|Table of Contents|

Study of Fault Diagnosis System Based on Wavelet Packet-neural Network(PDF)

《南京理工大学学报》（自然科学版）[ISSN:1005-9830/CN:32-1397/N]

Issue:
2004年04期
Page:
356-359
Research Field:
Publishing date:

Info

Title:
Study of Fault Diagnosis System Based on Wavelet Packet-neural Network
Author(s):
WANG Shu liang 1; WANG Dong 2; FENG Zhen 2;  HAO Yue zhao 3; LIU Gui lin 4
1.Department of Computer Science and Technology,Jiangsu Teachers’ University of Technics,Changzhou 213001,China;2.School of Electromechanical Engineering, Xidian University,Xi’an 710071,China;3.Laboratory of Automation,Xianxi Lvliang Electric Power Filiale Company,Lishi 033000,China;4.Xianxi Coal Imports and Exports Company,Taiyuan 030026,China
Keywords:
features;  rotating machinery;  w avelet packet;  fault diagnosis;  neural network
PACS:
TH17
DOI:
-
Abstract:
The models of neural network recognit ion to fault diagnosis of rotat ing machinery are developed. The features of special f requency segment of the signal picked up by the method of w avelet packets decomposit ion are used as the inputs of neural netw ork. The model can recognize and compute fault swatch of rotat ing machinery . The analysis of the ex perimental data proves that the proposed method is ef ficient.

References:

[ 1] 杨福生1 小波变换的工程分析与应用[ M] . 北京: 科学出版社, 2000.
[ 2] 傅瑜, 冯象初, 徐国华1 钻头不同磨损期振动信号的分维特征[ J] . 西安电子科技大学学报, 2001, 28 ( 2) : 242~ 244.
[ 3] 聂伟荣, 朱继南1 运动目标地震动信号的时频特征分析[ J] . 南京理工大学学报, 2002,26( 5) : 478~ 481.
[ 4] Kim K, Parlos A G, Bharadwaj R M. Senso rless fault diagnosis of induction motors[ J] . IEEE Transactions on Induction Electronics, 2003, 50( 5) : 1 038~ 1 051.
[ 5] Carpenter G A, Grossberg S. ART2: Sel-f organizition of stable category recog nit ion codes for analog input patterns[ J] . Appl Opt, 1987, 26( 23) : 4 919~ 4 930.
[ 6] Sorsa T, Koivo H N, Koiv isto H. Neural netw ork in process fault diagnosis[ J] . IEEE Tr ansactions on System, Man, and Cybernetics, 1991, 21( 4) : 815~ 825.

Memo

Memo:
-
Last Update: 2013-03-11