In this paper we show that the MOESP (Multivariable Output-Error State
sPace) class of subspace model identification (SMI) schemes can be ex
tended to identify Wiener systems, a series connection of a linear dyn
amic system followed by a static nonlinearity. Methods are developed f
or two cases: firstly when the nonlinearity is not an even function, a
nd secondly for systems which include even nonlinearities. Simulations
are used to demonstrate the efficacy of these algorithms, and to comp
are them to existing, correlation based techniques.