Numerical Solution of Bratu’s Problem Using Multilayer Perceptron Neural Network Method

In this article, an artificial neural network (ANN) method is presented to obtain the closed analytic form of the one dimensional Bratu type equations, which are widely applicable in fuel ignition of the combustion theory and heat transfer. Our goal is to provide optimal solution of Bratu type equations with reduced calculus effort using ANN method in comparison to the other existing methods. Various test cases have been simulated using proposed neural network model and the accuracy has been substantiated by considering a large number of simulation data for each model with enough independent runs. Numerical results show that this method has potentiality to become an efficient approach for solving Bratu’s problems with less computing time and memory space.

[1]  Mohsen Hayati,et al.  Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations , 2009, Appl. Soft Comput..

[2]  Kevin Stanley McFall,et al.  Artificial Neural Network Method for Solution of Boundary Value Problems With Exact Satisfaction of Arbitrary Boundary Conditions , 2009, IEEE Transactions on Neural Networks.

[3]  Raja Muhammad Asif Zahoor,et al.  Numerical treatment for solving one-dimensional Bratu problem using neural networks , 2012, Neural Computing and Applications.

[4]  Muhammed I. Syam,et al.  An efficient method for solving Bratu equations , 2006, Appl. Math. Comput..

[5]  Aregbesola Y.A.S.,et al.  NUMERICAL SOLUTION OF BRATU PROBLEM USING THE METHOD OF WEIGHTED RESIDUAL , 2003 .

[6]  Y. Shirvany,et al.  Numerical solution of the nonlinear Schrodinger equation by feedforward neural networks , 2008 .

[7]  Patrick van der Smagt.  Minimisation methods for training feedforward neural networks , 1994, Neural Networks.

[8]  K. Schmitt,et al.  The Liouville–Bratu–Gelfand Problem for Radial Operators , 2002 .

[9]  John P. Boyd,et al.  One-point pseudospectral collocation for the one-dimensional Bratu equation , 2011, Appl. Math. Comput..

[10]  John P. Boyd,et al.  Chebyshev polynomial expansions for simultaneous approximation of two branches of a function with application to the one-dimensional Bratu equation , 2003, Appl. Math. Comput..

[11]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

[12]  Hikmet Caglar,et al.  B-spline method for solving Bratu's problem , 2010, Int. J. Comput. Math..

[13]  Shih-Hsiang Chang,et al.  A new algorithm for calculating two-dimensional differential transform of nonlinear functions , 2009, Appl. Math. Comput..

[14]  Manoj Kumar,et al.  Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey , 2011, Comput. Math. Appl..

[15]  Yimin Wei,et al.  On integral representation of the generalized inverse AT, S(2) , 2003, Appl. Math. Comput..

[16]  Ron Buckmire,et al.  Application of a Mickens finite‐difference scheme to the cylindrical Bratu‐Gelfand problem , 2004 .