Identification of Wiener system with monotonous nonlinearity

Qinghua Zhang (1) , Anatoli B. Juditsky , Lennart Ljung (2)

1 SISYPHE - SIgnals and SYstems in PHysiology & Engineering
2 ISY/ICG - Information Coding - Department of Electrical Engineering [Linköping]

A Wiener system is composed of a linear dynamic subsystem followed by a static nonlinearity. It is well known in the literature that the identification of the linear subsystem of a Wiener system can be separated from that of the output nonlinearity, if the input signal is a Gaussian noise. In order to deal with the non Gaussian input case, two new algorithms are proposed in this paper for direct identification of the linear subsystem, regardless of any parametrization of the output nonlinearity. The essential assumption required in this paper is the strict monotonousness of the output nonlinearity.

Mots clés: nonlinear system identification; Wiener system; quadratic programming

Domaines: Automatique

Qinghua Zhang, Anatoli B. Juditsky, Lennart Ljung. Identification of Wiener system with monotonous nonlinearity. 14th IFAC Symposium on System Identification (SYSID), Mar 2006, Newcastle, Australia. pp.166-171, ⟨10.3182/20060329-3-AU-2901.00020⟩. ⟨hal-00854858⟩