Bearing Fault Diagnosis under Varying Work Conditions Based on Synchrosqueezing Transform, Random Projection, and Convolutional Neural Networks

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Mar 3, 2024
Boubker Najdi Mohammed Benbrahim Mohammed Nabil Kabbaj

Abstract

Bearings are critical components in rotating machinery, and their failure can lead to costly repairs and downtime. To prevent such failures, it is important to detect and diagnose bearing faults early. In recent years, deep-learning techniques have shown promise for detecting and diagnosing bearing faults automatically. While these algorithms can all achieve diagnostic accuracy of over 90%, their generalizability and robustness in complex, extreme variable loading conditions have not been thoroughly validated. In this paper, a feature extraction method based on Synchro-squeezing Wavelet Transform (SSWT), Random projection (RP), and deep learning (DL) is presented. To fulfill the data requirements of neural networks, data augmentation is initially utilized to augment the size of the original data. Subsequently, the SSWT technique is employed to convert the signals from the Time domain to the Time-Frequency domain, resulting in the conversion of the 1-D signal to a 2-D feature image. To decrease the complexity of deep learning computation, data preprocessing involves utilizing Random projection to reduce feature dimensionality. The final step involves constructing a Convolutional Neural Network (CNN) model that can identify fault features from the obtained Time-Frequency images and perform accurate fault classification. By utilizing the CWRU and IMS datasets to evaluate the method, the study demonstrates that the suggested approach outperforms advanced techniques in terms of both diagnostic accuracy and robustness.

Abstract 212 | PDF Downloads 175

##plugins.themes.bootstrap3.article.details##

Keywords

Data augmentation, Deep learning, Signal processing, Random projection, Synchrosqueezing Wavelet Transform, Convolutional Neural Networks, Predictive Maintenance, Bearing Diagnosis, Fault detection

References
Achlioptas, D. (2003). Database-friendly random projections: Johnson-lindenstrauss with binary coins. Journal of Computer and System Sciences, 66(4), 671-687. Retrieved from https://www.sciencedirect.com/science/article/pii/S0022000003000254 (Special Issue on PODS 2001) doi: https://doi.org/10.1016/S0022-0000(03)00025-4
Altman, J., & Mathew, J. (2001). Multiple band-pass autoregressive demodulation for rolling-element bearing fault diagnosis. Mechanical Systems and Signal Processing, 15(5), 963-977. doi: https://doi.org/10.1006/mssp.2001.1410
Auger, F., & Flandrin, P. (1995). Improving the readability of time-frequency and time-scale representations by the reassignment method. IEEE Transactions on Signal Processing, 43(5), 1068-1089. doi: 0.1109/78.382394
Auger, F., Flandrin, P., Lin, Y.-T., McLaughlin, S., Meignen, S., Oberlin, T., & Wu, H.-T. (2013). Time-frequency re-assignment and synchrosqueezing: An overview. IEEE Signal Processing Magazine, 30(6), 32-41. doi: 10.1109/MSP.2013.2265316
Bengio, Y. (2016). Deep learning. London, England: MIT Press.
Bingham, E., & Mannila, H. (2001). Random projection in dimensionality reduction: Applications to image and text data. In Proceedings of the seventh acm sigkdd international conference on knowledge discovery and data mining (p. 245–250). New York, NY, USA: Association for Computing Machinery. Retrieved from https://doi.org/10.1145/502512.502546 doi: 10.1145/502512.502546
Bouvrie, J. (2006). Notes on convolutional neural networks.
Chen, Z., Mauricio, A., Li, W., & Gryllias, K. (2020, 01). A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks. Mechanical Systems and Signal Processing, 140. doi: 10.1016/j.ymssp.2020.106683
Daubechies, I. (1992). Ten lectures on wavelets. Society for Industrial and Applied Mathematics. doi: 10.1137/1.9781611970104
Daubechies, I. (2000, 11). A nonlinear squeezing of the continuous wavelet transform based on auditory nerve models.
Gai, J., Shen, J., Hu, Y., & Wang, H. (2020). An integrated method based on hybrid grey wolf optimizer improved variational mode decomposition and deep neural network for fault diagnosis of rolling bearing. Measurement, 162, 107901. doi: https://doi.org/10.1016/j.measurement.2020.107901
Ghosh, A., Sufian, A., Sultana, F., Chakrabarti, A., & De, D. (2020, 01). Fundamental concepts of convolutional neural network. In (p. 519-567). doi: 10.1007/978-3-030-32644-936
Hu, Q. (2006). Intelligent diagnosis for incipient fault based on lifting wavelet package transform and support vector machines ensemble. Chinese Journal of Mechanical Engineering, 42, 16.
J. Lee, H. Qiu, G. Yu, J. Lin, and Rexnord Technical Services. (2007). Ims, university of Cincinnati. ”bearing data set”, nasa prognostics data repository, nasa ames research center, moffett field, ca. https://www.nasa.gov/content/prognostics-center-of-excellence-data-set-repository/Bearings.
Johnson, W., & Lindenstrauss, J. (1984, 01). Extensions of lipschitz maps into a hilbert space. Contemporary Mathematics, 26, 189-206. doi: 10.1090/conm/026/737400
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv. Retrieved from https://arxiv.org/abs/1412.6980 doi: 10.48550/ARXIV.1412.6980
Kononenko, I., & Kukar, M. (2007). Chapter 7 - data preprocessing. In I. Kononenko & M. Kukar (Eds.), Machine learning and data mining (p. 181-211). Woodhead Publishing. doi: https://doi.org/10.1533/9780857099440.181
LeCun, Y., Bengio, Y., & Hinton, G. (2015, May). Deep learning. Nature, 521(7553), 436–444. Retrieved from http://dx.doi.org/10.1038/nature14539 doi: 10.1038/nature14539
Lee, I., Chen, D., Wu, Y., & Jamerson, C. (1989). Modeling of control loop behavior of magamp post regulators. In Conference proceedings., eleventh international telecommunications energy conference (p. 20.1/1-20.1/8 vol.2). doi: 10.1109/INTLEC.1989.88338
Lei, Y. (2008, 01). Fault diagnosis based on novel hybrid intelligent model. Chinese Journal of Mechanical Engineering - CHIN J MECH ENG, 44. doi: 10.3901/JME.2008.07.112
Liang, X., Zuo, M. J., & Feng, Z. (2018). Dynamic modeling of gearbox faults: A review. Mechanical Systems and Signal Processing, 98, 852-876. doi: https://doi.org/10.1016/j.ymssp.2017.05.024
Liu, Y., Li, K., & Chen, P. (2018, 03). Fault diagnosis for rolling bearings based on synchrosqueezing wavelet transform. Zhongguo Jixie Gongcheng/China Mechanical Engineering, 29, 585-590. doi: 10.3969/j.issn.1004-132X.2018.05.013
M.Benbrahim. (2014). Classification automatique des signaux sismiques. Omniscriptum.
Pham, M.-T., Kim, J.-M., & Kim, C.-H. (2021a). 2d cnn-based multi-output diagnosis for compound bearing faults under variable rotational speeds. Machines, 9(9). doi: 10.3390/machines9090199
Pham, M. T., Kim, J.-M., & Kim, C. H. (2021b). Efficient fault diagnosis of rolling bearings using neural network architecture search and sharing weights. IEEE Access, 9, 98800-98811. doi: 10.1109/ACCESS. 2021.3096036
Renwick, J. T., & Babson, P. E. (1985). Vibration analysis—a proven technique as a predictive maintenance tool. IEEE Transactions on Industry Applications, IA-21(2), 324-332. doi: 10.1109/TIA.1985.349652
Ricci, R., & Pennacchi, P. (2011). Diagnostics of gear faults based on emd and automatic selection of intrinsic mode functions. Mechanical Systems and Signal Processing, 25(3), 821-838. Retrieved from https://www.sciencedirect.com/science/article/pii/S0888327010003201 doi: https://doi.org/10.1016/j.ymssp.2010.10.002
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 60. doi: 10.1186/s40537-019-0197-0
Smith, W. A., & Randall, R. B. (2015). Rolling element bearing diagnostics using the case western reserve university data: A benchmark study. Mechanical Systems and Signal Processing, 64-65, 100-131. Retrieved from https://www.sciencedirect.com/science/article/pii/S0888327015002034 doi: https://doi.org/10.1016/j.ymssp.2015.04.021
Wang, J., Wang, D., Wang, S., Li, W., & Song, K. (2021). Fault diagnosis of bearings based on multi-sensor information fusion and 2d convolutional neural network. IEEE Access, 9, 23717-23725. doi: 10.1109/ACCESS.2021.3056767
Wang, J., Zhuang, J., Duan, L., & Cheng, W. (2016). A multi-scale convolution neural network for featureless fault diagnosis. In 2016 international symposium on flexible automation (isfa) (p. 65-70). doi: 10.1109/ISFA.2016.7790137
Wen, J., Gao, H., Li, S., Zhang, L., He, X., & Liu, W. (2015, 10). Fault diagnosis of ball bearings using synchrosqueezed wavelet transforms and svm. In (p. 1-6). doi: 10.1109/PHM.2015.7380084
Wen, L., Li, X., Gao, L., & Zhang, Y. (2018). A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics, 65(7), 5990-5998. doi: 10.1109/TIE.2017.2774777
Wu, K., Tao, J., Yang, D., Xie, H., & Li, Z. (2022, 06). A rolling bearing fault diagnosis method based on enhanced integrated filter network. Machines, 10, 481. doi: 10.3390/machines10060481
Zan, T.,Wang, H.,Wang, M., Liu, Z., & Gao, X. (2019). Application of multi-dimension input convolutional neural network in fault diagnosis of rolling bearings. Applied Sciences, 9(13). doi: 10.3390/app9132690
Zhang, R., Peng, Z., wu, L., Yao, B., & Guan, Y. (2017, 03). Fault diagnosis from raw sensor data using deep neural networks considering temporal coherence. Sensors, 17, 549. doi: 10.3390/s17030549
Zhang, W., Peng, G., Li, C., Chen, Y., & Zhang, Z. (2017). A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors, 17(2). Retrieved from https://www.mdpi.com/1424-8220/17/2/425 doi: 10.3390/s17020425
Section
Technical Papers