Download PDFOpen PDF in browser

Modeling of Oxidative Desulfurization Process by Artificial Neural Network

EasyChair Preprint no. 7943

9 pagesDate: May 14, 2022

Abstract

In recent years Oxidative desulfurization process, having significant advantage against other well-known desulfurization process, have received considerable attention. In this study, modeling of Oxidative desulfurization of fuel oil was investigated using artificial neural network (ANN). It is found that ANN provides a useful method for developing nonlinear relations between variables. To determine effective parameters on ODS process; a principal component analysis was performed on dat

In recent years Oxidative desulfurization process, having significant advantage against other well-known desulfurization process, have received considerable attention. In this study, modeling of Oxidative desulfurization of fuel oil was investigated using artificial neural network (ANN). It is found that ANN provides a useful method for developing nonlinear relations between variables. To determine effective parameters on ODS process; a principal component analysis was performed on data. The results showed that oxidant quantity, contact time and reactor temperature play important roles in determination of desulfurization performance. An artificial neural network, using back propagation (BP), was also utilized for modeling oxidative desulfuration process of fuel oil. Different structures were tried with several neurons in the hidden layer and the total error was calculated. Finally, eight hidden neurons were applied. The comparison between the outputs of ANN modeling being referred as BP-NN 5:8:1 and the experimental data showed satisfactory agreement.

Keyphrases: Artificial Neural Network, desulfurization, modeling

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:7943,
  author = {Mehdi Gheisari},
  title = {Modeling of Oxidative Desulfurization Process by Artificial Neural Network},
  howpublished = {EasyChair Preprint no. 7943},

  year = {EasyChair, 2022}}
Download PDFOpen PDF in browser