Application of artificial neural networks in the prediction of sugarcane juice Pol
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019000100009 |
Resumo: | ABSTRACT Innovative techniques that seek to minimize the costs of production and the laboriousness of certain operations are one of the great challenges in the sugar-energy sector nowadays. Thus, the objective of the present study was to estimate the Pol values of sugarcane juice as a function of °Brix and wet cake weight (WCW) using artificial neural network (ANN) modeling. A database was organized consisting of 204 technological analyses from a field experiment with 15 treatments and 2 years of evaluation. 75% of the data were used for the calibration of the model and 25% for its validation. Multilayer Perceptron ANNs were used for calibration and validation of the data. Before calibration, the variables were normalized. The training algorithm used was backpropagation and the activation function was the sigmoid. The ANNs were established with two hidden layers and the number of neurons ranging from 4 to 20 in each. The 15 ANNs with the lowest root mean square errors were randomly presented by the software, among which 6 were chosen to verify the accuracy. The ANNs had a high accuracy in the estimation of sugarcane juice Pol, both in the calibration phase (R2 = 0.948, RMSE = 0.36%) and in the validation (R2 = 0.878, RMSE = 0.41%), and can replace the standard method of analysis. Simpler networks can be trained to have the same accuracy as more complex networks. |
id |
UFCG-1_d1a4f461c2eacddd5aa06754decb60d8 |
---|---|
oai_identifier_str |
oai:scielo:S1415-43662019000100009 |
network_acronym_str |
UFCG-1 |
network_name_str |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
repository_id_str |
|
spelling |
Application of artificial neural networks in the prediction of sugarcane juice PoltrsBrixsucrosetechnological qualityABSTRACT Innovative techniques that seek to minimize the costs of production and the laboriousness of certain operations are one of the great challenges in the sugar-energy sector nowadays. Thus, the objective of the present study was to estimate the Pol values of sugarcane juice as a function of °Brix and wet cake weight (WCW) using artificial neural network (ANN) modeling. A database was organized consisting of 204 technological analyses from a field experiment with 15 treatments and 2 years of evaluation. 75% of the data were used for the calibration of the model and 25% for its validation. Multilayer Perceptron ANNs were used for calibration and validation of the data. Before calibration, the variables were normalized. The training algorithm used was backpropagation and the activation function was the sigmoid. The ANNs were established with two hidden layers and the number of neurons ranging from 4 to 20 in each. The 15 ANNs with the lowest root mean square errors were randomly presented by the software, among which 6 were chosen to verify the accuracy. The ANNs had a high accuracy in the estimation of sugarcane juice Pol, both in the calibration phase (R2 = 0.948, RMSE = 0.36%) and in the validation (R2 = 0.878, RMSE = 0.41%), and can replace the standard method of analysis. Simpler networks can be trained to have the same accuracy as more complex networks.Departamento de Engenharia Agrícola - UFCG2019-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019000100009Revista Brasileira de Engenharia Agrícola e Ambiental v.23 n.1 2019reponame:Revista Brasileira de Engenharia Agrícola e Ambiental (Online)instname:Universidade Federal de Campina Grande (UFCG)instacron:UFCG10.1590/1807-1929/agriambi.v23n1p9-15info:eu-repo/semantics/openAccessCoelho,Anderson P.Bettiol,João V. T.Dalri,Alexandre B.Fischer Filho,João A.Faria,Rogério T. dePalaretti,Luiz F.eng2019-02-11T00:00:00Zoai:scielo:S1415-43662019000100009Revistahttp://www.scielo.br/rbeaaPUBhttps://old.scielo.br/oai/scielo-oai.php||agriambi@agriambi.com.br1807-19291415-4366opendoar:2019-02-11T00:00Revista Brasileira de Engenharia Agrícola e Ambiental (Online) - Universidade Federal de Campina Grande (UFCG)false |
dc.title.none.fl_str_mv |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
title |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
spellingShingle |
Application of artificial neural networks in the prediction of sugarcane juice Pol Coelho,Anderson P. trs Brix sucrose technological quality |
title_short |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
title_full |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
title_fullStr |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
title_full_unstemmed |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
title_sort |
Application of artificial neural networks in the prediction of sugarcane juice Pol |
author |
Coelho,Anderson P. |
author_facet |
Coelho,Anderson P. Bettiol,João V. T. Dalri,Alexandre B. Fischer Filho,João A. Faria,Rogério T. de Palaretti,Luiz F. |
author_role |
author |
author2 |
Bettiol,João V. T. Dalri,Alexandre B. Fischer Filho,João A. Faria,Rogério T. de Palaretti,Luiz F. |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Coelho,Anderson P. Bettiol,João V. T. Dalri,Alexandre B. Fischer Filho,João A. Faria,Rogério T. de Palaretti,Luiz F. |
dc.subject.por.fl_str_mv |
trs Brix sucrose technological quality |
topic |
trs Brix sucrose technological quality |
description |
ABSTRACT Innovative techniques that seek to minimize the costs of production and the laboriousness of certain operations are one of the great challenges in the sugar-energy sector nowadays. Thus, the objective of the present study was to estimate the Pol values of sugarcane juice as a function of °Brix and wet cake weight (WCW) using artificial neural network (ANN) modeling. A database was organized consisting of 204 technological analyses from a field experiment with 15 treatments and 2 years of evaluation. 75% of the data were used for the calibration of the model and 25% for its validation. Multilayer Perceptron ANNs were used for calibration and validation of the data. Before calibration, the variables were normalized. The training algorithm used was backpropagation and the activation function was the sigmoid. The ANNs were established with two hidden layers and the number of neurons ranging from 4 to 20 in each. The 15 ANNs with the lowest root mean square errors were randomly presented by the software, among which 6 were chosen to verify the accuracy. The ANNs had a high accuracy in the estimation of sugarcane juice Pol, both in the calibration phase (R2 = 0.948, RMSE = 0.36%) and in the validation (R2 = 0.878, RMSE = 0.41%), and can replace the standard method of analysis. Simpler networks can be trained to have the same accuracy as more complex networks. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019000100009 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019000100009 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1807-1929/agriambi.v23n1p9-15 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Departamento de Engenharia Agrícola - UFCG |
publisher.none.fl_str_mv |
Departamento de Engenharia Agrícola - UFCG |
dc.source.none.fl_str_mv |
Revista Brasileira de Engenharia Agrícola e Ambiental v.23 n.1 2019 reponame:Revista Brasileira de Engenharia Agrícola e Ambiental (Online) instname:Universidade Federal de Campina Grande (UFCG) instacron:UFCG |
instname_str |
Universidade Federal de Campina Grande (UFCG) |
instacron_str |
UFCG |
institution |
UFCG |
reponame_str |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
collection |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
repository.name.fl_str_mv |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) - Universidade Federal de Campina Grande (UFCG) |
repository.mail.fl_str_mv |
||agriambi@agriambi.com.br |
_version_ |
1750297686455615488 |