화학공학소재연구정보센터
Industrial & Engineering Chemistry Research, Vol.49, No.19, 9423-9429, 2010
Prediction of Pressure Drop Using Artificial Neural Network for Gas Non-Newtonian Liquid Flow through Piping Components
The ANN approach proved its worth when rigorous fluid mechanics treatment based on the solution of first principle equations is not tractable. Evaluation and prediction of the frictional pressure drop across different piping components such as orifices, gate and globe valves, elbows, and horizontal pipe in 0.0127 m diameter for gas non-Newtonian liquid flow is manifested in this paper. In this paper, we have used the power-law-model (Oswald-de Waele model) liquids only. The experimental data used for the prediction is taken from OM earlier work, Bandyopadhyay (Bandyopadhyay, T. K. Studies on non-Newtonian and gas-non-Newtonian liquid flow through horizontal tube and piping components. Ph.D Thesis, University of Calcutta, Kolkata, India, 2002) and the subsequent publications (Banerjee T. K.; Das, S. K. Gas-non-Newtonian liquid flow through globe and gate valves. Chem. Eng. Commun. 1998, 167, 133-146. Samanta A. K. Banerjee, T. K.; Das, S. K. Pressure loses in orifices for the flow of gas-non-Newtonian liquids. Can. J. Chem. Eng. 1999, 77, 579-583. Bandyopadhyay, T. K.; Banerjee, T. K.; Das, S. K. Gas-non-Newtonian liquid flow through elbows. Chem. Eng. Commun. 2000, 82, 21-33). The proposed approach toward the prediction is clone using a multilayer perceptron (M LP with one hidden layer and four different transfer functions), which is trained with backpropagation algorithm.