Fault Diagnosis of Rotating Machinery Based on Improved Self-Supervised Learning Method and Very Few Labeled Samples
Abstract
:1. Introduction
2. The Framework of DTC-SimCLR Method
3. The Fault Diagnosis Based on DTC-SimCLR under Few Labeled Samples
3.1. Data Transformation for Signal Data Sample
3.2. The Self-Supervised Learning of Representations Based on SimCLR
3.3. Fault Diagnosis under Very Few Fault Samples
4. Case Studies and Experiments Results
4.1. Case One: Cutting Tooth Fault Diagnosis
4.1.1. Experimental Setup and Data Description
4.1.2. Results and Discussion
- (1)
- The comparison of DTCs
- (2)
- CNN without DTC vs. CNN with DTC vs. DTC-SimCLR
- (3)
- DTC-SimCLR vs. other common methods.
4.2. Case Two: Bearing Fault Diagnosis
4.2.1. Dataset Description
4.2.2. Results and Discussion
- (1)
- The comparison of DTCs
- (2)
- CNN without DTC vs. CNN with DTC vs. DTC-SimCLR
- (3)
- DTC-SimCLR vs. other common methods.
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Hu, K.; Liu, Z.; Tasiu, I.A.; Chen, T. Fault Diagnosis and Tolerance with Low Torque Ripple for Open-Switch Fault of IM Drives. IEEE Trans. Transp. Electrif. 2020, 7, 133–146. [Google Scholar] [CrossRef]
- Li, G.; Wu, J.; Deng, C.; Chen, Z.; Shao, X. Convolutional Neural Network-Based Bayesian Gaussian Mixture for Intelligent Fault Diagnosis of Rotating Machinery. IEEE Trans. Instrum. Meas. 2021, 70, 3517410. [Google Scholar] [CrossRef]
- Kong, J.; Wang, K.; Zhang, J.; Zhang, H. Multiple Open-Switch Fault Diagnosis for Five-Phase Permanent Magnet Ma-chine Utilizing Currents in Stationary Reference Frame. IEEE Trans. Energy Convers. 2020, 36, 314–324. [Google Scholar] [CrossRef]
- Sohaib, M.; Kim, J.-M. Fault Diagnosis of Rotary Machine Bearings Under Inconsistent Working Conditions. IEEE Trans. Instrum. Meas. 2019, 69, 3334–3347. [Google Scholar] [CrossRef]
- Long, J.; Sun, Z.; Li, C.; Hong, Y.; Bai, Y.; Zhang, S. A novel sparse echo autoencoder network for data-driven fault diagno-sis of delta 3-D printers. IEEE Trans. Instrum. Meas. 2019, 69, 683–692. [Google Scholar] [CrossRef]
- Liu, Z.-H.; Jiang, L.-B.; Wei, H.-L.; Chen, L.; Li, X.-H. Optimal Transport Based Deep Domain Adaptation Approach for Fault Diagnosis of Rotating Machine. IEEE Trans. Instrum. Meas. 2021, 70. [Google Scholar] [CrossRef]
- Zhong, J.; Wang, D.; Guo, J.e.; Cabrera, D.; Li, C. Theoretical investigations on kurtosis and entropy and their improve-ments for system health monitoring. IEEE Trans. Instrum. Meas. 2020, 70, 3503710. [Google Scholar]
- Zhang, Z.; Verma, A.; Kusiak, A. Fault Analysis and Condition Monitoring of the Wind Turbine Gearbox. IEEE Trans. Energy Convers. 2012, 27, 526–535. [Google Scholar] [CrossRef]
- Pan, H.; Yang, Y.; Li, X.; Zheng, J.; Cheng, J. Symplectic geometry mode decomposition and its application to rotating ma-chinery compound fault diagnosis. Mech. Syst. Signal Process. 2019, 114, 189–211. [Google Scholar] [CrossRef]
- Li, G.; Tang, G.; Luo, G.; Wang, H. Underdetermined blind separation of bearing faults in hyperplane space with varia-tional mode decomposition. Mech. Syst. Signal Process. 2019, 120, 83–97. [Google Scholar] [CrossRef]
- Li, Y.; Xu, M.; Yu, W.; Huang, W. Health condition monitoring and early fault diagnosis of bearings using SDF and intrin-sic characteristic-scale decomposition. IEEE Trans. Instrum. Meas. 2016, 65, 2174–2189. [Google Scholar] [CrossRef]
- Jain, S.; Panda, R.; Tripathy, R.K. Multivariate sliding-mode singular spectrum analysis for the decomposition of multi-sensor time series. IEEE Sens. Lett. 2020, 4, 7002404. [Google Scholar] [CrossRef]
- Li, X.L.; Yuan, Z.H. Tool wear monitoring with wavelet packet transform—Fuzzy clustering method. Wear 1998, 219, 145–154. [Google Scholar]
- Li, G.; Deng, C.; Wu, J.; Xu, X.; Shao, X.; Wang, Y. Sensor Data-Driven Bearing Fault Diagnosis Based on Deep Convolutional Neural Networks and S-Transform. Sensors 2019, 19, 2750. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cheng, Y.; Lin, M.; Wu, J.; Zhu, H.; Shao, X. Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowl.-Based Syst. 2021, 216, 106796. [Google Scholar] [CrossRef]
- Ravikumar, K.; Madhusudana, C.; Kumar, H.; Gangadharan, K. Classification of gear faults in internal combustion (IC) engine gearbox using discrete wavelet transform features and K star algorithm. Eng. Sci. Technol. Int. J. 2021. [Google Scholar] [CrossRef]
- Rudsari, F.N.; Kazemi, A.A.R.; Shoorehdeli, M.A. Fault Analysis of High-Voltage Circuit Breakers Based on Coil Current and Contact Travel Waveforms Through Modified SVM Classifier. IEEE Trans. Power Deliv. 2019, 34, 1608–1618. [Google Scholar] [CrossRef]
- Gao, L.; Li, D.; Yao, L.; Gao, Y. Sensor drift fault diagnosis for chiller system using deep recurrent canonical correlation analysis and k-nearest neighbor classifier. ISA Trans. 2021. [Google Scholar] [CrossRef]
- Jiang, G.; He, H.; Yan, J.; Xie, P. Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox. IEEE Trans. Ind. Electron. 2018, 66, 3196–3207. [Google Scholar] [CrossRef]
- Jin, T.; Yan, C.; Chen, C.; Yang, Z.; Wang, S. Light neural network with fewer parameters based on CNN for fault diagno-sis of rotating machinery. Measurement 2021, 181, 109639. [Google Scholar] [CrossRef]
- Ye, Z.; Yu, J. Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis. Mech. Syst. Signal Process. 2021, 161, 107984. [Google Scholar] [CrossRef]
- Zhou, Z.-H. A brief introduction to weakly supervised learning. Natl. Sci. Rev. 2017, 5, 44–53. [Google Scholar] [CrossRef] [Green Version]
- Zhu, X.J. Semi-Supervised Learning Literature Survey; University of Wisconsin Madison: Madison, WI, USA, 2005. [Google Scholar]
- Settles, B. Active Learning Literature Survey; University of Wisconsin-Madison, Department of Computer Sciences: Madison, WI, USA, 2009. [Google Scholar]
- He, H.; Garcia, E.A. Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 2009, 21, 1263–1284. [Google Scholar]
- Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 2009, 22, 1345–1359. [Google Scholar] [CrossRef]
- Zhang, D.; Chen, Y.; Guo, F.; Karimi, H.R.; Dong, H.; Xuan, Q. A New Interpretable Learning Method for Fault Diagnosis of Rolling Bearings. IEEE Trans. Instrum. Meas. 2020, 70, 3507010. [Google Scholar] [CrossRef]
- Hochreiter, S.; Younger, A.S.; Conwell, P.R. Learning to Learn Using Gradient Descent. In Proceedings of the International Conference on Artificial Neural Networks, Vienna, Austria, 21–25 August 2001. [Google Scholar]
- Guo, Q.; Li, Y.; Song, Y.; Wang, D.; Chen, W. Intelligent Fault Diagnosis Method Based on Full 1-D Convolutional Generative Adversarial Network. IEEE Trans. Ind. Inform. 2019, 16, 2044–2053. [Google Scholar] [CrossRef]
- Liang, P.; Deng, C.; Wu, J.; Li, G.; Yang, Z.; Wang, Y. Intelligent Fault Diagnosis via Semisupervised Generative Adversarial Nets and Wavelet Transform. IEEE Trans. Instrum. Meas. 2019, 69, 4659–4671. [Google Scholar] [CrossRef]
- Dong, Y.; Li, Y.; Zheng, H.; Wang, R.; Xu, M. A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: Solving the small sample problem. ISA Trans. 2021. [Google Scholar] [CrossRef]
- Ruan, H.; Wang, Y.; Li, X.; Qin, Y.; Tang, B.; Wang, P. A Relation-Based Semisupervised Method for Gearbox Fault Diagno-sis With Limited Labeled Samples. IEEE Trans. Instrum. Meas. 2021, 70, 3510013. [Google Scholar]
- Kumar, A.; Vashishtha, G.; Gandhi, C.P.; Zhou, Y.; Glowacz, A.; Xiang, J. Novel Convolutional Neural Network (NCNN) for the Diagnosis of Bearing Defects in Rotary Machinery. IEEE Trans. Instrum. Meas. 2021, 70, 3510710. [Google Scholar] [CrossRef]
- Dixit, S.; Verma, N.K.; Ghosh, A.K. Intelligent Fault Diagnosis of Rotary Machines: Conditional Auxiliary Classifier GAN Coupled with Meta Learning Using Limited Data. IEEE Trans. Instrum. Meas. 2021, 70, 3517811. [Google Scholar] [CrossRef]
- Zhao, J.; Yang, S.; Li, Q.; Liu, Y.; Gu, X.; Liu, W. A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network. Measurement 2021, 176, 109088. [Google Scholar] [CrossRef]
- Wang, Y.; Yao, Q.; Kwok, J.; Ni, L.M. Generalizing from a Few Examples: A Survey on Few-Shot Learning; Association for Computing Machinery: New York, NY, USA, 2020. [Google Scholar]
- Chen, T.; Kornblith, S.; Norouzi, M.; Hinton, G. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning, Montréal, QC, Canada, 6–8 July 2020; pp. 1597–1607. [Google Scholar]
- PHM Data Challenge; PHM Society: Portland, OR, USA, 2010; Available online: https://phmsociety.org/phm-data-challenge/ (accessed on 15 November 2021).
- Zhao, R.; Wang, D.; Yan, R.; Mao, K.; Shen, F.; Wang, J. Machine health monitoring using local feature-based gated recur-rent unit networks. IEEE Trans. Ind. Electron. 2017, 65, 1539–1548. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Hang, J.; Zhang, J.; Xia, M.; Ding, S.; Hua, W. Interturn Fault Diagnosis for Model-Predictive-Controlled-PMSM Based on Cost Function and Wavelet Transform. IEEE Trans. Power Electron. 2019, 35, 6405–6418. [Google Scholar] [CrossRef]
- Xu, Y.; Deng, Y.; Zhao, J.; Tian, W.; Ma, C. A Novel Rolling Bearing Fault Diagnosis Method Based on Empirical Wavelet Transform and Spectral Trend. IEEE Trans. Instrum. Meas. 2019, 69, 2891–2904. [Google Scholar] [CrossRef]
- Lessmeier, C.; Kimotho, J.K.; Zimmer, D.; Sextro, W. Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification. In Proceedings of the European Conference of the Prognostics and Health Management Society, Bilbo, Spain, 5–8 July 2016. [Google Scholar]
Wear Stage | Initial Wear | Smooth Wear | Rapid Wear | Severe Wear | Complete Wear |
---|---|---|---|---|---|
VB | 0~94.5 | 94.5~113.0 | 113~134.2 | 134.2~165 | >165.0 |
Signal | 1~95 | 95~175 | 176~240 | 241~297 | 298~315 |
Fault | Label | Condition Samples | Labeled Samples | Testing Samples |
---|---|---|---|---|
IW | 1 | 1000 | 10 | 300 |
MW | 2 | 1000 | 10 | 300 |
RW | 3 | 1000 | 10 | 300 |
SW | 4 | 1000 | 10 | 300 |
CW | 5 | 1000 | 10 | 300 |
Parameters | Size |
---|---|
Input size | 1024 |
Temperature () | 10 |
Feature encoder | 16 convolutional layers |
Output size | 128 |
Training epoch | 200 |
No. | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | Accuracy |
---|---|---|---|---|---|---|---|---|---|
1 | Normalization | Rotation | horizontal flip | Grayscale | Color Jitter | Affine | Resize crop | Center Crop | 28.31% |
2 | Normalization | Rotation | horizontal flip | Grayscale | - | - | Resize crop | - | 83.50% |
3 | Normalization | Rotation | horizontal flip | - | - | - | Resize crop | - | 80.24% |
4 | Normalization | Rotation | - | - | - | - | Resize crop | - | 81.44% |
5 | Normalization | - | - | - | - | - | Resize crop | - | 90.24% |
6 | - | Rotation | - | - | - | - | - | - | 20.32% |
7 | Normalization | - | - | - | - | - | - | - | 93.40% |
Method | std (%) | ||
---|---|---|---|
50 Samples | 25 Samples | 5 Samples | |
DTC-SimCLR | 93.11 0.24 | 75.39 | 30.70 5.76 |
Methods | Testing Accuracy (%) | Training Time (s) | ||
---|---|---|---|---|
50 Labeled Samples | 3500 Labeled Samples | 50 Labeled Samples | 3500 Labeled Samples | |
Complex tree | 28.9 | 59.3 | 5.68 | 108.16 |
Cubic SVM | 47.9 | 92.1 | 8.24 | 215.30 |
Ensemble KNN | 50.4 | 81.0 | 14.42 | 1695.9 |
Weighted KNN | 47.9 | 81.6 | 10.27 | 724.81 |
WT + Cubic SVM | 39.3 | 66.7 | 4.55 | 724.32 |
CNN | 68.6 | 93.7 | 18.52 | 772.59 |
GAN | 85.6 | - | 500.23 | - |
DTC-SimCLR | 93.1 | - | 19.10 | - |
Conditions | Label | Condition Samples | Labeled Samples | Testing Samples |
---|---|---|---|---|
Normal | 1 | 1000 | 10 | 300 |
IRF | 2 | 1000 | 10 | 300 |
ORF | 3 | 1000 | 10 | 300 |
Method | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | Average |
---|---|---|---|---|---|---|---|---|---|---|---|
CNN | 67.1 | 67.0 | 66.1 | 65.8 | 68.7 | 69.9 | 66.0 | 67.7 | 67.6 | 67.3 | 67.32 |
DTC + CNN | 79.7 | 77.3 | 79.9 | 79.9 | 79.3 | 79.2 | 79.8 | 78.3 | 79.8 | 79.2 | 79.24 |
DTC-SimCLR | 82.0 | 85.8 | 82.2 | 83.4 | 83.8 | 82.8 | 83.4 | 82.6 | 85.2 | 84.0 | 83.52 |
Methods | Testing Accuracy (%) | Training Time (s) | ||
---|---|---|---|---|
30 Labeled Samples | 2100 Labeled Samples | 30 Labeled Samples | 2100 Labeled Samples | |
Complex tree | 46.7 | 56.0 | 2.44 | 13.39 |
Cubic SVM | 43.3 | 63.9 | 3.02 | 24.42 |
Ensemble KNN | 36.7 | 52.0 | 7.76 | 84.31 |
Cosine KNN | 53.3 | 68.8 | 5.46 | 37.74 |
WT + Cubic SVM | 34.5 | 63.6 | 2.35 | 56.56 |
CNN | 67.32 | 84.00 | 8.32 | 182.51 |
GAN | 71.2 | - | 326.5 | - |
DTC-SimCLR | 83.52 | - | 8.54 | - |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wei, M.; Liu, Y.; Zhang, T.; Wang, Z.; Zhu, J. Fault Diagnosis of Rotating Machinery Based on Improved Self-Supervised Learning Method and Very Few Labeled Samples. Sensors 2022, 22, 192. https://doi.org/10.3390/s22010192
Wei M, Liu Y, Zhang T, Wang Z, Zhu J. Fault Diagnosis of Rotating Machinery Based on Improved Self-Supervised Learning Method and Very Few Labeled Samples. Sensors. 2022; 22(1):192. https://doi.org/10.3390/s22010192
Chicago/Turabian StyleWei, Meirong, Yan Liu, Tao Zhang, Ze Wang, and Jiaming Zhu. 2022. "Fault Diagnosis of Rotating Machinery Based on Improved Self-Supervised Learning Method and Very Few Labeled Samples" Sensors 22, no. 1: 192. https://doi.org/10.3390/s22010192
APA StyleWei, M., Liu, Y., Zhang, T., Wang, Z., & Zhu, J. (2022). Fault Diagnosis of Rotating Machinery Based on Improved Self-Supervised Learning Method and Very Few Labeled Samples. Sensors, 22(1), 192. https://doi.org/10.3390/s22010192