Friction Factor Prediction for Newtonian and Non-Newtonian Fluids in Pipe Flows Using Neural Networks

The friction factors (f) for Newtonian, power law, Bingham plastic and Herschel-Bulkely fluids were predicted after developing and training four neural networks (NN). Three and four layer NN and Wardnet slab were used for f predictions. When average velocity (u), pipe diameter (D), fluid density and fluid viscosity were used for predicting f values for Newtonian fluids, average absolute error was only 0.00004 with standard deviation of 0.00050 and correlation coefficient (r) of 0.9981. When using flow behaviour index (n), u, D, density and consistency coefficient (k) as inputs of an NN for power law fluids, the average absolute error of predicting f was 0.0116 with r of 0.9998. For prediction of f using yield stress, u, D, density and plastic viscosity as inputs to an NN for Bingham plastic fluids, the average absolute error was 0.0044 with r of 0.9961. The average absolute error was 0.0169 with r of 0.9996 for the prediction of f taking n, yield stress, u, D, density and k as inputs to an NN for Herschel-Bulkely fluids. Inputs except n and density and output were transformed on a logarithmic base to 10 scale. Prediction using log f or extension of f limit reduced prediction errors.