Optimized line balancing application considering demand forecast and artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista Produção Online |
Texto Completo: | https://www.producaoonline.org.br/rpo/article/view/4734 |
Resumo: | Having a line balancing model linked to fluctuations in demand can directly contribute to the important reduction of costs linked to manufacturing. With organizations undergoing more and more transformations and facing high competitiveness, it is essential to adopt quantitative methods and optimized processes that guarantee greater efficiency in resource management. Predicting market behavior is not a simple task, especially when there is high variability in demand. Thus, it is important to consider robust mathematical models with optimized configurations so that they are able to recognize patterns, in order to predict the sales volume with the least possible error. In view of this, the historical sales data of the five main products of a multinational company, those that represent the highest profit, were used, and the demands were calculated using the moving average, exponential smoothing, Box-Jenkins and RNA models. Afterwards, in order to choose the most accurate method, that is, the one with the lowest error, the errors of each of the methods used (RMSE, MAE and MAPE) were calculated in isolation, thus enabling the comparison between them. In view of the result obtained, the balancing of the assembly lines in which the products are produced was modeled, the number of employees for the expected demand was calculated, using a mathematical model of non-linear programming, having as main objective improve current efficiency by organizing lines. Thus, it was found that the ANNs represented greater accuracy for forecasting demand and that, in comparison with the current method used by the company, it proved to be a more reliable method of predicting quantities for resource planning. Afterwards, it was visualized that the balancing method developed brought important adjustments of resources, thus leading to an increase in the efficiency of the production lines by a percentage of 29%, which is considered quite satisfactory. |
id |
ABEPRO-2_af9935d294a24112269561061ed2fac9 |
---|---|
oai_identifier_str |
oai:ojs.emnuvens.com.br:article/4734 |
network_acronym_str |
ABEPRO-2 |
network_name_str |
Revista Produção Online |
repository_id_str |
|
spelling |
Optimized line balancing application considering demand forecast and artificial neural networksAplicação de balanceamento de linha otimizado considerando previsão de demanda e redes neurais artificiaisLine balancingDemand forecastArtificial intelligenceBalanceamento de linhaPrevisão de demanda Inteligência artificialHaving a line balancing model linked to fluctuations in demand can directly contribute to the important reduction of costs linked to manufacturing. With organizations undergoing more and more transformations and facing high competitiveness, it is essential to adopt quantitative methods and optimized processes that guarantee greater efficiency in resource management. Predicting market behavior is not a simple task, especially when there is high variability in demand. Thus, it is important to consider robust mathematical models with optimized configurations so that they are able to recognize patterns, in order to predict the sales volume with the least possible error. In view of this, the historical sales data of the five main products of a multinational company, those that represent the highest profit, were used, and the demands were calculated using the moving average, exponential smoothing, Box-Jenkins and RNA models. Afterwards, in order to choose the most accurate method, that is, the one with the lowest error, the errors of each of the methods used (RMSE, MAE and MAPE) were calculated in isolation, thus enabling the comparison between them. In view of the result obtained, the balancing of the assembly lines in which the products are produced was modeled, the number of employees for the expected demand was calculated, using a mathematical model of non-linear programming, having as main objective improve current efficiency by organizing lines. Thus, it was found that the ANNs represented greater accuracy for forecasting demand and that, in comparison with the current method used by the company, it proved to be a more reliable method of predicting quantities for resource planning. Afterwards, it was visualized that the balancing method developed brought important adjustments of resources, thus leading to an increase in the efficiency of the production lines by a percentage of 29%, which is considered quite satisfactory.Ter um modelo de balanceamento de linha vinculado às oscilações de demanda pode contribuir diretamente na tão importante redução de custos atrelados à manufatura. Com as organizações sofrendo cada vez mais transformações e confrontando-se com elevada competitividade, é imprescindível adotar métodos quantitativos e processos otimizados que garantam maior eficiência no gerenciamento de recursos. Antever o comportamento do mercado não é uma tarefa simples, principalmente quando há alta variabilidade de demanda. Desta forma, é importante considerar modelos matemáticos robustos com configurações otimizadas para que sejam capazes de reconhecer padrões, a fim de predizer o volume de vendas com menor erro possível. Diante disso, foram utilizados os dados históricos de vendas dos cinco principais produtos de uma multinacional, aqueles que representam maior lucro, e foram calculadas as demandas por meio dos modelos de média móvel, suavização exponencial, Box-Jenkins e RNA. Após, com o intuito de escolher o método mais acurado, ou seja, que apresenta o menor erro, foi calculado isoladamente os erros de cada um dos métodos utilizados (RMSE, MAE e MAPE) possibilitando assim a comparação entre eles. Diante do resultado obtido, modelou-se o balanceamento das linhas de montagem em que são produzidos os produtos, calculou-se, por meio de um modelo matemático de programação não linear, o número adequado de funcionários para a demanda prevista, tendo como principal objetivo melhorar a eficiência atual por meio da organização das linhas. Sendo assim, constatou-se que as RNAs representaram maior acurácia para a previsão de demanda e que, em comparação com o atual método utilizado pela empresa, mostrou-se ser um método mais confiável de predição de quantidades para planejamento de recursos. Após, visualizou-se que o método de balanceamento desenvolvido trouxe importantes adequações de recursos acarretando, assim, o aumento na eficiência das linhas de produção em um percentual de 29%, o que se considera bastante satisfatório.Associação Brasileira de Engenharia de Produção2023-03-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfaudio/mpeghttps://www.producaoonline.org.br/rpo/article/view/473410.14488/1676-1901.v22i2.4734Revista Produção Online; Vol. 22 No. 2 (2022); 2886-2912Revista Produção Online; v. 22 n. 2 (2022); 2886-29121676-1901reponame:Revista Produção Onlineinstname:Associação Brasileira de Engenharia de Produção (ABEPRO)instacron:ABEPROporhttps://www.producaoonline.org.br/rpo/article/view/4734/2187https://www.producaoonline.org.br/rpo/article/view/4734/2188Copyright (c) 2023 Revista Produção Onlinehttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessMoraes, Nathalia TessariCorso, Leandro Luís2023-03-03T18:34:49Zoai:ojs.emnuvens.com.br:article/4734Revistahttp://producaoonline.org.br/rpoPUBhttps://www.producaoonline.org.br/rpo/oai||producaoonline@gmail.com1676-19011676-1901opendoar:2023-03-03T18:34:49Revista Produção Online - Associação Brasileira de Engenharia de Produção (ABEPRO)false |
dc.title.none.fl_str_mv |
Optimized line balancing application considering demand forecast and artificial neural networks Aplicação de balanceamento de linha otimizado considerando previsão de demanda e redes neurais artificiais |
title |
Optimized line balancing application considering demand forecast and artificial neural networks |
spellingShingle |
Optimized line balancing application considering demand forecast and artificial neural networks Moraes, Nathalia Tessari Line balancing Demand forecast Artificial intelligence Balanceamento de linha Previsão de demanda Inteligência artificial |
title_short |
Optimized line balancing application considering demand forecast and artificial neural networks |
title_full |
Optimized line balancing application considering demand forecast and artificial neural networks |
title_fullStr |
Optimized line balancing application considering demand forecast and artificial neural networks |
title_full_unstemmed |
Optimized line balancing application considering demand forecast and artificial neural networks |
title_sort |
Optimized line balancing application considering demand forecast and artificial neural networks |
author |
Moraes, Nathalia Tessari |
author_facet |
Moraes, Nathalia Tessari Corso, Leandro Luís |
author_role |
author |
author2 |
Corso, Leandro Luís |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Moraes, Nathalia Tessari Corso, Leandro Luís |
dc.subject.por.fl_str_mv |
Line balancing Demand forecast Artificial intelligence Balanceamento de linha Previsão de demanda Inteligência artificial |
topic |
Line balancing Demand forecast Artificial intelligence Balanceamento de linha Previsão de demanda Inteligência artificial |
description |
Having a line balancing model linked to fluctuations in demand can directly contribute to the important reduction of costs linked to manufacturing. With organizations undergoing more and more transformations and facing high competitiveness, it is essential to adopt quantitative methods and optimized processes that guarantee greater efficiency in resource management. Predicting market behavior is not a simple task, especially when there is high variability in demand. Thus, it is important to consider robust mathematical models with optimized configurations so that they are able to recognize patterns, in order to predict the sales volume with the least possible error. In view of this, the historical sales data of the five main products of a multinational company, those that represent the highest profit, were used, and the demands were calculated using the moving average, exponential smoothing, Box-Jenkins and RNA models. Afterwards, in order to choose the most accurate method, that is, the one with the lowest error, the errors of each of the methods used (RMSE, MAE and MAPE) were calculated in isolation, thus enabling the comparison between them. In view of the result obtained, the balancing of the assembly lines in which the products are produced was modeled, the number of employees for the expected demand was calculated, using a mathematical model of non-linear programming, having as main objective improve current efficiency by organizing lines. Thus, it was found that the ANNs represented greater accuracy for forecasting demand and that, in comparison with the current method used by the company, it proved to be a more reliable method of predicting quantities for resource planning. Afterwards, it was visualized that the balancing method developed brought important adjustments of resources, thus leading to an increase in the efficiency of the production lines by a percentage of 29%, which is considered quite satisfactory. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-03-03 |
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://www.producaoonline.org.br/rpo/article/view/4734 10.14488/1676-1901.v22i2.4734 |
url |
https://www.producaoonline.org.br/rpo/article/view/4734 |
identifier_str_mv |
10.14488/1676-1901.v22i2.4734 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://www.producaoonline.org.br/rpo/article/view/4734/2187 https://www.producaoonline.org.br/rpo/article/view/4734/2188 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 Revista Produção Online https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 Revista Produção Online https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf audio/mpeg |
dc.publisher.none.fl_str_mv |
Associação Brasileira de Engenharia de Produção |
publisher.none.fl_str_mv |
Associação Brasileira de Engenharia de Produção |
dc.source.none.fl_str_mv |
Revista Produção Online; Vol. 22 No. 2 (2022); 2886-2912 Revista Produção Online; v. 22 n. 2 (2022); 2886-2912 1676-1901 reponame:Revista Produção Online instname:Associação Brasileira de Engenharia de Produção (ABEPRO) instacron:ABEPRO |
instname_str |
Associação Brasileira de Engenharia de Produção (ABEPRO) |
instacron_str |
ABEPRO |
institution |
ABEPRO |
reponame_str |
Revista Produção Online |
collection |
Revista Produção Online |
repository.name.fl_str_mv |
Revista Produção Online - Associação Brasileira de Engenharia de Produção (ABEPRO) |
repository.mail.fl_str_mv |
||producaoonline@gmail.com |
_version_ |
1761536951989567488 |