Neural-network methods for boundary value problems with irregular boundaries

Partial differential equations (PDEs) with boundary conditions (Dirichlet or Neumann) defined on boundaries with simple geometry have been successfully treated using sigmoidal multilayer perceptrons in previous works. This article deals with the case of complex boundary geometry, where the boundary is determined by a number of points that belong to it and are closely located, so as to offer a reasonable representation. Two networks are employed: a multilayer perceptron and a radial basis function network. The later is used to account for the exact satisfaction of the boundary conditions. The method has been successfully tested on two-dimensional and three-dimensional PDEs and has yielded accurate results.

[1]  G. R. Walsh,et al.  Methods Of Optimization , 1976 .

[2]  D. Fotiadis,et al.  Artificial neural network methods in quantum mechanics , 1997, quant-ph/9705029.

[3]  J. Miller.  Numerical Analysis , 1966, Nature.

[4]  J. Douglas Faires,et al.  Numerical Analysis , 1981 .

[5]  Efstratios Gallopoulos,et al.  An Iterative Method for Nonsymmetric Systems with Multiple Right-Hand Sides , 1995, SIAM J. Sci. Comput..

[6]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[7]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[8]  Dimitris G. Papageorgiou,et al.  The Merlin control language for strategic optimization , 1998 .

[9]  Roger Fletcher,et al.  Practical methods of optimization; (2nd ed.) , 1987 .

[10]  Dimitrios I. Fotiadis,et al.  Flow and heat transfer in CVD reactors : comparison of Raman temperature measurements and finite element model predictions , 1990 .

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[13]  Dimitrios I. Fotiadis,et al.  Frequency spectrum of the human head-neck system , 1997 .

[14]  Dimitris A. Karras,et al.  Neural network training and simulation using a multidimensional optimization system , 1998, Int. J. Comput. Math..

[15]  Dimitris G. Papageorgiou,et al.  Merlin-3.0. A multidimensional optimization environment , 1998 .