Rolling bearing fault diagnosis based on manifold feature domain adaptation

ZHOU Hongdi,HUANG Tao,LI Zhi,ZHONG Fei

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (5) : 94-102.

PDF(2341 KB)
PDF(2341 KB)
Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (5) : 94-102.

Rolling bearing fault diagnosis based on manifold feature domain adaptation

  • ZHOU Hongdi,HUANG Tao,LI Zhi,ZHONG Fei
Author information +
History +

Abstract

The distributions of different domains under varying working conditions are often complex, which will lead to the challenges of mitigating feature distortion and divergence during data alignment in the original space. In this study, a rolling bearing fault diagnosis method based on Manifold Feature Domain Adaptation (MFDA) is proposed. An intermediate domain whose distribution is similar with source domain is firstly generated with unsupervised techniques. Then, a common space connected with the source, intermediate, and target domains is constructed. Meanwhile, the local generative discrepancy metric is adopted to preserve the local manifold geometry of the data within the subspace, which can prevent the distortion and divergence during alignment process. The maximum mean discrepancy is adopted to align the intermediate and target domain and minimize the distributional difference of those two domains, the correlation between local and global structures of data is consequently ensured. Finally, the learned features are utilized for cross-domain fault identification of rolling bearings using the least squares method. Three datasets of rolling bearing is utilized, and the experimental results demonstrate the effectiveness of proposed method in mitigating feature distortion and divergence. Furthermore, the proposed method exhibits exceptional generalization performance compared with other intelligent recognition algorithms.

Key words

rolling bearing / transfer learning / variable working conditions / Fault diagnosis / Manifold feature domain adaptation

Cite this article

Download Citations
ZHOU Hongdi,HUANG Tao,LI Zhi,ZHONG Fei. Rolling bearing fault diagnosis based on manifold feature domain adaptation[J]. Journal of Vibration and Shock, 2024, 43(5): 94-102

References

[1] Tan Zhenhua, Ning Jingyu, Peng Kai, et al. Logistic-ELM: a novel fault diagnosis method for rolling bearings [J]. Journal of The Brazilian Society of Mechanical Sciences and Engineering, 2022, 44(11): 553. [2] M Azim Naz, R Sarath Combined classification models for bearing fault diagnosis with improved ICA and MFCC feature set [J]. Advances In Engineering Software, 2022, 173. [3] An Yiyao, Zhang Ke, Chai Yi, et al. Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditions [J]. Expert Systems with Applications, 2023, 212. [4] 雷亚国, 杨彬, 李乃鹏, 等. 跨设备的机械故障靶向迁移诊断方法 [J]. 机械工程学报, 2022, 58(12): 1-9. Lei Yaguo, Yang Bin, Li Naipeng, et al. Cross-equipment targeted migration diagnosis of mechanical faults [J]. Journal of Mechanical Engineering, 2022, 58(12): 1-9. [5] Xu Huoyao, Wang Junlang, Liu Jie, et al. A novel joint distinct subspace learning and dynamic distribution adaptation method for fault transfer diagnosis [J]. Measurement, 2022, 203. [6] 邵海东, 张笑阳, 程军圣, 等. 基于提升深度迁移自动编码器的轴承智能故障诊断 [J]. 机械工程学报, 2020, 56(09): 84-90. Shao Haidong, Zhang Xiaoyang, Cheng Junsheng, et al. Intelligent fault diagnosis of bearings based on lifting depth migration autoencoder [J]. Journal of Mechanical Engineering, 2020, 56(09): 84-90. [7] Dong Shaojiang, He Kun, Tang Baoping. The fault diagnosis method of rolling bearing under variable working conditions based on deep transfer learning [J]. Journal of The Brazilian Society of Mechanical Sciences and Engineering, 2020, 42(11). [8] 曹洁, 尹浩楠, 雷晓刚, 等. 基于领域自适应的变工况轴承故障诊断 [J]. 北京航空航天大学学报, 2022, 48(0): 1-13. Cao Jie, Yin Haonan, Lei Xiaogang, et al. Domain-based adaptive fault diagnosis for variable operating conditions bearings [J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(0): 1-13. [9] Pan Sinno Jialin, Tsang Ivor W, Kwok James T, et al. Domain Adaptation via Transfer Component Analysis [J]. IEEE Transactions on Neural Networks, 2011, 22(2): 199-210. [10] 田威威, 陈俊杰, 林意. 基于迁移成分分析和词包模型的变工况轴承诊断方法 [J]. 重庆大学学报, 2022, 45(06): 98-107. Tian Weiwei, Chen Junjie, Lin Yi. Diagnosis method of variable condition bearings based on migration component analysis and word packet model [J]. Journal of Chongqing University, 2022, 45(06): 98-107. [11] 陈仁祥, 朱玉清, 胡小林, 等. 自适应正则化迁移学习的不同工况下滚动轴承故障诊断 [J]. 仪器仪表学报, 2021, 41(08): 95-103. Chen Renxiang, Zhu Yuqing, Hu Xiaolin, et al. Adaptive regularized migration learning for fault diagnosis of rolling bearings under different operating conditions [J]. Journal of Instrumentation, 2021, 41(08): 95-103. [12] He Xiaofei, Yan Shuicheng, Hu, Yuxiao, et al. Face recognition using Laplacianfaces [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-40. [13] Zhang Lei, Wang Shanshan, Huang Guang-Bin, et al. Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation [J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(12): 3759-73. [14] Wang Xiaogang, Ren Jie, Liu Sen. Distribution Adaptation and Manifold Alignment for complex processes fault diagnosis [J]. KNOWLEDGE-BASED SYSTEMS, 2018, 156: 100-12. [15] 沈长青, 雷飘, 冯毅雄, 等. 基于自适应流形嵌入动态分布对齐的轴承故障诊断 [J]. 电子测量与仪器学报, 2021, 35(02): 33-40. Shen Changqing, Lei Piao, Feng Yixiong, et al. Bearing fault diagnosis based on adaptive flow embedding dynamic distribution alignment [J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(02): 33-40. [16] 刘海宁, 宋方臻, 窦仁杰, 等. 小数据条件下基于测地流核函数的域自适应故障诊断方法研究 [J]. 振动与冲击, 2018, 37(18): 36-42. Liu Haining, Song Fangzhen, Dou Renjie, et al. Research on domain adaptive fault diagnosis method based on geodesic flow kernel function under small data conditions [J]. Vibration and Shock, 2018, 37(18): 36-42. [17] Zhang Zhongwei, Chen Huaihai, Li Shunming, et al. A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition [J]. Neurocomputing, 2020, 376: 54-64. [18] Lai Zhihui, Bao Jiaqi, Kong Heng, et al. Discriminative low-rank projection for robust subspace learning [J]. International Journal Of Machine Learning And Cybernetics, 2020, 11(10): 2247-60. [19] Cai Jian-Feng, Candès Emmanuel J, Shen Zuowei.A Singular Value Thresholding Algorithm for Matrix Completion [J]. SIAM Journal on Optimization, 2010, 20(4): 1956-82. [20] Lei Yaguo, He Zhengjia, Zi Yanyang, et al, et al. Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs [J]. Mechanical Systems and Signal Processing, 2007, 21(5): 2280-94. [21] Deng Xiaogang, Tian Xuemin. Sparse Kernel Locality Preserving Projection and Its Application in Nonlinear Process Fault Detection [J]. Chinese Journal of Chemical Engineering, 2013, 21(2): 163-70. [22] Zhang Zhongwei, Chen Huaihai, Li Shunming, et al. A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition [J]. Neurocomputing, 2020, 376: 54-64. [23] Tuerxun Wumaier, Chang Xu, Hongyu Guo, et al. Fault Diagnosis of Wind Turbines Based on a Support Vector Machine Optimized by the Sparrow Search Algorithm [J]. IEEE Access, 2021, 9: 69307-15. [24] Snoek Jasper, Larochelle Hugo, Adams Ryan P. Practical Bayesian optimization of machine learning algorithms [Z]. Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada; Curran Associates Inc. 2012: 2951–9 [25] Zheng Huailiang, Wang Rixin, Yin Jiancheng, et al. A new intelligent fault identification method based on transfer locality preserving projection for actual diagnosis scenario of rotating machinery [J]. Mechanical Systems and Signal Processing, 2020, 135. [26] Zhao Zhibin, Zhang Qiyang, Yu Xiaolei, et al. Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-28. [27] Loparo K A. Bearing vibration data set, Case Western Reserve University [Z]. 2003 [28] Bechhoefer D E. MFPT Bearing Fault Data Sets [Z].
PDF(2341 KB)

276

Accesses

0

Citation

Detail

Sections
Recommended

/