Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UFPB |
Texto Completo: | https://repositorio.ufpb.br/jspui/handle/123456789/20949 |
Resumo: | The volume of information to be collected and processed today is greater than human capacity. The amount of data is a reality in the various areas of science, as engineering, industrial sectors, both in manufacturing and in the provision of services. The dynamics of exponential increase in the amount of information needing to be treated has motivated the implementation of computational approaches and tools over the last decades, aiming to develop the ability to handle data automatically and efficiently in organizations. In this sense, the field of data mining science addresses methods and algorithms from different areas of science, such as operational research, metaheuristics and artificial intelligence. The field of materials sciences and engineering, composite materials, such as concrete, have several characteristics that can be taken in a clustering method, in order to make it possible to obtain the best possible groupings per set of characteristics, as the performance metrics stipulated. Such results can bring countless benefits and applications in industrial decisions, mainly related to the production processes and problems of selection of raw materials, being able to significantly improve the operational performance, reduce production costs or even caused environmental impacts, according to the organization’s objectives. In this sense, this study aims to develop an automatic clustering optimization approach that allows the determination of optimal mixtures of components and their respective attributes, so that they meet multiple optimization criteria. In this work, the criteria studied are the chemical and mineralological compositions of rocks used as aggregates for concrete in the Northeast region of Brazil. For this, an evolutionary hybrid metaheuristic was developed in order to achieve an optimal clustering of data related to the chemical and mineralogical compositions of such materials, aiming to optimize the clustering according to the properties and characteristics chosen, considering also constraints and objectives involved in the problem. In view of the results achieved with the method, it was possible to evaluate the attribute configurations that enabled a more efficient clustering in its best solution, determining the most promising and impacting oxides and reasons. In addition, the work also aimed to carry out correlation analyzes between the clusters obtained with their mineralogical compositions and their densities of probabilities of expansion, enabling the establishment of significant relationships between the clusters formed and the analyzed criteria. The results achieved with the method and the studies carried out made it possible to obtain high quality and efficient clusters (as well as the identification of their correlations with multiple criteria), as well as enabling innovative analyzes and insights about the materials and clusters formed, thus being able to serve as a tool for industrial decision-making. |
id |
UFPB_c4aaaf7e39ae23aeb55eb6d025d30512 |
---|---|
oai_identifier_str |
oai:repositorio.ufpb.br:123456789/20949 |
network_acronym_str |
UFPB |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository_id_str |
|
spelling |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm OptimizationOtimização por enxame de partículasAlgoritmo evolucionárioMetaheurísticaClusterizaçãoConcretoParticle Swarm OptimizationEvolutionary algorithmMetaheuristicClusteringConcreteCNPQ::ENGENHARIAS::ENGENHARIA MECANICAThe volume of information to be collected and processed today is greater than human capacity. The amount of data is a reality in the various areas of science, as engineering, industrial sectors, both in manufacturing and in the provision of services. The dynamics of exponential increase in the amount of information needing to be treated has motivated the implementation of computational approaches and tools over the last decades, aiming to develop the ability to handle data automatically and efficiently in organizations. In this sense, the field of data mining science addresses methods and algorithms from different areas of science, such as operational research, metaheuristics and artificial intelligence. The field of materials sciences and engineering, composite materials, such as concrete, have several characteristics that can be taken in a clustering method, in order to make it possible to obtain the best possible groupings per set of characteristics, as the performance metrics stipulated. Such results can bring countless benefits and applications in industrial decisions, mainly related to the production processes and problems of selection of raw materials, being able to significantly improve the operational performance, reduce production costs or even caused environmental impacts, according to the organization’s objectives. In this sense, this study aims to develop an automatic clustering optimization approach that allows the determination of optimal mixtures of components and their respective attributes, so that they meet multiple optimization criteria. In this work, the criteria studied are the chemical and mineralological compositions of rocks used as aggregates for concrete in the Northeast region of Brazil. For this, an evolutionary hybrid metaheuristic was developed in order to achieve an optimal clustering of data related to the chemical and mineralogical compositions of such materials, aiming to optimize the clustering according to the properties and characteristics chosen, considering also constraints and objectives involved in the problem. In view of the results achieved with the method, it was possible to evaluate the attribute configurations that enabled a more efficient clustering in its best solution, determining the most promising and impacting oxides and reasons. In addition, the work also aimed to carry out correlation analyzes between the clusters obtained with their mineralogical compositions and their densities of probabilities of expansion, enabling the establishment of significant relationships between the clusters formed and the analyzed criteria. The results achieved with the method and the studies carried out made it possible to obtain high quality and efficient clusters (as well as the identification of their correlations with multiple criteria), as well as enabling innovative analyzes and insights about the materials and clusters formed, thus being able to serve as a tool for industrial decision-making.O volume de informações a serem coletadas e tratadas nos dias atuais é maior que a capacidade humana. A quantidade enorme de dados é uma realidade nas diversas áreas das ciências, engenharias e setores industriais. A dinâmica de aumento exponencial na quantidade de informações necessitando serem tratadas motivou a implementação de abordagens e ferramentas computacionais ao longo das últimas décadas, visando principalmente desenvolver a capacidade de tratar dados de forma automática e eficiente nas organizações. Neste sentido, o campo da ciência de mineração de dados aborda métodos e algoritmos de diferentes áreas das ciências, como pesquisa operacional, metaheurísticas e inteligência artificial. O campo das ciências e engenharia dos materiais, os materiais compósitos, tais como os concretos, possuem diversas características que podem ser levadas em consideração em um método de clausterização, de modo a tornar possível a obtenção dos melhores agrupamentos possíveis por conjunto de características, conforme as métricas de desempenho estipuladas. Tais resultados podem trazer inúmeros benefícios e aplicações em decisões industriais, principalmente relacionadas aos processos produtivos e problemas de seleção de matérias-primas, podendo melhorar significativa o desempenho operacional, reduzir custos de produção ou até mesmo impactos ambientais causados. Neste sentido, o objetivo geral do trabalho consiste no desenvolvimento de um método de clusterização para agregados de concreto da região Nordeste do Brasil, com base em suas características químicas e mineralógicas. Para tanto, desenvolveu-se uma metaheurística híbrida evolucionária visando realizar um agrupamento ótimo de dados relacionados as composições químicas e mineralógicas de tais materiais, objetivando otimizar os agrupamentos conforme as propriedades e características escolhidas, considerando ainda as restrições e métricas de desempenho associadas ao problema. Em posse dos resultados alcançados com o método, foi possível avaliar as configurações de atributos que possibilitaram uma clusterização mais eficiente em sua melhor solução, determinando os óxidos e razões mais promissores e impactantes. Além disso, o trabalho objetivou também a realização de análises de correlação entre os clusters obtidos com suas composições mineralógicas e suas densidades de probabilidades de expansão, possibilitando o estabelecimento de relações significativas entre os clusters formados e os critérios analisados. Os resultados alcançados com o método e os estudos realizados permitiram a obtenção de clusterizações de alta qualidade e eficiência (e a identificação de suas correlações com múltiplos critérios), bem como possibilitaram análises e insights inovadores acerca dos materiais e dos clusters formados, podendo assim servir de ferramenta para a tomada de decisão industrial.Universidade Federal da ParaíbaBrasilEngenharia MecânicaPrograma de Pós-Graduação em Engenharia MecânicaUFPBTorres, Sandro Mardenhttp://lattes.cnpq.br/1050045022082025Silva, Yuri Laio Teixeira Veras2021-08-31T19:48:40Z2021-04-272021-08-31T19:48:40Z2020-05-27info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesishttps://repositorio.ufpb.br/jspui/handle/123456789/20949porhttp://creativecommons.org/licenses/by-nd/3.0/br/info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFPBinstname:Universidade Federal da Paraíba (UFPB)instacron:UFPB2022-08-09T18:29:25Zoai:repositorio.ufpb.br:123456789/20949Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufpb.br/PUBhttp://tede.biblioteca.ufpb.br:8080/oai/requestdiretoria@ufpb.br|| diretoria@ufpb.bropendoar:2022-08-09T18:29:25Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB)false |
dc.title.none.fl_str_mv |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
title |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
spellingShingle |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization Silva, Yuri Laio Teixeira Veras Otimização por enxame de partículas Algoritmo evolucionário Metaheurística Clusterização Concreto Particle Swarm Optimization Evolutionary algorithm Metaheuristic Clustering Concrete CNPQ::ENGENHARIAS::ENGENHARIA MECANICA |
title_short |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
title_full |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
title_fullStr |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
title_full_unstemmed |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
title_sort |
Clusterização automática em seleção de materiais e processos de fabricação utilizando PSO - Particle Swarm Optimization |
author |
Silva, Yuri Laio Teixeira Veras |
author_facet |
Silva, Yuri Laio Teixeira Veras |
author_role |
author |
dc.contributor.none.fl_str_mv |
Torres, Sandro Marden http://lattes.cnpq.br/1050045022082025 |
dc.contributor.author.fl_str_mv |
Silva, Yuri Laio Teixeira Veras |
dc.subject.por.fl_str_mv |
Otimização por enxame de partículas Algoritmo evolucionário Metaheurística Clusterização Concreto Particle Swarm Optimization Evolutionary algorithm Metaheuristic Clustering Concrete CNPQ::ENGENHARIAS::ENGENHARIA MECANICA |
topic |
Otimização por enxame de partículas Algoritmo evolucionário Metaheurística Clusterização Concreto Particle Swarm Optimization Evolutionary algorithm Metaheuristic Clustering Concrete CNPQ::ENGENHARIAS::ENGENHARIA MECANICA |
description |
The volume of information to be collected and processed today is greater than human capacity. The amount of data is a reality in the various areas of science, as engineering, industrial sectors, both in manufacturing and in the provision of services. The dynamics of exponential increase in the amount of information needing to be treated has motivated the implementation of computational approaches and tools over the last decades, aiming to develop the ability to handle data automatically and efficiently in organizations. In this sense, the field of data mining science addresses methods and algorithms from different areas of science, such as operational research, metaheuristics and artificial intelligence. The field of materials sciences and engineering, composite materials, such as concrete, have several characteristics that can be taken in a clustering method, in order to make it possible to obtain the best possible groupings per set of characteristics, as the performance metrics stipulated. Such results can bring countless benefits and applications in industrial decisions, mainly related to the production processes and problems of selection of raw materials, being able to significantly improve the operational performance, reduce production costs or even caused environmental impacts, according to the organization’s objectives. In this sense, this study aims to develop an automatic clustering optimization approach that allows the determination of optimal mixtures of components and their respective attributes, so that they meet multiple optimization criteria. In this work, the criteria studied are the chemical and mineralological compositions of rocks used as aggregates for concrete in the Northeast region of Brazil. For this, an evolutionary hybrid metaheuristic was developed in order to achieve an optimal clustering of data related to the chemical and mineralogical compositions of such materials, aiming to optimize the clustering according to the properties and characteristics chosen, considering also constraints and objectives involved in the problem. In view of the results achieved with the method, it was possible to evaluate the attribute configurations that enabled a more efficient clustering in its best solution, determining the most promising and impacting oxides and reasons. In addition, the work also aimed to carry out correlation analyzes between the clusters obtained with their mineralogical compositions and their densities of probabilities of expansion, enabling the establishment of significant relationships between the clusters formed and the analyzed criteria. The results achieved with the method and the studies carried out made it possible to obtain high quality and efficient clusters (as well as the identification of their correlations with multiple criteria), as well as enabling innovative analyzes and insights about the materials and clusters formed, thus being able to serve as a tool for industrial decision-making. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-05-27 2021-08-31T19:48:40Z 2021-04-27 2021-08-31T19:48:40Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpb.br/jspui/handle/123456789/20949 |
url |
https://repositorio.ufpb.br/jspui/handle/123456789/20949 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Engenharia Mecânica Programa de Pós-Graduação em Engenharia Mecânica UFPB |
publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Engenharia Mecânica Programa de Pós-Graduação em Engenharia Mecânica UFPB |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFPB instname:Universidade Federal da Paraíba (UFPB) instacron:UFPB |
instname_str |
Universidade Federal da Paraíba (UFPB) |
instacron_str |
UFPB |
institution |
UFPB |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
collection |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB) |
repository.mail.fl_str_mv |
diretoria@ufpb.br|| diretoria@ufpb.br |
_version_ |
1801842980324114432 |