Experimental study of performance monitoring for centrifugal fan and fault diagnosis for pipe network in power plant

被引：0
作者：
Wang, SL [1 ]
Hou, JH [1 ]
Yuan, XJ [1 ]
An, LS [1 ]
Liu, TX [1 ]
机构：
[1] N China Elect Power Univ, Dept Power Engn, Baoding 071003, Hebei, Peoples R China
来源：
2002 IEEE REGION 10 CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND POWER ENGINEERING, VOLS I-III, PROCEEDINGS | 2002年
关键词：
flow-monitoring; centrifugal fan; pipe network; neural network; diagnosis;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, accurate fitting on performance curves of fan by RBF networks has been performed and then flow-monitoring model of fan is derived. The experimental study on the fan of 4-73No8D is taken on the condition of the change of rotate speed, resistance of pipe network and angle of regulator, and then the accurate monitoring results of flow are obtained. In the process of experimental study of jam-leak trouble diagnosis for pipe network, the resistance coefficient of pipe network and the static pressure of inlet and outlet of fan are defined as the eigenvector for trouble diagnosis, which act as the inputs of the neural networks. The jam and air leak in different position of pipe network are simulated in laboratory, some experimental data for training and others for test, as a result the troubles of pipe network are diagnosed accurately.
引用
收藏
页码：2019 / 2022
页数：4
相关论文
共 8 条
[1]  
AN LS, 2000, P 2 INT S FLUID MACH, V10, P514
[2]  
BOLTON AN, 1990, IMECH E, P1
[3]   ON THE APPROXIMATE REALIZATION OF CONTINUOUS-MAPPINGS BY NEURAL NETWORKS [J].
FUNAHASHI, K .
NEURAL NETWORKS, 1989, 2 (03) :183-192
[4]  
*GB T, 12362000 GBT
[5]   REGULARIZATION THEORY AND NEURAL NETWORKS ARCHITECTURES [J].
GIROSI, F ;
JONES, M ;
POGGIO, T .
NEURAL COMPUTATION, 1995, 7 (02) :219-269
[6]  
LI Y, 1998, CONT ENERGY CONSERVA, V1, P16
[7]   NETWORKS FOR APPROXIMATION AND LEARNING [J].
POGGIO, T ;
GIROSI, F .
PROCEEDINGS OF THE IEEE, 1990, 78 (09) :1481-1497
[8]  
WOOD CO, CS1693 EPRI
1