Abstract
An innovative deep-learning-based model, namely, deep anomaly detection with the same probability distribution (DADSPD) is proposed to improve the accuracy of anomaly detection (AD) of rolling bearings driven only by normal data. First, the main framework of feature extraction based on a residual network was established, and a three-layer encoder structure was used to extract multidimensional features. Second, a new loss function based on the same probability distribution is designed, and the function of its probability distribution is to complete the training of the model by calculating the similarity between the outputs. Subsequently, the vibration data were preprocessed using wavelet and envelope analysis, and the processed data are converted into two-dimensional image signals and used as the input of the DADSPD. Finally, the model is verified on three sets of run-to-failure experimental datasets of rolling bearing. The results demonstrate that the proposed DADSPD model reaches more than 99%, which indicates that the DADSPD model has a high fault early warning and AD capability.
Issue Section:
Technical Briefs
References
1.
Chen
,
G.
, 2009
, “
Feature Extraction and Intelligent Diagnosis for Ball Bearing Early Faults
,” Acta Aeronaut. Astronaut. Sin.
,
30
(2
), pp. 362
–367
.https://hkxb.buaa.edu.cn/CN/Y2009/V30/I2/3622.
Lei
,
Y. G.
,
Yang
,
B.
,
Jiang
,
X. W.
,
Jia
,
F.
,
Li
,
N. P.
, and
Nandi
,
A. K.
, 2020
, “
Applications of Machine Learning to Machine Fault Diagnosis: A Review and Roadmap
,” Mech. Syst. Signal Process.
,
138
, p. 106587
.10.1016/j.ymssp.2019.1065873.
Huang
,
X.
,
Wen
,
G. R.
,
Dong
,
S. Z.
,
Zhou
,
H. X.
,
Lei
,
Z. H.
,
Zhang
,
Z. F.
, and
Chen
,
X. F.
, 2021
, “
Memory Residual Regression Autoencoder for Bearing Fault Detection
,” IEEE Trans. Instrum. Meas.
,
70
(99
), p. 3515512
.10.1109/TIM.2021.30721314.
Xu
,
G. W.
,
Lin
,
M.
,
Jiang
,
Z. F.
,
Shen
,
W. M.
, and
Huang
,
C. X.
, 2019
, “
Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks
,” IEEE Trans. Instrum. Meas.
,
69
(2
), pp. 509
–520
.10.1109/TIM.2019.29020035.
Liu
,
F.
,
Chen
,
R. W.
,
Xing
,
K. L.
,
Ding
,
S. S.
, and
Zhang
,
M. Y.
, 2022
, “
Fast Fault Diagnosis Algorithm for Rolling Bearing Based on Transfer Learning and Deep Residual Network
,” J. Vib. Shock
,
41
(3
), pp. 154
–164
.10.13465/j.cnki.jvs.2022.03.0196.
Li
,
W. H.
,
Shan
,
W. P.
, and
Zeng
,
X. Q.
, 2016
, “
Bearing Fault Identification Based on Deep Belief Network
,” J. Vib. Eng.
,
29
(2
), pp. 340
–347
.10.16385/j.cnki.issn.1004-4523.2016.02.0207.
Wen
,
J. T.
,
Yan
,
C. H.
,
Sun
,
J. D.
, and
Qiao
,
Y. L.
, 2018
, “
Bearing Fault Diagnosis Method Based on Compressed Acquisition and Deep Learning
,” Chin. J. Sci. Instrum.
,
39
(1
), pp. 171
–179
.10.19650/j.cnki.cjsi.j17020748.
Chalapathy
,
R.
,
Menon
,
A. K.
, and
Chawla
,
S.
, 2017
, Robust, Deep and Inductive Anomaly Detection
,
Springer
,
Cham, Switzerland
.9.
Zhang
,
L.
,
Song
,
C. Y.
,
Zou
,
Y. J.
,
Hong
,
C.
, and
Wang
,
C. B.
, 2020
, “
Bearing Performance Degradation Assessment Based on Renyi Entropy and K-Medoids Clustering
,” J. Vib. Shock
,
39
(20
), pp. 24
–31
.10.13465/j.cnki.jvs.2020.20.00410.
Liu
,
Y.
,
Wang
,
C.
, and
Zhou
,
P.
, 2022
, “
An Early Warning Method for Rolling Bearing Fault of Civil Aero-Engine
,” J. Propul. Technol.
,
43
(2
), pp. 295
–304
.10.13675/j.cnki.tjjs.20028411.
Lin
,
T.
,
Chen
,
G.
,
Ouyang
,
W. L.
,
Zhang
,
Q. D.
,
Wang
,
H. W.
, and
Chen
,
L. B.
, 2018
, “
Hyper-Spherical Distance Discrimination: A Novel Data Description Method for Aero-Engine Rolling Bearing Fault Detection
,” Mech. Syst. Signal Process.
,
109
, pp. 330
–351
.10.1016/j.ymssp.2018.01.00912.
Hao
,
T. F.
, 2014
, Research on Fault Diagnosis of Aero-Engine Rolling Element Bearing Based on Kernel Methods
,
Nanjing University of Aeronautics and Astronautics
, Nanjing, China.13.
Zhao
,
C.
, and
Feng
,
Z. P.
, 2021
, “
Features Distribution Fitting and Intelligent Fault Diagnosis of Planet Bearings Under Time-Varying Condition
,” J. Vib. Shock
,
40
(14
), pp. 252
–260
.10.13465/j.cnki.jvs.2021.14.03314.
Zeng
,
M.
,
Yang
,
Y.
,
Luo
,
S. R.
, and
Cheng
,
J. S.
, 2016
, “
One-Class Classification Based on the Convex Hull for Bearing Fault Detection
,” Mech. Syst. Signal Process.
,
81
, pp. 274
–293
.10.1016/j.ymssp.2016.04.00115.
Pan
,
Y.
,
Chen
,
J.
, and
Guo
,
L.
, 2009
, “
Robust Bearing Performance Degradation Assessment Method Based on Improved Wavelet Packet–Support Vector Data Description
,” Mech. Syst. Signal Process.
,
23
(3
), pp. 669
–681
.10.1016/j.ymssp.2008.05.01116.
Chalapathy
,
R.
, and
Chawla
,
S.
, 2019
, “
Deep Learning for Anomaly Detection: A Survey
,” arXiv:1901.03407 [cs.LG]
.10.48550/arXiv.1901.0340717.
Dai
,
J.
,
Wang
,
J.
,
Zhu
,
Z. K.
,
Sheng
,
C. Q.
, and
Huang
,
W. G.
, 2019
, “
Anomaly Detection of Mechanical Systems Based on Generative Adversarial Network and Autoencoder
,” Chin. J. Sci. Instrum.
,
40
(9
), pp. 16
–26
.10.19650/j.cnki.cjsi.J190508318.
Zhao
,
X. L.
,
Jia
,
M. P.
, and
Liu
,
Z.
, 2020
, “
Fault Diagnosis Framework of Rolling Bearing Using Adaptive Sparse Contrative Auto-Encoder With Optimized Unsupervised Extreme Learning Machine
,” IEEE Access
,
8
, pp. 99154
–99170
.10.1109/ACCESS.2019.296319319.
Wu
,
J.
,
Zhao
,
Z.
,
Sun
,
C.
,
Yan
,
R.
, and
Chen
,
X.
, 2020
, “
Fault-Attention Generative Probabilistic Adversarial Autoencoder for Machine Anomaly Detection
,” IEEE Trans. Ind. Informat
,
16
(12
), pp. 7479
–7488
.10.1109/TII.2020.297675220.
Zhang
,
S.
,
Ye
,
F.
,
Wang
,
B. N.
, and
Habetler
,
T. G.
, 2019
, “
Semi-Supervised Learning of Bearing Anomaly Detection Via Deep Variational Autoencoders
,” preprint arXiv:1912.01096 [cs.LG]
.10.48550/arXiv.1912.0109621.
Ruff
,
L.
,
Vandermeulen
,
R. A.
,
Görnitz
,
N.
,
Deecke
,
L.
,
Siddiqui
,
S. A.
,
Binder
,
A.
,
M ¨uller
,
E.
, and
Kloft
,
M.
, 2018
, “
Deep One-Class Classification
,” International Conference on Machine Learning
, Stockholm, Sweden, July 10–15, pp. 4393
–4402
.22.
Ruff
,
L.
,
Vandermeulen
,
R. A.
,
Grnitz
,
N.
,
Binder
,
A.
,
Uller
,
M.
,
Müller
,
E.
, and
Kloft
,
K. R.
, 2019
, “
Deep Semi-Supervised Anomaly Detection
,” International Conference on Learning Representations
.10.48550/arXiv.1906.0269423.
Mao
,
W. T.
,
Chen
,
J. X.
,
Liang
,
X. H.
, and
Zhang
,
X. M.
, 2020
, “
A New Online Detection Approach for Rolling Bearing Incipient Fault Via Self-Adaptive Deep Feature Matching
,” IEEE Trans. Instrum. Meas.
,
69
(2
), pp. 443
–456
.10.1109/TIM.2019.290369924.
Chalapathy
,
R.
,
Menon
,
A. K.
, and
Chawla
,
S.
, 2018
, “
Anomaly Detection Using One-Class Neural Networks
,” preprint arXiv:1802.06360 [cs.LG]
.10.48550/arXiv.1802.0636025.
Zhang
,
H.
,
Wu
,
C. R.
,
Zhang
,
Z. Y.
,
Zhu
,
Y.
,
Lin
,
H. B.
,
Zhang
,
Z.
,
Sun
,
Y.
,
He
,
T.
,
Mueller
,
J.
,
Manmatha
,
R.
,
Li
,
M.
, and
Smola
,
A
, 2020
, “
ResNeSt: Split-Attention Networks
,” preprint arXiv:2004.08955
.10.48550/arXiv.2004.0895526.
He
,
K.
,
Zhang
,
X.
,
Ren
,
S.
, and
Sun
,
J.
, 2015
, “
Delving Deep Into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification
,” Proceedings of the IEEE International Conference on Computer Vision
, Santiago, Chile, Dec. 7–13, pp. 1026
–1034
.10.1109/ICCV.2015.12327.
Kang
,
Y. X.
,
Chen
,
G.
,
Wei
,
X. K.
, and
Zhou
,
L.
, 2022
, “
Deep Residual Hedging Network and Its Application in Fault Diagnosis of Rolling Bearings
,” Acta Aeronaut. Astronaut. Sin.
,
2022
(8
), pp. 63
–74
(in Chinese).https://hkxb.buaa.edu.cn/CN/10.7527/S1000-6893.2021.2520128.
Yann
,
L. C.
,
Corinna
,
C.
, and
Burges
,
C. J.
, 2010
, “
Mnist Handwritten Digit Database
,” AT&T Labs, accessed Oct. 12, 2023, http://yann.lecun.com/exdb/mnist29.
Krizhevsky
,
A.
, and
Geoffrey
,
H.
, 2009
, “
Learning Multiple Layers of Features From Tiny Images
,” Technical Report.30.
Qiu
,
H.
,
Lee
,
J.
,
Lin
,
J.
, and
Yu
,
G.
, 2006
, “
Wavelet Filter-Based Weak Signature Detection Method and Its Application on Rolling Element Bearing Prognostics
,” J. Sound Vib.
,
289
(4–5
), pp. 1066
–1090
.10.1016/j.jsv.2005.03.007Copyright © 2023 by ASME
You do not currently have access to this content.
