Nonlinear system identification and parameter estimation.

Title: Nonlinear system identification and parameter estimation.
Identifier: AAI3063856
identifier: 3063856
Creator: Lu, Sheng.
Contributor: Adviser: Ki Chon
Date: 2002
Language: English
Publisher: City University of New York.
Subject: Engineering, Electronics and Electrical
Abstract: I. System identification. The ARMA (autoregressive moving average) model plays an important role in system identification which is described as: yn=- i=1pai yn-i+j= 0qbjx n-j+en .;The ARMA model is broadly used in many diverse fields ranging from signal processing, communications, biomedicine, to economics.;The true ARMA model order (p,q) is unknown; therefore, to circumvent this inherent limitation with the ARMA model predication, we have developed two novel algorithms to obtain model order.;II. Parameter estimation. Once we have obtained the accurate ARMA structure, the next step is to calculate the parameters. The conventional methods are generally biased. We have developed a new algorithm to overcome this shortcoming.
Type: dissertation
Source: PQT Legacy CUNY.xlsx
degree: Ph.D.