基于NMF的SVM故障诊断方法

李建宏; 姜同敏; 何玉珠; 蒋觉义

基于NMF的SVM故障诊断方法

1.
北京航空航天大学可靠性与系统工程学院, 北京 100191
2. 北京航空航天大学仪器科学与光电工程学院, 北京 100191

详细信息

中图分类号: TP 206⁺.3
计量
- 文章访问数: 1616
- HTML全文浏览量: 221
- PDF下载量: 519
- 被引次数: 0
出版历程
- 收稿日期: 2011-09-23
- 网络出版日期: 2012-12-30

SVM fault diagnosis method based on NMF

1.
School of Reliability and Systems Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. School of Instrument Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 针对大维数系统故障诊断中存在特征提取困难和识别率低的问题,提出基于非负矩阵分解(NMF,Non-negative Matrix Factorization)的支持向量机(SVM,Support Vector Machine)诊断方法,避免了直接对故障特征的选择和提取,实现特征降维,提高故障模式分类的准确性和速度;对于NMF中的结果随机性问题,提出用前次分解所得系数矩阵求解样本降维特征矩阵的方法,保证多次NMF分解尺度一致.实验表明该方法能对故障特征有效降维,并具有较高的诊断效率和故障识别率.
- 故障诊断 /
- 非负矩阵分解 /
- 支持向量机
Abstract: For overcoming the difficulty of fault feature extraction and solving the low efficiency of fault feature classification in a large dimensions fault diagnosis system,an algorithm of support vector machine(SVM)based on non-negative matrix factorization(NMF)fault diagnosis was researched. It is to avoid the direct feature selection and extraction, to reduce the characteristic dimension,and improve the high-dimensional data feature mode classification speed and accuracy. In order to avoid NMF randomness,characteristics of fault samples dimensionality reduction by training samples coefficient matrix was calculated, so that the consistency of the scale of NMF decomposition times was ensured. The experiment shows that this algorithm can reduce the dimensions of fault feature. The method can enhance the running efficiency and the estimating accuracy.
- fault diagnosis /
- non-negative matrix factorization /
- support vector machine

HTML全文

参考文献(11)

[1]	Vapnik V N.统计学习理论的本质[M].北京:电子工业出版社,2009 Vapnik V N.The nature of statistical learning theory[M].Beijing:Electronic Manufacture Press,2009(in Chinese)
[2]	Yang Chanyun, Yang Jrsyu, Wang Jianjun.Margin calibration in SVM class-imbalanced learning[J].Neurocomputing,2009,73 (13) :397-411
[3]	Yeom Honggi, Jang Inhun, Sim Kweebo.Variance considered machines:modification of optimal hyperplanes in support vector machines //IEEE International Symposium on Industrial Electronics.Seoul:IEEE, 2009:1144-1147
[4]	Fung G, Mangasarian O L.Proximal support vector machine classifiers //Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2001:77-86
[5]	曹胜玉,刘来福.非负矩阵分解及其在基因表达数据分析中的应用[J].北京师范大学学报:自然科学版,2007,43(1):30-33 Cao Shengyu, Liu Laifu.Non-negative matrix factorization and its applications to gene expression data analysis[J].Journal of Beijing Normal University:Natural Science,2007,43(1):30-33(in Chinese)
[6]	陈清华,陈六君,郑涛,等.基于非负矩阵分解方法的汉字基本部件识别[J].计算机工程与应用, 2008,44(29):76-78 Chen Qinghua, Chen Liujun, Zheng Tao, et al.Base component discovery from Chinese characters by NMF methods[J].Computer Engineering and Applications 2008,44(29):76-78(in Chinese)
[7]	张磊,冯晓森,项学智.基于非负矩阵分解的中文文本主题分类[J].计算机工程,2009, 35(13):26-27 Zhang Lei, Feng Xiaosen, Xiang Xuezhi.Topic classification of Chinese document based on NMF[J].Computer Engineering, 2009, 35(13):26-27(in Chinese)
[8]	邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004 Deng Naiyang, Tian Yingjie.A new method of data mining:SVM[M].Beijing:Science Press,2004(in Chinese)
[9]	孙永奎.基于支持向量机的模拟电路故障诊断方法研究 .成都:电子科技大学自动化工程学院,2009 Sun Yongkui.Study on fault diagnosis in analog circuits based on support sector machine .Chengdu:School of Automation Engineering,University of Electronic Science and Technology of China,2009(in Chinese)
[10]	胡国胜,钱玲, 张国红.支持向量机的多分类算法[J].系统工程与电子技术,2006,28(1):127-132 Hu Guosheng, Qian Ling, Zhang Guohong.Survey of multi-classification algorithms based on support vector machine [J].Systems Engineering and Electronics,2006,28(1):127-132(in Chinese)
[11]	张建明,曾建武,谢磊,等.基于粗糙集的支持向量机故障诊断[J].清华大学学报:自然科学版, 2007,47(S2):1774-1777 Zhang Jianming, Zeng Jianwu, Xie Lei, et al.Fault diagnosis based on RS and SVM[J].Journal of Tsinghua University:Sience and Technology,2007,47(S2):1774-1777(in Chinese)