Neural-network based analysis and prediction of a compressor's characteristic performance map

被引：82

作者：

Yu, Youhong

Chen, Lingen ^{[1
]}

Sun, Fengrui

Wu, Chih

机构：

[1] Naval Univ Engn, Postgrad Sch, Wuhan 430033, Peoples R China

[2] USN Acad, Dept Mech Engn, Annapolis, MD 21402 USA

来源：

APPLIED ENERGY | 2007年 / 84卷 / 01期

关键词：

compressor; characteristic map; neural-network; performance prediction;

D O I：

10.1016/j.apenergy.2006.04.005

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

The difficulties, due to a lack of information about stage-by-stage axial-compressor performance, are analyzed. To overcome these issues, a three-layer back-propagation neural-network applied Leven berg-Marquardt algorithm is presented and discussed. The experimental data provided by manufacturers are used for the neural-network training. Through twice training, the compressor's performance map can be predicted. The results can be used for the development of an off-design model or overall dynamic simulation of the behaviour of a gas-turbine power-plant. (c) 2006 Elsevier Ltd. All rights reserved.

引用

页码：48 / 55

页数：8

共 20 条

[1]

[Anonymous], T ASME J ENG GAS TUR

[2]

[Anonymous], NEURAL NETWORK TOOLB

[3]

[Anonymous], 2001, NEURAL NETWORKS COMP

[4] Cooling load prediction for buildings using general regression neural networks [J].