Optimization of an artificial neural network by selecting the training function / José S. Torrecilla in Industrial & engineering chemistry research, Vol. 47 N°18 (Septembre 2008)  

Public ISBD [article]  inIndustrial & engineering chemistry research > Vol. 47 N°18 (Septembre 2008) . - p. 7072–7080 Titre : Optimization of an artificial neural network by selecting the training function : application to olive oil mills waste Type de document : texte imprimé Auteurs : José S. Torrecilla, Auteur ; José M. Aragón, Auteur ; María C. Palancar, Auteur Année de publication : 2008 Article en page(s) : p. 7072–7080 Note générale : Chemical engineering Langues : Anglais (eng) Mots-clés : Artificial neural network Olive oil mill waste Fluidized-bed dryer Résumé : This article describes the selection of the training algorithm of an artificial neural network (ANN) used to model the drying of olive oil mill waste in a fluidized-bed dryer. The ANN used was a three-layer perceptron that predicts the moisture value at time t + T from experimental data (solid moisture, input air, and fluidized-bed temperature) at t time; T is the sampling time. In this study, 14 training algorithms were tested. This selection was carried out by applying several statistical tests to the real and predicted moisture values. Afterward, an experimental design was carried out to analyze the influence of the training function parameters on the ANN performance. Finally, Polak−Ribiere conjugate gradient backpropagation was selected as the best training algorithm. The ANN trained with the selected algorithm predicted the moisture with a mean prediction error of 1.6% and a correlation coefficient of 0.998. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8001205 [article] Optimization of an artificial neural network by selecting the training function : application to olive oil mills waste [texte imprimé] / José S. Torrecilla, Auteur ; José M. Aragón, Auteur ; María C. Palancar, Auteur . - 2008 . - p. 7072–7080. Chemical engineering Langues : Anglais (eng) in Industrial & engineering chemistry research > Vol. 47 N°18 (Septembre 2008) . - p. 7072–7080 Mots-clés : Artificial neural network Olive oil mill waste Fluidized-bed dryer Résumé : This article describes the selection of the training algorithm of an artificial neural network (ANN) used to model the drying of olive oil mill waste in a fluidized-bed dryer. The ANN used was a three-layer perceptron that predicts the moisture value at time t + T from experimental data (solid moisture, input air, and fluidized-bed temperature) at t time; T is the sampling time. In this study, 14 training algorithms were tested. This selection was carried out by applying several statistical tests to the real and predicted moisture values. Afterward, an experimental design was carried out to analyze the influence of the training function parameters on the ANN performance. Finally, Polak−Ribiere conjugate gradient backpropagation was selected as the best training algorithm. The ANN trained with the selected algorithm predicted the moisture with a mean prediction error of 1.6% and a correlation coefficient of 0.998. En ligne : http://pubs.acs.org/doi/abs/10.1021/ie8001205

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire