基于UDGDP的转子故障数据集降维方法

摘要
图/表
参考文献(13)
相关文章 (15)

全文: PDF (1038 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对旋转机械智能故障辨识精度偏低的问题，提出一种基于不相关约束的双邻接图判别投影（Uncorrelated Double Graphs Discriminant Projection, UDGDP）降维算法。该算法通过构建两个流形结构图使低维空间同类样本更加紧凑、异类样本更加分散，同时引入不相关约束条件以降低投影变换后特征分量之间的相关性，进而达到提取敏感故障特征的目的。用转子故障数据集进行验证的结果表明：UDGDP算法能够降低所获得低维空间各特征之间的相关性，并且使故障各类别之间的差异性变得更加清晰，可有效提升分类器的辨识精度。该算法可为转子系统故障的智能辨识技术提供理论参考依据。
关键词：双邻接图判别投影；不相关约束；转子故障数据集；降维

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨泽本
	赵荣珍
	刘强

关键词 ：双邻接图判别投影, 不相关约束, 转子故障数据集, 降维

Abstract：Aiming at the problem of low accuracy in intelligent fault identification of rotating machinery, a dimension reduction algorithm based on uncorrelated double graphs discriminant projection (UDGDP) was proposed. The algorithm constructed two manifold structure graphs to make the intra-class samples more compact and the inter-class samples more separable in the low-dimensional space. At the same time, uncorrelated constraints were introduced to reduce the statistical correlation between feature components after projection transformation, and then the purpose of extracting sensitive fault features was achieved. The results of verification with rotor fault data set show that UDGDP algorithm can reduce the correlation between the features in the low dimensional space, and make the difference between the fault categories clearer, which effectively improves the identification accuracy of the classifier. The algorithm can provide a theoretical reference for the intelligent fault identification technology of rotor system.
Key words: double graphs discriminant projection; uncorrelated constraints; rotor fault data set; dimension reduction

Key words： double graphs discriminant projection uncorrelated constraints rotor fault data set dimension reduction

收稿日期: 2021-05-12 出版日期: 2022-08-28

引用本文:

杨泽本，赵荣珍，刘强. 基于UDGDP的转子故障数据集降维方法[J]. 振动与冲击, 2022, 41(16): 255-260.
YANG Zeben, ZHAO Rongzhen, LIU Qiang. A dimension reduction method for rotor fault data set based on UDGDP. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(16): 255-260.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2022/V41/I16/255

[1] 雷亚国, 杨彬, 杜兆钧, 等. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报, 2019, 55(07): 1-8.
LEI Yaguo, YANG Bin, DU Zhaojun, et al. Deep transform diagnosis method for machinery in big data era[J]. Journal of Mechanical Engineering, 2019, 55(07): 1-8.
[2] 石明宽, 赵荣珍. 基于局部边缘判别投影的机械故障诊断方法[J]. 振动.测试与诊断, 2021, 41(01): 126-132+204.
SHI Mingkuan, ZHAO Rongzhen. A method of mechanical fault diagnosis based on locality margin discriminant projection[J]. Journal of Vibration, Measurement & Diagnosis, 2021, 41(01): 126-132+204.
[3] 于洪, 何德牛, 王国胤, 等. 大数据智能决策[J]. 自动化学报, 2020, 46(05): 878–896.
YU Hong, HE Deniu, Wang Guoyin, et al. Big data for intelligent decision making[J]. Acta Automatica Sinica, 2020, 46(05): 878–896.
[4] He X. Locality preserving projections[J]. Advances in Neural Information Processing Systems, 2003, 16(1): 186-197.
[5] 江丽, 郭顺生. 基于无监督判别投影的滚动轴承故障诊断[J]. 中国机械工程, 2016, 27(16): 2202-2206.
JIANG Li, GUO Shunsheng. Fault diagnosis of rolling bearing based on unsupervised discriminant projection[J]. China Mechanical Engineering, 2016, 27(16): 2202-2206.
[6] SUGIYAMA M. Dimensionality reduction of multimodal labeled data by local Fisher discriminant analysis[J]. Journal of Machine Learning Research, 2007, 8(5): 1027–1061.
[7] 李锋, 王家序, 汤宝平, 等. 有监督不相关局部Fisher判别分析故障诊断[J]. 振动工程学报, 2015, 28(04): 657-665.
LI Feng, WANG Jiaxu, TANG Baoping, et al. Fault diagnosis method based on supervised uncorrelated local Fisher discriminant analysis[J]. Journal of Vibration Engineering, 2015, 28(04): 657-665
[8] DING C, ZHANG L. Double adjacency graphs-based discriminant neighborhood embedding[J]. Pattern Recognition, 2015, 48(5): 1734–1742.
[9] GOU J, XUE Y, MA H, et al. Double graphs-based discriminant projections for dimensionality reduction[J]. Neural Computing and Applications, 2020, 32(23): 17533–17550.
[10] 韩敏, 李宇, 韩冰. 基于改进结构保持数据降维方法的故障诊断研究[J]. 自动化学报, 2021, 47(02): 338–348.
HAN Min, LI Yu, HAN Bin. Research on fault diagnosis of data dimension reduction based on improved structure preserving algorithm[J]. Acta Automatica Sinica, 2021, 47(02): 338–348.
[11] 石明宽, 赵荣珍. 基于标准正交判别投影的转子故障数据集降维方法[J]. 振动与冲击, 2020, 39(18): 96–102.
SHI Mingkuan, ZHAO Rongzhen. Dimension reduction of a rotor faults data set based on standard orthogonal discriminant projection[J]. Journal of Vibration and Shock, 2020, 39(18): 96–102.
[12] CHEN F, TANG B, CHEN R. A novel fault diagnosis model for gearbox based on wavelet support vector machine with immune genetic algorithm[J]. Measurement, 2013, 46(1): 220–232.
[13] DING C, SUN Q. LBDAG-DNE: Locality Balanced Subspace Learning for Image Recognition[C]// WANG S, ZHOU A. Collaborate Computing: Networking, Applications and Worksharing. Cham: Springer International Publishing, 2017: 199–210.