Fourier Feature Refiner Network With Soft Thresholding for Machinery Fault Diagnosis Under Highly Noisy Conditions

被引:6
作者
Wang, Huan [1 ,2 ]
Luo, Wenjun [3 ]
Liu, Zhiliang [1 ]
Zhang, Junhao [4 ]
Zuo, Mingjian [1 ,4 ,5 ]
机构
[1] Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu 611731, Peoples R China
[2] Tsinghua Univ, Dept Ind Engn, Beijing 100084, Peoples R China
[3] Univ Elect Sci & Technol China, Glasgow Coll, Chengdu 611731, Peoples R China
[4] Qingdao Int Academician Pk Res Inst, Glasgow Coll, Qingdao 266041, Peoples R China
[5] Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu, T6G 1H9, Peoples R China
来源
IEEE INTERNET OF THINGS JOURNAL | 2024年 / 11卷 / 13期
基金
中国国家自然科学基金;
关键词
Deep learning; Fourier transform; machinery fault diagnosis; noise robustness; prognostic and health management (PHM); ENTROPY;
D O I
10.1109/JIOT.2024.3363216
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Machinery fault diagnosis plays an important role in machine prognostic and health management (PHM). Leveraging the abundant data obtained from the Industrial Internet of Things (IIoT), the health states of machines can be effectively recognized, thereby ensuring the safety of the mechanical system. However, the lack of noise robustness and insufficient frequency domain perception make traditional methods to extract weak fault-related signals difficult under highly noisy conditions in practical industrial scenarios. Therefore, a method with abundant frequency domain learning ability is urgently needed. To this end, this article proposes a PHM framework, a soft thresholding Fourier feature refiner network (Soft-FFRNet), for highly noisy bearing vibration signal diagnosis. Specifically, this framework includes a Fourier feature refiner which selectively extracts and refines the feature in the frequency domain from the perspectives of amplitude and phase. It achieves the extension from the time domain to the frequency domain. In addition, the proposed framework utilizes several residual blocks with soft thresholding to effectively improve the noise robustness. Their thresholds can adaptively change during the training process. The high-speed aeronautical (HSA) bearing and the motor bearing data sets with different noise levels are used to evaluate this framework. The results show that the proposed framework can effectively diagnose the faults under highly noisy conditions.
引用
收藏
页码:22880 / 22891
页数:12
相关论文
共 39 条
  • [1] A review on data-driven fault severity assessment in rolling bearings
    Cerrada, Mariela
    Sanchez, Rene-Vinicio
    Li, Chuan
    Pacheco, Fannia
    Cabrera, Diego
    de Oliveira, Jose Valente
    Vasquez, Rafael E.
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 99 : 169 - 196
  • [2] Multi-channel Calibrated Transformer with Shifted Windows for few-shot fault diagnosis under sharp speed variation
    Chen, Zhuohang
    Chen, Jinglong
    Liu, Shen
    Feng, Yong
    He, Shuilong
    Xu, Enyong
    [J]. ISA TRANSACTIONS, 2022, 131 : 501 - 515
  • [3] Challenges to IoT-Enabled Predictive Maintenance for Industry 4.0
    Compare, Michele
    Baraldi, Piero
    Zio, Enrico
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (05) : 4585 - 4597
  • [4] SUPPORT-VECTOR NETWORKS
    CORTES, C
    VAPNIK, V
    [J]. MACHINE LEARNING, 1995, 20 (03) : 273 - 297
  • [5] The Politecnico di Torino rolling bearing test rig: Description and analysis of open access data
    Daga, Alessandro Paolo
    Fasana, Alessandro
    Marchesiello, Stefano
    Garibaldi, Luigi
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 120 : 252 - 273
  • [6] Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks
    de Bruin, Tim
    Verbert, Kim
    Babuska, Robert
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (03) : 523 - 533
  • [7] DE-NOISING BY SOFT-THRESHOLDING
    DONOHO, DL
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 1995, 41 (03) : 613 - 627
  • [8] Full Graph Autoencoder for One-Class Group Anomaly Detection of IIoT System
    Feng, Yong
    Chen, Jinglong
    Liu, Zijun
    Lv, Haixin
    Wang, Jun
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (21): : 21886 - 21898
  • [9] Convformer-NSE: A Novel End-to-End Gearbox Fault Diagnosis Framework Under Heavy Noise Using Joint Global and Local Information
    Han, Songyu
    Shao, Haidong
    Cheng, Junsheng
    Yang, Xingkai
    Cai, Baoping
    [J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2023, 28 (01) : 340 - 349
  • [10] Huang Yujing, 2022, 2022 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control ( SDPC), P57, DOI 10.1109/SDPC55702.2022.9916010