<?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>0124-2253</journal-id>
<journal-title><![CDATA[Revista científica]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. Cient.]]></abbrev-journal-title>
<issn>0124-2253</issn>
<publisher>
<publisher-name><![CDATA[Universidad Distrital Francisco José de Caldas]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0124-22532022000100002</article-id>
<article-id pub-id-type="doi">10.14483/23448350.18275</article-id>
<title-group>
<article-title xml:lang="es"><![CDATA[Estimación de fugas en tuberías a presión para sistemas de agua potable mediante redes neuronales artificiales y Epanet]]></article-title>
<article-title xml:lang="en"><![CDATA[Leak Estimation in Pressure Pipes for Drinking Water Systems through Artificial Neuronal Networks and Epanet]]></article-title>
<article-title xml:lang="pt"><![CDATA[Estimación de vazamentos na pressão de tuberías para sistemas de água potável através de redes de neuronales artificiales e Epanet]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Ladino-Moreno]]></surname>
<given-names><![CDATA[Edgar-Orlando]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[García-Ubaque]]></surname>
<given-names><![CDATA[César-Augusto]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[García-Vaca]]></surname>
<given-names><![CDATA[María-Camila]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Distrital Francisco José de Caldas  ]]></institution>
<addr-line><![CDATA[Bogotá ]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad Distrital Francisco José de Caldas  ]]></institution>
<addr-line><![CDATA[Bogotá ]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad Católica de Colombia  ]]></institution>
<addr-line><![CDATA[Bogotá ]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>04</month>
<year>2022</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>04</month>
<year>2022</year>
</pub-date>
<numero>43</numero>
<fpage>2</fpage>
<lpage>19</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0124-22532022000100002&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0124-22532022000100002&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0124-22532022000100002&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen Este trabajo trata de la estimación de una fuga para un sistema de tubería principal sin ramificaciones. Se propone un algoritmo y una red neuronal con cuatro variables de entrada, una capa oculta con 25 neuronas y tres variables de salida. La obtención de los datos se realizó mediante un bucle anidado en Visual Basic (Excel®) estableciendo 35.837 escenarios de fuga para una tubería de 30 m que conduce agua con viscosidad cinemática de 0,000001 (m2/s), un diámetro igual a 0,15222 m, rugosidad de 0,0000015 m, pérdida de carga de 3,5 m y dos accesorios (k  1 , k  2 ) que suma 1,5. Se instalaron en el sistema hidráulico dos caudalímetros y dos manómetros virtuales al inicio y al final de la tubería. Asimismo, se utiliza Epanet® e Hydroflo® (Tahoe Design Software) para estructurar el modelo hidráulico y validar los datos iniciales. Se utilizó MatLab R2021a para analizar los algoritmos de aprendizaje de retropropagación y regularización bayesiana, adoptando la función de transferencia log sigmoide. Como función de control se implementó el error medio cuadrático y el coeficiente de determinación R  2 . El modelo neuronal obtenido presentó un error medio cuadrático de 1,44E-06 y un error relativo igual a 0,0055 % para los datos de entrenamiento. La validación cruzada de la red neuronal se realizó a partir de 5.973 datos de entrada independientes.]]></p></abstract>
<abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract This work deals with the estimation of a leak for a main pipe system without branches. An algorithm and a neural network with 4 input variables are proposed, a hidden layer with 25 neurons and 3 output variables. The data was obtained through a nested loop in Visual Basic (Excel®) establishing 35,837 leak scenarios for a 30 m pipe that conducts water with a kinematic viscosity of 0.000001 (m2/s), a diameter equal to 0.15222 m, roughness of 0.0000015 m, pressure drop of 3.5 m and two accessories (k  1 , k  2 ) that add up to 1.5. Two flowmeters and two virtual pressure gauges were installed in the hydraulic system at the beginning and end of the pipeline. Also, Epanet® and Hydroflo® (Tahoe Design Software) are used to structure the hydraulic model and validate the initial data. Matlab R2021a was used to analyze the Backpropagation and Bayesian Regularization learning algorithms adopting the log sigmoid transfer function. The mean square error and the coefficient of determination R  2 were implemented as a control function. The neural model obtained presented a mean square error of 1.44E-06 and a relative error equal to 0.0055% for the training data. The cross-validation of the neural network was carried out from 5,973 independent input data.]]></p></abstract>
<abstract abstract-type="short" xml:lang="pt"><p><![CDATA[Resumo Este trabalho trata da estimativa de vazamento para um sistema de tubulação principal sem ramificações. Um algoritmo e um vermelho neural com 4 variáveis de entrada são propostos, uma camada oculta com 25 neurônios e 3 variáveis de saída. A coleta de dados é realizada por meio de um loop aninhado no Visual Basic (Excel®) estabelecendo 35.837 cenários de fuga para uma tubulação de 30 m que transporta água com viscosidade cinemática de 0,000001 (m2/s), diâmetro igual a 0,15222 m, rugosidade de 0,0000015 m, perda de carga de 3,5 m dos acessórios (k  1 , k  2 ) que soma 1,5. É instalado no sistema hidráulico dos medidores de vazão e manômetros virtuais no início e no final da tubulação. Asimism, Epanet® e Hydroflo® (Tahoe Design Software) são usados para estruturar o modelo hidráulico e validar os dados iniciais. Use o Matlab R2021a para analisar os algoritmos de aprendizagem de retropropagação e regularização bayesiana adotando a função de transferência log sigmóide. A função de controle implementa o erro quadrático médio e o coeficiente de determinação R  2 . O modelo neuronal obtido apresenta um erro quadrático médio de 1,44E-06 e um erro relativo igual a 0,0055% para os dados de entrada. A validação cruzada do vermelho neuronal foi realizada a partir de 5.973 dados de entrada independentes.]]></p></abstract>
<kwd-group>
<kwd lng="es"><![CDATA[agua potable]]></kwd>
<kwd lng="es"><![CDATA[fugas]]></kwd>
<kwd lng="es"><![CDATA[gestión de los recursos hídricos]]></kwd>
<kwd lng="es"><![CDATA[Levenberg-Marquardt]]></kwd>
<kwd lng="es"><![CDATA[red neuronal artificial.]]></kwd>
<kwd lng="en"><![CDATA[artificial neural network]]></kwd>
<kwd lng="en"><![CDATA[drinking water]]></kwd>
<kwd lng="en"><![CDATA[leakage]]></kwd>
<kwd lng="en"><![CDATA[Levenberg-Marquardt]]></kwd>
<kwd lng="en"><![CDATA[water resources management.]]></kwd>
<kwd lng="pt"><![CDATA[água potável]]></kwd>
<kwd lng="pt"><![CDATA[gestão de recursos hídricos]]></kwd>
<kwd lng="pt"><![CDATA[Levenberg-Marquardt]]></kwd>
<kwd lng="pt"><![CDATA[rede neural artificial]]></kwd>
<kwd lng="pt"><![CDATA[vazamento.]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bishop]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural Networks for Pattern Recognition]]></source>
<year>2005</year>
<publisher-name><![CDATA[Oxford University Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bohórquez]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Alexander]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Simpson]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Lambert]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Leak detection and topology identification in pipelines using fluid transients and artificial neural networks]]></article-title>
<source><![CDATA[Journal of Water Resources Plannign and Management]]></source>
<year>2020</year>
<volume>146</volume>
<numero>6</numero>
<issue>6</issue>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Burton]]></surname>
<given-names><![CDATA[R. T.]]></given-names>
</name>
<name>
<surname><![CDATA[Ukrainetz]]></surname>
<given-names><![CDATA[P. R.]]></given-names>
</name>
<name>
<surname><![CDATA[Nikiforuk]]></surname>
<given-names><![CDATA[P. N.]]></given-names>
</name>
<name>
<surname><![CDATA[Schoenau]]></surname>
<given-names><![CDATA[G. J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Neural networks and hydraulic control-from simple to complex applications]]></article-title>
<source><![CDATA[Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering]]></source>
<year>1999</year>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Caputo]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Pelagagge]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Using neural networks to monitor piping systems]]></article-title>
<source><![CDATA[Process Safety Progress]]></source>
<year>2003</year>
<volume>22</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>119-27</page-range></nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fan]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Machine learning model and strategy for fast and accurate detection of leaks in water supply network]]></article-title>
<source><![CDATA[Journal of Infrastructure Preservation and Resilience]]></source>
<year>2021</year>
<numero>2</numero>
<issue>2</issue>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Foresee]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Hagan]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Gauss-Newton approximation to Bayesian learning]]></article-title>
<source><![CDATA[Proceedings of International Conference on Neural Networks (ICNN'97)]]></source>
<year>1997</year>
</nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gupta]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Kishore]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Jain]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Modeling and simulation of CEERI&#8217;s Water distribution network to detect leakage using HLR approach]]></article-title>
<source><![CDATA[6th International Conference on Reliability, Infocom Technologies and Optimization]]></source>
<year>2017</year>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jasper]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Mahinthakumar]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Ranjithan]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Brill]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Leak detection in water distribution systems using the dividing rectangles (DIRECT) search]]></article-title>
<source><![CDATA[World Environmental and Water Resources Congress]]></source>
<year>2013</year>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lambert]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Fantozzi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Shepherd]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Pressure: Leak flow rates using FAVAD: An improved fast-track practitioner&#8217;s approach]]></article-title>
<source><![CDATA[CCWi2017: Computing and Control in the Water Industry]]></source>
<year>2017</year>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Iseley]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Behbahani]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Fu]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Leakage detection techniques for oil and gas pipelines: State-of-the-art]]></article-title>
<source><![CDATA[Tunnelling and Underground Space Technology]]></source>
<year>2020</year>
<numero>98</numero>
<issue>98</issue>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mashford]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[De Silva]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Marney]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Burn]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An approach to leak detection in pipe networks using analysis of monitored pressure values by support vector machine]]></article-title>
<source><![CDATA[Third International Conference on Network and System Security]]></source>
<year>2009</year>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rojas]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Verde]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Torres]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Estimation of hydraulic gradient for a transport pipeline]]></article-title>
<source><![CDATA[Journal of Pressure Vessel Technology]]></source>
<year>2021</year>
<volume>143</volume>
<numero>3</numero>
<issue>3</issue>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rojek]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Studzinski]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Detection and localization of water leaks in water nets supported by an ICT system with artificial intelligence methods as away forward for smart cities]]></article-title>
<source><![CDATA[Sustainability]]></source>
<year>2019</year>
<volume>11</volume>
<numero>2</numero>
<issue>2</issue>
</nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sabu]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Mahinthakumar]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Ranjithan]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Levis]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Brill]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Water leakage detection using neural networks]]></article-title>
<source><![CDATA[World Environmental and Water Resources Congress 2021: Planning a Resilient Future along America&#8217;s Freshwaters]]></source>
<year>2021</year>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Simpson]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<source><![CDATA[Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations]]></source>
<year>1991</year>
<publisher-name><![CDATA[McGraw-Hill]]></publisher-name>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
