Title: A partly deterministic and partly stochastic scheme for the identification of fractional-order processes

Authors: Deepyaman Maiti, Mithun Chakraborty, Ayan Acharya, Amit Konar

Addresses: Department of Electronics and Telecommunication Engineering, Jadavpur University, 188 Raja S.C. Mallik Road, Kolkata 700 032, India. ' Department of Electronics and Telecommunication Engineering, Jadavpur University, 188 Raja S.C. Mallik Road, Kolkata 700 032, India. ' Department of Electronics and Telecommunication Engineering, Jadavpur University, 188 Raja S.C. Mallik Road, Kolkata 700 032, India. ' Department of Electronics and Telecommunication Engineering, Jadavpur University, 188 Raja S.C. Mallik Road, Kolkata 700 032, India

Abstract: This contribution proposes a simple yet elegant scheme for identifying a fractional-order dynamic system based on its observed response to a standard excitation. If the fractional powers in the transfer function are precisely known, a set of simultaneous linear equations connecting the unknown coefficient values is obtained and then solved deterministically to yield the desired estimates. In case the fractional powers are uncertain, these are estimated by formulating an optimisation problem and employing a stochastic search algorithm. Results show that the proposed method offers a high degree of accuracy even for data that are intentionally corrupted to simulate real-life conditions.

Keywords: differ-integral; fractional-order systems; Grunwald–Letnikov definition; PSO; particle swarm optimisation; system identification; transfer function.

DOI: 10.1504/IJAIP.2009.026572

International Journal of Advanced Intelligence Paradigms, 2009 Vol.1 No.3, pp.332 - 357

Published online: 19 Jun 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article