doiSerbia

Artificial neural network model with the parameter tuning assisted by a differential evolution technique: The study of the hold up of the slurry flow in a pipeline

Lahiri S.K. (Department of Chemical Engineering, NIT, Durgapur, West Bengal, India)
Ghanta K.C. (Department of Chemical Engineering, NIT, Durgapur, West Bengal, India)

This paper describes a robust hybrid artificial neural network (ANN) methodology which can offer a superior performance for the important process engineering problems. The method incorporates a hybrid artificial neural network and differential evolution technique (ANN-DE) for the efficient tuning of ANN meta parameters. The algorithm has been applied for the prediction of the hold up of the solid liquid slurry flow. A comparison with selected correlations in the literature showed that the developed ANN correlation noticeably improved the prediction of hold up over a wide range of operating conditions, physical properties, and pipe diameters.

Keywords: artificial neural network, differential evolution, slurry hold up, slurry flow