Search Documents

By Sylvain Létourneau

Help organizations maximize the benefits of the data that they collect ? perform scientific research in: machine learning, data mining, statistics, artificial intelligence, soft computing, information retrieval, information systems, and natural language processing ? preferred application areas: Equipment Health Management, Bioinformatics, Health, Web Mining ? today?s talk limited to Equipment Health Management While the aircraft is still in the air, IDS: ? clusters relevant WRN, FLR, and snag (pilot) messages ? identifies probable causes based on TSM and provide links to corresponding TSM pages ? assesses MEL conditions (GO, NOGO, GOIF, ?) ? displays relevant maintenance history, suggests fixes based on similar cases ? Commercialization with MxI Technologies Ltd and Air Canada in 2000

May 1, 2008

By E Ben-Dor, D Bakun-Mazor, Y Ben-Ari

Determining the mechanical properties of rocks is important for various civil engineering fields, including the mining of raw materials for aggregates used in the construction and paving industries. Traditionally, the mechanical properties of rocks are obtained through in situ and laboratory tests during geotechnical surveys. However, these time-consuming surveys involve many resources. In contrast, hyperspectral remote sensing methods make it possible to identify the mineralogical composition and crystallographic structure of the rock; properties that control the mechanical properties of the rocks. In this work, we characterise the mechanical properties of carbonate rocks by using a hyperspectral sensor in laboratory conditions. We collected about 150 cylindrical samples of carbonate rock, with a wide range of strength values from several rock outcrops in Israel. We used a point spectrometer in the range of 0.4–2.5 μm and a spectral image sensor in the range of 3.0–12.0 μm, scanning the samples to obtain the signature of their light reflections and spectral emissivity. We then measured the samples’ density, porosity, water absorption, and uniaxial compressive strength (UCS). We used sophisticated data mining to find statistical relationships between the hyperspectral signatures of the samples and their mechanical properties. We used this data to identify the most dominant wavelengths for predicting mechanical properties. We found that the density, porosity, and water absorption of carbonate rocks could be confidently predicted based on spectroscopy data, while the UCS of the rock could also be predicted, but less significantly. The results of the study pave the way for the development of measuring tools for the mechanical properties of rock, based on non-destructive tests of quarrying materials.

Nov 29, 2022

By S. Dessureault, M. Yildirim

More mining companies are now investing in IT, including updating one of the traditional IT process control tools used in the mining industry: real time in-pit truck allocation control and monitoring systems, or fleet management systems (FMS). These systems have been used to maximize the overall mine production by improving equipment utilization and reducing production costs. Most modern operations monitor the in-pit operations using GPS and wireless communications to produce data. Improvements in bandwidth, sensors, and computing power are causing modern systems to become more complex and generate more data. However, human analysis by simple regression or table generation in spreadsheets of the data is becoming impossible. Data mining solves this data management problem. Data mining finds patterns and relationships in very large data sets. This paper describes the application of modern data mining techniques on truck dispatching systems in a real open pit hard-rock copper mine. The analyses conducted included determining how the trucks performed under particular conditions and allocation systems. The long-term benefits of this work are to identify strengths and improvement opportunities in truck assignment systems and establish the skill sets and IT infrastructure needed in undertaking more complex datadriven technology such as a truck dispatcher trainer.

Jan 1, 2007

By B L. Dickson, E, M F. Lee, P A. Mikula

Computational techniques are needed to assist in the analysis and interpretation of the increasing amounts of geoscientific and mining related data and information that are routinely gathered at mine sites. New interpretation methods are needed to provide an integrated approach so as to establish relationships (cause and effect) or to be predictive about possible outcomes based on acquired data. Traditional multivariate statistical methods are often confused by variable relationships that are non-linear, data distributions that are non-normal, and by the data themselves that may contain missing values, text and both continuous and discontinuous numeric values. Modern data mining methods are available to understand the relationships within and between diverse data sets, and identify relationships or trends associated with processes, measurements and mine design parameters in mines. The self-organizing map (SOM) is a data mining approach with the advantage that all input data samples are represented as vectors in a data-space defined by the observations (variables). The SOM procedure is an exploratory analysis tool that highlights patterns and relationships. Results are internally derived, in an unsupervised fashion based on measures of vector similarity. Our SOM outputs are highly visual, which assists in understanding and illustrating the dataÆs structure and internal relationships. Two studies are presented. The first uses SOM to investigate the relationships between a range of measured and derived rock property parameters and their observed behaviours during mining. Our aim was to determine whether a SOM analysis would allow a better understanding of observed and predicted rock behaviours from their rock properties. The SOM analysis showed that there were indeed relationships between æbrittleÆ, æsugaryÆ, æslabbyÆ and æsqueezingÆ rock behaviours and a number of the input parameters. The computed SOM æstructureÆ was then used to assess the likely behaviour of unknown samples by assigning them into behavioural fields based on their measured and derived geotechnical responses. The second study was aimed at assessing whether a SOM analysis of microseismic data at the Kalgoorlie Consolidated Gold MineÆs (KCGM) Mt Charlotte mine can contribute towards understanding and potentially forecasting/minimising seismicity at the mine-design stage. The database comprised 40 sample æclustersÆ of microseismic parameters from the MS-RAP software package, which were derived from 2500 individual seismic events. The SOM analysis showed that some of the initial mining conditions are related to the seismic parameters. In each of the studies, the SOM procedures assisted in understanding the data and provided new insights. Because of its æordered vector quantisationÆ foundation, the SOM procedure is a substantial improvement over traditional statistical methods in three main areas:its ability to analyse data from disparate sources, including different data types; its ability to analyse sparse data sets with missing values; and its ability to analyse and visualise non-linear relationships within a data set.

Jan 1, 2006

By S. Dessureault

The relatively recent explosion of available data in all business sectors has induced a common expression of “drowning in data, starving for information.” The mining sector is affected by the information age through equipment-based sensors, process monitoring, and traditional enterprise data sources. Information technologists have developed techniques such as data mining that apply new and old statistical algorithms to large datasets. Mine planners and managers can apply these tools for improved planning and control, thereby increasing the use of the highly underutilized information system infrastructure in most modern mines. This paper describes the use of data mining and its enabling technology, data warehousing, in the development of an energy consumption model for large surface mines using real historical data.

Jan 1, 2007

By Austin Metz, Kevin Stanton, Ramin Motamed

"A recent study calibrated Load and Resistance Factor Design (LRFD) resistance factors for local soil conditions in the Las Vegas Valley. As a part of this calibration, an extensive database of drilled shaft load tests and associated subsurface soil information were collected and compiled. This database, deemed the Nevada Department of Transportation Deep Foundation Load Test Database or NDFLTD, was designed with the presentation of load test data, the subsurface soil conditions, and the spatial distribution of the data in mind. In addition, the NDFLTD was developed in a way that allows additional data to be added as it becomes available. As such, the rules of database normalization were followed to allow for additional and different types of data to be added to the database and reports. Microsoft Access was chosen to present the data because it is easily accessible to anyone with Microsoft office software, it has a quick learning curve, and it has the ability to present a relational database. The largest obstacle faced when creating the NDFLTD was normalizing the data used in the LRFD calibration, with the goal of reaching the 5th normal form.INTRODUCTIONLRFD is based on statistical performance of engineering components, as opposed to the more traditional Allowable Strength Design (ASD), which divides the strength of a component by a safety factor. Calibration of resistance factors for LRFD requires a robust statistical analysis of past performance. For drilled shafts this requires a database of full scale load tests (Abu-Hejleh et al. 2014). The FHWA developed the largest US based deep foundation load test database, deemed the DFLTD, collecting data from 1985 to 2003 when funds ran out (Abu-Hejleh et al. 2014). Recently, the DFLTD has been updated to modern standards (Petek et al. 2016). In October of 2007, the FHWA mandated state department of transportations (DOTs) to follow AAHSTO LRFD guidelines for their highway foundation designs (Abu-Hejleh et al. 2014). Since then multiple state DOTs have developed their own, region specific deep foundation load test databases. Florida has a long history of developing databases for deep foundation LRFD resistance factor calibration, with the two main databases being the FL database, and The Deep Foundations Database (Abu-Hejleh et al. 2014). Iowa developed a Microsoft Access based database in 2014 (Garder et al. 2014). Oregon developed a database compiling pertinent data from the DFLTD, Florida DOT’s Deep Foundation Database, as well as from other databases (Smith et al. 2011). Illinois developed the “International Database” for static and dynamic reliability based calibration (Long et al. 2009). Louisiana developed a database for LRFD Calibration of driven piles in 2009 (Abu-Farsakh et al. 2009). The California Department of Transportation has its own internal foundation database, which is housed within the Foundation Testing Branch archive (Smith et al. 2011). In 2016, the Nevada Department of Transportation (NDOT) presented its own LRFD calibration for the Las Vegas Valley (Stanton et al. 2017), and the NDFLTD was developed as a part of that project (Motamed et al. 2016)."

Jan 1, 2017

Jan 1, 1915

By A. N. Diehl

IT is the object of this paper (1) to deal with the elements in blast-furnace gas from the standpoint of their importance, and the part they are to play in future consumption, and (2) to give detailed information about the construction and operation of a plant designed among the first in this country for washing gas on a large scale.

Jan 5, 1914

By Ken Witherly

Modern airborne EM surveys typically acquire more data than is processed or analyzed at the time of acquisition Suitable additional processing can provide more diagnostic information, thereby allowing for more effective ranking and hopefully, follow-up of outcomes

Apr 1, 2005

By Shankar Narasimhan

Data Reconciliation is a technique that has been developed more than fifty years ago and has been refined over the past few decades and is now being deployed routinely in several process industries such as refining, petrochemicals, mineral processing and hydro-metallurgy. The main aim of data reconciliation is to obtain accurate estimates of all process variables and parameters using plant measurements that are invariably corrupted by random errors and may also contain biases and other gross errors. These reconciled estimates are subsequently used either in offline exercises such as simulation, retrofitting, and de-bottlenecking or in online optimization and control applications. In this presentation, a brief history of data reconciliation, its assumptions, and uses are reviewed. New developments in this area are highlighted such as robust data reconciliation to handle model uncertainties, and reconciliation using identified models derived purely from operating data. Several case studies in the mineral processing industries reported in the literature are also highlighted to indicate the potential benefits of this technique.

Sep 1, 2012

The objective of the paper is to develop a material balance calculation procedure for a production unit involving two plants separated by a pipeline. The case study is taken from the oil sands industry. The raw sands are first mixed with water in a conditioning plant, then transported through a pipeline to an oil extraction plant. The combination of pipeline dimensions and nominal throughput creates a significant variable time lag between the two plants. As usual, mass balance calculations required for the evaluation of plant performance indicators, such as bitumen recovery, are inaccurate due to measurement errors. In addition, in the present case study, the time lag of the pipe creates an additional source of uncertainty, which may lead to misinterpretations and wrong decisions. Raw data are usually reconciled through steady-state mass balancing, to correct for measurement errors. However, because of the significant pipeline dynamic lag, standard steady-state daily mass balance may fail at giving an appropriate picture of the operations. The proposed solution to the data reconciliation problem includes the use of a pipeline plug-flow model in the mass balance calculation. To fulfil the industrial constraint that current data reconciliation must not modify past reconciled values, while still satisfying dynamic constraints, a daily one-step method, i.e. a unitary filter-ing horizon, is recommended. The method is illustrated with simulation data, and the results com-pared to those of standard data reconciliation methods.

Jan 1, 2014

By K. El-Ouassiti, M. Zouadi, C. Bazin, D. Hodouin

Data reconciliation techniques are used to attenuate the effect of measurement errors and estimate unmeasured variables. This paper illustrates the application of data reconciliation to hydrometallurgy processes using measurements from leaching and solvent extraction obtained from laboratory experiments. The application of data reconciliation provides an efficient way to detect gross and systematic errors and produces reliable performance indices for process evaluation.

Jan 1, 2005

By A. Alfantazi, M. Mahon

The current efficiency in zinc electrowinning is a key indicator of the performance in a cell house. This is typically measured by comparing the weight of the cathode to the electric current applied over the deposition period. This calculation can be cumbersome because the deposition history of each pulled set of cathodes will be unique. It will depend on the applied current and electrolyte conditions from onset of deposition until the cathode is removed and stripped. Not accounting for these can introduce errors to the calculated current efficiency. To track this history and reconcile the current efficiency, a time based computer process simulation was made of an industrial cell house. Two months of hourly recorded measurements from the cell house were input to the simulation, including current to the cell houses, concentrations, flow rate, and temperature of the purified leach solution. The simulation’s predictions of the concentration of zinc in the circulated, spent, and returned electrolyte all showed good agreement with the industrial data over the two months giving a validated zinc balance. The simulation was then tuned to predict the instantaneous current efficiency for all times, as well as the expected masses for the deposits given their deposition history.

Jan 1, 2014

By Gerald V. Jergensen

Does an idea have merit? What does it cost to implement? Can the concept be implemented successfully? The ultimate proof is to try, then see. However, when there are many millions of dollars at stake, blindly building and trying requires considerable courage. Owners and investors in retrospect might choose other less complimentary words. So we might ask, "How might we establish the feasibility of an idea or concept before committing large sums of money to the ultimate test?" From this basic and prudent question, has evolved the engineering concept of the feasibility study. A feasibility study is simply a systematic evaluation of an idea or concept to determine the prospects for success. In a literal sense, a feasibility study considers an idea in terms of its data base, "builds" the idea on paper, "operates" that idea, calculates the cost and benefits, then measures the probable success in terms of some economic, technical or financial standard. Feasibility studies can be quite modest in scope yet provide useful insights as to the viability of an idea. A study might be initiated only to examine the completeness or validity of the metallurgical data base. Another study could be a search for a workable idea or solution to an already-identified possibly troublesome problem. In this latter case, the question, "Will it work?" may be far more important than, "How much will it cost?" Feasibility studies are sometimes global in scope, involving several dozens of specialists and examining an entire "grass roots" mining complex. Other studies may be less ambitious but equally important in examining an expansion proposal or developing new operating techniques. Studies may be commissioned to remove plant bottle-necks, solve maintenance problems and so on. The terms study and feasibility study are used interchangeably in this chapter. They denote a systematic method to examine a proposed concept or idea. DATA BASE Typically, studies are initiated with a minimum amount of specific information and a maximum number of assumptions. As the work proceeds and the data base expands, assumptions are replaced

Jan 1, 1982

By Dale R. Ralston, Roy E. Williams, Gerry V. Winter, George L. Bloomsburg

GENERAL STATEMENT The primary objectives of any field data gath¬ering effort should be to (1) identify and gather the data necessary for the project and (2) obtain the data in a state-of-the-art manner. All too often the initial field data are collected both areally and tem¬porally in an illogical manner without the guidance of a conceptual model of the ground water flow systems involved or even a review of existing geo¬logic literature on the area of interest. The initial data collected frequently are of limited value while necessary basic reconnaissance information is miss¬ing. Initial field data should be collected with the intent of developing a hydrologic overview of the potential mine site and surrounding area. Ob¬viously, one of the initial objectives is to define the area requiring a hydrologic investigation. The data requirements should be identified by the time frame in which collection should be made and by the corresponding increase in sophistication of the data requirements with development and operation of the mine. The data requirements are summarized in Table 1. INITIAL LEVEL SITE INVESTIGATION Area Determination The initial task of any hydrogeologic investi¬gation is to determine the boundaries of the area requiring study. Obviously, the site of the proposed mine is included in the study area. The areal extent beyond the site may be determined from an eval¬uation of existing geologic and topographic maps. Those formations that overlie the ore body, the formations containing the ore body, and the formation(s) that lies immediately beneath the ore body are of direct concern for proper site recon¬naissance. Additional formations below the ore body may require study depending upon their thick¬ness, hydraulic conductivity, and degree of inter¬connection with the mine workings. This initial viewpoint identifies hydrostratigraphic units based strictly on geologic concepts such as mineralogy and structure. Formation outcrops, synclines, an¬ticlines, faults, and fracture and joint patterns are used to delineate the area of the site reconnaissance. The simplistic hydrogeologic environment (il¬lustrated in Fig. 3, chapter 2) requires that field data be collected via test wells and/or geophysical techniques. This approach is necessitated by the lack of surface features such as formation outcrops, streams, and springs. Fig. 5 (chapter 2) illustrates a slightly more complex hydrogeologic regime. The potential mine sites at locations A, B, C, D, and E each intercept a different ground water flow sys¬tem or combination of flow systems. Therefore, each mine location requires that a different area and size of area be investigated. A more complex geologic setting as illustrated in Figs. 6 and 7 (chapter 2) may be approached differently. The area included for the site recon¬naissance should encompass sufficient surrounding area to include the outcrops of those formations suspected of being influenced by the future mine. Even adjacent areas not suspected of being influ¬enced may be investigated if the formations of in¬terest crop out in those areas. Such an extension of the area of investigation would provide a greater regional understanding of the hydrogeologic properties of the formations (hydrostratigraphic units) of interest. Geologic Investigation The initial step before conducting the site re¬connaissance is to review all existing literature on the geology of the area. Existing information should be augmented with new exploration data on the dip, strike, thickness, and lateral extent of the for¬mations in the area. Exploration hole logs should be reviewed for indications of lost circulation, rub¬ble zones, and water producing zones. Existing aer¬ial photos such as those available from the US Department of the Interior, EROS Data Center,

Jan 1, 1986

By Jeffery L. Kohler, Harvinder Singh, Jon G. Bredeson

A survey of electromagnetic noise reports was performed and a summary of the results are given. Industrial concerns were surveyed for techniques to minimize the effects of electromagnetic noise and are presented. The common types of communication links used in mines today are presented. A mathematical development was presented which determines the probability of bit errors versus distance for various types of communication links designed for in mine use. The probability of undetected errors for the protocols of the communication links is given together with burst error detection.

Jan 2, 1981

By B. Samanta

Abstract - Ore reserve estimation, based on sparse drill hole data, was conducted for a placer gold property in Nome, Alaska. A problem with sparse data is that random subdivision of the data into modelling and evaluation subsets (as is commonly done) becomes a problem, as random selection may result in biased/skewed subsets. Therefore, a technique that combined data segmentation with genetic algorithms (GA) was applied to divide the samples into three equivalent subsets: training, validation and testing. Data segmentation was done on the basis of the distribution of gold values. Neural network and a variety of kriging techniques were used to estimate gold grades. A multi-layer feed forward neural network along with "early/quick stop" training was used for neural network modelling. A comparative evaluation of kriging and neural network methods was then performed. The results revealed that neural network was generally superior to the kriging techniques for gold grade estimation in the Nome deposit.

Jan 1, 2002

By C. Sunderman, R. Jacksha

"Mine monitoring through various sensors is a vital component of successful miner safety and health programs. Data from environmental, geotechnical, infrastructure, and other types of sensors are increasingly being used to discover and mitigate health and safety concerns in underground mines. In many smaller underground mines, as well as in new development headings of larger underground mines, leaky feeder communication systems may be the only available means to transport crucial monitoring data. In addition, data transport is increasingly being delivered using Internet Protocol (IP) while older forms of serial communication are being retired. This paper presents the selection, configuration, and testing methodologies that were employed by researchers from the National Institute for Occupational Safety and Health (NIOSH) to integrate commercially available land mobile data radios into an existing leaky feeder communication system to provide Internet Protocol data transport. INTRODUCTION To enhance the health and safety of their mining workforce, mine owners and operators are increasingly installing environmental monitoring and control systems in underground mines. Real-time, mine-wide monitoring is becoming a reality with the implementation of the Industrial Internet of Things (IIoT) into the underground mining industry [1]. However, not all underground mines, especially smaller mines and new development headings in larger mines, have the information technology (IT) infrastructure in place to handle the data transport requirements for the newer IP-based technologies that are part of IIoT. This was the case with a mine in the Western United States; it lacked the infrastructure to perform critical monitoring in remote headings. The mine partnered with the U.S. National Institute for Occupational Safety and Health’s (NIOSH’s) Spokane Mining Research Division (SMRD) to develop and evaluate a cost-effective solution for real-time monitoring of geotechnical conditions in relatively remote sections of the mine. This paper describes SMRD’s solution to leverage the mine’s existing leaky feeder system to achieve IP data transport using commercially available land mobile data radios. DATA RADIO SELECTION The primary selection criteria for the data radios were network data format, modulation type, and radio channel spacing. The network data format decided upon was Internet Protocol. This format allowed for straightforward integration between the IP-enabled data acquisition system located in a remote heading and the network switch located in the control room. It also eliminated the added complexity of additional network hardware such as Ethernet to Serial converters. IP additionally provided a direct path to integration into higher bandwidth networks, such as fiber optic, should they become available."

Jan 1, 2018

By C. Sunderman, R. Jacksha

"Mine monitoring through various sensors is a vital component of successful miner safety and health programs. Data from environmental, geotechnical, infrastructure and other types of sensors are increasingly used to discover and mitigate health and safety concerns in underground mines. In many smaller underground mines, as well as in the new development headings of larger underground mines, leaky feeder communication systems may be the only available means to transport crucial monitoring data. In addition, data transport is increasingly being delivered using Internet Protocol (IP), while older forms of serial communication are being retired. This paper presents the selection, configuration and testing methodologies employed by researchers from the U.S. National Institute for Occupational Safety and Health (NIOSH) to integrate commercially available land mobile data radios into an existing leaky feeder communication system to provide IP data transport.IntroductionTo enhance the health and safety of their mining workforce, mine owners and operators are increasingly installing environmental monitoring and control systems in underground mines. Real-time, mine-wide monitoring is becoming a reality with the implementation of the Industrial Internet of Things (IIoT) into the underground mining industry (Zhou et al., 2017). However, not all underground mines, especially smaller mines and new development headings in larger mines, have the information technology infrastructure in place to handle the data transport requirements for the newer Internet Protocol (IP)-based technologies that are part of IIoT.This was the case with a mine in the Western United States. It lacked the infrastructure to perform critical monitoring in remote headings. Therefore, the mine partnered with the U.S. National Institute for Occupational Safety and Health’s (NIOSH) Spokane Mining Research Division (SMRD) to develop and evaluate a cost-effective solution for the real-time monitoring of geotechnical conditions in relatively remote sections of the mine. This paper describes SMRD’s solution to leverage the mine’s existing leaky feeder communications system to achieve IP data transport using commercially available land mobile data radios (NIOSH, 2013; Forooshani et al., 2013; Novak, Snyder and Kohler, 2010; Yarkan et al., 2009). The solution, fully evaluated in laboratory and mine environments, requires no modifications to the existing system, is economical, simple to implement, and reliable. It also allows for transition to higher-bandwidth IT networks, such as fiber optic or WiFi, should they become available."

Dec 1, 2018

By Frédéric Flament

The aim of this paper is to present the development of a data validation software as component of a commercial mass balance package. Data reconciliation through mass balance is basically an optimization problem constrained by the law of mass conservation. As any optimization problem solved with a modern and robust software application, erroneous information or starting point will always lead to a solution, whether it is realistic or not. Moreover, good information wrongly weighted by an incorrect error model will lead to the same bad ending. In an industrial context where competition requires accurate information, data reconciliation without validation can be disastrous and calls for data validation before and after reconciliation. The challenge in automated data validation resides in the development of general theoretical solutions. Until now, none has been presented and only partial solutions are available. The development presented in this paper incorporates some of these partial solutions. The integration of human knowledge into the application paved the way to a more general solution. The combination ?theoretical validation ? human expertise? proved to be flexible and reliable enough to be integrated in a commercial data validation package. Numerous examples though industrial applications are presented. These applications demonstrate the validation of raw measurements, user support in the development of error models and validation of reconciled measurements.

May 1, 2001