People Education Research Industrial Agenda  
Current Research Archive Publications PhD theses Software      

next up previous contents

Identification of nonlinear state-space systems

Project members: V. Verdult, M. Verhaegen

Over the years considerable attention has been given to the identification of linear systems. Linear systems have proven their usefulness in numerous engineering applications, and many theoretical results have been derived for the identification and control of these systems. However, most real-life systems inherently show nonlinear dynamic behavior. Consequently, the use of linear models has its limitations. When performance requirements are high, the linear model is no longer accurate enough, and nonlinear models have to be used. This motivates the development of identification methods for nonlinear systems.

In this project, new system identification methods are developed for nonlinear state-space systems. Although most work on nonlinear system identification deals with nonlinear input-output descriptions, state-space systems are considered, because they are especially suitable for dealing with multiple inputs and outputs, and they usually require less parameters to describe a system than input-output descriptions do. Equally important, the starting point of many nonlinear control methods is a state-space model of the system to be controlled. Currently, identification methods have been developed for three particular types of nonlinear systems: linear parameter-varying state-space systems, bilinear state-space systems, and local linear state-space systems.

next up previous contents
Next: Development of computationally efficient and Up: System identification Previous: Bounding uncertainty in subspace identification

Back to top

Last modified: 24 March 2005, 10:16 UTC
Search   Site map