Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform
Abstract
:1. Introduction
- (1)
- The CAE model is only trained by using healthy operation data at the beginning of an asset’s life cycle. Therefore, unlike most methods to construct a , this model can be trained online without requiring historical failure data from similar assets or fleets. In addition, since the CAE model is trained by the CWT image, it is applicable for equipment that operates under stationary and non-stationary conditions.
- (2)
- The values of the bottleneck nodes of the CAE model are used as extracted features. Using these values reduces any dependencies on the prior knowledge, and thus the is constructed automatically.
2. Background Theory
2.1. Continuous Wavelet Transform
2.2. Convolutional Networks
3. Methodology
3.1. Data Acquisition and Analyzing
3.2. Convolutional Autoencoder Model
3.3. Construction of HI
4. Experimental Results
4.1. Dataset Description
4.2. Analysis of Wavelet Power Spectrum Images
4.3. Training the CAE Model
4.4. Smoothing the
4.5. Results
4.6. Comparison with Other Traditional Methods
- Root mean square (RMS),
- Variance,
- Kurtosis,
- Skewness,
5. Discussion
6. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Wang, D.; Tsui, K.-L.; Miao, Q. Prognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators. IEEE Access 2018, 6, 665–676. [Google Scholar] [CrossRef]
- Yan, J.; Meng, Y.; Lu, L.; Li, L. Industrial Big Data in an Industry 4.0 Environment: Challenges, Schemes, and Applications for Predictive Maintenance. IEEE Access 2017, 5, 23484–23491. [Google Scholar] [CrossRef]
- Booyse, W.; Wilke, D.N.; Heyns, P.S. Deep digital twins for detection, diagnostics and prognostics. Mech. Syst. Signal Process. 2020, 140, 106612. [Google Scholar] [CrossRef]
- Tao, F.; Zhang, M.; Liu, Y.; Nee, A.Y.C. Digital twin driven prognostics and health management for complex equipment. CIRP Ann. 2018, 67, 169–172. [Google Scholar] [CrossRef]
- Wang, J.; Ye, L.; Gao, R.X.; Li, C.; Zhang, L. Digital Twin for rotating machinery fault diagnosis in smart manufacturing. Int. J. Prod. Res. 2019, 57, 3920–3934. [Google Scholar] [CrossRef]
- Qi, Q.; Tao, F. Digital Twin and Big Data Towards Smart Manufacturing and Industry 4.0: 360 Degree Comparison. IEEE Access 2018, 6, 3585–3593. [Google Scholar] [CrossRef]
- Dinardo, G.; Fabbiano, L.; Vacca, G. A smart and intuitive machine condition monitoring in the Industry 4.0 scenario. Measurement 2018, 126, 1–12. [Google Scholar] [CrossRef]
- Wan, J.; Sun, Y.; Liu, X.; Zheng, Y. A Digital-Twin-Assisted Fault Diagnosis Using Deep Transfer Learning. IEEE Access 2019, 7, 19990–19999. [Google Scholar] [CrossRef]
- Tuegel, E. The Airframe Digital Twin: Some Challenges to Realization. In Proceedings of the 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Honolulu, HI, USA, 23–26 April 2012; pp. 1812–1820. [Google Scholar]
- Li, N.; Lei, Y.; Lin, J.; Ding, S.X. An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings. IEEE Trans. Ind. Electron. 2015, 62, 7762–7773. [Google Scholar] [CrossRef]
- Deutsch, J.; He, M.; He, D. Remaining Useful Life Prediction of Hybrid Ceramic Bearings Using an Integrated Deep Learning and Particle Filter Approach. Appl. Sci. 2017, 7, 649. [Google Scholar] [CrossRef] [Green Version]
- Singleton, R.K.; Strangas, E.G.; Aviyente, S. Extended Kalman Filtering for Remaining-Useful-Life Estimation of Bearings. IEEE Trans. Ind. Electron. 2015, 62, 1781–1790. [Google Scholar] [CrossRef]
- Guo, L.; Li, N.; Jia, F.; Lei, Y.; Lin, J. A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 2017, 240, 98–109. [Google Scholar] [CrossRef]
- Liu, Z.; Zhang, L. A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings. Measurement 2020, 149, 107002. [Google Scholar] [CrossRef]
- Rai, A.; Upadhyay, S. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol. Int. 2016, 96, 289–306. [Google Scholar] [CrossRef]
- Fu, S.; Liu, K.; Xu, Y.; Liu, Y. Rolling Bearing Diagnosing Method Based on Time Domain Analysis and Adaptive Fuzzy-means clustering. Shock. Vib. 2015, 2016, 9412787. [Google Scholar]
- Bustos, A.; Rubio, H.; Castejon, C.; Garciaprada, J.C. Condition monitoring of critical mechanical elements through Graphical Representation of State Configurations and Chromogram of Bands of Frequency. Measurement 2019, 135, 71–82. [Google Scholar] [CrossRef]
- Al-Badour, F.; Sunar, M.; Cheded, L. Vibration analysis of rotating machinery using time–frequency analysis and wavelet techniques. Mech. Syst. Signal Process. 2011, 25, 2083–2101. [Google Scholar] [CrossRef]
- Gao, H.; Wan, X.; Chen, X.; Xu, G. Feature extraction and recognition for rolling element bearing fault utilizing short-time Fourier transform and non-negative matrix factorization. Chin. J. Mech. Eng. 2014, 28, 96–105. [Google Scholar] [CrossRef]
- Elbouchikhi, E.; Choqueuse, V.; Amirat, Y.; Benbouzid, M.E.H.; Turri, S. An Efficient Hilbert–Huang Transform-Based Bearing Faults Detection in Induction Machines. IEEE Trans. Energy Convers. 2017, 32, 401–413. [Google Scholar] [CrossRef]
- Singru, P.; Krishnakumar, V.; Natarajan, D.; Raizada, A. Bearing failure prediction using Wigner-Ville distribution, modified Poincare mapping and fast Fourier transform. J. Vibroeng. 2018, 20, 127–137. [Google Scholar] [CrossRef]
- Li, L.; Liu, P.; Xing, Y.; Guo, H. Time-frequency analysis of acoustic signals from a high-lift configuration with two wavelet functions. Appl. Acoust. 2018, 129, 155–160. [Google Scholar] [CrossRef]
- Kankar, P.K.; Sharma, S.C.; Harsha, S.P. Fault diagnosis of ball bearings using continuous wavelet transform. Appl. Soft Comput. 2011, 11, 2300–2312. [Google Scholar] [CrossRef]
- Liu, Z.; Zuo, M.J.; Qin, Y. Remaining Useful Life Prediction of Rolling Ement Bearings Based on Health State Assessment. Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci. 2016, 230, 314–330. [Google Scholar] [CrossRef] [Green Version]
- Lei, Y.; Li, N.; Gontarz, S.; Lin, J.; Radkowski, S.; Dybala, J. A Model-Based Method for Remaining Useful Life Prediction of Machinery. IEEE Trans. Reliab. 2016, 65, 1314–1326. [Google Scholar] [CrossRef]
- Duong, B.P.; Khan, S.A.; Shon, D.; Im, K.; Park, J.; Lim, D.S.; Jang, B.; Kim, J.-M. A Reliable Health Indicator for Fault Prognosis of Bearings. Sensors 2018, 18, 3740. [Google Scholar] [CrossRef] [Green Version]
- He, J.; Ouyang, M.; Yong, C.; Chen, D.; Guo, J.; Zhou, Y. A Novel Intelligent Fault Diagnosis Method for Rolling Bearing Based on Integrated Weight Strategy Features Learning. Sensors 2020, 20, 1774. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Hasan, J.; Kim, J.M. Bearing Fault Diagnosis under Variable Rotational Speeds Using Stockwell Transform-Based Vibration Imaging and Transfer Learning. Appl. Sci. 2018, 8, 2357. [Google Scholar] [CrossRef] [Green Version]
- Zan, T.; Wang, H.; Wang, M.; Liu, Z.; Gao, X.S. Application of Multi-Dimension Input Convolutional Neural Network in Fault Diagnosis of Rolling Bearings. Appl. Sci. 2019, 9, 2690. [Google Scholar] [CrossRef] [Green Version]
- Mao, W.; He, J.; Zuo, M.J. Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning. IEEE Trans. Instrum. Meas. 2019, 69, 1594–1608. [Google Scholar] [CrossRef]
- Yang, F.; Zhang, W.; Tao, L.; Ma, J. Transfer Learning Strategies for Deep Learning-based PHM Algorithms. Appl. Sci. 2020, 10, 2361. [Google Scholar] [CrossRef] [Green Version]
- Yoo, Y.; Baek, J.-G. A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network. Appl. Sci. 2018, 8, 1102. [Google Scholar] [CrossRef] [Green Version]
- Abed, W.; Sharma, S.; Sutton, R.; Motwani, A. A Robust Bearing Fault Detection and Diagnosis Technique for Brushless DC Motors Under Non-stationary Operating Conditions. J. Control Autom. Electr. Syst. 2015, 26, 241–254. [Google Scholar] [CrossRef] [Green Version]
- Yin, H.; Li, Z.; Zuo, J.; Liu, H.; Yang, K.; Li, F. Wasserstein Generative Adversarial Network and Convolutional Neural Network (WG-CNN) for Bearing Fault Diagnosis. Math. Probl. Eng. 2020, 2020, 1–16. [Google Scholar] [CrossRef]
- Zhang, S.; Zhang, S.; Wang, B.; Habetler, T.G. Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review. IEEE Access 2020, 8, 29857–29881. [Google Scholar] [CrossRef]
- Liu, H.; Zhou, J.; Xu, Y.; Zheng, Y.; Peng, X.; Jiang, W. Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks. Neurocomputing 2018, 315, 412–424. [Google Scholar] [CrossRef]
- Khan, S.; Yairi, T. A review on the application of deep learning in system health management. Mech. Syst. Signal Process. 2018, 107, 241–265. [Google Scholar] [CrossRef]
- Guo, S.; Yang, T.; Gao, W.; Yang, T. A Novel Fault Diagnosis Method for Rotating Machinery Based on a Convolutional Neural Network. Sensors 2018, 18, 1429. [Google Scholar] [CrossRef] [Green Version]
- Tang, B.; Liu, W.; Song, T. Wind turbine fault diagnosis based on Morlet wavelet transformation and Wigner-Ville distribution. Renew. Energy 2010, 35, 2862–2866. [Google Scholar] [CrossRef]
- Kim, D.; Kim, J.; Kim, J. Elastic exponential linear units for convolutional neural networks. Neurocomputing 2020, 406, 253–266. [Google Scholar] [CrossRef]
- Hua, C.; Zhang, Q.; Xu, G.; Zhang, Y.; Xu, T. Performance reliability estimation method based on adaptive failure threshold. Mech. Syst. Signal Process. 2013, 36, 505–519. [Google Scholar] [CrossRef]
- Wan, F.; Guo, G.; Zhang, C.; Guo, Q.; Liu, J. Outlier Detection for Monitoring Data Using Stacked Autoencoder. IEEE Access 2019, 7, 173827–173837. [Google Scholar] [CrossRef]
- Bera, S.; Shrivastava, V.K. Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification. Int. J. Remote. Sens. 2019, 41, 2664–2683. [Google Scholar] [CrossRef]
- Ahn, J.; Lee, M.H.; Lee, J.A. Distance-based outlier detection for high dimension, low sample size data. J. Appl. Stat. 2018, 46, 13–29. [Google Scholar] [CrossRef]
- PCoE Datasets, Bearing Data Set, Intelligent Maintenance Systems (IMS), University of Cincinnati. Available online: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/ (accessed on 10 June 2020).
- Chollet, F. Keras: The Python Deep Learning API. Available online: https://keras.io/ (accessed on 27 August 2020).
- Abadi, M.A.; Barham, P.A.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G.S.; Davis, A.; Dean, J.; Devin, M. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: http://tensorflow.org/ (accessed on 16 May 2020).
- Xu, F.; Huang, Z.; Yang, F.; Wang, D.; Tsui, K.L. Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion. Appl. Soft Comput. 2020, 89, 106119. [Google Scholar] [CrossRef]
- Yan, R.; Gao, R.X. Approximate Entropy as a diagnostic tool for machine health monitoring. Mech. Syst. Signal Process. 2007, 21, 824–839. [Google Scholar] [CrossRef]
- Rai, A.; Upadhyay, S. Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering. Mech. Syst. Signal Process. 2017, 93, 16–29. [Google Scholar] [CrossRef]
Bearing | Subset 1 Bearing 3 | Subset 1 Bearing 4 | Subset 2 Bearing 1 | Subset 3 Bearing3 |
---|---|---|---|---|
Load (lbs) | 6000 | 6000 | 6000 | 6000 |
Speed (rpm) | 2000 | 2000 | 2000 | 2000 |
Defect type | Inner race | Roller element | Outer race | Outer race |
Endurance duration | 34 days 12 h | 34 days 12 h | 6 days 20 h | 45 days 9 h |
Number of healthy samples | 61,069 | 43,381 | 19,146 | 200,474 |
Failure threshold | 27 days 20 h | 19 days 20 h | 3 days 21 h | 41 days 2 h |
Number of faulty samples | 19,800 | 31,090 | 14,780 | 20,230 |
Metrics | Proposed Method | RMS | Variance | ApEn | Kurtosis | Skewness | EMD-SVD- K-Medoids |
---|---|---|---|---|---|---|---|
Mon | 0.7587 | 0.0113 | 0.0140 | 0.0051 | 0.0063 | 0.0016 | 0.0229 |
Rob | 0.9484 | 0.8411 | 0.7565 | 0.8790 | 0.8875 | 0.4427 | 0.6971 |
Corr | 0.9969 | 0.6363 | 0.4480 | −0.3814 | 0.3622 | −0.4282 | 0.6358 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 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 (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kaji, M.; Parvizian, J.; van de Venn, H.W. Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform. Appl. Sci. 2020, 10, 8948. https://doi.org/10.3390/app10248948
Kaji M, Parvizian J, van de Venn HW. Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform. Applied Sciences. 2020; 10(24):8948. https://doi.org/10.3390/app10248948
Chicago/Turabian StyleKaji, Mohammadreza, Jamshid Parvizian, and Hans Wernher van de Venn. 2020. "Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform" Applied Sciences 10, no. 24: 8948. https://doi.org/10.3390/app10248948
APA StyleKaji, M., Parvizian, J., & van de Venn, H. W. (2020). Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform. Applied Sciences, 10(24), 8948. https://doi.org/10.3390/app10248948