Evaluating the Influence of Time Domain Feature Distributions on Estimating Rolling Bearing Flaking Size with Explainability
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
To enhance the maintainability of rotating machines, such as wind turbines, where the response to bearing damage is both costly and time-consuming, it is essential to predict the progression of flaking, which is a common rolling bearing fault. Conventional rule-based methods estimate the magnitude of flaking by analyzing the time interval of feature vibrations. However, this method requires trial-and-error adjustments by experts, limiting its applicability to a wide range of rotating machines. To overcome this limitation, we developed a deep learning-based estimation model and demonstrated that its performance depends on the distribution of time-domain features in the training data, which are associated with flaking damage. We then analyzed the manner in which these feature distributions impose limitations on the estimation accuracy of the model. Additionally, we incorporated explainability using Grad-CAM to verify that the extracted features were aligned with the physical phenomena of flaking damage, thereby confirming the link between the feature vibrations and estimation results. Our experiments under various training–test split conditions indicate that time-domain shifts of these features affect the model’s performance, providing insight into how feature distributions constrain the estimation of the flaking size.
##plugins.themes.bootstrap3.article.details##
Rolling Bearing, Machine Learning, Explainability, Domain Shift
Chen, J., Huang, R., Zhao, K., Wang, W., Liu, L., & Li, W. (2021). Multiscale convolutional neural network with feature alignment for bearing fault diagnosis. IEEE Trans. Instrum. Meas., 70, 1–10.
Elman, J. L. (1990, March). Finding structure in time. Cogn. Sci., 14(2), 179–211.
Hochreiter, S., & Schmidhuber, J. (1997, November). Long short-term memory. Neural Comput., 9, 1735–1780.
Hu, J., Shen, L., & Sun, G. (2018, June). Squeeze-andexcitation networks. In 2018 ieee/cvf conference on computer vision and pattern recognition (pp. 7132–7141). IEEE.
Ioffe, S., & Szegedy, C. (2015, February). Batch normalization: Accelerating deep network training by reducing internal covariate shift. ICML, abs/1502.03167, 448–456.
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998, November). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
Li, X., Zhang, W., & Ding, Q. (2019, August). Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism. Signal Processing, 161, 136–154.
Liu, R., Lehman, J., Molino, P., Such, F. P., Frank, E., Sergeev, A., & Yosinski, J. (2018, July). An intriguing failing of convolutional neural networks and the CoordConv solution. arXiv [cs.CV].
Lu, H., Pavan Nemani, V., Barzegar, V., Allen, C., Hu, C., Laflamme, S., . . . Zimmerman, A. T. (2023, May). A physics-informed feature weighting method for bearing fault diagnostics. Mech. Syst. Signal Process., 191, 110171.
Maekawa, T., Mizokuchi, H., Taguchi, K., Miyasaka, T., & Shibasaki, K. (2018). Spall length estimation of rolling element bearings by using vibration signal. Proc. Symp. Eval. Diagn.(In Japanese), 2018.17(0), 110.
Neil, D., Pfeiffer, M., & Liu, S.-C. (2016, October). Phased LSTM: Accelerating recurrent network training for long or event-based sequences. arXiv [cs.LG].
Randall, R. B., & Antoni, J. (2011, February). Rolling element bearing diagnostics—a tutorial. Mech. Syst. Signal Process., 25(2), 485–520.
Sawalhi, N., & Randall, R. B. (2011, April). Vibration response of spalled rolling element bearings: Observations, simulations and signal processing techniques to track the spall size. Mech. Syst. Signal Process., 25(3), 846–870.
Selvaraju, R. R., Cogswell, M., Das, A., & others. (n.d.). Grad-cam: Visual explanations from deep networks via gradient-based localization.
Shi, Y., Liu, Y., & Gao, X. (2021). Study of wind turbine fault diagnosis and early warning based on SCADA data. IEEE Access, 9, 124600–124615.
Smith, W. A., Hu, C., Randall, R. B., & Peng, Z. (2015). Vibration-based spall size tracking in rolling element bearings. In Proceedings of the 9th iftomm international conference on rotor dynamics (pp. 587–597). Springer International Publishing.
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024, February). RoFormer: Enhanced transformer with rotary position embedding. Neurocomputing, 568(127063), 127063.
Vaswani, A., Shazeer, N. M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., . . . Polosukhin, I. (2017, June). Attention is all you need. Neural Inf Process Syst, 5998–6008.
Yoshimatsu, O., Taguchi, K., Yoshihiro, S., & Yairi, T. (2023, September). Size estimation of flaking in rolling bearings using deep learning with explainability. PHMAP CONF, 4(1).
Zhang, F., Huang, J., Chu, F., & Cui, L. (2020, December). Mechanism and method for the full-scale quantitative diagnosis of ball bearings with an inner race fault. J. Sound Vib., 488, 115641.
Zhang, W., Peng, G., Li, C., Chen, Y., & Zhang, Z. (2017, February). A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors, 17(2).
Zhou, A. Y., & Farimani, A. B. (2023, December). Fault-Former: Pretraining transformers for adaptable bearing fault classification. IEEE Access, 12, 70719–70728.