to the sought-after response. The literature shows that, for the problem of rock type identification, basic neural networks perform well (Simonyan, (2013)), but lack uncertainty estimates. This is a data-driven model, and in this sense, the model training was carried out using data from multiple operations in the large copper mining industry in Chile. In these databases, data consistency and the balance of the various independent variables that have the greatest impact on the model were ensured. With the above, the optimal hyperparameters of the model were determined, obtaining a predictive R-squared of 0.94.

Jan 21, 2025

By R. Alford

In the modern world of demolition safety is paramount and unnecessary or unquantifiable risks are not accepted (FasterCapital, 2024) and all risks must be kept As Low As Reasonably Practicable (ALARP) (BSI, 2017). This principle has led to a huge reduction in deaths in the last 50 years and the statistics continue to improve although this is starting to plateau (Beal, 2007). Under normal circumstances, this is now simply part of the normal way work is done and systems are in place to ensure both safety and economic profits are assured. What happens when the environment is less controlled and risks are unknown, such as after a natural disaster, war, an accident or a stand-up from a failed demolition attempt? A dangerous structure cannot responsibly be left alone with a fence around it so some action must be taken, but how can this be done safely and responsibly? An incident in Didcot, England in which half of a power station’s boiler house being prepared for an explosive demolition collapsed suddenly, killing four men in 2016 provides a useful case study of how technology, creativity and planning can be used to conduct complex demolition fully remotely to avoid any further risk to life.

Jan 21, 2025