Search Documents

By Sebastian Avalos, Julian M. Ortiz, Willy Kracht

Semi-autogenous grinding mills play a critical role in the processing stage of many mining operations. They are also one of the most intensive energy consumers of the entire process. Current forecasting techniques of energy consumption base their inferences on feeding ore mineralogical features, SAG dimensions, and operational variables. Experts recognize their capabilities to provide adequate guidelines but also their lack of accuracy when real-time forecasting is desired. As an alternative, we propose the use of real-time operational variables (feed tonnage, bearing pressure, and spindle speed) to forecast the upcoming energy consumption via machine learning and deep learning techniques. Several predictive methods were studied: polynomial regression, k-nearest neighbor, support vector machine, multilayer perceptron, long short-term memory, and gated recurrent units. A step-by-step workflow on how to deal with real datasets, and how to find optimum models and final model selection is presented. In particular, recurrent neural networks achieved the best forecasting metrics in the energy consumption prediction task. The workflow has the potential of being extended to any other temporal and multivariate mineral processing datasets.

Jun 16, 2020

By B Laidens, D Souza, W Bielefeldt

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

Jun 19, 2024

By Maral Malekian, Pat Bellett, Eranda Tennakoon, Fernanda Carrea, Moe Momayez

Slope instabilities in open-pit mines pose a safety risk to workers and a financial burden on production. The direct impact of slope stability on safety and production makes slope failure predictions one of the important challenges in the mining industry. Predicting the precise time of slope failure has been the subject of much research in conjunction with the development of innovative monitoring technology designed to prevent sudden failures. This paper investigates the use of AutoRegressive Integrated Moving Average (ARIMA) model to predict the time of slope failure. Input data such as inverse velocity (IV) and dimensionless inverse velocity (DIV) from 20 slope failures were used to train the model predict the failure time. For comparison purposes, the time of slope failure using the traditional inverse velocity method is also provided. We show that ARIMA provides 90% more accurate predictions than the TIV approach.

Jul 12, 2023

By P M. Hetherington, F A. Pym, M P. Murphy, K E. Crook

Consultants in the mining industry have the opportunity to visit interesting deposits all over the world. Each deposit has its own set of challenges to face when it comes to defining and understanding the deposit geology and the economics to make it viable for extraction. Some of the challenges can include appropriate data capture, sampling techniques, structural characteristics, geochemistry, geophysics, lithology definition, and economic boundaries. It is essential that the practices used at each deposit (eg drilling, sampling, geological modelling, resource estimation etc) are documented and the results obtained are robust and defensible. The Competent Person is not always aware of instances where their resource estimation practices have not been substantiated. ‘You don’t know what you don’t know’ is a phrase frequently used during a mineral resource audit. Technical work to substantiate drilling, sampling, density, assaying, geological modelling and estimation processes is not always completed. Audited Competent Persons often comment: • ‘I was unaware that this was required.’ • ‘I have not had training in this area and do not know how to complete the checks required.’ • ‘This is how we’ve always done it.’ Examples of audits where it was found that geological practices were not substantiated are examined here. A discussion is included on why substantiation of these practices is important, and potential reasons as to why there are instances of unsubstantiated processes and practices are discussed.

Mar 22, 2022

By B P. Voutharoj, R A. Dutch, M Paknezhad, T Ostersen

With the proliferation of new sensor technologies, acquiring multiple data sets over the same ground is becoming cheaper and easier than ever. This new, higher resolution multivariate data provides a significant resource for exploration and resource geologists but comes with the added complexity of effectively integrating the various data sets in useful and meaningful ways to elucidate new geological understanding. Both geophysical data sets and hyperspectral data are extensively used for exploration targeting, providing different information at different resolutions and crustal scales. One of the biggest challenges comes from trying to effectively integrate data sets that record very different physical properties, across the different scales these data are captured at, in a way which can allow for a data-driven analysis of these combined data sets.

Sep 1, 2024

By S. Frimpong, D. Ali

For achieving bulk economic excavation, large dump trucks are being used in majority of the earth moving operations resulting in high impact shovel loading operations (HISLO) which exposes the operators to high levels of whole body vibrations (WBV). As the truck ages, hydro-pneumatic suspension struts loses their capability to effectively attenuate the vibration. A system is required to monitor and predict the performance of the suspension struts in real time. Machine learning and artificial intelligence (AI) has been applied for modeling and predicting the suspension system performance for lighter/smaller vehicles. However, no work has been done to implement machine learning or AI for modelling and predicting the performance of hydro-pneumatic struts in large dump trucks. Therefore, current work is going to be a pioneering effort towards developing machine learning and AI models for solving this problem. Support vector machine (SVM) and regularized dual non-linear regression has been implemented in order to achieve the goal. 3D virtual simulator for CAT793D was used to conduct experiments in MSC.ADMAS environment. The two main recorded outputs were the RMS accelerations in the vertical and horizontal directions at the operator seat for characterizing the performance of the suspension system. During the development and the training of the models, eighty percent (80%) of the total experimental data was used and the remaining 20% was used during the testing and validation of the developed models. SVM model showed the desired accuracy in terms of hydro-pneumatic suspension system performance prediction for large dump trucks. These models can be implemented in the dump truck controller which can then be used to monitor the performance of the suspension system in real-time, and with that proper maintenance and/or replacement can be scheduled by the maintenance personnel. Workplace safety, operator’s health and the overall system efficiency can be greatly improved with an implementation of such an intelligent system. INTRODUCTION Large capacity dump trucks are being employed in any earth moving operation throughout the world for achieving bulk economic excavation [1, 2]. A large dynamic impact force is produced with large capacity shovels dumping material weighing 100 tons or more in to the dump truck under gravity. This dynamic impact force generates high frequency shockwaves which travels throug0068 the truck body, chassis and reaches the operator’s cabin and thus exposes the operator to severe levels of whole body vibrations (WBV). Recommended safe limits have been listed by the International Standards Organization (ISO) in sections 1, 2, 4 and 5 of ISO 2631 (1997, 2003, 2001 and 2004). An operator can got through a long term back, shoulders, arms and neck disability and disorders if exposed to the WBV levels beyond those limits. The dynamic impact force generated as a result of the high impact shovel loading operations (HISLO) was modelled by Ali and Frimpong [2]. Furthermore, the complete methodology for optimizing the dumping process and reducing the impact force has been provided by Ali and Frimpong [1]. The vibration attenuation system present in the dump truck requires improvement in addition to the dumping process optimization. The vibration attenuation system in the dump truck commonly consists of hydro-pneumatic suspension struts. As the dump truck ages, its suspension system deteriorates and therefore loses its capability to effectively attenuate the shockwaves and the resulting vibrations produced by the dumping process. The deterioration tales place due to the contamination of the hydraulic oil or oil and nitrogen mixing or due to the gas accumulator diaphragm rupturing. The monitoring of the output vibration levels can be used to evaluate the effectiveness of any suspension system. With the dump truck suspension system, the vibration levels at the operator’s seat can be used for the evaluation of the effectiven

Jan 1, 2019

By K. KAKLIS, O. SAUBI, Z. Agioutantis, R. JAMISOLA

Three-point bending (TPB) tests were conducted on prismatic Nestos marble (Greece) specimens. The specimens were instrumented with piezoelectric sensors, and comprehensive recordings of acoustic emission (AE) signals were obtained. Machine learning in the form of artificial neural networks (ANNs) was then applied in an effort to investigate whether specimen load evolution can be predicted as a function of AE signals. A number of ANN models were developed, and the optimum model was selected based on the highest coefficient of determination (CoD) value as well as the lowest root mean square error (RMSE) value that was calculated for each model. The best performing ANN model exhibits accuracy above 99% with an RMSE value below 4%. It can be concluded that ANNs can potentially be applied to predict rock behavior under load especially when such loads lead to failure.

Sep 7, 2022

By S McGregor, J Sharp, I Entezari, T Boulter

The piezocone penetration test (CPTu) is one of the primary screening tools used by the mining industry to evaluate whether tailings are susceptible to liquefaction (static or cyclic). Liquefaction analysis using the CPTu is influenced by the fines content of the soil, and most CPT screening tools empirically use the behaviour type index (Ic) to correct for fines. The issue with this approach is that such empirical relationships have been developed using data collected from natural soils and their applicability to different tailings deposits needs to be studied. In this paper, we explore the use of machine learning to develop a site-specific model to estimate fines content of tailings using gamma piezocone penetration testing (GCPTu) measurements. The results are then compared to the fines content derived from the soil behavior type index (Ic) proposed by Robertson and Wride (1998). A dataset of paired GCPTu and laboratory results were compiled and a support vector machine (SVM) algorithm was employed to calibrate a model to estimate tailings fines content from in-situ GCPTu data. We calibrated GCPTu data to geotechnical 75 μm fines content measured in the laboratory. The geotechnical fines content is the fines content as a percentage of solids. The development dataset was comprised of paired GCPTu-laboratory results collected in 2009-2019 from a mining area with predominately clay mineral and quartz sand tailings. Results show that the developed model predicts the geotechnical 75 μm fines content of the studied deposits with 7.8% error. The Ic based method estimates the fines content with 31% error. Evidently, the Ic method is not applicable to the studied tailings deposits. It is appreciated that many tailings fines do not contain clay, and that the success on this program may not be repeatable everywhere. However, the authors wish to point out that the application of site-specific machine learning algorithms may be used to significantly improve empirical geotechnical parameters.

Jul 1, 2021

By J. Peck, F. Brackebusch, M. Scobie

"A number of alternative strategies exist to improve narrow orebody stope productivity and safety through mechanization. Particular attention is given to one of these: the development of an in-stope mining machine. This paper summarizes those characteristics of vein orebodies in Canadian mines which are considered to govern such mining machine design. It then reviews past and current attempts to develop hardrock mining machines which could potentially be applicable to narrow stope widths.IntroductionSerious interest is mounting to exploit new technology in the development of methods and machinery to stope narrow, hardrock, orebodies. The motives relate not only to the foreseen need to maintain or reduce production costs, but also to considerations of manpower availability, safety, ground control, ore recovery and dilution. This also follows the demonstrated success of technology application in larger metal orebody stoping, where machine development has been seen to lead to improved productivity as well as the future prospects of continuous mining systems and eventual automation, e.g. ITH blasthole drill development and bulk mining. This paper deals in particular with machine design for ore fragmentation in narrow, hardrock orebodies. It is considered that such machine design closely interacts with the over-all stoping method design and that both require consideration in parallel to ensure success in mechanization."

Jan 1, 1990

By George Jones

MACHINE mining on the pitch plays an important part in the produc-tion schedule at the Salem Hill Colliery of the Haddock Mining Co. This mine is just outside the city of Pottsville, in Schuylkill County, along the southern border of the Anthracite Region. The entrance to the mine is through a cross-measure tunnel 15 ft. above water level and running north 1500 ft. until it strikes the Rabbit Hole vein, where the machine mining is carried on. The main slope, dipping south, was sunk 1200 ft. in the Rabbit Hole vein with levels turned off at 300-ft. intervals. The vein is from 24 to 30 in. thick on a varying pitch of 20° to 40°. The overburden has differed from 50 to 466 ft., the most recent work having the maximum overburden. Immediately over the Rabbit Hole vein is a seam of soft sand slate from 1 to 4 ft. thick which presents a problem at times because it dis-integrates rapidly when exposed to the air. It will crack up and fall without any audible warning, therefore the workmen must always be on the alert, watching for loose slabs. The main top is sandstone, vary-ing in thickness from 8 to 20 ft. The bottom rock is similar to the top, but is finer grained and subject to a more complete disintegration. The vein has a 3 to 4-in. shelly band along the bottom, and all under-cutting has been done in this soft band.

Jan 1, 1935

By L Mottola

Three decades ago mining companies, principally in North America, aided by machine and explosive manufacturers, started significant attempts to develop and implement automated mining systems, mainly underground. These tended to be motivated by decreasing cost, increasing productivity, reducing labour requirements, and improving safety. These are important business drivers, however, little attention was given to the underlying goal of mining automation, namely to bring upstream processes in control and reducing variation, as seen in downstream mineral processing plants.This paper first reviews the nature of Lean Thinking and its application in the context of the growing commitments by industry to develop future automated mine production systems. The paper then makes reference to prior and current experiences in open pit blasthole drill and shovel performance monitoring, to demonstrate the principle that machine performance data offers as a means, not only to characterise the dynamic geological and working environment, but also to provide a foundation for automation. In this case, drill and shovel monitoring was originally motivated as a means to optimise blast fragmentation through more effective drill and blast designs that are based on an accurate determination of the bench geological and geotechnical characteristics, hence managing variation in the drilling and blasting process. This paper considers how automating and integrating such components of the mine production system would bring processes into a controlled state, creating value at the face, within a framework of Lean mining.

Nov 22, 2011

By C. Hendricks

This paper is based upon field studies conducted in a western Canadian open pit coal mine. This work has involved the adaptation of microprocessor-based instrumentation to monitor various operating parameters on-board blasthole drills and mining shovels. A review of instrumentation and monitoring methodology will first be presented. Based upon experience from field-based studies, the paper will subsequently focus on the application of monitoring technology within the framework of an integrated Equipment Monitoring System. Such a system will permit the real-time performance evaluation of key equipment involved in surface mille production.

Jan 1, 1991

By J. Sajkiewicz

In a synthetic way discussed are certain results of papers realized at the Wroclaw Technical University in a field of the theory of exploitation of machine systems with conveyor-belt transport. The attention is paid to the two lines in these works which are concerned with the development of analytical as well as simulation methods, in both cases realized with the help of digilat computers.

Jan 1, 1977

By I. Ocak

Initial investment for mechanical boring of tunnels is found to be high in most cases. Conventional drilling and blasting is not the possible especially in urban area. In these conditions impact hammer offers many advantages over conventional drill and blast techniques and boring tunnels. These include improved safety, minimal ground disturbances, elimination of blast vibration, reduced ventilation requirements, reduced cost etc. Therefore, hydraulic impact hammers have been used widely in metro tunnelling projects in Istanbul since 1992. Accumulated and published data from various tunnelling projects serve to improve predicting the machine performance and scheduling of job duration. This paper is prepared under this objective. Machine utilization time of impact hammer was evaluated in this study. The main rock formation named Kartal formation arepaleozoic aged sedimentary rocks, shale, sandstone, siltstone, andesite dykes and sediment fillings. The first stage of the project is commissioned to Yapi Merkezi- Yuksel- Dogus- Yenigun- Belen consortium.

Jan 1, 2011

By G. R. Forbes

Flotation froth machine vision systems provide consistent real-time measurements pertaining to the state of the flotation cell being monitored. Typical measurements include froth velocity, froth colour, froth texture and froth stability. This paper presents the results from test work conducted on the molybdenite rougher circuit at the Kennecott Utah Copper Concentrator during February 2006. Machine vision results show that it is not possible to accurately determine bubble size distribution information for the molybdenite froth, despite using state-of-the-art methods. Instead, it is necessary to make use of texture measurements to classify the various different froth states. Numerous combinations of texture measurements and classifiers are used to determine the best combination. Results show that the Fourier ring based texture measurements perform the best when both K nearest neighbour and Gaussian mixture model classifiers are used. The concentrate grade of the flotation cell is modelled using combinations of froth velocity and froth texture descriptors. The results show that by using a linear combination of these descriptors rather than either one by itself it is possible to account for a much larger percentage of the variation observed in the concentrate grade data. Adjusted R2 values of 92% and 84% are achieved when modelling the copper and the molybdenite concentrate grade respectively.

Jan 1, 2014

By R. J. Robbins, D. L. Anderson

A tunnel boring machine has potential use in al- most any type of mining where the access shaft (or adit) is large enough or can be made large enough for its initial entry and where the orebody is of sufficient size to warrant its use. Some time will inevitably be lost in negotiating curves or making lateral moves and moving from level to level. Nevertheless, if the orebody is sufficiently large, advance scheduling can minimize the lost time encountered in such moves. Ideally, a mine will be planned for the use of these machines, thus eliminating access and transport problems. From the viewpoint of time involved, the rate of advance by boring as compared to conventional means is worthy of review. For instance, the Blanco Tunnel, one section of the Bureau of Reclamation's San Juan-Chama Project in southern Colorado, was bored in competent sedimentary rock with the following performance:

Jan 7, 1967

By A. Adhikari, P. Tukkaraja, S. Jayaraman Sridharan

Shafts are critical components of the mine ventilation systems and contribute significantly to the mine ventilation pressure. Estimation of shaft pressure losses is an important aspect of mine ventilation planning and shaft frictional pressure losses are extensively studies. Shock losses contributed by shaft buntons are estimated using the interference factor model developed half a century ago. This study aims to develop a better performing prediction model for shaft buntons using state of the art experiment and numerical data, and machine learning techniques. Results show that the present prediction model is performing poorly, and the prediction performance can be improved by incorporating additional predictor variables. The Artificial Neural Network standardized Machine Learning model developed in this study is able to predict the shaft bunton shock loss with high accuracy (R2 = 0.956).

Jun 25, 2023

Control dust generated during mining in salt mines. Approach A machine-mounted exhaust ventilation system which moves with the cutting machine from place to place was developed. The system captures the dust at the face of the heading and exhausts it downstream of the heading in the crosscut. This helps cause fresh air from the crosscut to flow over the machine operator's position, and aids in keeping the dust cloud close to the face. How It Works The system consists of (1) a circular intake hood with a 10-inch slot extending 250 degrees around the base, bolted to the gearhead; (2) 20-inch-diameter wire-wound flexible ducting to connect the intake hood to the fan (25 ft. is allowed sufficient slack for bar movement); (3) an industrial exhaust fan capable of generating 10,000 cfm with 13 inches water gage pressure at 1435 rpm; and (4) 150 ft. of collapsible 24-inch tubing for the exhaust duct which is de-played and returned In each heading by the cutter operator and/or his helper.

Jan 1, 1983

By G. Kris Kapoor

Each new period of public concern, whether rooted in things political, social, economical, or technological, brings with it new words or phrases which highlight that new interest. With people's awareness of our rapid depletion of readily available energy sources and the enormous increase in energy .costs came the new, and now often heard, terms "energy intensive", "energy sensitive", and "energy conservation". Since its birth in 1926, Fuller Company had been directly associated and involved with energy intensive products and processes. We are located in the heart of the Cement Industry. Many of our products and processes are geared to the needs of the portland cement manufacturer, and a look at the inferno within an operating cement or lime kiln will certainly convince anyone that here is an energy intensive process. Fuller Company, then, has always been energy sensitive. Process kilns, hard rock crushers, tube and roller mills, fluid bed thermal reactors, pneumatic compressors and conveyors, material coolers - all are Fuller Company products utilizing or transferring large amounts of energy. Consequently, much of our success in the marketplace depends on how wisely we design and plan for efficient use of power and for conservation of each unit of heat available.

Jan 1, 1975

By A. Smithson

It is generally accepted by British mining engineers that coal will continue to be worked by the. advancing or retreating longwall system for the foreseeable future. At the coal face, the emphasis will be on better machine utilization; increased equipment reliability; modular design and more standardization; remote control and monitoring; and a continuing drive to increase productivity and safety. Improvements at the face can be sustained only if there are corresponding improvements in efficiency elsewhere in the mine. Coal handling systems, for example, must be able to accept increased tonnages without creating bottlenecks. As workings move further from the shafts, the time taken to transport men and materials must be kept within reasonable limits. Development drivages must he on schedule to be ready for the planned opening of new faces, and face ends must keep up with faster moving faces.

Jan 8, 1981