A gradient-based parameter identification method for time-delay chaotic systems

In this paper, the parameter identification problem for a general class of time-delay chaotic systems is considered. The objective of the problem is to determine optimal values for an unknown time-delay and unknown system parameters such that the dynamic model of the system best fits given experimental data. We propose a gradient-based optimization algorithm to solve this problem, where accurate values for the partial derivatives of the error function are obtained by solving a set of auxiliary time-delay systems. Simulation results for two example problems show that the proposed algorithm is robust and efficient.