[1]L IHong-fang,ZHANG Qing-hua,et al.Application of a novel immune network learn ing algor ithm to fault diagnosis[J].CAAI Transactions on Intelligent Systems,2008,3(5):449-454.
Copy

Application of a novel immune network learn ing algor ithm to fault diagnosis

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 3 Number of periods: 2008 5 Page number: 449-454 Column: 学术论文—机器学习 Public date: 2008-10-25
Title:
Application of a novel immune network learn ing algor ithm to fault diagnosis
Author(s):
L IHong-fang1;  2 ;  ZHANG Qing-hua1 ;  XIE Ke-ming2
1. College of Electronic Information and Computer, Maoming University, Maoming 525000, China;
2. College of Information Engi2 neering, Taiyuan University of Technology, Taiyuan 030024, China
Keywords:
clone selection;  fault diagnosis;  immune network;  non2dimensional parameter
CLC:
TP18
DOI:
-
Abstract:
Immune algorithms have p roblems diagnosing faults in rotatingmachines. This is due to the volume of u2 nique data points they must p rocess, and the difficulty in eliminating redundant data. Hence, a novel immune net2 work learning algorithm was formulated, in which antibody supp ression was introduced in the p rocess of generating initial antibodies, and a supp ression threshold for antibodies with respect to neighboring antibodies was defined. Redundant antibodies were eliminated, while allowing the diversity of antibodies to be enhanced. In addition, a new learning rate was defined, increasing the speed antibodies search in the direction of antigens. Finally, the al2 gorithm was tested in fault diagnosis for rotatingmachines. Experimental results indicated that this algorithm can ef2 fectively classify and recognize five typ ical kinds of faults
References:
[ 1 ]De CASTRO L N. An evolutionary immune system network for data clustering[ C ] / / Proceedings of Brazilian Symposi2 um on Neural Networks. IEEE Computer Society Press, 2000: 84289.
[ 2 ]张清华. 基于人工免疫系统的机组故障诊断技术研究 [D ]. 广州:华南理工大学, 2004.
ZHANG Qinghua. The research on technique of fault diagno2 sis based2on artificial immune system [ D ]. Guangzhou: South China University of Technology, 2004.
?[ 3 ]李春华,朱燕飞,毛宗源. 一种新型的自适应人工免疫算法[ J ]. 计算机工程与应用, 2004, 22: 84287.
L I Chunhua, ZHU Yanfei, HAO Zhongyuan. A novel adap2 tive artificial immune algorithm [ J ]. Computer Engineering and App lications, 2004, 22: 84287.
?[ 4 ] TIMM IS J. A resource limited artificial immune system for data analysis[ J ]. Knowledge Based Systems, 2002, 14: 1212 130.
[ 5 ]岳　训,迟忠先,莫宏伟. 人工免疫网络模型的数据特征提取性能评价技术[ J ]. 小型微型计算机系统, 2007, 28 (5) : 8862890.
?YUE Xun, CH I Zhongxian, MO Hongwei. Evaluating ap2 p roach on feature extraction performance of aritificial immune networks[ J ]. Joumal of Chinese Computer Systems, 2007, 28 (5) : 8862890.
?[ 6 ]De CASTRO L N, TIMM IS J. Atificial immune systems as a novel soft computing paradigm[ J ]. Soft Computing, 2003, 7 (8) : 5262544.
?[ 7 ] TIMM IS J , NEAL M, Hunt J. An artificial immune systems for data analysis[M ]. Biosytems , 2000: 1432150.
[ 8 ]杜海峰,王孙安. 基于ART2人工免疫网络的多级压缩机故障诊断[ J ]. 机械工程学报, 2002, 38 (4) : 88290.
DU Haifeng,WANG Sun’an. Fault diagnosis of the recip ro2 cating comp ressor based on ART2artificial immune network [ J ]. Chinese Journal ofMechanical Engineering, 2002, 38 (4) : 88290.
[ 9 ]熊　浩,孙才新. 基于克隆选择分类算法的电力变压器故障诊断[ J ]. 电网技术, 2006, 30 (4) : 65268.
XIONG Hao, SUN Caixin. Power transformer fault diagnosis based on clone selection classification algorithm [ J ]. Power System Technology, 2006, 30 (4) : 65268.
Similar References:

Memo

-

Last Update: 2009-05-18

Copyright © CAAI Transactions on Intelligent Systems