A Multidisciplinary Framework for Vibration-Based Gear Fault Diagnosis Using Experiments, Modeling, and Machine Learning

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

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

Published Nov 5, 2024
Lior Bachar Jacob Bortman

Abstract

Vibration-based gear diagnosis is crucial for ensuring the reliability of rotating machinery, making the monitoring of gear health essential for preventing costly downtime and optimizing performance. This study proposes a multidisciplinary framework to enhance gear diagnosis, that aligns with the new era of digital twins by integrating experiments, dynamic modeling, physical preprocessing, and machine learning. Within this framework, we focus on three core procedures: domain adaptation to reduce discrepancies between measured data and synthetic data generated by dynamic models; physical preprocessing, grounded in in-depth investigations dictating signal processing and feature engineering techniques; and learning algorithms, encompassing the process of training AI-based models. We demonstrate this framework through a comprehensive case study of localized tooth fault diagnosis, using controlled-degradation tests and realistic simulations. First, we detect faults using unsupervised learning algorithms; then, we use zero-shot-learning for classifying between localized and distributed faults; finally, we adopt a one-shot-learning strategy for severity estimation. Above all, this hybrid framework bridges the gaps between physical-based and AI-based approaches by combining physical knowledge and advanced algorithmics with machine learning. This contributes to the PHM field by offering valuable insights into integrating different aspects of research, thereby enhancing performance in gear diagnosis tasks.

How to Cite

Bachar, L., & Bortman, J. (2024). A Multidisciplinary Framework for Vibration-Based Gear Fault Diagnosis Using Experiments, Modeling, and Machine Learning. Annual Conference of the PHM Society, 16(1). https://doi.org/10.36001/phmconf.2024.v16i1.4162
Abstract 94 | PDF Downloads 92

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

Keywords

gear fault diagnosis, anomaly detection, domain adaptation, fault classification, fault severity estimation, dynamic modeling

References
Bachar, L., Dadon, I., Klein, R., & Bortman, J. (2021). The effects of the operating conditions and tooth fault on gear vibration signature. Mechanical Systems and Signal Processing, 154, 107508. https://doi.org/10.1016/J.YMSSP.2020.107508 Bachar, L., Klein, R., Tur, M., &

Bortman, J. (2022). Fault diagnosis of gear transmissions via optic Fiber Bragg Grating strain sensors. Mechanical Systems and Signal Processing, 169. https://doi.org/10.1016/j.ymssp.2021.108629

Bachar, L., Matania, O., Cohen, R., Klein, R., Lipsett, M. G., & Bortman, J. (2023). A novel hybrid physical AIbased strategy for fault severity estimation in spur gears with zero-shot learning. Mechanical Systems and Signal Processing, 204. https://doi.org/10.1016/j.ymssp.2023.110748

Cerrada, M., Sánchez, R., Li, C., … F. P.-… S. and S., & 2018, undefined. (2018). A review on data-driven fault severity assessment in rolling bearings. Elsevier. https://www.sciencedirect.com/science/article/pii/S08 88327017303242?casa_token=MeMxmyHKbHwAA AAA:TbKPBWg7SxdDjxdbOkhQ2Hv5l_cdwAlw7Zl OvCRBqv6wXH6JNVwfiY__iqGXRTtY5KvuQDQwz0

Cox, D. R. (1972). Regression Models and Life-Tables. Journal of the Royal Statistical Society Series B: Statistical Methodology, 34(2), 187–202. https://doi.org/10.1111/J.2517-6161.1972.TB00899.X

Dadon, I., Koren, N., Klein, R., & Bortman, J. (2018). A realistic dynamic model for gear fault diagnosis. Engineering Failure Analysis, 84. https://doi.org/10.1016/j.engfailanal.2017.10.012 Dadon, I., Koren, N., Klein, R., &

Bortman, J. (2019). A step toward fault type and severity characterization in spur gears. Journal of Mechanical Design, 141(8). https://doi.org/10.1115/1.4043367

DENG, W., NGUYEN, K. T. P., MEDJAHER, K., GOGU, C., & MORIO, J. (2023). Physics-informed machine learning in prognostics and health management: State of the art and challenges. Applied Mathematical Modelling, 124, 325–352. https://doi.org/10.1016/J.APM.2023.07.011

Eugene E. Shipley. (1967). GEAR FAILURES. Penton Publishing Co. https://www.xtek.com/wpcontent/uploads/2018/05/xtek-gear-failures.pdf Feng, K., Ji, J. C., Ni, Q., & Beer, M. (2023). A review of vibration-based gear wear monitoring and prediction techniques. In Mechanical Systems and Signal Processing (Vol. 182). https://doi.org/10.1016/j.ymssp.2022.109605

Kumar, A., Gandhi, C. P., Zhou, Y., Kumar, R., & Xiang, J. (2020). Latest developments in gear defect diagnosis and prognosis: A review. In Measurement: Journal of the International Measurement Confederation (Vol. 158). https://doi.org/10.1016/j.measurement.2020.107735

Kundu, P., Darpe, A. K., & Kulkarni, M. S. (2021). A review on diagnostic and prognostic approaches for gears. Structural Health Monitoring, 20(5), 2853–2893. https://doi.org/10.1177/1475921720972926/ASSET/I MAGES/LARGE/10.1177_1475921720972926- FIG7.JPEG

Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. In Mechanical Systems and Signal Processing (Vol. 138). https://doi.org/10.1016/j.ymssp.2019.106587

Liang, X., Zhang, M., Feng, G., Wang, D., Xu, Y., & Gu, F. (2023). Few-Shot Learning Approaches for Fault Diagnosis Using Vibration Data: A Comprehensive Review. Sustainability, 15(20), 14975. https://doi.org/10.3390/su152014975

Liang, X., Zuo, M. J., & Feng, Z. (2018). Dynamic modeling of gearbox faults: A review. Mechanical Systems and Signal Processing, 98, 852–876. https://doi.org/10.1016/J.YMSSP.2017.05.024

Liu, F., Ting, K., international, Z. Z.-2008 eighth ieee, & 2008, undefined. (2008). Isolation forest. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/4781136 /?casa_token=cAMoWKo1ZnkAAAAA:3lFnB_- my6ecFZ3RA8fSioWjkE2kqQrdHzsZueHF9CJlvHbAGXYl8L132L0k279b5Z7xrTfw6Wo

Mohammed, O. D., & Rantatalo, M. (2020). Gear fault models and dynamics-based modelling for gear fault detection – A review. Engineering Failure Analysis, 117, 104798. https://doi.org/10.1016/J.ENGFAILANAL.2020.1047 98

Oppenheim, A., Schafer, R., & Buck, J. (1999). Discrete-time signal processing. https://dl.acm.org/doi/abs/10.5555/294797

Orozco, B. P., & Roberts, S. J. (2020). Zero-shot and fewshot time series forecasting with ordinal regression recurrent neural networks. ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 503–508.

Pourpanah, F., Abdar, M., Luo, Y., … X. Z.-I. transactions on, & 2022, undefined. (2022). A review of generalized zero-shot learning methods. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/9832795 /

Randall, R. B. (1982). A New Method of Modeling Gear Faults. Journal of Mechanical Design, 104(2), 259– 267. https://doi.org/10.1115/1.3256334

Wang, D., Tsui, K. L., & Miao, Q. (2017). Prognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators. IEEE Access, 6, 665–676. https://doi.org/10.1109/ACCESS.2017.2774261

Wang, H., Li, Q., Liu, Y., Machines, S. Y.-, & 2022, undefined. (2022). Anomaly data detection of rolling element bearings vibration signal based on parameter optimization isolation forest. Mdpi.Com. https://www.mdpi.com/2075-1702/10/6/459

Wang, Y., Yao, Q., Kwok, J., (csur), L. N.-A. computing surveys, & 2020, undefined. (2020). Generalizing from a few examples: A survey on few-shot learning. Dl.Acm.Org, 53(3). https://doi.org/10.1145/3386252

Yuan, D., Han, Y., Zhu, Y., -, al, Zhang, H., Tang, Q., Xu, D., Liu, S., Ye, Z., Yi, L., Wang, H., Yang, S., Liu, Y., & Li, Q. (2023). A novel abnormal data detection method based on dynamic adaptive local outlier factor for the vibration signals of rotating parts. Iopscience.Iop.Org, 18(11), 11. https://doi.org/10.1088/1361-6501/accbda

Zhang Examiner, Y., Bi, X., & Kedziora, D. (2024). Development of vibration signal preprocessing and outlier application. https://lutpub.lut.fi/handle/10024/167465 Zhang, T., Chen, J., Li, F., Zhang, K., Lv, H., He, S., transactions, E. X.-I., & 2022, undefined. (2022). Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions. Elsevier.
Section
Technical Research Papers

Most read articles by the same author(s)