PMID- 37177689
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20230514
LR  - 20230515
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 23
IP  - 9
DP  - 2023 May 4
TI  - Method for Diagnosing Bearing Faults in Electromechanical Equipment Based on 
      Improved Prototypical Networks.
LID - 10.3390/s23094485 [doi]
LID - 4485
AB  - Due to the complexity of electromechanical equipment and the difficulties in 
      obtaining large-scale health monitoring datasets, as well as the long-tailed 
      distribution of data, existing methods ignore certain characteristics of health 
      monitoring data. In order to solve these problems, this paper proposes a method 
      for the fault diagnosis of rolling bearings in electromechanical equipment based 
      on an improved prototypical network-the weight prototypical networks (WPorNet). 
      The main contributions of this paper are as follows: (1) the prototypical 
      networks, which perform well on small-sample classification tasks, were improved 
      by calculating the different levels of influence of support sample distributions 
      in order to achieve the prototypical calculation. The change in sample influence 
      was calculated using the Kullback-Leibler divergence of the sample distribution. 
      The influence change in a specific sample can be measured by assessing how much 
      the distribution changes in the absence of that sample; and (2) The Gramian 
      Angular Field (GAF) algorithm was used to transform one-dimensional time series 
      into two-dimensional vibration images, which greatly improved the application 
      effect of the 2D convolutional neural network (CNN). Through experiments on 
      MAFAULDA and CWRU bearing datasets, it was shown that this network effectively 
      solves the shortcomings of a small number of valid samples and a long-tail 
      distribution in health monitoring data, it enhances the dependency between the 
      samples and the global data, it improves the model's feature extraction ability, 
      and it enhances the accuracy of model classification. Compared with the 
      prototypical network, the improved network model increased the performance of the 
      2-way 10-shot, 2-way 20-shot, and 2-way 50-shot classification tasks by 5.23%, 
      5.74%, and 4.37%, respectively, and it increased the performance of the 4-way 
      10-shot, 4-way 20-shot, and 4-way 50-shot classification tasks by 12.02%, 10.47%, 
      and 4.66%, respectively. Experimental results show that the improved prototypical 
      network model has higher sample classification accuracy and stronger 
      anti-interference ability compared with traditional small-sample classification 
      models.
FAU - Wang, Zilong
AU  - Wang Z
AUID- ORCID: 0009-0008-4257-1211
AD  - Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute 
      of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 
      130033, China.
AD  - Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of 
      Sciences, Changchun 130033, China.
AD  - University of Chinese Academy of Sciences, Beijing 100039, China.
FAU - Shen, Honghai
AU  - Shen H
AUID- ORCID: 0000-0002-8085-9805
AD  - Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute 
      of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 
      130033, China.
AD  - Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of 
      Sciences, Changchun 130033, China.
AD  - University of Chinese Academy of Sciences, Beijing 100039, China.
FAU - Xiong, Wenzhuo
AU  - Xiong W
AD  - Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of 
      Sciences, Changchun 130033, China.
AD  - University of Chinese Academy of Sciences, Beijing 100039, China.
FAU - Zhang, Xueming
AU  - Zhang X
AD  - Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of 
      Sciences, Changchun 130033, China.
AD  - University of Chinese Academy of Sciences, Beijing 100039, China.
FAU - Hou, Jinghua
AU  - Hou J
AD  - Jiuquan Satellite Launch Centre, Jiuquan 732750, China.
LA  - eng
GR  - 2022YFB3902300/National Key R&D Program of China/
PT  - Journal Article
DEP - 20230504
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
PMC - PMC10181651
OTO - NOTNLM
OT  - Gramian angular field
OT  - Kullback-Leibler divergence
OT  - fault diagnosis
OT  - meta-learning
COIS- The authors declare no conflict of interest.
EDAT- 2023/05/13 15:13
MHDA- 2023/05/13 15:14
PMCR- 2023/05/04
CRDT- 2023/05/13 01:40
PHST- 2023/03/14 00:00 [received]
PHST- 2023/04/20 00:00 [revised]
PHST- 2023/04/25 00:00 [accepted]
PHST- 2023/05/13 15:14 [medline]
PHST- 2023/05/13 15:13 [pubmed]
PHST- 2023/05/13 01:40 [entrez]
PHST- 2023/05/04 00:00 [pmc-release]
AID - s23094485 [pii]
AID - sensors-23-04485 [pii]
AID - 10.3390/s23094485 [doi]
PST - epublish
SO  - Sensors (Basel). 2023 May 4;23(9):4485. doi: 10.3390/s23094485.