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

Confidence Region Test in Closed Loop System Identification
Here, we construct a new confidence region to test the quality of closed loop system identification. This confidence region with respect to model parameters is derived based on an asymptotic normal distribution of the parameter estimator and its covariance matrix, which are estimated from sampled data. The uncertainty bound of the model parameter is constructed in the probabilistic sense by using the inner product form of the asymptotic covariance matrix. Further, the statistical analysis result is used to design the optimal input signal. Thus, our result in this short paper can extend the breadth of the system identification field. Finally, the simulation example results confirm the theoretical identification results.
Keywords:Closed Loop Identification; Model Uncertainty; Confidence Region Test
Author: Jian-hong Wang,Yong-hong Zhu,Xiao-yong Guo


  1. Urban Forssel and Lennart Ljung, “Closed loop identification revisited,” Automatica, vol. 35, no. 7, pp. 1215-1241, July 1999.
  2. L Ljung, System identification: Theory for the user, Prentice Hall, pp. 246-258, May 1999.
  3. R Pintelon and J Schoukens, System identification: a frequency domain approach, New York: IEEE Press, pp. 630-650, June 2001.
  4. Juan C Augero, “A virtual closed loop method for closed loop identification,” Automatica, vol. 47, no. 8, pp. 1626-1637, Aug. 2011.
  5. U Forssell and L Ljung, “Some results on optimal experiment design,” Automatica, vol. 36, no. 5, pp. 749-756, May 2000.
  6. M Leskers, “Closed loop identification of multivariable process with part of the inputs controlled,” International Journal of Control, vol. 80, no. 10, pp. 1552-1561, Oct. 2007.
  7. Hakan Hjalmarssion, “From experiment design to closed loop control,” Automatica, vol. 41, no. 3, pp. 393-438, Mar. 2005.
  8. Hakan Hjalmarssion, “Closed loop experiment design for linear time invariant dynamical systems via LMI,” Automatica, vol. 44, no. 3, pp. 623-636, Mar. 2008.
  9. X Bombois, “Least costly identification experiment for control,” Automatica, vol. 42, no. 10, pp. 1651-1662, Oct. 2006.
  10. Roland Hildebrand, “Identification for control: optimal input design with respect to a worst case gap cost function,” SIAM Journal of Control Optimization, vol. 41, no. 5, pp. 1586-1608, May 2003.
  11. M Gevers, “Identification of multi input systems: variance analysis and input design issues,” Automatica, vol. 42, no. 10, pp. 559-572, Oct. 2006.
  12. M Gevers, “Identification and information matrix: how to get just sufficiently rich,” IEEE Transactions on Automatic Control, vol. 54, no. 12, pp. 2828-2840, Dec. 2009.
  13. Graham C Goodin, “Bias issues in closed loop identification with application to adaptive control,” Communications in Information and Systems, vol. 2, no. 4, pp. 349-370, Apr. 2002.
  14. James S Welsh, “Finite sample properties of indirect nonparametric closed loop identification,” IEEE Transactions on Automatic Control, vol. 47, no. 8, pp. 1277-1291, Aug. 2002.
  15. Sippe G Douma, “Validity of the standard cross correlation test for model structure validation,” Automatica, vol. 44, no. 4, pp. 1285-1294, Apr. 2008.
  16. Abhishek Halder and Raktin Bhattacharya, “Probabilistic model validation for uncertain nonlinear systems,” Automatica, vol. 50, no. 8, pp. 2038-2050, Aug. 2008.