Design of bio-inspired computational intelligence technique for solving steady thin film flow of Johnson-Segalman fluid on vertical cylinder for drainage problems

In the present study, bio-inspired computing technique is designed for solving governing mathematical relation for steady thin film flow of Johnson-Segalman fluid on vertical cylinder for drainage problems using Artificial Neural Networks (ANNs), genetic algorithms (GAs) and active-set algorithm (ASA). The strength of ANN modeling is exploited for the transformed equation of drainage problem which is derived from original partial differential equation using similarity transform. Training of design parameter of ANNs is carried out with evolutionary computing approach based on GAs hybrid with ASA for rapid local convergence. Design scheme is evaluated for number of cases of all four scenarios of drainage problem based on variations in Stokes number, Weissenberg number, ratio of viscosities, and slip parameters. Comparison of the results is made with Adams numerical method for each case in order to validate the accuracy of the proposed scheme. Results of statistical analysis in terms of performance measures based on mean, standard deviation, mean absolute deviation, root mean square error and Nash-Sutcliffe efficiency as well as their global variations further established the worth of the given scheme for each variant of drainage problem. (C) 2015 Taiwan Institute of Chemical Engineers. Published by Elsevier B.V. All rights reserved.