Open Access Open Access  Restricted Access Subscription or Fee Access

Frictional Pressure Drop Prediction Using ANN for Gas-Non-Newtonian Liquid Flow through 45° Bend

Nirjhar Bar, Manindra Nath Biswas, Sudip Kumar Das

Abstract


Applicability of Artificial Neural Networks (ANN) methodology was investigated using experimental data obtained from our earlier experimental studies on the frictional pressure drop per unit length for gas-non-Newtonian liquid flow through 45° bend. This approach proved its worth when rigorous fluid mechanics treatment based on the solution of first principle equations is not tractable. The proposed approach towards the prediction is done using a Multilayer Perceptron (MLP), which is trained with backpropagation algorithm with the help of four different transfer functions in a hidden layer. Statistical analysis confirms that the transfer function 1 with 20 processing elements in the hidden layer gives the best prediction.

Keywords


Bend, Artificial Neural Network (ANN), Multilayer Perceptron (MLP), Backpropagation (BP).

Full Text:

PDF

References


D. M. Himmelblau, “Application of artificial neural network in chemical engineering,” Korean J. Chem. Engg., vol. 17, 2000, pp 373 – 392.

S. K. Das, Studies on two-phase gas-non-Newtonian liquid flow in horizontal, vertical tubes and bends, Ph.D. Thesis, Indian Institute of Technology, Kharagpur, 1988.

K. Yetilmezsoy and S. Demirel, “Artificial neural network (ANN) approach for modeling of Pb(II) adsorption from aqueous by Antep pistachio (Pistacia Vera L.) shells,” J. Haz. Mat., vol 153, 2008, pp 1288 – 1300.

J. Sola and J. Sevilla, “Importance of input data normalization for the application of neural networks to complex industrial problems,” IEEE Trans. Nuclear Sci., vol 44(3), 1997, pp 1464 – 1468.

Guan-De Wu and Shang-Lien Lo, “Effects of data normalization and inherent-factor on decision of optimal coagulant dosage in water treatment by artificial neural network,” Expert Systems with App., vol 37(7), 2010, pp 4974 – 4983.


Refbacks

  • There are currently no refbacks.