Chaotic system identification via genetic algorithm

In this paper a novel approach for identifying the asymptotic behaviour of non-linear chaotic dynamic systems is proposed. The problem has been faced like an optimisation procedure and it has been solved by using the genetic algorithm approach. Given the asymptotic time evolution of the state variables of the non-linear system that has to be identified, they are used to synchronise another system with the same mathematical model. The difference between the given time evolution and the derived trajectories is used in order to define the functional to be minimised.