Bearing fault diagnosis method based on HCDDP

PDF(2654 KB)

Journal of Vibration and Shock ›› 2023, Vol. 42 ›› Issue (23) : 103-111.

SU Shuzhi,ZHANG Zhipeng

Author information +

History +

Abstract

Aiming at the difficulty of fault classification caused by the high dimension of rolling bearing fault data and the interleaving of different feature attributes, a dimension reduction method of bearing fault data based on Hypergraph Correlation Distance Discriminant Projection(HCDDP) was proposed. This method uses hypergraph structure to describe the spatial structure relationship between fault samples, and uses the supervision information of bearing fault signals to construct intra-class and inter-class hypergraphs. The hypergraph more effectively reveals the complex multiple structure of fault data, and better expresses the intrinsic nature and multivariate relationship between fault samples than the traditional simple graph structure. At the same time, Pearson correlation coefficient is used to construct a new metric in the hypergraph to calculate the geodesic distance of samples in the high-dimensional manifold, which solves the problem of inaccurate classification caused by the sensitivity of Euclidean distance to the value range of fault data. The hypergraph correlation distance discriminant projection method has the ability of high-order correlation of nonlinear data to better solve the cost-sensitive classification of bearing faults. This method is verified on the bearing dataset of Case Western Reserve University and Xi 'an Jiaotong University in the United States. Experimental results show that the proposed method can effectively use the multivariate structural relationship and discriminant information between samples, and improve the recognition rate of bearing faults.

Key words

fault diagnosis / rolling bearing / graph learning / dimension reduction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

SU Shuzhi,ZHANG Zhipeng. Bearing fault diagnosis method based on HCDDP[J]. Journal of Vibration and Shock, 2023, 42(23): 103-111

References

[1] 雷亚国. 混合智能技术及其在故障诊断中的应用研究[D]. 西安交通大学, 2007.
Yaguo L. Research on Hybrid Intelligent Technique and Its Applications in Fault Diagnosis[J]. Xi’an, China: Xi’an Jiaotong University, 2007.
[2] 何正嘉, 曹宏瑞, 訾艳阳, 等. 机械设备运行可靠性评估的发展与思考[J]. 机械工程学报, 2014, 50(2): 171-186.
He Z, Cao H, Zi Y, et al. Developments and thoughts on operational reliability assessment of mechanical equipment[J]. Journal of Mechanical Engineering, 2014, 50(2): 171-186.
[3] Peng Z, Chu F, He Y. Vibration signal analysis and feature extraction based on reassigned wavelet scalogram[J]. Journal of Sound and Vibration, 2002, 253(5): 1087-1100.
[4] Yan R, Gao R X. Hilbert–Huang transform-based vibration signal analysis for machine health monitoring[J]. IEEE Transactions on Instrumentation and measurement, 2006, 55(6): 2320-2329.
[5] Neupane D, Seok J. Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: A review[J]. IEEE Access, 2020, 8: 93155-93178.
[6] 戚晓利, 叶绪丹, 蔡江林, 等. 基于变分模态分解与流形学习的滚动轴承故障特征提取方法[J]. 振动与冲击, 2018, 37(23): 133-140.
Qi X L, Ye X D, Cai J L, et al. Fault feature extraction method of rolling bearings based on VMD and manifold learning[J]. Journal of vibration and shock, 2018, 37(23): 133-140.
[7] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. science, 2000, 290(5500): 2323-2326.
[8] Wang X, Zheng Y, Zhao Z, et al. Bearing fault diagnosis based on statistical locally linear embedding[J]. Sensors, 2015, 15(7): 16225-16247.
[9] Li B, Li Y R, Zhang X L. A survey on Laplacian eigenmaps based manifold learning methods[J]. Neurocomputing, 2019, 335: 336-351.
[10] 梁超, 路鹏, 郜宁, 等. 基于 LPP 的转子振动故障特征提取方法[J]. 振动工程学报, 2018, 31(3): 539G544.
Liang C , Peng L U , Gao N , et al. Feature extraction of
rotor vibration fault based on LPP algorithm[J]. Journal
of Vibration Engineering, 2018.
[11] Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics and intelligent laboratory systems, 1987, 2(1-3): 37-52.
[12] Zang F, Zhang J, Pan J. Face recognition using Elastic faces[J]. Pattern Recognition, 2012, 45(11): 3866-3876.
[13] He X, Cai D, Yan S, et al. Neighborhood preserving embedding[C]//Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1. IEEE, 2005, 2: 1208-1213.
[14] Zhou D, Huang J, Schölkopf B. Learning with hypergraphs: Clustering, classification, and embedding[J]. Advances in neural information processing systems, 2006, 19.
[15] 赵荣珍, 赵孝礼, 何敬举, 等. 相关流形距离在转子故障数据集分类中的应用方法[J]. 振动与冲击, 2017, 36(18): 125-130.
Zhao R Z, Zhao X L, He J J, et al. The Application in Classification method of Rotor Fault Data Set Using Correlation Manifold Distance[J]. Journal of vibration and shock, 2017, 36(18): 125-130.
[16] Yuan J, Zhao R, He T, et al. Fault diagnosis of rotor based on Semi-supervised Multi-Graph Joint Embedding[J]. ISA transactions, 2022.
[17] Shi M, Zhao R, Wu Y, et al. Fault diagnosis of rotor based on local-global balanced orthogonal discriminant projection[J]. Measurement, 2021, 168: 108320.
[18] 雷亚国, 韩天宇, 王彪, 等. XJTU-SY 滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16): 1-6.
Lei Y, Han T, Wang B, et al. XJTU-SY rolling element bearing accelerated life test datasets: a tutorial[J]. J. Mech. Eng., 2019, 55(2019): 1-6.