عیب‌یابی هوشمند خرابی یاتاقان غلتشی در شرایط کاری متغیر با شبکه‌ عصبی پیچشی برمبنای سیگنال‌های حوزه‌ زمان و فرکانس

نوع مقاله : مقاله پژوهشی

نویسندگان

آزمایشگاه پایش وضعیت، دانشکده مهندسی مکانیک، دانشگاه صنعتی شریف، تهران، ایران

10.24200/j40.2024.63396.1697

چکیده

تشخیص هوشمند عیوب‌ یاتاقان غلتشی‌ امری بسیار مهم در زمینه‌ پایش وضعیت تجهیزات دوار است. تشخیص زودهنگام عیب‌ها جهت نگهداری و برنامه‌ریزی در واحدهای صنعتی ارزش اقتصادی بسیاری دارد. استفاده از الگوریتم‌های سنتی تشخیص هوشمند، متشکل از دو بخش استخراج ویژگی و دسته‌بندی، زمان‌بر و نیازمند تجربه‌ کارشناسان این حوزه برای استخراج مشخصه‌های مناسب هستند. شبکه‌ عصبی پیچشی در مقایسه با روش‌های سنتی، می‌تواند با دقت بالا، حجم وسیعی از اطلاعات را پردازش و ویژگی‌ها را به‌طور خودکار از سیگنال ارتعاشی استخراج کند. به همین سبب در این پژوهش سعی می‌شود با استفاده از این روش، علاوه بر تعیین سلامت یا خرابی یاتاقان غلتشی، نوع عیوب در صورت تشخیص خرابی شناسایی گردد. در این راستا از یک شبکه‌ عصبی پیچشی ساده و کم عمق برای بررسی سه عیب متداول یاتاقان غلتشی استفاده می‌شود. به‌منظور یافتن بهترین دقت و کارایی شبکه از ورودی‌های مختلف از جمله سیگنال زمانی، طیف فرکانسی و انولوپ سیگنال استفاده و نتایج آنها با یکدیگر مقایسه می‌گردد. برای پیاده‌ سازی و ارزیابی الگوریتم‌ها، یک ستاپ آزمایشگاهی طراحی و ساخته شده است و با ایجاد خرابی‌های مصنوعی روی یاتاقان‌ها، تست‌های آزمایشگاهی در چهار وضعیت سالم، خرابی رینگ داخلی، خرابی رینگ خارجی و خرابی ساچمه در 36 شرایط کاری مختلف (9 سرعت دورانی متفاوت و در هر سرعت با 4 حالت بارگذاری) انجام گردیده است. نتایج حاصله نشان می‌دهد که دقت و کارایی مدل در تشخیص وجود و نوع عیب یاتاقان غلتشی در حالتی که ورودی آن طیف فرکانسی است، بیشتر از دو ورودی دیگر و برابر 95 درصد می‌باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Intelligent Fault Detection of Rolling Element Bearing under Variable Operating Conditions by Convolutional Neural Network using Time and Frequency Domain Signals

نویسندگان [English]

  • A. Farahani
  • A. Davoodabadi
  • S. Mohammadi
  • M. Behzad
Condition Monitoring Lab, Department of Mechanical Engineering, Sharif University of Technology, Tehran, Iran
چکیده [English]

Intelligent detection of rolling element bearing faults is a critical aspect of rotating equipment condition monitoring. Early detection of faults holds significant economic value for industrial units in terms of maintenance and planning. Traditional intelligent fault detection algorithms, which rely on a combination of feature extraction and signal classification, are time-consuming and require a high level of expertise. In comparison to traditional methods, Convolutional Neural Networks (CNNs) can process a large volume of data with high accuracy and automatically extract features from vibration signals. Therefore, in this research, an attempt has been made to use a simple and shallow CNN to not only determine the health state of rolling element bearings but also identify the defective element. For this purpose, a CNN model has been employed to investigate three common faults in rolling element bearings. In order to achieve the best performance, various inputs, including time waveforms, spectra, and envelopes, have been utilized. To implement and validate the algorithms, a laboratory setup was designed and constructed. After creating artificial faults on the bearings, experiments were conducted under 36 different operating conditions, comprising 9 different speeds, each at 4 different loads, encompassing four healthy states, including healthy, inner race fault, outer race fault, and rolling element fault. The obtained results have illustrated that the fault detector model with the frequency spectrum input is more accurate, with an accuracy of 95% than the models receiving the other two inputs.

کلیدواژه‌ها [English]

  • Condition Monitoring
  • Intelligent Fault Diagnosis
  • Convolutional Neural Network
  • Rolling Element Bearing
  • Variable Operating Conditions
  • Vibration Analysis
1. Wen, L., Gao, L. and Li, X., 2017. A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Transactions on systems, man, and cybernetics: systems, 49(1), pp.136-144. DOI: 10.1109/TSMC.2017.2754287 2. Abdel-Hamid, O., Mohamed, A.R., Jiang, H. and Penn, G., 2012, March. Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In 2012 IEEE international conference on Acoustics, speech and signal processing (ICASSP) (pp. 4277-4280). IEEE. DOI: 10.1109/ICASSP.2012.6288864 3. Kim, Y., 2014. Convolutional neural networks for sentence classification proceedings of the 2014 conference on empirical methods in natural language processing, emnlp 2014, october 25-29, 2014, doha, qatar, a meeting of sigdat, a special interest group of the acl. Association for Computational Linguistics, Doha, Qatar. DOI: 10.3115/v1/D14-1181 4. Song, X., Cong, Y., Song, Y., Chen, Y. and Liang, P., 2022. A bearing fault diagnosis model based on CNN with wide convolution kernels. Journal of Ambient Intelligence and Humanized Computing, 13(8), pp.4041-4056. https://doi.org/10.1177/1077546314524260 5. Chen, X., Zhang, B. and Gao, D., 2021. Bearing fault diagnosis base on multi-scale CNN and LSTM model. Journal of Intelligent Manufacturing, 32(4), pp.971-987. https://doi.org/10.1007/s10845-020-01600-2 6. .Jia, F., Lei, Y., Lin, J., Zhou, X. and Lu, N., 2016. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical systems and signal processing, 72, pp.303-315. https://doi.org/10.1016/j.ymssp.2015.10.025 7. Xu, G., Liu, M., Jiang, Z., Söffker, D. and Shen, W., 2019. Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning. Sensors, 19(5), p.1088. https://doi.org/10.3390/s19051088 8. Eren, L., 2017. Bearing fault detection by one‐dimensional convolutional neural networks. Mathematical Problems in Engineering, 2017(1), p.8617315. https://doi.org/10.1155/2017/8617315 9. Chen, J., Jiang, J., Guo, X. and Tan, L., 2021. An Efficient CNN with Tunable Input-Size for Bearing Fault Diagnosis. Int. J. Comput. Intell. Syst., 14(1), pp.625-634. https://doi.org/10.2991/ijcis.d.210113.001 10. Peng, D., Wang, H., Liu, Z., Zhang, W., Zuo, M.J. and Chen, J., 2020. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition. IEEE Transactions on Industrial Informatics, 16(7), pp.4949-4960. DOI: 10.1109/TII.2020.2967557 11. Zhu, X., Luo, X., Zhao, J., Hou, D., Han, Z. and Wang, Y., 2020. Research on deep feature learning and condition recognition method for bearing vibration. Applied Acoustics, 168, p.107435. https://doi.org/10.1016/j.apacoust.2020.107435 12. Peng, D., Wang, H., Desmet, W. and Gryllias, K., 2023. RMA-CNN: A residual mixed-domain attention CNN for bearings fault diagnosis and its time-frequency domain interpretability. Journal of Dynamics, Monitoring and Diagnostics, 2(2), pp.115-132. https://doi.org/10.37965/jdmd.2023.156 13. Wang, B., Feng, G., Huo, D. and Kang, Y., 2022. A bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network. Processes, 10(7), p.1426. https://doi.org/10.3390/pr10071426 14. Pham, M.T., Kim, J.M. and Kim, C.H., 2020. Accurate bearing fault diagnosis under variable shaft speed using convolutional neural networks and vibration spectrogram. Applied Sciences, 10(18), p.6385. https://doi.org/10.3390/app10186385 15. Zhang, W., Peng, G. and Li, C., 2017. Rolling element bearings fault intelligent diagnosis based on convolutional neural networks using raw sensing signal. In Advances in Intelligent Information Hiding and Multimedia Signal Processing: Proceeding of the Twelfth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Nov., 21-23, 2016, Kaohsiung, Taiwan, Volume 2 (pp. 77-84). Springer International Publishing. https://doi.org/10.1007/978-3-319-50212-0_10 16. Hasan, M.J., Islam, M.M. and Kim, J.M., 2021. Bearing fault diagnosis using multidomain fusion-based vibration imaging and multitask learning. Sensors, 22(1), p.56. https://doi.org/10.3390/s22010056 17. Qin, Y. and Shi, X., 2022. Fault diagnosis method for rolling bearings based on two-channel CNN under unbalanced datasets. Applied Sciences, 12(17), p.8474. https://doi.org/10.3390/app12178474 18. Xin, Y., Li, S., Wang, J., An, Z. and Zhang, W., 2020. Intelligent fault diagnosis method for rotating machinery based on vibration signal analysis and hybrid multi‐object deep CNN. IET Science, Measurement & Technology, 14(4), pp.407-415. https://doi.org/10.1049/iet-smt.2018.5672 19. Yuan, Z., Zhang, L., Duan, L. and Li, T., 2018, October. Intelligent fault diagnosis of rolling element bearings based on HHT and CNN. In 2018 Prognostics and System Health Management Conference (PHM-Chongqing) (pp. 292-296). IEEE. DOI: 10.1109/PHM-Chongqing.2018.00056 20. Verstraete, D., Ferrada, A., Droguett, E.L., Meruane, V. and Modarres, M., 2017. Deep learning enabled fault diagnosis using time‐frequency image analysis of rolling element bearings. Shock and Vibration, 2017(1), p.5067651. https://doi.org/10.1155/2017/5067651 21. Pandhare, V., Singh, J. and Lee, J., 2019, May. Convolutional neural network based rolling-element bearing fault diagnosis for naturally occurring and progressing defects using time-frequency domain features. In 2019 Prognostics and System Health Management Conference (PHM-Paris) (pp. 320-326). IEEE. DOI: 10.1109/PHM-Paris.2019.00061 22. Bai, R., Meng, Z., Xu, Q. and Fan, F., 2023. Fractional Fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions. Reliability Engineering & System Safety, 232, p.109076. https://doi.org/10.1016/j.ress.2022.109076 23. Zhang, X., Chen, G., Hao, T. and He, Z., 2020. Rolling bearing fault convolutional neural network diagnosis method based on casing signal. Journal of Mechanical Science and Technology, 34, pp.2307-2316. https://doi.org/10.1007/s12206-020-0506-8 24. Youcef Khodja, A., Guersi, N., Saadi, M.N. and Boutasseta, N., 2020. Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks. The International Journal of Advanced Manufacturing Technology, 106, pp.1737-1751. https://doi.org/10.1007/s00170-019-04726-7 25. Zhu, X., Zhao, J., Hou, D. and Han, Z., 2019. An SDP Characteristic Information Fusion‐Based CNN Vibration Fault Diagnosis Method. Shock and Vibration, 2019(1), p.3926963. https://doi.org/10.1155/2019/3926963 26. Kumar, A., Vashishtha, G., Gandhi, C.P., Tang, H. and Xiang, J., 2021. Tacho-less sparse CNN to detect defects in rotor-bearing systems at varying speed. Engineering applications of artificial intelligence, 104, p.104401. https://doi.org/10.1016/j.engappai.2021.104401 27. LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), pp.2278-2324. DOI: 10.1109/5.726791 28. Singh, J., Azamfar, M., Li, F. and Lee, J., 2020. A systematic review of machine learning algorithms for prognostics and health management of rolling element bearings: fundamentals, concepts and applications. Measurement Science and Technology, 32(1), p.012001. DOI 10.1088/1361-6501/ab8df9 29. McFadden, P.D. and Smith, J.D., 1984. Vibration monitoring of rolling element bearings by the high-frequency resonance technique—a review. Tribology international, 17(1), pp.3-10. https://doi.org/10.1016/0301-679X(84)90076-8 30. SKF Bearing Select, in, pp. https://skfbearingselect.com/#/size-lubrication/single-bearing. 31. SDT, Vigilant, in, pp. https://sdtultrasound.com/products/permanent-monitoring/vigilant/.