Multi-innovation gradient estimation algorithms for multivariate equation-error autoregressive moving average systems based on the filtering technique

This study concentrates on the parameter estimation of multivariate pseudo-linear autoregressive moving average systems by means of the multi-innovation identification theory and data filtering technique. A multi-innovation stochastic gradient algorithm is derived by introducing the innovation lengt...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET control theory & applications Ročník 13; číslo 13; s. 2086 - 2094
Hlavní autoři:	Ma, Ping, Ding, Feng, Hayat, Tasawar
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	The Institution of Engineering and Technology 03.09.2019
Témata:	autoregressive moving average processes data filtering technique filtering theory gradient methods multiinnovation gradient estimation algorithms multiinnovation stochastic gradient algorithm multivariate equation‐error autoregressive multivariate pseudolinear autoregressive moving average systems parameter estimation Research Article multiinnovation gradient estimation algorithms autoregressive moving average processes filtering theory multivariate equation-error autoregressive parameter estimation data filtering technique multivariate pseudolinear autoregressive moving average systems gradient methods multiinnovation stochastic gradient algorithm
ISSN:	1751-8644, 1751-8652
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This study concentrates on the parameter estimation of multivariate pseudo-linear autoregressive moving average systems by means of the multi-innovation identification theory and data filtering technique. A multi-innovation stochastic gradient algorithm is derived by introducing the innovation length in the stochastic gradient algorithm. Then, the original system is transformed into two subsystems by using a filter. A filtering-based multi-innovation stochastic gradient algorithm is presented, whose parameter estimation accuracy is higher than the multi-innovation stochastic gradient algorithm. The simulation results confirm that these two algorithms are effective.
ISSN:	1751-8644 1751-8652
DOI:	10.1049/iet-cta.2018.6132