Title :
Maximum likelihood gradient based identification algorithm for output error systems with colored noises
Author :
Li Junhong ; Ding Rui
Author_Institution :
Sch. of Electr. Eng., Nantong Univ., Nantong, China
Abstract :
This paper considers the parameter estimation problems of output error autoregressive (OEAR) systems based on the maximum likelihood principle and the gradient search principle. A maximum likelihood forgetting factor stochastic gradient algorithm and a maximum likelihood iterative gradient identification algorithm are developed. The simulation results show that the proposed algorithms can effectively estimate the parameters of the OEAR systems.
Keywords :
autoregressive processes; gradient methods; iterative methods; maximum likelihood estimation; parameter estimation; search problems; OEAR systems; colored noises; gradient search principle; maximum likelihood iterative gradient identification algorithm; maximum likelihood principle; output error autoregressive systems; parameter estimation problems; stochastic gradient algorithm; Educational institutions; Maximum likelihood estimation; Parameter estimation; Signal processing algorithms; Stochastic processes; Vectors; Iterative identification; Maximum likelihood; Parameter estimation; Stochastic gradient;
Conference_Titel :
Control Conference (CCC), 2013 32nd Chinese
Conference_Location :
Xi´an
