Title :
The APA based time-variant system identification
Author :
Semushin, Innokentiy
Author_Institution :
Fac. of Math. & Inf. Technol., Ulyanovsk State Univ., Ulyanovsk, Russia
Abstract :
The paper presents the development of Active Principle of Adaptation (APA) in application to time-variant system model identification. In contrast to the Minimum Prediction Error identification methods, the APA based methods allow for consideration the Exact System Models (ESMs), rather than Approximate System Models (ASMs). This results in a development of a new class of Minimum State Prediction Error Methods.
Keywords :
identification; time-varying systems; APA based time-variant system identification; ESM; active principle of adaptation; exact system models; minimum prediction error identification methods; minimum state prediction error methods; Adaptation models; Adaptive filters; Mathematical model; Optimization; Performance analysis; Stochastic processes; Vectors;
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.2014.7040033