Electrohydrodynamic flow solution in ion drag in a circular cylindrical conduit using hybrid neural network and genetic algorithm
Keywords:Artificial neural network modelling, electrohydrodynamic flow analysis, genetic algorithm optimization
In this work, we consider the Electrohydrodynamic (EHD) flow equation in ion drag in a circular cylindrical conduit using artificial neural network (ANN) optimized with genetic algorithm (GA). The governing equation is highly nonlinear of degree two and its nonlinearity is based on parameter. We proposed the solution of EHD using three layer ANN with ten
neurons in each layer and optimized with GA. The results of the proposed algorithm are compared with numerical solution obtained through MATLAB and least square method (LSM) and are in good agreement with these two methods reported in literature.
Assareh, E., Behran, M. A., Ghalambaz, M. &
Noghrehabadi, A. R. (2011). A new solution for natural
convection of darcian fluid about a vertical full cone
embedded in porous media prescribed wall temperature by
using a hybrid neural network-particle swarm optimization
method. International Journal of Mechanical, Aerospace,
Industrial, Mechatronics, and Manufacturing Engineering,
Bég, O.A., Hameed, M. & Bég, T.A. (2013). Chebyshev
spectral collocation simulation of nonlinear boundary value
problems in electrohydrodynamic. International Journal
of ComputationalMethods, Engineering Science and
Espinosa, J. & Vandewalle, J.(2000). Constructing fuzzy
models with linguistic integrity from numerical data-
AFRELI algorithm. IEEE Transaction on Fuzzy Systems,
Espinosa, J. & Vandewalle, J. (1998). Fuzzy Modeling
and Identification, Using AFRELI and FuZion Algorithms,
Ghasemi, S.E., Hatami, M., Mehdizadeh,G.R.& Ganji,
D.D. (2014). Electrohydrodynamic flow analysis in a circular
cylindrical conduit using Least Square Method. Journal of
Khan, A., Raja, M.A.Z. & Qureshi, I.M. (2012). An
application of evolutionary computational technique
to non-linear singular system arising in polytrophic
and isothermal sphere. Global Journal of Research in
Engineering, 12(1):9- 15.
Malek, A.&Shekari, B.R. (2006). Numerical solution
for high order differential equations using a hybrid neural
network—optimization method. Applied Mathematics and
Malik, S.A., Qureshi, I.M., Amir, M. & Haq, I. (2014).
Nature inspired computational technique for the numerical
solution of non-linear singular boundary value problems
arising in physiology. The ScientificWorld Journal,
Mastroberardino, A.(2011). Homotopy analysis method
applied to electrohydrodynamic flow. Communications
in Nonlinear Science and Numerical Simulation, 16(7):
McKee, S., Watson, R., Cuminato, J.A., Caldwell, J. &
Chen, M.S. (1997). Calculation of electrohydrodynamicflow
in a circular cylindrical conduit. ZAMM - Journal of Applied
Mathematics and Mechanics, 77(6):457–465.
Moghtadaei, M., Nik, H.S. & Abbasbandy, S. (2015).
A spectral method for the electrohydrodynamic flow in a
circular cylindrical conduit. Chinese Annals of Mathematics,
Series B, 36(2):307–322.
Pandey, R.K., Baranwal, V.K., Singh, C.S. & Singh, O.P.
(2012). Semi-analytic algorithms for the electrohydrodynamic
flow equation. Journal ofTheoretical and Applied Physics,
Parisi, D.R., Mariani, M.C. & Laborde, M.A. (2003).
Solving differential equations with unsupervised neural
networks. Chemical Engineering and Processing: Process
Intensification, 42(8- 9):715–721.
Paullet, J.E. (1999). On the solutions of
electrohydrodynamicflow in a circular cylindrical conduit.
ZAMM-Journal of Applied Mathematics and Mechanics,
Raja, M. A. Z., Qureshi, I.M. & Khan, J.A. (2011). Swarm
intelligent optimized neural networks for solving fractional
differential equations. International Journal of Innovative
Computations, Information and Control, 7(11):6301–6318.
Raja, M.A.Z. (2014). Solution of the one-dimensional
Bratu equation arising in the fuel ignition model using
ANN optimised with PSO and SQP. Connection Science,
Sadoghi, Y.H., Pakdaman, M. & Modaghegh, H. (2011).
Unsupervised kernel least mean square algorithm for
solving ordinary differential equations. Neurocomputing,
Subha, M., Ananthaswamy, V. & Rajendran, L. (2014).
Analytical solution of non-linear boundary value problem
for the electrohydrodynamicflow equation. International
Journal of Automation and Control Engineering, 3(2):48- 56.
Ünal, M. A. A., Topuz, V. & Erdal, H. (2013). Optimization
of PID controllers using ant colony and genetic algorithms.
Studies in Computational Intelligence.
Yazdi, H.S., Modaghegh, H. & Pakdaman, M. (2012).
Ordinary differential equations solution in kernel space.
Neural Computing and Applications, 21(1):79–85.