EXPERIMENTAL ANALYSIS WITH SPECIFIC HEAT OF WATER-BASED ZIRCONIUM OXIDE NANOFLUID ON THE EFFECT OF TRAINING ALGORITHM ON PREDICTIVE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK

Basit Öğe Kaydı
dc.authoridColak, Andac Batur/0000-0001-9297-8134
dc.contributor.authorColak, Andac Batur
dc.date.accessioned2024-11-07T13:25:04Z
dc.date.available2024-11-07T13:25:04Z
dc.date.issued2021
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description.abstractIn this study, the effect of the algorithms used in the training of artificial neural networks on the prediction performance of artificial neural networks has been extensively investigated. In order to make this analysis, three different artificial neural network models have been developed using the Levenberg-Marquardt, Bayesian regularization, and scaled conjugate gradient training algorithms, which are frequently used in the literature. In the training of artificial neural networks, the specific heat values measured experimentally by the differential thermal analysis method of ZrO2/water nanofluid prepared in five different volumetric concentrations have been used. Temperature (T) and volumetric concentration (phi) are defined as input parameters of the multilayer perceptron feed-forward back-propagation artificial neural network model with 15 neurons in the hidden layer and specific heat values are predicted at the output layer. The results showed that artificial neural networks are an ideal tool for predicting the thermophysical properties of nanofluids. However, it has been found that the artificial neural network designed with the Bayesian regularization training algorithm has the highest prediction performance with an average margin of deviation of 0.00009%. It has been observed that the artificial neural network developed with the scaled conjugate gradient training algorithm has the lowest prediction performance with an average error of -0.0032%.
dc.identifier.doi10.1615/HeatTransRes.2021036697
dc.identifier.endpage93
dc.identifier.issn1064-2285
dc.identifier.issn2162-6561
dc.identifier.issue7
dc.identifier.scopus2-s2.0-85106550717
dc.identifier.scopusqualityQ3
dc.identifier.startpage67
dc.identifier.urihttps://doi.org/10.1615/HeatTransRes.2021036697
dc.identifier.urihttps://hdl.handle.net/11480/14473
dc.identifier.volume52
dc.identifier.wosWOS:000649755600005
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherBegell House Inc
dc.relation.ispartofHeat Transfer Research
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241106
dc.subjectartificial neural network
dc.subjecterror rates
dc.subjecttraining algorithm
dc.subjectnanofluid
dc.subjectspecific heat
dc.titleEXPERIMENTAL ANALYSIS WITH SPECIFIC HEAT OF WATER-BASED ZIRCONIUM OXIDE NANOFLUID ON THE EFFECT OF TRAINING ALGORITHM ON PREDICTIVE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu