Identification of linearly overparametrized nonlinear systems
- 1 July 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 37 (7) , 1073-1078
- https://doi.org/10.1109/9.148376
Abstract
Often, a dynamical model is nonlinear in the unknown parameters, but it can be transformed into an overparametrized linear regression model, where the components of the overparametrization vector are nonlinear functions of the smaller number of unknown parameters. We present an algorithm that directly identifies the unknown parameters, we characterize the convergence domains under two different sets of assumptions on the excitation of the signals, and we compute the corresponding convergence ratesKeywords
This publication has 6 references indexed in Scilit:
- Adaptive identification of systems with polynomial parameterizationsIEEE Transactions on Circuits and Systems, 1988
- Identification of physical parameters in structured systemsAutomatica, 1988
- Parameter identification using prior information†International Journal of Control, 1986
- Self-tuning control with a priori plant knowledgePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Robust identification of partially known systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- Adaptive observers with exponential rate of convergenceIEEE Transactions on Automatic Control, 1977