Identification of the Wiener system composed of an infinite impulse response (IIR) linear subsystem followed by a static nonlinearity is considered. The recursive estimates for unknown coefficients of the linear subsystem and for the values of the nonlinear function at any fixed points are given by the stochastic approximation algorithms with expanding truncations (SAAWET). With the help of properties of the Markov chain connected with the linear subsystem, all estimates derived in the paper are proved to be strongly consistent. In comparison with the existing results on the topic, the method presented in the paper simplifies the convergence analysis and requires weaker conditions. A numerical example is given, and the simulation results are consistent with the theoretical analysis.
Wiener system recursive identification stochastic approximation Markov chain strong consistency
Chen H F, Guo L. Identification and Stochastic Adaptive Control. Boston: Birkhäuser, 1991MATHGoogle Scholar
Fan J Q, Yao Q. Nonlinear Time Series: Nonparametric and Parametric Approach. New York: Springer-Verlag, 2003MATHCrossRefGoogle Scholar
Ljung L. System Identification: Theory for Users. Upper Saddle River: Prentice Hall, 1987Google Scholar
Zhao W X, Chen H F, Zheng W X. Recursive identification for nonlinear ARX systems based on stochastic approximation algorithm. IEEE Trans Autom Control, 2010, 55: 1287–1299MathSciNetCrossRefGoogle Scholar
Bussgang J J. Crosscorrelation functions of amplitude-distorted Gaussian signals. Technical Report 216. MIT Research Laboratory of Electronics, 1952Google Scholar