Predicting the Conversion Ratio for the Leaching of Celestite in Sodium Carbonate Solution Using an Adaptive Neuro-Fuzzy Inference System

Inal M. M.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, cilt.53, sa.12, ss.4975-4980, 2014 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 53 Sayı: 12
  • Basım Tarihi: 2014
  • Doi Numarası: 10.1021/ie500225a
  • Dergi Adı: INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.4975-4980
  • Kocaeli Üniversitesi Adresli: Evet

Özet

In this study, an adaptive neuro-fuzzy inference system (ANFIS) was used to predict conversion kinetics as the percent ratio of SrSO4 to SrCO3 in sodium carbonate solution. The results of the ANFIS were compared to a previous study of multilayer perceptron (MLP) artificial neural networks (ANNs) that used the same data set. The ANFIS model showed proper fitting to the experimental data according to the mean absolute error (MAE) and determination coefficient (R-2 value). The ANFIS model can easily determine the conversion ratio of SrSO4 to SrCO3. Hence, it is possible to predict the ratio without measuring parameters under different experiments. The Matlab program was used for all coding. Moreover, a user interface program was developed in Simulink to simulate the ANFIS model for entering combinations of input parameters. The ANFIS output showed a satisfactory result in terms of overall performance.