Journal of Control and Systems Engineering
Journal of Control and Systems Engineering(JCSE)

ISSN:2331-2963(Print)
ISSN:2331-2971(Online)
Website: www.bowenpublishing.com/jcse/
Identification Accuracy Analysis under Prior Parameters Known in Second Order System
Abstract:
In this paper, the identification accuracy of unknown parameters are analyzed in one second order system. The asymptotic covariance expressions about unknown parameters are derived by using the matrix inversion formula. When one or two parameters are known, the asymptotic covariance expressions corresponding to other parameters are derived. By comparing these asymptotic covariance expressions, we find that the identification accuracy of other parameters did not show any improvement if one parameter is known previously. Also, if each parameter of the other three is known, the identification accuracy of other parameters improves. Finally, the efficiency of the proposed strategy can be confirmed by the simulation example results.
Keywords:Second Order System; Prior Parameter; System Identification; Accuracy Analysis
Author: Jian-hong Wang,Yan-xiang Wang,Yong-hong Zhu,Zhi-feng Xiao

References:

  1. Brett Ninness and Fredrik Gustafsson, “A unifying construction of orthogonal basis for system identification,” IEEE Transaction on Automatic Control, vol. 42, iss. 4, pp. 515-522, Apr. 1997.
  2. E I Silva and G C Goodwin, “Control system design subject to SNR constraints,” Automatica, vol. 46, iss. 2, pp. 299-310, Feb. 2006.
  3. Brett Ninness, “The asymptotic CRLB for the spectrum of ARMA process,” IEEE Transaction on Signal Processing, vol. 51, iss. 6, pp. 1520-1531, June 2003.
  4. Brett Ninness and Hakan Hjalmarsson, “Variance error quantifications that are exact for the finite model order,” IEEE Transaction on Automatic Control, vol. 49, iss. 8, pp. 1275-1291, Aug. 2004.
  5. Brett Ninness, “On the CRLB for combined model and model order estimation of stationary stochastic process,” IEEE Signal Processing Letters, vol. 11, iss. 2, pp. 293-297, Feb. 2004.
  6. Brett Ninness and Hakan Hjalmarsson, “The fundamental role of general orthogonal bases in system identification,” IEEE Transaction on Automatic Control, vol. 44, iss. 7, pp. 1384-1406, July 1999.
  7. Brett Ninness, “Frequency domain analysis of tracking and noise performance of adaptive algorithms,” IEEE Transaction on Signal Processing, vol. 46, iss. 5, pp. 1314-1332, May 1998.
  8. Brett Ninness and Hakan Hjalmarsson, “The effect of regularization on variance error,” IEEE Transaction on Automatic Control, vol. 49, iss. 7, pp. 1142-1147, July 2004.
  9. Brett Ninness and Stuart Gibson, “Quantifying the accuracy of Hammerstein model estimation,” Automatica, vol. 38, iss. 5, pp. 2037-2051, May 2002.
  10. Brett Ninness and Hakan Hjalmarsson, “On the frequency domain accuracy of closed loop estimation,” Automatica, vol. 41, iss. 3, pp. 1109-1122, Mar. 2005.
  11. Brett Ninness and Hakan Hjalmarsson, “Analysis of the variability of joint input output estimation methods,” Automatica, vol. 41, iss. 3, pp. 1123-1132, Mar. 2005.
  12. Hakan Hjalmarsson and Brett Ninness, “Least squares estimation of a class of frequency functions: a finite sample variance expression,” Automatica, vol. 42, iss. 2, pp. 589-600, Feb. 2006.
  13. Jian hong Wang, “Fast gradient algorithm in subspace predictive control under fault estimation,” Journal of Shanghai Jiao Tong University, vol. 47, iss. 7, pp. 1015-1021, July 2013.