Title :
Ensuring stability in continuous time system identification instrumental variable method for over-parameterized models
Author :
Huong Ha ; Welsh, James S.
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., Univ. of Newcastle, Newcastle, NSW, Australia
Abstract :
The aim of this paper is to develop constraints to ensure stability of the model in the continuous time, simplified refined instrumental variable system identification algorithm (SRIVC) for over-parameterized models. Specifically, a convex stability domain in the space of polynomial coefficients will be generated and the system parameters will be estimated within this domain. It is found that the model fit obtained using the proposed method offers an improvement to the typical SRIVC method. A Monte Carlo simulation is presented to illustrate the performance of the proposed approach.
Keywords :
Monte Carlo methods; continuous time systems; convex programming; identification; polynomials; stability; Monte Carlo simulation; SRIVC; continuous time system identification; convex stability domain; instrumental variable method; over-parameterized model; polynomial coefficient; simplified refined instrumental variable system identification algorithm; system parameter; Instruments; Poles and zeros; Polynomials; Signal to noise ratio; Stability criteria; Continuous time identification; instrumental variable methods; least squares;
Conference_Titel :
Decision and Control (CDC), 2014 IEEE 53rd Annual Conference on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-1-4799-7746-8
DOI :
10.1109/CDC.2014.7039786
