Comparison of Modeling Approaches for Prediction of Cleaning Efficiency of the Electromagnetic Filtration Process

Yildiz Z., Yuceer M., ABBASOV T.

APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL, vol.26, no.11, pp.899-906, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 26 Issue: 11
  • Publication Date: 2011
  • Journal Name: APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.899-906
  • Inonu University Affiliated: Yes

Abstract

The present study aims at applying different methods for predicting the cleaning efficiency of the electromagnetic filtration process (psi) in the mixtures of water and corrosion particles (rust) of low concentrations. In our study, artificial neural network (ANN), multivariable least square regression (MLSR), and mechanistic modelling approaches were applied and compared for prediction of the cleaning efficiency for the electromagnetic filtration process. The results clearly show that the use of ANN led to more accurate results than the mechanistic filtration and MLSR models. Therefore, it is expected that this study can be a contribution to the cleaning efficiency.