Development of an SVM model for predictive maintenance of metal-cutting equipment
- Authors: Javadov N.G.1, Amirov A.M.1, Ismayilov V.M.1
-
Affiliations:
- National Aerospace Agency
- Issue: Vol 75, No 2 (2025)
- Pages: 75-81
- Section: Information Technologies
- URL: https://journals.rcsi.science/2079-0279/article/view/317033
- DOI: https://doi.org/10.14357/20790279250209
- EDN: https://elibrary.ru/AMBERY
- ID: 317033
Cite item
Full Text
Abstract
This article is devoted to the development of a machine learning model for optimizing cutting tool maintenance using the support vector machines (SVM). The paper considers the main stages of creating a multiclass classification model from pre-processing of raw signals to selection of hyperparameters. The choice of the algorithm is determined by computational efficiency, as well as the possibility of working with data with nonlinear structure. As a result of testing the model, the average accuracy reached 81%. The obtained results demonstrate that the algorithm based on the method of support vectors can handle the task in conditions of limited computational power.
About the authors
N. G. Javadov
National Aerospace Agency
Email: cavadov-natiq@mail.ru
Professor. Doctor of Technical Sciences Baku, Azerbaijan
A. M. Amirov
National Aerospace Agency
Email: ali.amirov@mail.com
Candidate of Technical Sciences Baku, Azerbaijan
V. M. Ismayilov
National Aerospace Agency
Email: ismailovvugar99@gmail.com
Baku, Azerbaijan
References
- Javadov N.G., Amirov A.M., Ismayilov V.M. 2024. Tehnicheskie aspekty sozdanija sistemy monitoringa metallorezhushhego oborudovanija s primeneniem mashinnogo obuchenija. Vestnik komp'juternyh i informacionnyh tehnologij 21(10):10–16. doi: 10.14489/vkit.2024.10.pp.010-016.
- Montero Jimenez J.J., Schwartz S., Vingerhoeds R., et al. Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics // Journal of Manufacturing Systems. 2020. Vol. 56. P. 539–557. doi: 10.1016/j.jmsy.2020.04.012.
- Fahle S., Prinz C., Kuhlenkötter B. Systematic review on machine learning (ML) methods for manufacturing processes – Identifying artificial intelligence (AI) methods for field application // Procedia CIRP. 2020. Vol. 93. P. 413–418. doi: 10.1016/j.procir.2020.04.109.
- Montero Jimenez J.J., Schwartz S., Vingerhoeds R., Grabot B., Salaün M. Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics // Journal of Manufacturing Systems. 2020. Vol. 56. P. 539–557. doi: 10.1016/j.jmsy.2020.04.012.
- Çınar Z.M., Nuhu A.A., Zeeshan Q., Korhan O., Asmael M., Safaei B. Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0 // Sustainability. 2020. Vol. 12, No. 19. P. 8211. doi: 10.3390/su12198211.
- Krupitzer C., Wagenhals T., Züfle M., Lesch V., Schäfer D., Mozaffarin A., Edinger J., Becker C., Kounev S. A survey on predictive maintenance for Industry 4.0 // arXiv preprint. 2020. arXiv:2002.08224. doi: 10.48550/arXiv.2002.08224. URL: https://doi.org/10.48550/arXiv.2002.08224
- Munaro R., Attanasio A., Del Prete A. Tool wear monitoring with artificial intelligence methods: A review // Journal of Manufacturing and Materials Processing. 2023. Vol. 7, No. 4. P. 129. doi: 10.3390/jmmp7040129.
- James G., Witten D., Hastie T., Tibshirani R. An Introduction to Statistical Learning, With Applications in Python. 2nd ed. New York: Springer, 2023. 597 p.
- Vapnik V.N. The Nature of Statistical Learning Theory. New York: Springer, 2000. 314 p.
- Agogino A, Goebel K. Milling Data Set. 2007. doi:http://ti.arc.nasa.gov/project/prognostic-data-repository.
Supplementary files
