Fast Frequency Sparsity Learning Approach for Missing Data-Resistant Bearing Fault Diagnosis

被引:0
作者
Cao, Zheng [1 ,2 ]
Dai, Jisheng [1 ,2 ]
Xu, Weichao [3 ]
Xiong, Weizu [4 ]
机构
[1] Jiangsu Univ, Dept Elect Engn, Zhenjiang 212013, Peoples R China
[2] Donghua Univ, Coll Informat Sci & Technol, Shanghai 201620, Peoples R China
[3] Guangdong Univ Technol, Dept Automat Control, Guangzhou 525000, Peoples R China
[4] Sichuan Univ Sci & Engn, Sch Automat & Informat Engn, Yibin 643099, Peoples R China
基金
中国国家自然科学基金;
关键词
Fault diagnosis; Bayes methods; Time-frequency analysis; Vibrations; Imputation; Data mining; Harmonic analysis; Time-domain analysis; Databases; Data models; Bearing fault diagnosis; fault frequency extraction; generalized approximate message passing (GAMP); missing data; sparse Bayesian learning (SBL);
D O I
10.1109/TIM.2025.3550638
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Bearing fault diagnosis in the presence of missing data poses a significant challenge due to the substantial information loss brought by incomplete databases. Current state-of-the-art techniques for addressing missing data, whether involving data imputation or listwise deletion, are susceptible to notable algorithmic deterioration as the proportion of missing samples within a database increases. In this article, we novelly propose a missing data-resistant Bayesian optimal approach to directly learn the fault frequencies from the incomplete signal envelope. We first introduce an enhanced sparse frequency learning model to avoid time-domain signal recovery and frequency transformation. Then, we characterize the missing samples within the Bayesian framework to pave the way to extract fault frequencies of interest without compromising performance under missing data conditions. Finally, we resort to the generalized approximate message-passing (GAMP) method to marginalize the missing data automatically and identify the fault frequencies accurately. The proposed method offers a considerable performance improvement while maintaining low computational complexity. Both simulation and real dataset results verify the superiority of the proposed method.
引用
收藏
页数:13
相关论文
共 39 条
  • [1] Principal component analysis
    Abdi, Herve
    Williams, Lynne J.
    [J]. WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS, 2010, 2 (04): : 433 - 459
  • [2] A GAMP-Based Low Complexity Sparse Bayesian Learning Algorithm
    Al-Shoukairi, Maher
    Schniter, Philip
    Rao, Bhaskar D.
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (02) : 294 - 308
  • [3] Compressive sampling-based data loss recovery for wireless sensor networks used in civil structural health monitoring
    Bao, Yuequan
    Li, Hui
    Sun, Xiaodan
    Yu, Yan
    Ou, Jinping
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2013, 12 (01): : 78 - 95
  • [4] Bearing Fault Diagnosis With Frequency Sparsity Learning
    Cao, Zheng
    Dai, Jisheng
    Xu, Weichao
    Chang, Chunqi
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [5] Group-Sparsity Learning Approach for Bearing Fault Diagnosis
    Dai, Jisheng
    So, Hing Cheung
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (07) : 4566 - 4576
  • [6] Compressed sensing
    Donoho, DL
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (04) : 1289 - 1306
  • [7] A Motor Current Signal-Based Bearing Fault Diagnosis Using Deep Learning and Information Fusion
    Duy Tang Hoang
    Kang, Hee-Jun
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2020, 69 (06) : 3325 - 3333
  • [8] Fault Diagnosis of Hydraulic Systems Based on Deep Learning Model With Multirate Data Samples
    Huang, Keke
    Wu, Shujie
    Li, Fanbiao
    Yang, Chunhua
    Gui, Weihua
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (11) : 6789 - 6801
  • [9] A class alignment method based on graph convolution neural network for bearing fault diagnosis in presence of missing data and changing working conditions
    Kavianpour, Mohammadreza
    Ramezani, Amin
    Beheshti, Mohammad T. H.
    [J]. MEASUREMENT, 2022, 199
  • [10] Frequency Estimation of Vibration Signals: A Subspace Approach for Bearing Fault Diagnosis
    Li, Changjie
    Cao, Zheng
    Li, Shanliang
    Dai, Jisheng
    [J]. IEEE SENSORS JOURNAL, 2024, 24 (01) : 449 - 459