Abstract
System identification has been growing in an engineering community over the last 60 years, and an intensive research has been published in this field. This study presents an identification method of a linear time-invariant continuous dynamic system directly from time series data. The considered system is represented in a state space form. All states are assumed to be measured. The proposed identification algorithm is demonstrated and investigated, with noise-free data and noisy data, on a MATLAB simulation environment. The results confirm that the simple procedures of the proposed algorithm give an effective and successful estimation of the system parameter matrices.
Publisher
Alasmarya Islamic University
Reference35 articles.
1. M. Moonen, B. De Moor, L. Vandenberghe, and J. Vandewalle, "On- and Off-Line Identification of Linear State-Space Models," International Journal of Control, vol. 49, no.1, pp. 219-232, 1989.
2. D. Park and S-K. Hong, "On-line System Identification using State Observer," Kintex, Gyeonggi-Do, Korea, June 2-5, 2005.
3. N. K. Sinha and B. Kuszta, Modeling and Identification of Dynamic systems, Van Nostrand Reinhold Company Inc, New York, Cincinnati, Toronto, London, Melbourne, 1983.
4. S. Ahmed, "Identification from Step Response – The Integral Equation Approach," The Canadian Journal for Chemical Engineering, vol. 94, pp. 2243-2256, 2016.
5. Q. G. Wang, X. Guo, and Y. Zhang, "Direct identification of continuous time delay systems from step response," Journal of Process Control, vol 11, pp. 531–542, 2001.