Rights statement: This is the author’s version of a work that was accepted for publication in Reliability Engineering and System Safety. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Reliability Engineering and System Safety, 202, 2020 DOI: 10.1016/j.ress.2020.107050
Accepted author manuscript, 4.3 MB, PDF document
Available under license: CC BY-NC-ND
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Multi-scale deep intra-class transfer learning for bearing fault diagnosis
AU - Wang, X.
AU - Shen, C.
AU - Xia, M.
AU - Wang, D.
AU - Zhu, J.
AU - Zhu, Z.
N1 - This is the author’s version of a work that was accepted for publication in Reliability Engineering and System Safety. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Reliability Engineering and System Safety, 202, 2020 DOI: 10.1016/j.ress.2020.107050
PY - 2020/10/1
Y1 - 2020/10/1
N2 - The tremendous success of deep learning in machine fault diagnosis is dependent on the hypothesis that training and test datasets are subordinated to the same distribution. This subordination is difficult to meet in practical scenarios of industrial applications. On the one hand, the working conditions of rotating machinery can change easily. On the other hand, vibration data and labels are difficult to obtain to train a specific model for each working condition. In this study, we solve these problems by constructing a novel deep transfer learning model called multi-scale deep intra-class adaptation network, which first uses the modified ResNet-50 to extract low-level features and then constructs a multiple scale feature learner to analyze these low-level features at multiple scales and obtain high-level features as input for the classifier. Pseudo labels are then computed to shorten the conditional distribution distance of vibration data collected under different working loads for intra-class adaptation. The proposed method is validated using two datasets to recognize the bearing normal state, the inner race, the ball and outer race faults, and their fault degrees under four different working loads. The high-precision diagnosis results of 24 transfer learning experiments reveal the reliability and generalizability of the constructed model.
AB - The tremendous success of deep learning in machine fault diagnosis is dependent on the hypothesis that training and test datasets are subordinated to the same distribution. This subordination is difficult to meet in practical scenarios of industrial applications. On the one hand, the working conditions of rotating machinery can change easily. On the other hand, vibration data and labels are difficult to obtain to train a specific model for each working condition. In this study, we solve these problems by constructing a novel deep transfer learning model called multi-scale deep intra-class adaptation network, which first uses the modified ResNet-50 to extract low-level features and then constructs a multiple scale feature learner to analyze these low-level features at multiple scales and obtain high-level features as input for the classifier. Pseudo labels are then computed to shorten the conditional distribution distance of vibration data collected under different working loads for intra-class adaptation. The proposed method is validated using two datasets to recognize the bearing normal state, the inner race, the ball and outer race faults, and their fault degrees under four different working loads. The high-precision diagnosis results of 24 transfer learning experiments reveal the reliability and generalizability of the constructed model.
KW - Deep transfer learning
KW - Fault diagnosis
KW - Intra-class adaptation
KW - Multi-scale feature learner
KW - Bearings (machine parts)
KW - Failure analysis
KW - Fault detection
KW - Learning systems
KW - Transfer learning
KW - Bearing fault diagnosis
KW - Conditional distribution
KW - High-level features
KW - High-precision
KW - Low-level features
KW - Machine fault diagnosis
KW - Multiple scale
KW - Vibration data
KW - Deep learning
U2 - 10.1016/j.ress.2020.107050
DO - 10.1016/j.ress.2020.107050
M3 - Journal article
VL - 202
JO - Reliability Engineering and System Safety
JF - Reliability Engineering and System Safety
SN - 0951-8320
M1 - 107050
ER -