تحلیل خرابی‌های کوپلینگ با داده‌های پایش وضعیت با رویکرد یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی صنایع و سیستمها، دانشگاه تربیت مدرس

2 دانشگاه تربیت مدرس، دانشکده مهندسی صنایع و سیستم‌ها،گروه سیستم‌های اقتصادی و اجتماعی

3 دانشکده مهندسی صنایع و سیستم ها، دانشگاه تربیت مدرس، تهران، ایران

چکیده
کوپلینگ‌ها در صنعت کاربرد بسیاری داشته و این تجهیزات با توجه به چرخش مداوم، همیشه در معرض خرابی هستند. ‏تجزیه‌وتحلیل ارتعاش یک تکنیک مناسب برای تحلیل خرابی‌ها و تشخیص حالات خرابی تجهیزات دوار است. هدف این پژوهش تحلیل ‏خرابی‌های رخ‌داده در یک کوپلینگ است که داده‌های آن در حالت عادی و سه حالت نقص با چهار سنسور متصل به کوپلینگ ‏جمع‌آوری‌شده است. بدین منظور دو نوع استخراج ویژگی متفاوت استفاده‌شده و همچنین از هفت الگوریتم یادگیری ماشین و یک ‏الگوریتم یادگیری عمیق برای طبقه‌بندی حالات بهره برده شده است. در این پژوهش به بررسی کارکرد هر کدام از الگوریتم‌های ‏پیاده‌سازی شده و اهمیت ویژگی‌های استخراجی پرداخته و به بررسی نقش سنسورها و بررسی اهمیت آن‌ها برای کاهش تعداد سنسور‌ها ‏پرداخته‌شده است. از نتایج این پژوهش می‌توان به تعیین اهمیت بالای ویژگی‌های حوزه فرکانس در دقت مدل‌های اجراشده و همچنین ‏کارایی بالای دو عدد از سنسور‌ها برای طبقه‌بندی اشاره نمود.‏

کلیدواژه‌ها


عنوان مقاله English

Coupling failure analysis using condition monitoring data with machine learning approach

نویسندگان English

Reza Sadeghi 1
Bakhtiar Ostadi 3
1 Faculty of Industrial and Systems Engineering, Tarbiat Modares University
3 Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran
چکیده English

Couplings are widely used in the industry and this equipment are always subject to defects and failures due to continuous rotation. Vibration analysis is a suitable technique for failure analysis and failure detection of rotating equipment. The purpose of this research is to analyze the failures that occurred in a coupling, whose data was collected in normal state and three failure states with four sensors connected to the coupling. For this purpose, two different types of feature extraction have been used, and seven machine learning algorithms and one deep learning algorithm have been used to classify situations. In this research, the performance of each of the implemented algorithms and the importance of extracted features have been investigated, and the role of sensors and their importance to reduce the number of sensors have been investigated. From the results of this research, we can point out the high importance of the features of the frequency domain in the accuracy of the implemented models, as well as the high efficiency of two sensors for classification.

کلیدواژه‌ها English

Predictive maintenance
Machine learning
failure analysis
rotating equipment
  1. Abdi, H., & Williams, L. J. (2010). Principal component analysis. Wiley interdisciplinary reviews: computational statistics2(4), 433-459.
  2. Akmal, M. (2023). Enhancing Rotary Machine Reliability Through Condition-Based Maintenance Optimization. Pakistan Journal of Scientific Research3(1), 7-13.
  3. Dargie, W. (2009, August). Analysis of time and frequency domain features of accelerometer measurements. In 2009 Proceedings of 18th International Conference on Computer Communications and Networks(pp. 1-6). IEEE.
  4. Jablon, L. S., Avila, S. L., Borba, B., Mourão, G. L., Freitas, F. L., & Penz, C. A. (2021). Diagnosis of rotating machine unbalance using machine learning algorithms on vibration orbital features. Journal of Vibration and Control27(3-4), 468-476.
  5. Junior, R. F. R., dos Santos Areias, I. A., Campos, M. M., Teixeira, C. E., da Silva, L. E. B., & Gomes, G. F. (2022). Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals. Measurement190, 110759.
  6. Kanwal, N., Girdhar, A., Kaur, L., & Bhullar, J. S. (2019, April). Detection of digital image forgery using fast fourier transform and local features. In 2019 international conference on automation, computational and technology management (ICACTM)(pp. 262-267). IEEE.
  7. Karhan, Z., & Ergen, B. (2013, April). Classification of face images using discrete cosine transform. In 2013 21st Signal Processing and Communications Applications Conference (SIU)(pp. 1-4). IEEE.
  8. Kıral, Z., & Karagülle, H. (2006). Vibration analysis of rolling element bearings with various defects under the action of an unbalanced force. Mechanical systems and signal processing20(8), 1967-1991.
  9. Kotsiantis, S. B., Zaharakis, I. D., & Pintelas, P. E. (2006). Machine learning: a review of classification and combining techniques. Artificial Intelligence Review26, 159-190.
  10. Manikandan, S., & Duraivelu, K. (2021). Fault diagnosis of various rotating equipment using machine learning approaches–A review. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering235(2), 629-642.
  11. Nayana, B. R., & Geethanjali, P. (2017). Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal. IEEE Sensors Journal17(17), 5618-5625.
  12. Pintelon, L., Pinjala, S. K., & Vereecke, A. (2006). Evaluating the effectiveness of maintenance strategies. Journal of quality in maintenance engineering12(1), 7-20.
  13. Sanchez, R. V., Lucero, P., Vasquez, R. E., Cerrada, M., Macancela, J. C., & Cabrera, D. (2018). Feature ranking for multi-fault diagnosis of rotating machinery by using random forest and KNN. Journal of Intelligent & Fuzzy Systems34(6), 3463-3473.
  14. Sen, P.C., Hajra, M. and Ghosh, M., 2020. Supervised classification algorithms in machine learning: A survey and review. In Emerging Technology in Modelling and Graphics: Proceedings of IEM Graph 2018(pp. 99-111). Springer Singapore.
  15. Shafiee, M. (2015). Maintenance strategy selection problem: an MCDM overview. Journal of Quality in Maintenance Engineering21(4), 378-402.
  16. Sreejith, B., Verma, A. K., & Srividya, A. (2008, December). Fault diagnosis of rolling element bearing using time-domain features and neural networks. In 2008 IEEE region 10 and the third international conference on industrial and information systems(pp. 1-6). IEEE.
  17. Srinivasan, V., Eswaran, C., & Sriraam, A. N. (2005). Artificial neural network based epileptic detection using time-domain and frequency-domain features. Journal of Medical Systems29, 647-660.
  18. Telford, S., Mazhar, M. I., & Howard, I. (2011, January). Condition based maintenance (CBM) in the oil and gas industry: An overview of methods and techniques. In Proceedings of the 2011 international conference on industrial engineering and operations management, Kuala Lumpur, Malaysia(pp. 22-24).
  19. Umbrajkaar, A. M., Krishnamoorthy, A., & Dhumale, R. B. (2020). Vibration analysis of shaft misalignment using machine learning approach under variable load conditions. Shock and Vibration2020, 1-12.
  20. Vishwakarma, M., Purohit, R., Harshlata, V., & Rajput, P. R. A. M. O. D. (2017). Vibration analysis & condition monitoring for rotating machines: a review. Materials Today: Proceedings4(2), 2659-2664.
  21. Yang, H., Mathew, J., & Ma, L. (2003). Vibration feature extraction techniques for fault diagnosis of rotating machinery: a literature survey. In Asia-pacific vibration conference(No. 42460, pp. 801-807).
  22. Zhang, D., Ding, D., Li, J., & Liu, Q. (2015). Pca based extracting feature using fast fourier transform for facial expression recognition. In Transactions on Engineering Technologies: International MultiConference of Engineers and Computer Scientists 2014(pp. 413-424). Springer Netherlands.