Bearing Fault Diagnosis Using Grad-CAM and Acoustic Emission Signals
Source abstract
Abstract
Bearing failure generates impulses when the rolling elements pass the cracked surface of the bearing. Over the past decade, acoustic emission (AE) techniques have been used to detect bearing failures operated in low-rotating speeds. However, since the high sampling rates of the AE signals make it difficult to design and extract discriminative fault features, deep neural network-based approaches have been proposed in several recent studies. This paper proposes a convolutional neural network (CNN)-based bearing fault diagnosis technique. In this work, the normalized bearing characteristic component (NBCC) is used as the input of CNN, which is an effective form of representing bearing failure symptoms. In addition, importance-weight is extracted using gradient-weighted class activation mapping (Grad-CAM) for visual explanation of CNN. In the experiment result, the proposed approach achieves high classification accuracy with reasonable visualization, which shows that CNN successfully learned the components of bearing characteristic frequency for each type of bearing failure.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Advanced machining processes and optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Korea
Funding
Korea Institute of Energy Technology Evaluation and Planning
References (22)
Show source-provided references
1. Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review10.1109/TEC.2005.847955 ↗
2. Accelerated natural fault diagnosis in slow speed bearings with Acoustic Emission10.1016/j.engfracmech.2009.09.016 ↗
3. Diagnosis of bearing defects under variable speed conditions using energy distribution maps of acoustic emission spectra and convolutional neural networks10.1121/1.5065071 ↗
4. Park, J.J., Loia, V., Yi, G., and Sung, Y. (2018). Bearing Fault Diagnosis Based on Convolutional Neural Networks with Kurtogram Representation of Acoustic Emission Signals. Advances in Computer Science and Ubiquitous Computing, Springer.10.1007/978-981-10-7605-3 ↗
5. Acoustic emission sensor network based fault diagnosis of induction motors using a gabor filter and multiclass support vector machines
6. Sun, H., Wu, C., Liang, X., and Zeng, Q. (2018). Identification of Multiple Faults in Gearbox Based on Multipoint Optional Minimum Entropy Deconvolution Adjusted and Permutation Entropy. Entropy, 20.10.3390/e20110850 ↗
7. Li, Z., Ma, J., Wang, X., and Wu, J. (2019). MVMD-MOMEDA-TEO Model and Its Application in Feature Extraction for Rolling Bearings. Entropy, 21.10.3390/e21040331 ↗
8. Cai, W., and Wang, Z. (2018). Application of an Improved Multipoint Optimal Minimum Entropy Deconvolution Adjusted for Gearbox Composite Fault Diagnosis. Sensors, 18.10.3390/s18092861 ↗
9. Wasmer, K., Saeidi, F., Meylan, B., Le Quang, T., and Shevchik, S. (2018, January 12–14). When AE (Acoustic Emission) meets AI (Artificial Intelligence) II. Proceedings of the EWGAE 2018, Senlis, France.
10. Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network10.1016/j.compind.2019.01.008 ↗
11. Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions10.1016/j.measurement.2019.02.075 ↗
12. Reliable fault diagnosis of bearings with varying rotational speeds using envelope spectrum and convolution neural networks10.1007/s00500-018-3256-0 ↗
13. Bhatia, S.K., Tiwari, S., Mishra, K.K., and Trivedi, M.C. (2019). Fault Diagnosis of Bearings with Variable Rotational Speeds Using Convolutional Neural Networks. Advances in Computer Communication and Computational Sciences, Springer.
14. Bhatia, S.K., Tiwari, S., Mishra, K.K., and Trivedi, M.C. (2019). Fault Diagnosis of Multiple Combined Defects in Bearings Using a Stacked Denoising Autoencoder. Advances in Computer Communication and Computational Sciences, Springer.
15. Tra, V., Kim, J., Khan, S.A., and Kim, J.-M. (2017). Bearing Fault Diagnosis under Variable Speed Using Convolutional Neural Networks and the Stochastic Diagonal Levenberg-Marquardt Algorithm. Sensors, 17.10.3390/s17122834 ↗
16. Phon-Amnuaisuk, S., Ang, S.-P., and Lee, S.-Y. (2017). Speed Invariant Bearing Fault Characterization Using Convolutional Neural Networks. Multi-disciplinary Trends in Artificial Intelligence, Springer International Publishing.
17. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization10.1007/s11263-019-01228-7 ↗
18. Bearing Fault Diagnosis Method Based on Hilbert Envelope Demodulation Analysis10.1088/1757-899X/436/1/012009 ↗
19. Time-Varying and Multiresolution Envelope Analysis and Discriminative Feature Analysis for Bearing Fault Diagnosis10.1109/TIE.2015.2460242 ↗
20. Rolling element bearing diagnostics—A tutorial10.1016/j.ymssp.2010.07.017 ↗
21. Sainath, T.N., Mohamed, A., Kingsbury, B., and Ramabhadran, B. (2013, January 26–31). Deep convolutional neural networks for LVCSR. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.10.1109/ICASSP.2013.6639347 ↗
22. Zhang, Z., and Sabuncu, M.R. (, January 3–8). Generalized cross entropy loss for training deep neural networks with noisy labels. Proceedings of the the 32nd International Conference on Neural Information Processing Systems, Montréal, QC, Canada.