PMID- 34833837
OWN - NLM
STAT- MEDLINE
DCOM- 20211130
LR  - 20211130
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 21
IP  - 22
DP  - 2021 Nov 22
TI  - A New Bearing Fault Diagnosis Method Based on Capsule Network and Markov 
      Transition Field/Gramian Angular Field.
LID - 10.3390/s21227762 [doi]
LID - 7762
AB  - Compared to time-consuming and unreliable manual analysis, intelligent fault 
      diagnosis techniques using deep learning models can improve the accuracy of 
      intelligent fault diagnosis with their multi-layer nonlinear mapping 
      capabilities. This paper proposes a model to perform fault diagnosis and 
      classification by using a time series of vibration sensor data as the input. The 
      model encodes the raw vibration signal into a two-dimensional image and performs 
      feature extraction and classification by a deep convolutional neural network or 
      improved capsule network. A fault diagnosis technique based on the Gramian 
      Angular Field (GAF), the Markov Transition Field (MTF), and the Capsule Network 
      is proposed. Experiments conducted on a bearing failure dataset from Case Western 
      Reserve University investigated the impact of two coding methods and different 
      network structures on the diagnosis accuracy. The results show that the GAF 
      technique retains more complete fault characteristics, while the MTF technique 
      contains a small number of fault characteristics but more dynamic 
      characteristics. Therefore, the proposed method incorporates GAF images and MTF 
      images as a dual-channel image input to the capsule network, enabling the network 
      to obtain a more complete fault signature. Multiple sets of experiments were 
      conducted on the bearing fault dataset at Case Western Reserve University, and 
      the Capsule Network in the proposed model has an advantage over other 
      convolutional neural networks and performs well in the comparison of fault 
      diagnosis methods proposed by other researchers.
FAU - Han, Bin
AU  - Han B
AUID- ORCID: 0000-0002-9503-1576
AD  - College of Computer and Control Engineering, Qiqihar University, Qiqihar 161003, 
      China.
FAU - Zhang, Hui
AU  - Zhang H
AD  - College of Computer and Control Engineering, Qiqihar University, Qiqihar 161003, 
      China.
FAU - Sun, Ming
AU  - Sun M
AD  - College of Computer and Control Engineering, Qiqihar University, Qiqihar 161003, 
      China.
FAU - Wu, Fengtong
AU  - Wu F
AD  - College of Computer and Control Engineering, Qiqihar University, Qiqihar 161003, 
      China.
LA  - eng
GR  - LH2019F038/the Joint guiding project of Natural Science Foundation of 
      Heilongjiang Province/
GR  - 135209311/Project supported by the Scientific Research Fundation of the Education 
      Department of Hei-longjiang Province/
PT  - Journal Article
DEP - 20211122
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - Humans
MH  - Intelligence
MH  - *Neural Networks, Computer
MH  - Physical Therapy Modalities
MH  - *Vibration
PMC - PMC8622607
OTO - NOTNLM
OT  - convolutional neural networks
OT  - intelligent fault diagnosis
OT  - time series classification
COIS- The authors declare no conflict of interest.
EDAT- 2021/11/28 06:00
MHDA- 2021/12/01 06:00
PMCR- 2021/11/22
CRDT- 2021/11/27 01:22
PHST- 2021/09/27 00:00 [received]
PHST- 2021/11/11 00:00 [revised]
PHST- 2021/11/19 00:00 [accepted]
PHST- 2021/11/27 01:22 [entrez]
PHST- 2021/11/28 06:00 [pubmed]
PHST- 2021/12/01 06:00 [medline]
PHST- 2021/11/22 00:00 [pmc-release]
AID - s21227762 [pii]
AID - sensors-21-07762 [pii]
AID - 10.3390/s21227762 [doi]
PST - epublish
SO  - Sensors (Basel). 2021 Nov 22;21(22):7762. doi: 10.3390/s21227762.