Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product

Autores
Álvarez, Dolores María Eugenia; Bálsamo, Nancy Florentina; Modesti, Mario Roberto; Crivello, Mónica Elsie
Año de publicación
2019
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Biodiesel is generally manufactured by transesterification, obtaining glycerol as a by-product. The transesterification of methyl stearate selectively produced monoglycerides, for glycerol valuation. Mixed oxides containing lithium catalysed the reaction. The purpose of this work was to develop and compare mathematical models obtained through artificial neural networks (ANN), capable for characterising the relationship between the mole percent conversion of methyl stearate and the yield of the products mono-, di- and triglycerides. The lowest mean squared error (MSE), the highest correlation coefficient (R), similarity in the evolution of validation and simulation errors and absence of data overlearning were considered to select the best model. Three ANNs with backpropagation structures were compared. They evidenced high correspondence between the estimated product yield values and the interpolated experimental ones. The ANN containing 35 neurons with sigmoid transfer function in the hidden layer and a linear neuron in the output one was the simplest. Consequently, the 5, 15 and 60 neurons were also explored in the hidden layer. The ANN structured with an intermediate number of neurons (35) achieved the most adequate MSE, considering mono- and diglyceride products (0.011193, 0.000489). The development of these models contributes to the dynamic estimation of the process.
Fil:Álvarez, Dolores María Eugenia. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil:Bálsamo, Nancy Florentina. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil: Crivello, Mónica Elsie. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil: Modesti, Mario Roberto. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Centro de Investigación en Informática para la Ingeniería (CIII). Argentina.
Peer Reviewed
Fuente
Journal of Engineering Science and Technology Review 12 (4) (2019) 103 - 107
Materia
Artificial Neural Network
Monoglycerides
Yield
Nivel de accesibilidad
acceso abierto
Condiciones de uso
2021-05-27T20:35:23Z
Repositorio
Repositorio Institucional Abierto (UTN)
Institución
Universidad Tecnológica Nacional
OAI Identificador
oai:ria.utn.edu.ar:20.500.12272/5177
Acceder
id RIAUTN_3661c50bfb12f2dc53f8f4356b390b38
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/5177
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-productÁlvarez, Dolores María EugeniaBálsamo, Nancy FlorentinaModesti, Mario RobertoCrivello, Mónica ElsieArtificial Neural NetworkMonoglyceridesYieldBiodiesel is generally manufactured by transesterification, obtaining glycerol as a by-product. The transesterification of methyl stearate selectively produced monoglycerides, for glycerol valuation. Mixed oxides containing lithium catalysed the reaction. The purpose of this work was to develop and compare mathematical models obtained through artificial neural networks (ANN), capable for characterising the relationship between the mole percent conversion of methyl stearate and the yield of the products mono-, di- and triglycerides. The lowest mean squared error (MSE), the highest correlation coefficient (R), similarity in the evolution of validation and simulation errors and absence of data overlearning were considered to select the best model. Three ANNs with backpropagation structures were compared. They evidenced high correspondence between the estimated product yield values and the interpolated experimental ones. The ANN containing 35 neurons with sigmoid transfer function in the hidden layer and a linear neuron in the output one was the simplest. Consequently, the 5, 15 and 60 neurons were also explored in the hidden layer. The ANN structured with an intermediate number of neurons (35) achieved the most adequate MSE, considering mono- and diglyceride products (0.011193, 0.000489). The development of these models contributes to the dynamic estimation of the process.Fil:Álvarez, Dolores María Eugenia. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. ArgentinaFil:Bálsamo, Nancy Florentina. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. ArgentinaFil: Crivello, Mónica Elsie. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. ArgentinaFil: Modesti, Mario Roberto. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Centro de Investigación en Informática para la Ingeniería (CIII). Argentina.Peer Reviewed2021-05-27T20:35:23Z2021-05-27T20:35:23Z2019-07-17info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfJournal of Engineering Science and Technology Review 12 (4) (2019) 103 - 10http://hdl.handle.net/20.500.12272/5177Journal of Engineering Science and Technology Review 12 (4) (2019) 103 - 107reponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacionaleng[1] D.M. Alonso, J.Q. Bon and J.A. Dumesic, Green Chem. 12 1493[2] J.C. Juan, D.A. Kartika, T.Y. Wu and T.Y. Hin, Bioresour. Technol. 102, 452 (2011).[3] D. Singh, P. Patidar, A. Ganesh and S. Mahajani, Ind. Eng. Chem. Res. 52 (42), 14776 (2013).[4] P.G. Belelli, C.A. Ferretti, C.R. Apesteguía, R.M. Ferullo and J.I. Di Cosimo, J. Catal. 323, 132 (2015).[5] N. Balsamo, S. Mendieta, M. Oliva, G. Eimer and M. Crivello, Procedia Mat. Sci. 1, 506 (2012).[6] R. Chimentao, S. Abelló, F. Medina, J. Llorca, J. Sueiras, Y. Cesteros and P. Salagre, J. Catal. 252, 249 (2007).[7] E. Angelescu, O. Pavel, R. Birjega, M. Florea and R. Zavoianu, Appl. Catal. A: General 341, 50 (2008).[8] C. Ferretti, C. Apesteguía and J. Di Cosimo, Appl. Catal. A: General 399, 146 (2011).[9] F. Yang and M. Hannaand, Biotech. for Biofuels, 5, 1 (2012).[10] Ö.D. Bozkurt, F.M. Tunç, N. Bağlar, S. Çelebi, İ.D. Günbaş and A. Uzun, Fuel Process. Technol. 138, 780 (2015).[11] F. Elfghi, Chem. Eng. Res. Diseño, 113, 264 (2016).[12] Z. Nagy, Chem. Eng. J., 127, 95 (2007).[13] K. Desai, S. Survase, P. Saudagar, S. Lele y R. Singhal, Biochem. Eng. J. 41, 266 (2008).[14] MB Abdul Rahman, N. Chaibakhsh, M. Basri, AB Salleh y RNZR Abdul Rahman, Appl. Biochem. Biotechnol. 158, 722 (2009).[15] K. Shahbaz, S. Baroutian, FS Mjalli ,, MA Hashim e IM AlNashef, Chemom. Intell. Laboratorio. Syst. 118, 193 (2012).[16] P. Shivakumar, BR Srinivasa Pai y R. Shrinivasa, Appl. Energy 88, 2344 (2011).[17] R. Chakraborty, Appl. Energía 114, 827 (2014).[18] CI Rocabruno-Valdés, LF Ramírez-Verduzco y JA Hernández, Combustible 147, 9 (2015).[19] GR Moradi, S. Dehghani, F. Khosravian y A. Arjmandzadeh, Renew. Energy 50, 915 (2013).[20] N. Bálsamo, K. Sapag, M. Oliva, G. Pecchi, G. Eimer y M. Crivello, Catal. Hoy. 279 (2), 209 (2017).info:eu-repo/semantics/openAccess2021-05-27T20:35:23ZAttribution-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 InternacionalÁlvarez, Dolores - BáLsamo, Nancy Florentina - Modesti, Mario Roberto -Crivello, Mónica Elsiehttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es2026-10-01T11:58:48Zoai:ria.utn.edu.ar:20.500.12272/5177instacron:UTNInstitucionalhttp://ria.utn.edu.ar/Universidad públicaNo correspondehttp://ria.utn.edu.ar/oaigestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:a2026-10-01 11:58:48.938Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
title Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
spellingShingle Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
Álvarez, Dolores María Eugenia
Artificial Neural Network
Monoglycerides
Yield
title_short Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
title_full Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
title_fullStr Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
title_full_unstemmed Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
title_sort Comparison of neural networks. an estimation model in yield of monoglycerides from biodiesel by-product
dc.creator.none.fl_str_mv Álvarez, Dolores María Eugenia
Bálsamo, Nancy Florentina
Modesti, Mario Roberto
Crivello, Mónica Elsie
author Álvarez, Dolores María Eugenia
author_facet Álvarez, Dolores María Eugenia
Bálsamo, Nancy Florentina
Modesti, Mario Roberto
Crivello, Mónica Elsie
author_role author
author2 Bálsamo, Nancy Florentina
Modesti, Mario Roberto
Crivello, Mónica Elsie
author2_role author
author
author
dc.subject.none.fl_str_mv Artificial Neural Network
Monoglycerides
Yield
topic Artificial Neural Network
Monoglycerides
Yield
dc.description.none.fl_txt_mv Biodiesel is generally manufactured by transesterification, obtaining glycerol as a by-product. The transesterification of methyl stearate selectively produced monoglycerides, for glycerol valuation. Mixed oxides containing lithium catalysed the reaction. The purpose of this work was to develop and compare mathematical models obtained through artificial neural networks (ANN), capable for characterising the relationship between the mole percent conversion of methyl stearate and the yield of the products mono-, di- and triglycerides. The lowest mean squared error (MSE), the highest correlation coefficient (R), similarity in the evolution of validation and simulation errors and absence of data overlearning were considered to select the best model. Three ANNs with backpropagation structures were compared. They evidenced high correspondence between the estimated product yield values and the interpolated experimental ones. The ANN containing 35 neurons with sigmoid transfer function in the hidden layer and a linear neuron in the output one was the simplest. Consequently, the 5, 15 and 60 neurons were also explored in the hidden layer. The ANN structured with an intermediate number of neurons (35) achieved the most adequate MSE, considering mono- and diglyceride products (0.011193, 0.000489). The development of these models contributes to the dynamic estimation of the process.
Fil:Álvarez, Dolores María Eugenia. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil:Bálsamo, Nancy Florentina. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil: Crivello, Mónica Elsie. Universidad Tecnológica Nacional. CONICET. Facultad Regional Córdoba. Centro de Investigación y Tecnología Química. Argentina
Fil: Modesti, Mario Roberto. Universidad Tecnológica Nacional. Facultad Regional Córdoba. Centro de Investigación en Informática para la Ingeniería (CIII). Argentina.
Peer Reviewed
description Biodiesel is generally manufactured by transesterification, obtaining glycerol as a by-product. The transesterification of methyl stearate selectively produced monoglycerides, for glycerol valuation. Mixed oxides containing lithium catalysed the reaction. The purpose of this work was to develop and compare mathematical models obtained through artificial neural networks (ANN), capable for characterising the relationship between the mole percent conversion of methyl stearate and the yield of the products mono-, di- and triglycerides. The lowest mean squared error (MSE), the highest correlation coefficient (R), similarity in the evolution of validation and simulation errors and absence of data overlearning were considered to select the best model. Three ANNs with backpropagation structures were compared. They evidenced high correspondence between the estimated product yield values and the interpolated experimental ones. The ANN containing 35 neurons with sigmoid transfer function in the hidden layer and a linear neuron in the output one was the simplest. Consequently, the 5, 15 and 60 neurons were also explored in the hidden layer. The ANN structured with an intermediate number of neurons (35) achieved the most adequate MSE, considering mono- and diglyceride products (0.011193, 0.000489). The development of these models contributes to the dynamic estimation of the process.
publishDate 2019
dc.date.none.fl_str_mv 2019-07-17
2021-05-27T20:35:23Z
2021-05-27T20:35:23Z
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv Journal of Engineering Science and Technology Review 12 (4) (2019) 103 - 10
http://hdl.handle.net/20.500.12272/5177
identifier_str_mv Journal of Engineering Science and Technology Review 12 (4) (2019) 103 - 10
url http://hdl.handle.net/20.500.12272/5177
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv [1] D.M. Alonso, J.Q. Bon and J.A. Dumesic, Green Chem. 12 1493
[2] J.C. Juan, D.A. Kartika, T.Y. Wu and T.Y. Hin, Bioresour. Technol. 102, 452 (2011).
[3] D. Singh, P. Patidar, A. Ganesh and S. Mahajani, Ind. Eng. Chem. Res. 52 (42), 14776 (2013).
[4] P.G. Belelli, C.A. Ferretti, C.R. Apesteguía, R.M. Ferullo and J.I. Di Cosimo, J. Catal. 323, 132 (2015).
[5] N. Balsamo, S. Mendieta, M. Oliva, G. Eimer and M. Crivello, Procedia Mat. Sci. 1, 506 (2012).
[6] R. Chimentao, S. Abelló, F. Medina, J. Llorca, J. Sueiras, Y. Cesteros and P. Salagre, J. Catal. 252, 249 (2007).
[7] E. Angelescu, O. Pavel, R. Birjega, M. Florea and R. Zavoianu, Appl. Catal. A: General 341, 50 (2008).
[8] C. Ferretti, C. Apesteguía and J. Di Cosimo, Appl. Catal. A: General 399, 146 (2011).
[9] F. Yang and M. Hannaand, Biotech. for Biofuels, 5, 1 (2012).
[10] Ö.D. Bozkurt, F.M. Tunç, N. Bağlar, S. Çelebi, İ.D. Günbaş and A. Uzun, Fuel Process. Technol. 138, 780 (2015).
[11] F. Elfghi, Chem. Eng. Res. Diseño, 113, 264 (2016).
[12] Z. Nagy, Chem. Eng. J., 127, 95 (2007).
[13] K. Desai, S. Survase, P. Saudagar, S. Lele y R. Singhal, Biochem. Eng. J. 41, 266 (2008).
[14] MB Abdul Rahman, N. Chaibakhsh, M. Basri, AB Salleh y RNZR Abdul Rahman, Appl. Biochem. Biotechnol. 158, 722 (2009).
[15] K. Shahbaz, S. Baroutian, FS Mjalli ,, MA Hashim e IM AlNashef, Chemom. Intell. Laboratorio. Syst. 118, 193 (2012).
[16] P. Shivakumar, BR Srinivasa Pai y R. Shrinivasa, Appl. Energy 88, 2344 (2011).
[17] R. Chakraborty, Appl. Energía 114, 827 (2014).
[18] CI Rocabruno-Valdés, LF Ramírez-Verduzco y JA Hernández, Combustible 147, 9 (2015).
[19] GR Moradi, S. Dehghani, F. Khosravian y A. Arjmandzadeh, Renew. Energy 50, 915 (2013).
[20] N. Bálsamo, K. Sapag, M. Oliva, G. Pecchi, G. Eimer y M. Crivello, Catal. Hoy. 279 (2), 209 (2017).
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
2021-05-27T20:35:23Z
Attribution-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Álvarez, Dolores - BáLsamo, Nancy Florentina - Modesti, Mario Roberto -Crivello, Mónica Elsie
https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
eu_rights_str_mv openAccess
rights_invalid_str_mv 2021-05-27T20:35:23Z
Attribution-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Álvarez, Dolores - BáLsamo, Nancy Florentina - Modesti, Mario Roberto -Crivello, Mónica Elsie
https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.source.none.fl_str_mv Journal of Engineering Science and Technology Review 12 (4) (2019) 103 - 107
reponame:Repositorio Institucional Abierto (UTN)
instname:Universidad Tecnológica Nacional
reponame_str Repositorio Institucional Abierto (UTN)
collection Repositorio Institucional Abierto (UTN)
instname_str Universidad Tecnológica Nacional
repository.name.fl_str_mv Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacional
repository.mail.fl_str_mv gestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.ar
_version_ 1877862400624951296
score 13.365483

Publicaciones similares