Identification of distributed parameter systems a neural network based approach

Abstract

In recent years, Advances in scientific computation and developments in spatially resolved sensor technology have critically enhanced the ability to develop modeling strategies, and experimental techniques for the study of the spatiotemporal response of distributed nonlinear systems. Usual alternatives for the modeling of these systems are some simplifying techniques that seek to capture the distributed system dynamics through lumped parameter models, they can be drastically under-resolved, and, miss important features of the true system response. Robust implementations of distributed system identification algorithms based on detailed spatiotemporal experimental data have, therefore, an important role to play. In this project, we present a methodology for the identification of distributed parameter systems, based on artificial neural network architectures.