14th IFAC Symposium on System Identification, SYSID 2006

SYSID-2006 Paper Abstract


Paper FrB1.5

Wang, Cong (South China Univ. of Tech.), Hill, David J. (The Australian National Univ.)

Locally-Accurate Identification of Nonlinear Systems Using Output Measurements

Scheduled for presentation during the Regular Session "Kernel Based Nonlinear System Identification" (FrB1), Friday, March 31, 2006, 16:50−17:10, Concert Hall

14th IFAC Symposium on System Identification, March 29 - 31, 2006, Newcastle, Australia

This information is tentative and subject to change. Compiled on September 24, 2018

Keywords Nonlinear System Identification, Neural Networks, Continuous Time System Estimation


A ``deterministic learning'' theory was recently proposed for locally-accurate identification of nonlinear system dynamics with full-state measurements. In this paper, it is shown that for a class of nonlinear systems with only output measurements, locally-accurate identification of the underlying system dynamics can be achieved. Specifically, by using a high-gain observer and a dynamical radial basis function network (RBFN), when state estimation is achieved by the high-gain observer, a partial persistence of excitation (PE) condition can still be satisfied, and accurate identification of system dynamics can be achieved in a local region along the estimated state trajectory. The significance of this paper is that it reveals that the difficult problem in nonlinear observer design can be successfully resolved by incorporating the deterministic learning mechanism.