Machine learning in the determination of soft phyllite strength parameters
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/39693 |
Resumo: | Geological-geotechnical aspects must be taken into account cince geological exploration studies in mining projects. Some accidents that occurred in mines in recent decades could be avoided if the geological and geotechnical conditions of the rock mass were understood. There is still great difficulty in classifying some types of rocks, especially rocks considered soft, through known geomechanical classification systems. The vast majority of existing classifications were developed based on hard rock characteristics. For rock masses with little strength, it is necessary to adapt current systems or develop new classification systems, which are specific for practically continuous soft rock masses. The objective of this article is to propose the use of Machine Learning techniques to predict geotechnical parameters of soft rocks, especially phyllite. Were used historical data from the results of geotechnical laboratory stress measures campaign of rocks from mines in the Iron Quadrangle are used, which, through optimized interaction, and with the aid of Artificial Intelligence techniques, such as the Artificial Neural Network and Linear Regression, are capable of generating results of interest for stability analysis and geotechnical modeling. Of the techniques used, results showed that the Linear Regression method was satisfactory in determining the strength parameters of soft phyllites and with good prospects for expansion and use for other parameters, as well as other types of rocks. |
id |
UNIFEI_c814230fff388de780927d1978d868bb |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/39693 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Machine learning in the determination of soft phyllite strength parametersAprendizaje automático en la determinación de parámetros de resistencia de filita blandaAprendizagem de máquina na determinação de parâmetros de resistência de filitos brandosSoft rocksPhyllitesStrength parametersMachine learningArtificial neural networksLinear regression.Rocas blandasFilitasParámetros de resistênciaAprendizaje automáticoRedes neuronales artificialesRegresión lineal.Rochas brandasFilitosParâmetros de resistênciaAprendizagem de máquinaRedes neurais artificiaisRegressão linear.Geological-geotechnical aspects must be taken into account cince geological exploration studies in mining projects. Some accidents that occurred in mines in recent decades could be avoided if the geological and geotechnical conditions of the rock mass were understood. There is still great difficulty in classifying some types of rocks, especially rocks considered soft, through known geomechanical classification systems. The vast majority of existing classifications were developed based on hard rock characteristics. For rock masses with little strength, it is necessary to adapt current systems or develop new classification systems, which are specific for practically continuous soft rock masses. The objective of this article is to propose the use of Machine Learning techniques to predict geotechnical parameters of soft rocks, especially phyllite. Were used historical data from the results of geotechnical laboratory stress measures campaign of rocks from mines in the Iron Quadrangle are used, which, through optimized interaction, and with the aid of Artificial Intelligence techniques, such as the Artificial Neural Network and Linear Regression, are capable of generating results of interest for stability analysis and geotechnical modeling. Of the techniques used, results showed that the Linear Regression method was satisfactory in determining the strength parameters of soft phyllites and with good prospects for expansion and use for other parameters, as well as other types of rocks.Los aspectos geológicos-geotécnicos deben ser tomados en cuenta a partir de los estudios de exploración geológica en proyectos mineros. Algunos accidentes ocurridos en minas en las últimas décadas podrían evitarse si se entendieran las condiciones geológicas y geotécnicas del macizo. Todavía existe una gran dificultad para clasificar algunos tipos de rocas, especialmente rocas consideradas blandas, a través de sistemas de clasificación geomecánicos conocidos. La gran mayoría de las clasificaciones existentes se desarrollaron con base en las características de las rocas duras. Para macizos rocosos con poca resistencia es necesario adaptar los sistemas actuales o desarrollar nuevos sistemas de clasificación, que sean específicos para macizos rocosos blandos prácticamente continuos. El objetivo de este artículo es proponer el uso de técnicas de Machine Learning para predecir parámetros geotécnicos de rocas blandas, especialmente filita. Fueron usados datos históricos de los resultados de los ensayos de laboratorio geotécnico de rocas de las minas del Cuadrángulo de Hierro, que mediante una interacción optimizada y con la ayuda de técnicas de Inteligencia Artificial, como la Red Neuronal Artificial y la Regresión Lineal, son capaces de generar resultados. de interés para análisis de estabilidad y modelado geotécnico. De las técnicas utilizadas, los resultados mostraron que el método de Regresión Lineal fue satisfactorio en la determinación de los parámetros de resistencia de las filitas blandas y con buenas perspectivas de expansión y uso para otros parámetros, así como para otros tipos de rocas.Aspectos geológico-geotécnicos devem ser levados em consideração desde os estudos de exploração geológica, em empreendimentos mineiros. Alguns acidentes ocorridos em minas, nas últimas décadas, poderiam ser evitados, caso as condições geológico-geotécnicas do maciço fossem compreendidas. Ainda existe grande dificuldade em se classificar alguns tipos de rochas, sobretudo as rochas consideradas brandas, por meio dos sistemas de classificação geomecânica conhecidos. A grande maioria das classificações existentes foram desenvolvidos baseadas em características de rochas duras. Para maciços rochosos pouco resistentes, é necessário adaptar os sistemas atuais ou desenvolver novos sistemas de classificação, que sejam específicos para maciços rochosos brandos praticamente contínuos. O objetivo deste artigo é propor a utilização de técnicas de Aprendizagem de Máquina para previsão de parâmetros geotécnicos de rochas brandas, especialmente filito. Foram utilizados dados históricos de resultados de ensaios geotécnicos de laboratório de rochas de minas do Quadrilátero Ferrífero, que, por meio da interação otimizada, e com auxílio de técnica de Inteligência Artificial, como a Rede Neural Artificial e Regressão Linear, sejam capazes de gerar resultados de interesse para análises de estabilidade e modelagens geotécnicas. Das técnicas utilizadas, resultados mostraram que o método de Regressão Linear se mostrou satisfatório na determinação de parâmetros de resistência de filitos brandos e com boas perspectivas de ampliação e utilização para outros parâmetros, assim como outros tipos de rochas.Research, Society and Development2023-01-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/3969310.33448/rsd-v12i1.39693Research, Society and Development; Vol. 12 No. 1; e19012139693Research, Society and Development; Vol. 12 Núm. 1; e19012139693Research, Society and Development; v. 12 n. 1; e190121396932525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIporhttps://rsdjournal.org/index.php/rsd/article/view/39693/32614Copyright (c) 2023 Lívia Aparecida Gonçalves Pinto; José Margarida da Silvahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessPinto, Lívia Aparecida Gonçalves Silva, José Margarida da 2023-01-13T10:30:42Zoai:ojs.pkp.sfu.ca:article/39693Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2023-01-13T10:30:42Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Machine learning in the determination of soft phyllite strength parameters Aprendizaje automático en la determinación de parámetros de resistencia de filita blanda Aprendizagem de máquina na determinação de parâmetros de resistência de filitos brandos |
title |
Machine learning in the determination of soft phyllite strength parameters |
spellingShingle |
Machine learning in the determination of soft phyllite strength parameters Pinto, Lívia Aparecida Gonçalves Soft rocks Phyllites Strength parameters Machine learning Artificial neural networks Linear regression. Rocas blandas Filitas Parámetros de resistência Aprendizaje automático Redes neuronales artificiales Regresión lineal. Rochas brandas Filitos Parâmetros de resistência Aprendizagem de máquina Redes neurais artificiais Regressão linear. |
title_short |
Machine learning in the determination of soft phyllite strength parameters |
title_full |
Machine learning in the determination of soft phyllite strength parameters |
title_fullStr |
Machine learning in the determination of soft phyllite strength parameters |
title_full_unstemmed |
Machine learning in the determination of soft phyllite strength parameters |
title_sort |
Machine learning in the determination of soft phyllite strength parameters |
author |
Pinto, Lívia Aparecida Gonçalves |
author_facet |
Pinto, Lívia Aparecida Gonçalves Silva, José Margarida da |
author_role |
author |
author2 |
Silva, José Margarida da |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Pinto, Lívia Aparecida Gonçalves Silva, José Margarida da |
dc.subject.por.fl_str_mv |
Soft rocks Phyllites Strength parameters Machine learning Artificial neural networks Linear regression. Rocas blandas Filitas Parámetros de resistência Aprendizaje automático Redes neuronales artificiales Regresión lineal. Rochas brandas Filitos Parâmetros de resistência Aprendizagem de máquina Redes neurais artificiais Regressão linear. |
topic |
Soft rocks Phyllites Strength parameters Machine learning Artificial neural networks Linear regression. Rocas blandas Filitas Parámetros de resistência Aprendizaje automático Redes neuronales artificiales Regresión lineal. Rochas brandas Filitos Parâmetros de resistência Aprendizagem de máquina Redes neurais artificiais Regressão linear. |
description |
Geological-geotechnical aspects must be taken into account cince geological exploration studies in mining projects. Some accidents that occurred in mines in recent decades could be avoided if the geological and geotechnical conditions of the rock mass were understood. There is still great difficulty in classifying some types of rocks, especially rocks considered soft, through known geomechanical classification systems. The vast majority of existing classifications were developed based on hard rock characteristics. For rock masses with little strength, it is necessary to adapt current systems or develop new classification systems, which are specific for practically continuous soft rock masses. The objective of this article is to propose the use of Machine Learning techniques to predict geotechnical parameters of soft rocks, especially phyllite. Were used historical data from the results of geotechnical laboratory stress measures campaign of rocks from mines in the Iron Quadrangle are used, which, through optimized interaction, and with the aid of Artificial Intelligence techniques, such as the Artificial Neural Network and Linear Regression, are capable of generating results of interest for stability analysis and geotechnical modeling. Of the techniques used, results showed that the Linear Regression method was satisfactory in determining the strength parameters of soft phyllites and with good prospects for expansion and use for other parameters, as well as other types of rocks. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-01-11 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/39693 10.33448/rsd-v12i1.39693 |
url |
https://rsdjournal.org/index.php/rsd/article/view/39693 |
identifier_str_mv |
10.33448/rsd-v12i1.39693 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/39693/32614 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 Lívia Aparecida Gonçalves Pinto; José Margarida da Silva https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 Lívia Aparecida Gonçalves Pinto; José Margarida da Silva https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 12 No. 1; e19012139693 Research, Society and Development; Vol. 12 Núm. 1; e19012139693 Research, Society and Development; v. 12 n. 1; e19012139693 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052616152186880 |