基于局部主成分保持投影的旋转机械故障数据降维方法

摘要
图/表
参考文献(19)
相关文章 (15)

全文: PDF (1709 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对旋转机械高维故障特征集存在的特征冗余导致的分类困难问题，提出一种基于局部主成分保持投影(Locality Principal Component Preserving Projection，LPCPP)的故障数据集降维算法。该算法将类间可分性判据、主成分计算两种思想与局部保持投影(Locality Preserving Projection，LPP)相融合，使得算法具有剔除冗余特征、减小降维盲目性的能力，从而可以更好地保留能够反映机械运行状态的高价值密度的故障信息以及特征的主要成分。通过两个不同型号的双跨度转子系统的振动信号对所提算法进行验证，并分别以可分性指标和三种不同分类器的识别准确率对本算法的降维性能进行评价。结果表明，本算法能够达到降低故障分类难度与提高故障分类准确率的功能，其可为积累高价值密度的数据资源和基于“工业大数据”的旋转机械智能决策技术工程实现，提供一种数据运算的理论依据。

	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
	原健辉
	赵荣珍
	马驰

关键词 ：故障诊断, 局部保持投影, 可分性, 主成分计算, 旋转机械

Abstract：Aiming at the classification difficulty caused by feature redundancy in high-dimensional fault feature set of rotating machinery, a dimension reduction algorithm of fault data set based on Local Principal Component Preserving Projection (LPCPP) is proposed. The algorithm integrates two ideas of inter-class separability criterion and principal component calculation with Locality Preserving Projection (LPP), which makes the algorithm have the ability to eliminate redundant features and reduce dimensionality reduction blindness, so that it can better retain the fault information with high value density and the main components of features that can reflect the operation status of machinery. The proposed algorithm is verified by the vibration signals of two different types of two span rotor systems, and the dimensionality reduction performance of the algorithm is evaluated by the separability index and the recognition accuracy of three different classifiers. The results show that the algorithm can achieve the function of reducing the difficulty of fault classification and improving the accuracy of fault classification, which can provide a theoretical basis for data computing to accumulate the data resources with high value density and the engineering implementation of intelligent decision-making technology for rotating machinery based on "industrial big data".

Key words： Fault diagnosis Local preserving projection Separability Principal component calculation Rotating machinery

收稿日期: 2021-11-25 出版日期: 2023-03-28

引用本文:

原健辉，赵荣珍，马驰. 基于局部主成分保持投影的旋转机械故障数据降维方法[J]. 振动与冲击, 2023, 42(6): 24-30.
YUAN Jianhui，ZHAO Rongzhen，MA Chi. Dimension reduction method for rotating machinery fault data based on local principal component preserving projection. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(6): 24-30.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I6/24

[1] 雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
LEI Ya-guo, JIA Feng, KONG De-tong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[2] 李杰,李响, 许元铭, 等. 工业人工智能及应用研究现状及展望[J]. 自动化学报, 2020, 46(10): 2031-2044.
LEE Jay, LI Xiang, XU Yuan-ming, et al. Recent advances and prospects in industrial aI and applications[J]. Acta Automatica Sinica, 2020, 46(10): 2031-2044.
[3] 柴天佑. 工业人工智能发展方向[J]. 自动化学报, 2020, 46(10): 2005-2012.
CHAI Tian-you. Development directions of industrial artificial intelligence[J]. Acta Automatica Sinica, 2020, 46(10): 2005-2012.
[4] 黄宏臣, 韩振南, 张倩倩, 等. 基于拉普拉斯特征映射的滚动轴承故障识别[J]. 振动与冲击, 2015, 34(05): 128-134.
HUANG Hong-chen, Han Zhen-nan, Zhang Qian-qian, et al. Fault Identification of Rolling Bearings Based on Laplacian Feature Mapping[J]. Journal of Vibration and Shock, 2015, 34(05): 128-134.
[5] KHEDIRI I B, LIMAM M, WEIHS C . Variable window adaptive Kernel Principal Component Analysis for nonlinear nonstationary process monitoring[J]. Computers & IndustrialEngineering, 2011, 61(3):437-446.
[6] Martinez A M, Kak A C. PCA versus LDA[J]. IEEE Transactions on pattern analysis and machine intelligence, 2001, 23(2): 228-233.
[7] X. He, P. Niyogi, Locality preserving projections[J]. Proc. Neural Inf. Process. Syst. 2003, 16(1): 186-197.
[8] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323-2326.
[9] JIANG Quansheng, JIA Minping, HU Jianzhong, et al. Modified laplacian eigenmap method for fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2008, 21(3): 90-93.
[10] 杨望灿, 张培林, 张云强. 基于邻域自适应局部保持投影的轴承故障诊断模型[J]. 振动与冲击, 2014, 33( 1) : 39-44．
YANG Wang-can, ZHANG Pei-lin, ZHANG Yun-qiang. Bearing fault diagnosis model based on neighborhood adaptive locality preserving projections[J]. Journal of Vibration and Shock, 2014, 33( 1) : 39-44．
[11] 张恒, 赵荣珍. 故障特征选择与特征信息融合的加权 KPCA 方法研究[J]. 振动与冲击, 2014, 33(09): 89-93+121.
ZHANG Heng, ZHAO Rong-zhen. Weighted KPCA based on fault feature selection and feature information fusion[J].Journal of Vibration and Shock, 2014, 33(09): 89-93+121.
[12] 王满.基于PCA与KPCA的多光谱遥感影像特征提取对比研究[J]. 矿山测量, 2016, 44(02): 49-52．
WANG Man. Comparative study on feature extraction of multispectral remote sensing images based on PCA and KPCA [J]. Journal of Mine Survey, 2016, 44(02) : 49-52．
[13] 苏祖强, 汤宝平, 姚金宝. 基于敏感特征选择与流形学习维数约简的故障诊断[J]. 振动与冲击, 2014, 33(3):70-75.
Su Zu-qiang, Tang Bao-ping, Yao Jin-bao. Fault diagnosis based on sensitive feature selection and manifold learning dimension reduction[J]. Journal of Vibration and Shock, 2014, 33(3): 70-75.
[14] 赵孝礼, 赵荣珍. 全局与局部判别信息融合的转子故障数据集降维方法研究[J]. 自动化学报, 2017, 43(4):560-567.
ZHAO Xiao-li ZHAO Rong-zhen. A Method of Dimension Reduction of Rotor Faults Data Set Based on Fusion of Global and Local Discriminant Information[J]. Acta Automatica Sinica, 2017, 43(4): 560-567.
[15] 李学军,李平,蒋玲莉. 类均值核主元分析法及在故障诊断中的应用[J]. 机械工程学报, 2014, 050(003): 123-129.
LI Xue-jun, LI Ping, JIANG Ling-li. Class mean Kernel Principal Component Analysis and its application in fault diagnosis[J]. Journal of Mechanical Engineering, 2014,050(003): 123-129.
[16] LIU R , YANG B , ZIO E , et al. Artificial intelligence for fault diagnosis of rotating machinery: A review[J]. Mechanical
Systems & Signal Processing, 2018, 108(AUG.):33-47.
[17] 李从志,郑近德,潘海洋,等. 基于精细复合多尺度散布熵与支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程, 2019, 30(14): 1713-1719+1726.
LI Cong-zhi, ZHENG Jin-de, PAN Hai-yang, et al. Fault Diagnosis Method of Rolling Bearings Based on Refined Composte Multiscal Dispersion Entropy and Support Vector Machine[J]. China Mechanical Engineering, 2019, 30(14):1713-1719+1726.
[18] 都明宇,王志恒,荀一,等. 多模式人手动作分类识别方法[J]. 中国机械工程, 2019, 30(12): 1474-1479.
DU Ming-yu, WANG Zhi-heng, XUN Yi, et al. Classification and identification of multi-partern of hand actions[J]. China Mechanical Engineering, 2019, 30(12): 1474-1479.
[19] 李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012.
LI Hang. Statistical learning method [M]. Beijing: TsinghuaUniversity Press, 2012.