Consumption Electrical Energy Forecast for a Automotive Paint Shop
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista de Engenharia e Pesquisa Aplicada |
Texto Completo: | http://revistas.poli.br/index.php/repa/article/view/2780 |
Resumo: | This article aims to predict the consumption behavior of electrical energy in a Paint Shop of a typical automotive industry by the usage of time series. From the data and it's relationship taken from the installed machines it will be used data science tools to correlate and predict it's consumption and even to model the next time series. The analysis will covers from an initial understanding of the data to it’s implementation in predictive models for future time series. It will focus on advanced applications in order to achieve valuable insights of energy consumption pattern. It will also consider the machinery complexes iterations. Deep understanding of those relationships will provide a better base for accurate models. Finally it will allow a much efficient consumption energy management for a Paint Shop. |
id |
UFPE-2_4d99b1fad3daa9f46cb6a42cc9194dc5 |
---|---|
oai_identifier_str |
oai:ojs.poli.br:article/2780 |
network_acronym_str |
UFPE-2 |
network_name_str |
Revista de Engenharia e Pesquisa Aplicada |
repository_id_str |
|
spelling |
Consumption Electrical Energy Forecast for a Automotive Paint ShopAnálise de Consumo de Energia Elétrica de Equipamentos em Oficina de Pintura AutomotivaThis article aims to predict the consumption behavior of electrical energy in a Paint Shop of a typical automotive industry by the usage of time series. From the data and it's relationship taken from the installed machines it will be used data science tools to correlate and predict it's consumption and even to model the next time series. The analysis will covers from an initial understanding of the data to it’s implementation in predictive models for future time series. It will focus on advanced applications in order to achieve valuable insights of energy consumption pattern. It will also consider the machinery complexes iterations. Deep understanding of those relationships will provide a better base for accurate models. Finally it will allow a much efficient consumption energy management for a Paint Shop.Este artigo tem como objetivo principal prever o comportamento do consumo de energia elétrica em uma oficina de pintura localizada dentro de uma fábrica automotiva de caráter industrial. A abordagem adotada será baseada em séries temporais, regressão e otimização, utilizando técnicas de ciência de dados para explorar os dados disponíveis e identificar as relações entre os diversos equipamentos instalados na oficina em três passos(steps). Para cada cada step foram definidos modelos de machine e deep learning. A análise se estendeu desde uma compreensão inicial dos dados até a implementação de modelos preditivos e de otimização. A ênfase ocorre na aplicação de métodos avançados que definiram os modelos de LSTM, Deep Learning e Algoritmo Genético nos steps 1, 2 e 3, consequentemente. As métricas para a seleção dos modelos foram MAPE e MSE. Os resultados produziram uma arquitetura de modelos capazes de produzir insights valiosos sobre os padrões de consumo de energia, levando consideração as interações complexas entre os equipamentos. A solução proposta proporcionou uma base sólida para a construção de modelos robustos e precisos, contribuindo para uma gestão eficiente do consumo de energia na oficina de pintura industrial.Escola Politécnica de Pernambuco2023-12-28info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdftext/htmlhttp://revistas.poli.br/index.php/repa/article/view/278010.25286/repa.v9i1.2780Journal of Engineering and Applied Research; Vol 9 No 1 (2024): Edição Especial em Ciência de Dados e Analytics; 69-78Revista de Engenharia e Pesquisa Aplicada; v. 9 n. 1 (2024): Edição Especial em Ciência de Dados e Analytics; 69-782525-425110.25286/repa.v9i1reponame:Revista de Engenharia e Pesquisa Aplicadainstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEporhttp://revistas.poli.br/index.php/repa/article/view/2780/903http://revistas.poli.br/index.php/repa/article/view/2780/904Copyright (c) 2024 Rafael Barbosa de Oliveira, Paulo Henrique Couto de Lima Souza, Thiago Cavalcanti Silva, Victor Ernesto Santos Kirschnerhttp://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessOliveira, Rafael Barbosa deCouto de Lima Souza, Paulo HenriqueSilva, Thiago CavalcantiKirschner, Victor Ernesto SantosLorenzato, FaustoMaciel, Alexandre M.A.2023-12-30T10:15:41Zoai:ojs.poli.br:article/2780Revistahttp://revistas.poli.br/index.php/repaONGhttp://revistas.poli.br/index.php/repa/oai||repa@poli.br2525-42512525-4251opendoar:2023-12-30T10:15:41Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE)false |
dc.title.none.fl_str_mv |
Consumption Electrical Energy Forecast for a Automotive Paint Shop Análise de Consumo de Energia Elétrica de Equipamentos em Oficina de Pintura Automotiva |
title |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
spellingShingle |
Consumption Electrical Energy Forecast for a Automotive Paint Shop Oliveira, Rafael Barbosa de |
title_short |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
title_full |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
title_fullStr |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
title_full_unstemmed |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
title_sort |
Consumption Electrical Energy Forecast for a Automotive Paint Shop |
author |
Oliveira, Rafael Barbosa de |
author_facet |
Oliveira, Rafael Barbosa de Couto de Lima Souza, Paulo Henrique Silva, Thiago Cavalcanti Kirschner, Victor Ernesto Santos Lorenzato, Fausto Maciel, Alexandre M.A. |
author_role |
author |
author2 |
Couto de Lima Souza, Paulo Henrique Silva, Thiago Cavalcanti Kirschner, Victor Ernesto Santos Lorenzato, Fausto Maciel, Alexandre M.A. |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Oliveira, Rafael Barbosa de Couto de Lima Souza, Paulo Henrique Silva, Thiago Cavalcanti Kirschner, Victor Ernesto Santos Lorenzato, Fausto Maciel, Alexandre M.A. |
description |
This article aims to predict the consumption behavior of electrical energy in a Paint Shop of a typical automotive industry by the usage of time series. From the data and it's relationship taken from the installed machines it will be used data science tools to correlate and predict it's consumption and even to model the next time series. The analysis will covers from an initial understanding of the data to it’s implementation in predictive models for future time series. It will focus on advanced applications in order to achieve valuable insights of energy consumption pattern. It will also consider the machinery complexes iterations. Deep understanding of those relationships will provide a better base for accurate models. Finally it will allow a much efficient consumption energy management for a Paint Shop. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-28 |
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 |
http://revistas.poli.br/index.php/repa/article/view/2780 10.25286/repa.v9i1.2780 |
url |
http://revistas.poli.br/index.php/repa/article/view/2780 |
identifier_str_mv |
10.25286/repa.v9i1.2780 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/2780/903 http://revistas.poli.br/index.php/repa/article/view/2780/904 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf text/html |
dc.publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
dc.source.none.fl_str_mv |
Journal of Engineering and Applied Research; Vol 9 No 1 (2024): Edição Especial em Ciência de Dados e Analytics; 69-78 Revista de Engenharia e Pesquisa Aplicada; v. 9 n. 1 (2024): Edição Especial em Ciência de Dados e Analytics; 69-78 2525-4251 10.25286/repa.v9i1 reponame:Revista de Engenharia e Pesquisa Aplicada instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Revista de Engenharia e Pesquisa Aplicada |
collection |
Revista de Engenharia e Pesquisa Aplicada |
repository.name.fl_str_mv |
Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
||repa@poli.br |
_version_ |
1798036000526565376 |