On the Use of System Identification for Accurate Parametric Modelling of Non-Linear Systems using Noisy Measurements.

摘要

This paper gives a survey of identification methods for static strongly non-linear systems and proposes a robust and efficient estimation algorithm. Besides the asymptotic properties of the different estimators, practical consideration for non-linear modelling are given. The properties of the discussed system identification methods are illustrated on the measured strongly non-linear DC-characteristic of a forward biased PIN-diode.