Finite-element neural networks for solving differential equations

The solution of partial differential equations (PDE) arises in a wide variety of engineering problems. Solutions to most practical problems use numerical analysis techniques such as finite-element or finite-difference methods. The drawbacks of these approaches include computational costs associated with the modeling of complex geometries. This paper proposes a finite-element neural network (FENN) obtained by embedding a finite-element model in a neural network architecture that enables fast and accurate solution of the forward problem. Results of applying the FENN to several simple electromagnetic forward and inverse problems are presented. Initial results indicate that the FENN performance as a forward model is comparable to that of the conventional finite-element method (FEM). The FENN can also be used in an iterative approach to solve inverse problems associated with the PDE. Results showing the ability of the FENN to solve the inverse problem given the measured signal are also presented. The parallel nature of the FENN also makes it an attractive solution for parallel implementation in hardware and software.

[1]  C. Hall Barbosa,et al.  Automation of SQUlD nondestructive evaluation of steel plates by neural networks , 1999, IEEE Transactions on Applied Superconductivity.

[2]  Pei-bai Zhou.  Numerical Analysis of Electromagnetic Fields , 1993 .

[3]  Jiménez,et al.  Neural network differential equation and plasma equilibrium solver. , 1995, Physical review letters.

[4]  Dante C. Youla,et al.  Generalized Image Restoration by the Method of Alternating Orthogonal Projections , 1978 .

[5]  D. Youla,et al.  Image Restoration by the Method of Convex Projections: Part 1ߞTheory , 1982, IEEE Transactions on Medical Imaging.

[6]  N. Phan-Thien,et al.  Neural-network-based approximations for solving partial differential equations , 1994 .

[7]  Hyuk Lee,et al.  Neural algorithm for solving differential equations , 1990 .

[8]  Weidong Chen,et al.  A new extrapolation algorithm for band-limited signals using the regularization method , 1993, IEEE Trans. Signal Process..

[9]  Robert J. Marks,et al.  Inversion of feedforward neural networks: algorithms and applications , 1999, Proc. IEEE.

[10]  Wu Qing,et al.  Using wavelet neural networks for the optimal design of electromagnetic devices , 1997 .

[11]  Lalita Udpa,et al.  Electromagnetic NDE signal inversion by function-approximation neural networks , 2002 .

[12]  Yukio Kosugi,et al.  Neural network representation of finite element method , 1994, Neural Networks.

[13]  Peter S. Hall,et al.  NFDTD concept , 2005, IEEE Transactions on Neural Networks.

[14]  E. Cardelli,et al.  Artificial neural network application for material evaluation by electromagnetic methods , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[15]  Jens Kalkkuhl,et al.  FEM-based neural-network approach to nonlinear modeling with application to longitudinal vehicle dynamics control , 1999, IEEE Trans. Neural Networks.

[16]  Guy Littlefair,et al.  Application of FE-based neural networks to dynamic problems , 1999, ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378).

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

[18]  Dimitris G. Papageorgiou,et al.  Neural-network methods for boundary value problems with irregular boundaries , 2000, IEEE Trans. Neural Networks Learn. Syst..

[19]  Ryusuke Masuoka,et al.  Neural Networks Learning Differential Data , 2000 .

[20]  Carretera de Valencia,et al.  The finite element method in electromagnetics , 2000 .

[21]  Peng Zhang,et al.  Finite element analysis based Hopfield neural network model for solving nonlinear electromagnetic field problems , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[22]  A. Lent,et al.  An iterative method for the extrapolation of band-limited functions , 1981 .

[23]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[24]  Dimitris P. Labridis,et al.  A finite-element mesh generator based on growing neural networks , 2002, IEEE Trans. Neural Networks.