Nonlinear Inverse Problems for Von Karman Equations: A Neural Network Approximation

Natalia I. Obodan

Oles Honchar Dnipro National University, Dnipro, Ukraine.

Oleksii S. Mahas *

Oles Honchar Dnipro National University, Dnipro, Ukraine.

Vasilii A. Gromov

Oles Honchar Dnipro National University, Dnipro, Ukraine.

*Author to whom correspondence should be addressed.


Abstract

This paper considers the coefficient inverse problem for the nonlinear boundary problem of von Karman equations. The Fréchet differentiability of the inverse operator is proved and its neural network approximation is constructed with neuroevolution augmented topology model. The model used proves efficient to solve the coefficient inverse problem even for the parameters values close to those corresponding to singular solutions of the direct problem.

Keywords: The coefficient inverse problem, nonlinear boundary problem, von Karman equations, the inverse operator, the Fréchet differentiability, neuro-evolution augmented topologies.


How to Cite

Obodan, Natalia I., Oleksii S. Mahas, and Vasilii A. Gromov. 2017. “Nonlinear Inverse Problems for Von Karman Equations: A Neural Network Approximation”. Asian Research Journal of Mathematics 7 (3):1-9. https://doi.org/10.9734/ARJOM/2017/37856.

Downloads

Download data is not yet available.