System identification: theory for the user
System identification: theory for the user
Structure identification of nonlinear dynamic systems—a survey on input/output approaches
Automatica (Journal of IFAC)
Nonlinear dynamical control systems
Nonlinear dynamical control systems
N4SID: subspace algorithms for the identification of combined deterministic-stochastic systems
Automatica (Journal of IFAC) - Special issue on statistical signal processing and control
Efficient methods for identification of Volterra filter models
Proceedings of of the IEEE winter workshop on Nonlinear digital signal processing
Subspace-based methods for the identification of linear time-invariant systems
Automatica (Journal of IFAC) - Special issue on trends in system identification
IIR Volterra filtering with application to bilinear systems
IEEE Transactions on Signal Processing
Paper: Volterra series and geometric control theory
Automatica (Journal of IFAC)
An analysis of the parametrization by data driven local coordinates for multivariable linear systems
Automatica (Journal of IFAC)
Hi-index | 22.14 |
In this paper, the identification of a class of nonlinear systems which admits input-output maps described by a finite degree Volterra series is considered. In actual fact, it appears that this class can model many important nonlinear multivariable processes not only in engineering, but also in biology, socio-economics, and ecology. To solve this identification problem, we propose a method based on local gradient search in a local parameterization of the state-space realization of finite degree Volterra series with infinite horizon. Using the local parameterization not only reduces the amount of the gradient calculations to the minimal value, but also overcomes the nonuniqueness problem of the optimal solution. Moreover, we propose a sequential projection method to provide an initial estimation of the parameters of finite degree Volterra series realization. This initial estimation is used to initialize the gradient search method.