NARX models of an industrial power plant gas turbine

被引：64

作者：

Basso, M ^{[1
]}

Giarré, L

Groppi, S

Zappa, G

机构：

[1] Univ Florence, Dipartimento Sistemi & Informat, I-50139 Florence, Italy

[2] Univ Palermo, Dipartimento Automaz & Sistemi, I-90128 Palermo, Italy

[3] Gen Elect Nuovo Pignone, I-50127 Florence, Italy

来源：

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY | 2005年 / 13卷 / 04期

关键词：

gas turbines; identification; modeling; nonlinear systems; power systems; turbines;

D O I：

10.1109/TCST.2004.843129

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This brief reports the experience with the identification of a nonlinear autoregressive with exogenous inputs (NARX) model for the PGT10B1 power plant gas turbine manufactured by General Electric-Nuovo Pignone. Two operating conditions of the turbine are considered: isolated mode and nonisolated mode. The NARX model parameters are estimated iteratively with a Gram-Schmidt procedure, exploiting both forward and stepwise regression. Many indexes have been evaluated and compared in order to perform subset selection in the functional basis set and determine the structure of the nonlinear model. Various input signals (from narrow to broadband) for identification and validation have been considered.

引用

页码：599 / 604

页数：6