DEMIN - Departamento de Engenharia de Minas
URI permanente desta comunidadehttp://www.hml.repositorio.ufop.br/handle/123456789/510
Navegar
10 resultados
Resultados da Pesquisa
Item Quality index of dimension stones for application in building industry using technological characterization lab tests.(2022) Zagôto, Juliano Tessinari; Lana, Milene Sabino; Pereira, Tiago MartinsDimension stones have been used in many different environments, like airports, shopping malls, commercial buildings and houses, due to their beauty and quality. However, the choice of the ideal material for application in a given environment is a challenging decision. Esthetic patterns determine the choice in most of the cases, instead of the physical and mechanical properties, which can cause damages and even accidents. Thus, this research aims to propose a quality index using technological characterization lab tests established by international and national regulations. This index can be used to help practitioners in the choice of the proper dimension stone for a given environment, minimizing pathologies. An extensive database encompassing many lab tests for technological characterization of dimension stones was used in this research.Item Evaluation of machine learning methods for rock mass classification.(2022) Santos, Allan Erlikhman Medeiros; Lana, Milene Sabino; Pereira, Tiago MartinsSolutions in geotechnics have been optimizing with the aid of machine learning methods. The aim of this paper is to apply different machine learning algorithms in order to achieve rock mass classification. It is demonstrated that RMR classifi- cation system can be obtained using only variables which are closely related to rock mass quality, instead of all RMR variables, without missing significant accuracy. The different machine learning algorithms used are the naı ̈ve Bayes, random forest, artificial neural networks and support vector machines. The variables to calculate RMR, selected by factor analysis, are: rock strength, rock weathering, spacing, persistence and aperture of discontinuities and presence of water. The machine learning models were trained and tested thirty times, with random subsampling, using two-thirds of the total database for training sample. The models presented average accuracy greater than 0.81, which was calculated from the confusion matrix, using the proportion of true positives and true negatives in the test sample. Significant values of efficiency, precision and reproducibility rates were achieved. The study shows the application of machine learning algorithms allows obtaining the RMR classes, even with a small number of variables. In addition, the results of the evaluation metrics of the developed algorithms show that the methodology can be applied to new database, working as a valuable way to achieve rock mass classification.Item Probability density function of rock mass discontinuity distances.(2020) Bruzzi, Antonio Fernando Gorgulho; Alameda Hernández, Pedro Manuel; Klen, André Monteiro; Pereira, Tiago Martins; Lana, Milene SabinoRock masses are presenting an enduring challenge since the first authors began trying to model these natural structures. This modelling needs a parametrisation and a latter value assignment for those parameter value series, which show high variability, and a lack of clear patterns, in nature. Understanding the statistical nature of these values is an essential goal of rock mechanics, searching for the most appropriate probability density function (pdf) for fitting each one of those parameter values. The identification of those pdf is an aid for a better understanding of the rock mass nature and a need for correct discrete fracture network generation, or any probabilistic calculation. The parameter studied in this work is the degree of fracturing, in particular: the distances between fractures in a borehole rock core, which determines the Rock Quality Designation (RQD) value. The most accepted hypothesis is that these values fit a negative exponential pdf, however, with some criticism. Through the analysis of 1985 m of borehole rock core from five lithologies from two rock masses, this work shows the lognormality of the data series. The negative exponential does not fit correctly; however, the old approach for RQD based on this hypothesis offers satisfying results. Furthermore, it has been observed that schist presents the unclearer random pattern.Item Rock mass classification by multivariate statistical techniques and artificial intelligence.(2020) Santos, Allan Erlikhman Medeiros; Lana, Milene Sabino; Pereira, Tiago MartinsThis study aims to improve the quality and accuracy of RMR classification system for rock masses in open pit mines. A database of open pit mines comprising basic parameters for obtaining the RMR was used. Techniques applied in this research were multivariate statistics and artificial intelligence. In relation to multivariate statistics, factor analysis was capable of identifying underlying factors not observable in the original variables, using the variables of these factors in the classification system, instead of all RMR variables. The proposed classifier was obtained by training neural networks. The results of the factor analysis allowed the identification of three common factors. Factor 1 represents the strength and weathering of the rock mass. Factor 3 represents the fracturing degree of the rock mass. Finally Factor 2 represents water flow conditions. Thirty artificial neural networks were trained with randomly selected training samples. The trained networks proved to be effective and stable. Regarding the validation of the networks, the values obtained for the overall probability of success and apparent error rate showed normal distributions and a low dispersion rate, with average rates of 0.87 and 0.13, respectively. Regarding specific errors, error values were recorded only between contiguous RMR classes. The major contribution of the study is to present a new methodology for achieving rock mass classifications based on mathematical and statistical fundamentals, aiming at optimising the selection of variables and consequent reduction of subjectivity in the parameters and classification methods.Item Análise de agrupamento aplicada ao reconhecimento de diferentes tipos de itabiritos silicosos friáveis da Mina de Brucutu.(2019) Gonçalves, Gizele Maria Campos; Rocha, Geriane Macedo; Barreto, Paula Bernardes; Pereira, Tiago Martins; Lima, Rosa Malena FernandesA análise de agrupamento é uma técnica de estatística multivariada que permite separar as unidades amostrais em grupos homogêneos internamente e heterogêneos externamente. Neste estudo essa técnica foi aplicada, através do software R, com o objetivo de estratificar em subgrupos os minérios classificados como itabiritos silicosos friáveis da Mina de Brucutu, Quadrilátero Ferrífero-MG. A matriz de dados era composta por 3.519 amostras e 10 variáveis granulométricas e químicas. A análise hierárquica de agrupamento mostrou que as amostras podem ser subdivididas em quatro grupos, e então, as mesmas foram agrupadas pelo método não hierárquico K-means. Através da análise das características de cada grupo formado, os mesmos foram classificados e relacionados com a geologia da jazida. A Tipologia 1 (itabirito silicoso friável rico e fino), é localizada no topo do depósito e estratigraficamente acima das rochas intrusivas máficas. A Tipologia 2 (itabirito silicoso friável pobre e grosseiro) é marcado pela direção NW-SE, evento Brasiliano. A Tipologia 3 (itabirito silicoso friável pobre e fino) é dispersa ao longo do depósito, dificultando sua correlação com alguma fase geológica. A Tipologia 4 (itabirito semi-compacto pobre) concentra-se na região SW do depósito.Item A model for estimating the PFD80 transportable moisture limit of iron ore fines.(2019) Ferreira, Rodrigo Fina; Pereira, Tiago Martins; Lima, Rosa Malena FernandesShipping is an essential link in the mining industry production chain. Seaborne ore cargo transportation is internationally regulated by the International Maritime Organization (IMO), whose regulatory framework includes laws that aimto ensure the safety and security of shipping. Somewetmineral cargoesmay liquefy during passage under certain conditions. This phenomenon can shift the cargo and put the vessel and its crew at risk. According to the IMO regulations, in order to ship these cargoes, the moisture content shall be lower than the so-called Transportable Moisture Limit (TML), a regulatory parameter determined by laboratory tests. Iron ore fines with goethite content b35% are susceptible to liquefaction, and its TML can be obtained through the Modified Proctor/Fagerberg Test for Iron Ore Fines (PFD80), a compaction test that consists in compacting ore samples at several different moisture contents, theTML being themoisture content atwhich the material reaches 80% saturation. Since 2017, iron ore fines shippers from IMO Member States shall determine the TML of their cargoes preferably using this method, when applicable, which is obviously being included in the scope of ore characterization laboratories. This paper presents a novel empirical model that allows estimating the iron ore fines TML froma single PFD80 compaction point, the first predictionmodel in the literature related to this test. The method is a useful auxiliary tool for research and control of this parameter, which reduces the response time and the amount of sample required for testing. A performance evaluation conducted for 62 new samples, including other authors' data, showed good fit between observed and predicted TML, validating the proposed model.Item Análise de componentes principais aplicada à flotação de minério de ferro.(2018) Milhomem, Felipe de Orquiza; Silveira, Marcus Alexandre de Carvalho Winitskowski da; Souza, Tamíris Fonseca de; Cota, Tiany Guedes; Pereira, Tiago Martins; Rodrigues, Otávia MartinsA flotação é um processo de concentração, usualmente, empregado no beneficiamento do minério de ferro. O presente trabalho teve como objetivo avaliar a influência de variáveis no processo de flotação em bancada utilizando a técnica de análise de componentes principais. Para isso, realizou-se uma análise estatística com o auxílio do software R, onde foram estudados os teores de sílica e ferro na alimentação, no concentrado e no rejeito, teores dos contaminantes na alimentação (lama, óxido de cálcio e óxido de magnésio), perda por calcinação e dosagem de amina. Por meio da análise foi possível concluir que as duas primeiras componentes explicaram juntas aproximadamente 45% da variabilidade total da matriz de dados. A primeira componente explicou em torno de 25% da variância, sendo relacionada com a perda de seletividade do processo de flotação. Já a segunda componente explicou cerca de 20% da variância e descreveu a ineficiência do processo. Através dos estudos realizados, foi possível observar que a técnica de análise de componentes principais pode ser utilizada para melhor entendimento das variáveis dos processos de flotação em bancada.Item Quantitative hazard assessment system (Has-Q) for open pit mine slopes.(2018) Santos, Tatiana Barreto dos; Lana, Milene Sabino; Pereira, Tiago Martins; Canbulat, IsmetRock slope hazard assessment is an important part of risk analysis for open pit mines. The main parameters that can lead to rock slope failures are the parameters traditionally used in geomechanical classifications, the slope geometrical parameters and external factors like rainfall and blasting. This paper presents a methodology for a hazard assessment system for open pit mine slopes based on 88 cases collated around the world using principal components analysis, discriminant analysis and confidence ellipses. The historical cases used in this study included copper, gold, iron, diamond, lead and zinc, platinum and claystone mines. The variables used in the assessment methodology are uniaxial compressive strength of intact rock; spacing, persistence, opening, roughness, infilling and orientation of the main discontinuity set; weathering of the rock mass; groundwater; blasting method; and height and inclination of the pit. While principal component analysis was used to quantify the data, the discriminant analysis was used to establish a rule to classify new slopes about its stability condition. To provide a practical hazard assessment system, confidence ellipses were used to propose a hazard graph and generate the HAS-Q. The discriminant rule developed in this research has a high discrimination capacity with an error rate of 11.36%.Item Evaluation of rock slope stability conditions through discriminant analysis.(2018) Santos, Allan Erlikhman Medeiros; Lana, Milene Sabino; Cabral, Ivo Eyer; Pereira, Tiago Martins; Naghadehi, Masoud Zare; Silva, Denise de Fátima Santos da; Santos, Tatiana Barreto dosA methodology to predict the stability status of mine rock slopes is proposed. Two techniques of multivariate statistics are used: principal component analysis and discriminant analysis. Firstly, principal component analysis was applied in order to change the original qualitative variables into quantitative ones, as well as to reduce data dimensionality. Then, a boosting procedure was used to optimize the resulting function by the application of discriminant analysis in the principal components. In this research two analyses were performed. In the first analysis two conditions of slope stability were considered: stable and unstable. In the second analysis three conditions of slope stability were considered: stable, overall failure and failure in set of benches. A comprehensive geotechnical database consisting of 18 variables measured in 84 pit-walls all over the world was used to validate the methodology. The discriminant function was validated by two different procedures, internal and external validations. Internal validation presented an overall probability of success of 94.73% in the first analysis and 68.42% in the second analysis. In the second analysis the main source of errors was due to failure in set of benches. In external validation, the discriminant function was able to classify all slopes correctly, in analysis with two conditions of slope stability. In the external validation in the analysis with three conditions of slope stability, the discriminant function was able to classify six slopes correctly of a total of nine slopes. The proposed methodology provides a powerful tool for rock slope hazard assessment in open-pit mines.Item Cluster analysis for slope geotechnical prioritization of intervention for the Estrada de Ferro Vitória-Minas.(2017) Silva, Denise de Fátima Santos da; Santos, Allan Erlikhman Medeiros; Ferreira, Bruno Trindade; Pereira, Tiago Martins; Corteletti, Rosyelle CristinaThis article proposes the geotechnical prioritization of intervention of slopes with landslide scars for the Estrada de Ferro Vitória-Minas by cluster analysis and also the proposition of a relationship between area and volume in landslide scars. Cluster definition helps the decision-making associated to containment measures, mapping and study of landslides for the Estrada de Ferro Vitória-Minas. The database is composed of the variables: slope’s height, inclination, scar area and scar volume. The distance measure used was Gower’s index, with Ward’s methods to build the clusters. Eight characteristic groups were identified. It was possible to identify stretches that need attention in relation to the propensity of landslides, such as Group 7, stretches 362+600, 093+xxxE and 419+000. Group 7 presented high values for the scarred area and volume, such as maximum area 9.75 x 104 m² and minimum area 7.49 x 104 m², and maximum volume 9.20 x 105 m³ and minimum volume 4.08 x105 m³. Group 7 presented high ranges for slope height and inclination. The set of results about Group 7 can be interpreted as stretches with a predisposition for landslides. In relation to intervention measures, Group 7 presents the sections with priority. The relationship between area and volume of landslide scars obtained by the research was compared with the relationships established in literature.