Auxiliary Model-based Stochastic Gradient Algorithm for Multivariable Output Error Systems

The identification problem of multivariable output error systems is considered in this paper. By constructing an auxiliary model using available input-output data and by replacing the unknown inner variables in the information vector with the outputs of the auxiliary model, an auxiliary model-based stochastic gradient (AM-SG) identification algorithm is presented. Convergence analysis using the martingale convergence theorem indicates that the parameter estimates given by the AM-SG algorithm converge to their true values. The AM-SG algorithm with a forgetting factor is given to improve its convergence rate. The simulation results confirm the theoretical findings.

[1]  Wang Dong-qing.  Recursive extended least squares identification method based on auxiliary models , 2009 .

[2]  Feng Ding,et al.  Extended stochastic gradient identification algorithms for Hammerstein-Wiener ARMAX systems , 2008, Comput. Math. Appl..

[3]  Song Zhi-huan,et al.  Hierarchical Optimization Identiflcation of LTI State-space Systems by Projected Gradient Search , 2008 .

[4]  Feng Ding,et al.  Performance analysis of stochastic gradient algorithms under weak conditions , 2008, Science in China Series F: Information Sciences.

[5]  Zhang Yong.  Comparisons of bias compensation methods and other identification approaches for Box-Jenkins models , 2007 .

[6]  Thomas Kailath,et al.  Linear Systems , 1980 .

[7]  Lu-Sheng Zhong.  Hierarchical Optimization Identification of LTI State-space Systems by Projected Gradient Search: Hierarchical Optimization Identification of LTI State-space Systems by Projected Gradient Search , 2009 .

[8]  Feng Ding,et al.  Combined parameter and output estimation of dual-rate systems using an auxiliary model , 2004, Autom..

[9]  Feng Ding,et al.  Hierarchical least squares identification methods for multivariable systems , 2005, IEEE Trans. Autom. Control..

[10]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[11]  Feng Ding,et al.  Hierarchical gradient-based identification of multivariable discrete-time systems , 2005, Autom..

[12]  V. Solo.  The convergence of AML , 1979 .

[13]  Wei Xing Zheng,et al.  A bias correction method for identification of linear dynamic errors-in-variables models , 2002, IEEE Trans. Autom. Control..

[14]  Feng Ding,et al.  Auxiliary model based multi-innovation extended stochastic gradient parameter estimation with colored measurement noises , 2009, Signal Process..

[15]  Q. Zong,et al.  Iterative Identification and Control Design Based on Vinnicombe Distance: Iterative Identification and Control Design Based on Vinnicombe Distance , 2009 .

[16]  Yuqiang Wu,et al.  Asymptotic regulation of cascade systems with unknown control directions and nonlinear parameterization , 2009 .

[17]  Y. Hui.  Bias Compensation Recursive Least Squares Identification for Output Error Systems with Colored Noises , 2007 .

[18]  Feng Ding,et al.  Reconstruction of continuous-time systems from their non-uniformly sampled discrete-time systems , 2009, Autom..

[19]  Zhong Lu.  Hierarchical Optimization Identification of LTI State-space Systems by Projected Gradient Search , 2008 .

[20]  Ding Feng.  Auxiliary models based multi-innovation generalized extended stochastic gradient algorithms , 2008 .

[21]  Feng Ding,et al.  Performance analysis of multi-innovation gradient type identification methods , 2007, Autom..