Swarm intelligence optimized neural networks in solving fractional system of Bagley-Torvik equation

摘要

In this article a heuristic computational intelligence technique has been used for the solution of fractional order system represented by Bagley-Torvik equation. The mathematical model of the equation was made with the help of feed-forward artificial neural networks by defining an unsupervised error. The training of the networks was made with particle swarm optimization algorithm hybridized with Pattern search technique. Proposed scheme was tested successfully by applying to different forms of the equation. Comparisons of the results are made with available approximate analytic techniques, stochastic solvers and exact solutions.