The development of reactor coolant pump vibration monitoring and a diagnostic system in the nuclear power plant

被引:65
作者
Koo, IS [1 ]
Kim, WW [1 ]
机构
[1] Korea Atom Energy Res Inst, Yusung Ku, Taejon 305353, South Korea
关键词
vibration monitoring and diagnostics; rotating machine; Wigner distributor (WD); back propagation network (BPN);
D O I
10.1016/S0019-0578(00)00019-7
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Monitoring abnormalities within reactor coolant pumps due to vibration, we introduce a Wigner distribution (WD) to a vibration monitoring system for analyzing vibration signals, and develop an on-line diagnostic method using the neural network employing back propagation algorithm. A rotor kit is used to simulate the abnormal conditions in the pump such as bearing rubbing, shaft bending, misalignment, etc. The data collected from the kit are analyzed using both a conventional system based on the Fourier transform (FT) and the software developed with the WD in this study, and they are compared. The study shows that spectrum represented by WD makes it easy to analyze the vibration signals of a rotating machine and the developed diagnostic method will help the operators grasp the cause of vibrations. (C) 2000 Published by Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:309 / 316
页数:8
相关论文
共 6 条
[1]  
BOASHASH, 1988, IEEE T ACOUSTICS SPE, V36
[2]  
COHEN L, 1987, IEEE T ACOUSTICS SPE, V35
[3]  
Haykin S.S., 1995, Neural networks. A comprehensive foundation
[4]  
KOO IS, 1997, KAERIRR170596
[5]   THE APPLICATION OF THE WIGNER DISTRIBUTION TO THE IDENTIFICATION OF STRUCTURE-BORNE NOISE COMPONENTS [J].
WAHL, TJ ;
BOLTON, JS .
JOURNAL OF SOUND AND VIBRATION, 1993, 163 (01) :101-122
[6]  
1994, ASME OM S G 14