Identification of non-linear parametrically varying models using separable least squares
- 10 November 2004
- journal article
- research article
- Published by Taylor & Francis in International Journal of Control
- Vol. 77 (16) , 1382-1392
Abstract
In this paper a novel identification algorithm for a class of non-linear, possibly parameter varying models is proposed. The algorithm is based on separable least squares ideas. These models are given in the form of a linear fractional transformation (LFT) where the ‘forward’ part is represented by a conventional linear regression and the ‘feedback’ part is given by a non-linear map which can take into account scheduling variables available for measurement. The non-linear part of the model can be parameterized according to various paradigms, like, e.g. neural network (NN) or general nonlinear autoregressive exogenous (NARX) models. The estimation algorithm exploits the separability of the criterion used to estimate the parameters. When using a NN, it is possible the explicit computation of the Frechet derivative needed to implement a separable least square algorithm.Keywords
This publication has 26 references indexed in Scilit:
- Identification of multivariable bilinear state space systems based on subspace techniques and separable least squares optimizationInternational Journal of Control, 2001
- Identification of the rainfall–runoff relationship in urban drainage networksControl Engineering Practice, 1999
- Advanced gain-scheduling techniques for uncertain systemsIEEE Transactions on Control Systems Technology, 1998
- Design and analysis of gain-scheduled control using local controller networksInternational Journal of Control, 1997
- A convex characterization of gain-scheduled H/sub ∞/ controllersIEEE Transactions on Automatic Control, 1995
- Nonlinear model validation using correlation testsInternational Journal of Control, 1994
- Constructing NARMAX models using ARMAX modelsInternational Journal of Control, 1993
- Extended model set, global data and threshold model identification of severely non-linear systemsInternational Journal of Control, 1989
- Orthogonal least squares methods and their application to non-linear system identificationInternational Journal of Control, 1989
- A prediction-error and stepwise-regression estimation algorithm for non-linear systemsInternational Journal of Control, 1986