全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

旋转设备声学故障特征提取与优化方法

DOI: 10.13190/jbupt.201104.70.chenb, PP. 70-74

Keywords: 故障诊断,特征选取,遗传算法,支持向量数据描述

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对旋转设备原始故障特征空间中存在的冗余特征问题,提出一种基于支持向量数据描述(SVDD)和遗传算法的故障特征优化方法.通过理论和实验分析构造了相对完备的设备声学故障特征空间;依据特征可分离性评价准则和SVDD识别率从原始故障样本数据集中提取出先验知识,指导种群的初始化;以类〖JP9〗内-〖JP〗类间距离判据和故障分类器的识别率评价种群中个体的适应度,在此基础上建立改进的遗传算法搜索最优故障特征子集.基于转子振动台所模拟的不平衡故障实验样本数据集,验证了该方法的有效性.

References

[1]  Wei H L, Billings S A. Feature Subset Selection and Ranking for Data Dimensionality Reduction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1):162-166.
[2]  Robnik-Sikonja M, Kononenko I. Theoretical and Empirical Analysis of ReliefF and RReliefF [J]. Machine Learning, 2003, 53:23-69.
[3]  Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classification using support vector machines [J]. Machine Learning, 2002, 46 (1-3): 389-422.
[4]  Liu J, Ranka S, Kahveci T.Classification and feature selection algorithms for multi-class CGH data [J]. Bioinformatics, 2008, 24:i86-i95.
[5]  孙跃鹏,刘民,郝井华,等. 基于SVM特征选择的整经轴数预测算法 [J]. 北京邮电大学学报, 2009, 32(4):88-92.
[6]  SUN Yue-peng, LIU Min, HAO Jing-hua, et al. Prediction algorithm of trim beam number using modified SVM-based feature selection [J]. Journal of Beijing University of Posts and Telecommunications, 2009, 32(4):88-92.
[7]  Huang J, Cai Y, Xu X. A hybrid genetic algorithm for feature selection wrapper based on mutual information [J]. Pattern Recognition Letters, 2007, 28:1825-1844.
[8]  Tax D M J, Duin R P W. Support vector domain description [J]. Pattern Recognition Letters, 1999, 20(11-13):1191-1199.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133