<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0121-1129</journal-id>
<journal-title><![CDATA[Revista Facultad de Ingeniería]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. Fac. ing.]]></abbrev-journal-title>
<issn>0121-1129</issn>
<publisher>
<publisher-name><![CDATA[Universidad Pedagógica y Tecnológica de Colombia]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0121-11292020000100009</article-id>
<article-id pub-id-type="doi">10.19053/01211129.v29.n54.2020.10514</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Neural Model for the Prediction of Volume Losses in the Aging Process of Rums]]></article-title>
<article-title xml:lang="es"><![CDATA[Modelo neuronal para la predicción de mermas en el proceso de añejamiento de rones]]></article-title>
<article-title xml:lang="pt"><![CDATA[Modelo neuronal para a predição de mermas no processo de envelhecimento de runs]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[García-Castellanos]]></surname>
<given-names><![CDATA[Beatriz]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Pérez-Ones Ph. D.]]></surname>
<given-names><![CDATA[Osney]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Zumalacárregui-de-Cárdenas Ph. D.]]></surname>
<given-names><![CDATA[Lourdes]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Blanco-Carvajal M. Sc.]]></surname>
<given-names><![CDATA[Idania]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[López-de-la-Maza]]></surname>
<given-names><![CDATA[Luis-Eduardo]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Instituto Cubano de Investigaciones de los Derivados de la Caña de Azúcar  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad Tecnológica de La Habana &#8220;José Antonio Echeverría&#8221;  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad Tecnológica de La Habana &#8220;José Antonio Echeverría&#8221;  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af4">
<institution><![CDATA[,Instituto Cubano de Investigaciones de los Derivados de la Caña de Azúcar  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af5">
<institution><![CDATA[,Universidad Tecnológica de La Habana &#8220;José Antonio Echeverría  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>03</month>
<year>2020</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>03</month>
<year>2020</year>
</pub-date>
<volume>29</volume>
<numero>54</numero>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0121-11292020000100009&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0121-11292020000100009&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0121-11292020000100009&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract The rum aging process shows volume losses, called wastage. The numerical operation variables: product, boardwalk, horizontal and vertical positions, date, volume, alcoholic degree, temperature, humidity and aging time, recorded in databases, contain valuable information to study the process. MATLAB 2017 software was used to estimate volume losses. In the modeling of the rum aging process, the multilayer perceptron neuronal network with one and two hidden layers was used, varying the number of neurons in these between 4 and 10. The Levenberg-Marquadt (LM) and Bayesian training algorithms were compared (Bay) The increase in 6 consecutive iterations of the validation error and 1,000 as the maximum number of training cycles were the criteria used to stop the training. The input variables to the network were: numerical month, volume, temperature, humidity, initial alcoholic degree and aging time, while the output variable was wastage. 546 pairs of input/output data were processed. The statistical Friedman and Wilcoxon tests were performed to select the best neural architecture according to the mean square error (MSE) criteria. The selected topology has a 6-4-4-1 structure, with an MSE of 2.1&#8729;10-3 and a correlation factor (R) with experimental data of 0.9898. The neural network obtained was used to simulate thirteen initial aging conditions that were not used for training and validation, detecting a coefficient of determination (R2) of 0.9961.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen El proceso de añejamiento de ron experimenta pérdidas de volumen, denominadas mermas. Las variables numéricas de operación: producto, rambla, posiciones horizontal y vertical, fecha, volumen, grado alcohólico, temperatura, humedad y tiempo de añejamiento, registradas en bases de datos, contienen información valiosa para estudiar el proceso. Se utilizó el software MATLAB 2017 para estimar las pérdidas en volumen. En la modelación del proceso de añejamiento de ron se utilizó la red neuronal perceptrón multicapa con una y dos capas ocultas, variándose el número de neuronas en estas entre 4 y 10. Se compararon los algoritmos de entrenamiento Levenberg-Marquadt (L-M) y Bayesiano (Bay). El incremento en 6 iteraciones consecutivas del error de validación y 1 000 como número máximo de ciclo de entrenamiento fueron los criterios utilizados para detener el entrenamiento. Las variables de entrada a la red fueron: mes numérico, volumen, temperatura, humedad, grado alcohólico inicial y tiempo de añejamiento, mientras que la variable de salida fue mermas. Se procesaron 546 pares de datos de entrada/salida. Se realizaron las pruebas estadísticas de Friedman y Wilcoxon para la selección de la arquitectura neuronal de mejor comportamiento de acuerdo al criterio del error cuadrático medio (MSE). La topología seleccionada presenta la estructura 6-4-4-1, con un MSE de 2.1&#8729;10-3 y un factor de correlación (R) con los datos experimentales de 0.9981. La red neuronal obtenida se empleó para la simulación de trece condiciones iniciales de añejamiento que no fueron empleadas para el entrenamiento y la validación, detectándose un coeficiente de determinación (R2) de 0.9961.]]></p></abstract>
<abstract abstract-type="short" xml:lang="pt"><p><![CDATA[Resumo O processo de envelhecimento de rum experimenta perdas de volume, denominadas mermas. As variáveis numéricas de operação: produto, rambla, posições horizontal e vertical, data, volume, grau alcoólico, temperatura, humidade e tempo de envelhecimento, registradas em bases de dados, contêm informação valiosa para estudar o processo. Utilizou-se o software MATLAB 2017 para estimar as perdas em volume. Na modelação do processo de envelhecimento de rum utilizou-se a rede neuronal perceptron multicamada com uma e duas camadas ocultas, variando-se o número de neurônios nestas entre 4 e 10. Compararam-se os algoritmos de treinamento Levenberg-Marquadt (L-M) e Bayesiano (Bay). O incremento em 6 iterações consecutivas do erro de validação e 1 000 como número máximo de ciclo de treinamento foram os critérios utilizados para deter o treinamento. As variáveis de entrada à rede foram: mês numérico, volume, temperatura, humidade, grau alcoólico inicial e tempo de envelhecimento, enquanto que a variável de saída foi mermas. Processaram-se 546 pares de dados de entrada/saída. Realizaram-se as provas estatísticas de Friedman e Wilcoxon para a seleção da arquitetura neuronal de melhor comportamento de acordo ao critério do erro quadrático médio (ECM). A topologia selecionada apresenta a estrutura 6-4-4-1, com um ECM de 2.1&#8729;10-3 e um fator de correlação (R) com os dados experimentais de 0.9981. A rede neuronal obtida empregou-se para a simulação de treze condições iniciais de envelhecimento que não foram empregadas para o treinamento e a validação, detectando-se um coeficiente de determinação (R2) de 0.9961.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[aging]]></kwd>
<kwd lng="en"><![CDATA[artificial neural networks]]></kwd>
<kwd lng="en"><![CDATA[modeling]]></kwd>
<kwd lng="en"><![CDATA[rums]]></kwd>
<kwd lng="en"><![CDATA[volume losses]]></kwd>
<kwd lng="es"><![CDATA[añejamiento]]></kwd>
<kwd lng="es"><![CDATA[mermas]]></kwd>
<kwd lng="es"><![CDATA[modelación]]></kwd>
<kwd lng="es"><![CDATA[redes neuronales artificiales]]></kwd>
<kwd lng="es"><![CDATA[rones]]></kwd>
<kwd lng="pt"><![CDATA[envelhecimento]]></kwd>
<kwd lng="pt"><![CDATA[mermas]]></kwd>
<kwd lng="pt"><![CDATA[modelação]]></kwd>
<kwd lng="pt"><![CDATA[redes neuronais artificiais]]></kwd>
<kwd lng="pt"><![CDATA[runs]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>[1]</label><nlm-citation citation-type="">
<collab>Ministerio de la industria alimentaria.</collab>
<source><![CDATA[Resolución No. 12/19. La Habana, Cuba,]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B2">
<label>[2]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Marcano]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Tradición en Las Antillas]]></article-title>
<source><![CDATA[El ron.]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B3">
<label>[3]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Witten]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Frank]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Data Mining.]]></source>
<year>2005</year>
<publisher-loc><![CDATA[Amsterdam ]]></publisher-loc>
<publisher-name><![CDATA[Morgan Kaufmann Publishers]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<label>[4]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Servente]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Algoritmos TDIDT aplicados a la minería de datos inteligente]]></source>
<year>2002</year>
<publisher-loc><![CDATA[Buenos Aires ]]></publisher-loc>
<publisher-name><![CDATA[Universidad de Buenos Aires]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B5">
<label>[5]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zumalacárregui]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Pérez]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Hernández]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Cruz]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Modelación del equilibrio líquido-vapor a presión constante de mezclas etanol-agua utilizando redes neuronales artificiales]]></article-title>
<source><![CDATA[Tecnología Química]]></source>
<year>2018</year>
<volume>38</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>527-48</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>[6]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Abdi]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Williams]]></surname>
<given-names><![CDATA[L. J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Principal component analysis]]></article-title>
<source><![CDATA[Wiley Interdisciplinary Reviews: Computational Statistics]]></source>
<year>2010</year>
<volume>2</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>433-59</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>[7]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Caicedo]]></surname>
<given-names><![CDATA[E. F.]]></given-names>
</name>
<name>
<surname><![CDATA[López]]></surname>
<given-names><![CDATA[J. A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Una aproximación práctica a las redes neuronales artificiales]]></source>
<year>2017</year>
<publisher-loc><![CDATA[Santiago de Cali ]]></publisher-loc>
<publisher-name><![CDATA[Programa Editorial Universidad del Valle, Edición digital]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B8">
<label>[8]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Terán-Villanueva]]></surname>
<given-names><![CDATA[J. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Ibarra-Martínez]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Laria-Menchaca]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Castán-Rocha]]></surname>
<given-names><![CDATA[J. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Treviño-Berrones]]></surname>
<given-names><![CDATA[M. G.]]></given-names>
</name>
<name>
<surname><![CDATA[García-Ruiz]]></surname>
<given-names><![CDATA[A. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Martínez-Infante]]></surname>
<given-names><![CDATA[J. E.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Estudio de redes neuronales para el pronóstico de la demanda de asignaturas]]></article-title>
<source><![CDATA[Revista Facultad de Ingeniería]]></source>
<year>2019</year>
<volume>28</volume>
<numero>50</numero>
<issue>50</issue>
<page-range>30-9</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>[9]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Korany]]></surname>
<given-names><![CDATA[M. A]]></given-names>
</name>
<name>
<surname><![CDATA[Mahgoub]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Fahmy]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Maher]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Application of artificial neural networks for response surface modelling in HPLC method development]]></article-title>
<source><![CDATA[Journal of Advanced Research]]></source>
<year>2012</year>
<volume>3</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>53-63</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>[10]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[López]]></surname>
<given-names><![CDATA[L. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Zumalacárregui]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Pérez]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Llanes]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Obtención de un modelo neuronal para la estimación de la concentración de etanol en la destilería Héctor Molina]]></article-title>
<source><![CDATA[Tecnología Química]]></source>
<year>2018</year>
<volume>38</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>315-25</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
