Solution of Differential - Algebraic Equation Systems Using Neural Networks

Author

Samath, J. Abdul ; Balasubramaniam, P.

Author_Institution

Sri Krishna Coll. of Eng. & Technol., Coimbatore

Volume

1

fYear

2007

fDate

13-15 Dec. 2007

Firstpage

3

Lastpage

8

Abstract

In this paper, the solution of differential algebraic equations (DAES) is obtained using neural networks. The goal is to obtain accurate solution with reduced calculus effort by comparing the solution of the DAES obtained from Pade approximation and neural network method, the solution of DAE system is computed by feedforward neural network (FFNN). The solution of the neural network approach to this problem is very close to the exact solution. An illustrative numerical method is presented for the proposed method.

Keywords

approximation theory; differential algebraic equations; feedforward neural nets; Pade approximation; differential-algebraic equation systems; feedforward neural network; Artificial neural networks; Biological system modeling; Chemical engineering; Computer networks; Differential algebraic equations; Differential equations; Electronic mail; Feedforward neural networks; Neural networks; Nonlinear equations;

fLanguage

English

Publisher

ieee

Conference_Titel

Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on

Conference_Location

Sivakasi, Tamil Nadu

Print_ISBN

0-7695-3050-8

Type

conf

DOI

10.1109/ICCIMA.2007.49

Filename

4426544