A Globally Interpretable Convolutional Neural Network Combining Bearing Semantics for Bearing Fault Diagnosis

被引:0
|
作者
Wang, Zhen [1 ]
Han, Guangjie [2 ]
Liu, Li [3 ]
Wang, Feng
Zhu, Yuanyang [4 ]
机构
[1] Hohai Univ, Coll Artificial Intelligence & Automat, Changzhou 213200, Peoples R China
[2] Hohai Univ, Jiangsu Key Lab Power Transmiss & Distribut Equipm, Changzhou 213200, Peoples R China
[3] Jiangnan Univ, Sch Artificial Intelligence & Comp Sci, Wuxi 214126, Peoples R China
[4] Hohai Univ, Coll Comp Sci & Software Engn, Nanjing 211100, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
Bearing fault diagnosis; bearing semantics; convolutional neural network (CNN); fault characteristic frequency (FCF); interpretability;
D O I
10.1109/TIM.2025.3538068
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 is crucial for maintaining the safety of industrial systems. With the massive data collected by the Industrial Internet-of-Things technology, deep learning (DL)-based end-to-end models have been extensively utilized in bearing fault diagnosis. However, their limited interpretability poses challenges to their reliability, hindering further advancements in the field. To address this interpretability issue, we propose a globally interpretable convolutional neural network (CNN) combining bearing semantics for bearing fault diagnosis. Specifically, the physical semantics of bearing signals are first constructed based on the fault characteristic frequency (FCF). Based on this bearing semantics, a novel bearing semantic embedding method is proposed to enhance the interpretability of convolutional layers. Moreover, a globally interpretable network (GINet) structure is crafted to ensure that the bearing semantics are visible throughout the entire network. Experimental results on two datasets demonstrate that the network's performance remains comparable to the benchmark method while achieving global interpretability. This network also exhibits improved noise robustness, proving the effectiveness of semantic embedding. In addition, since this network is an interpretable modification of the basic CNN, it is not limited to bearing fault diagnosis. Theoretically, with the appropriate semantics, it can also be applied to other signal-based fault diagnosis tasks.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Interpretable quadratic convolutional residual neural network for bearing fault diagnosis
    Luo, Zhiyong
    Pan, Shuping
    Dong, Xin
    Zhang, Xin
    JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING, 2025, 47 (04)
  • [2] Interpretable parallel channel encoding convolutional neural network for bearing fault diagnosis
    Tong, Qingbin
    Du, Shouxin
    Jiang, Xuedong
    Lu, Feiyu
    Feng, Ziwei
    Liu, Ruifang
    Xu, Jianjun
    Huo, Jingyi
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (06)
  • [3] VKCNN: An interpretable variational kernel convolutional neural network for rolling bearing fault diagnosis
    Chen, Guangyi
    Tang, Gang
    Zhu, Zhixiao
    ADVANCED ENGINEERING INFORMATICS, 2024, 62
  • [4] A Review on Convolutional Neural Network in Bearing Fault Diagnosis
    Waziralilah, N. Fathiah
    Abu, Aminudin
    Lim, M. H.
    Quen, Lee Kee
    Elfakharany, Ahmed
    ENGINEERING APPLICATION OF ARTIFICIAL INTELLIGENCE CONFERENCE 2018 (EAAIC 2018), 2019, 255
  • [5] Convolutional Neural Network Based Bearing Fault Diagnosis
    Duy-Tang Hoang
    Kang, Hee-Jun
    INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2017, PT II, 2017, 10362 : 105 - 111
  • [6] Application of Convolutional Neural Network in Motor Bearing Fault Diagnosis
    Zhou, Shuiqin
    Lin, Lepeng
    Chen, Chu
    Pan, Wenbin
    Lou, Xiaochun
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [7] A review on convolutional neural network in rolling bearing fault diagnosis
    Li, Xin
    Ma, Zengqiang
    Yuan, Zonghao
    Mu, Tianming
    Du, Guoxin
    Liang, Yan
    Liu, Jingwen
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (07)
  • [8] Gradient-Based Interpretable Graph Convolutional Network for Bearing Fault Diagnosis
    Wen, Kairu
    Huang, Ruyi
    Li, Dongpeng
    Chen, Zhuyun
    Li, Weihua
    2023 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC, 2023,
  • [9] A Fault Diagnosis Method of Rolling Bearing Based on Convolutional Neural Network
    Zhang, Bangcheng
    Gao, Shuo
    Hu, Guanyu
    Gao, Zhi
    Zhao, Yadong
    Du, Jianzhuang
    2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 4709 - 4713
  • [10] An adaptive deep convolutional neural network for rolling bearing fault diagnosis
    Wang Fuan
    Jiang Hongkai
    Shao Haidong
    Duan Wenjing
    Wu Shuaipeng
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2017, 28 (09)