ASSESSMENT OF THE LUBRICATION CONDITION OF ROLLING BEARINGS USING CLASSIFICATION ALGORITHMS
Abstract
The purpose of this work is to solve the problem of unscheduled failures of rolling bearings installed
on industrial equipment as a result of their improper maintenance during operation. It is known that up to
50% of all unscheduled downtime of industrial equipment occurs due to bearing failure. In this case, the
main reason for bearing failures is violations of the lubrication regime of the rolling elements: excessive
and insufficient quantities of lubricants. These reasons account for up to 36% of the total number of bearing
failures. During equipment operation, it is very difficult to identify and prevent all problems with bearing
lubrication, due to the wide variety of factors influencing their occurrence. Therefore, an urgent task
for research is the development of an automated recommendation system for managing the maintenance of
industrial equipment, with control of the lubrication of bearing units. The paper discusses a method for
classifying the states of bearings depending on their diagnostic parameters: indicators of vibration velocity,
vibration acceleration and temperature. For this purpose, classical machine learning algorithms are
used: KNN, RandomForestClassifier and SVM models. For each model, hyperparameters are determined
to achieve maximum results during training. In the process of conducting the study, an analysis of the
influence of each of the diagnostic parameters - signs on the performance of the classification model was
carried out. Understanding which indicator of bearing performance will be the most important will allow
you to choose equipment condition monitoring devices at a manufacturing enterprise consciously, to solve
specific production problems. The developed algorithm allows us to qualitatively, with 98% accuracy, assess the lubrication condition of rolling bearings and issue recommendations for timely maintenance of
equipment. The classifier model is planned to be used as part of a complex for monitoring the technical
condition of equipment, expanding diagnostic capabilities: in addition to information about the probability
of equipment failure and predicted service life, the diagnostic complex, combined with the proposed
model, will allow influencing the mileage of bearings by improving the quality of their lubrication.
References
biznesa [Combating downtime as a way to increase the economic efficiency of business], Ekonomika i
zhizn' [Economics and Life], 2021, No. 33. Available at: https://www.eg-online.ru/article/440363 (data
obrashcheniya: 16.04.2024).
2. Shets S.P., Sakalo V.I. Vliyanie smazochnogo materiala na protsessy, protekayushchie v
podshipnikakh kacheniya [The influence of lubricant on the processes occurring in rolling bearings],
Transportnoe mashinostroenie [Transport engineering], 2016, No. 2, pp. 31-35.
3. Zhang X., Glovnea R., Morales-Espejel G.E., Félix-Quiñonez A. The Effect of Working Parameters
upon Elastohydrodynamic Film Thickness Under Periodic Load Variation, Tribology Letters, 2020,
Vol. 68, No. 2, pp. 1-10.
4. Zhang Sh., Jacobs G., Vafaei S. [et al.]. CFD investigation of starvation behaviors in a grease lubricated
EHL rolling contact, Forschung im Ingenieurwesen, 2023, Vol. 87, No. 1, pp. 353-362.
5. Wandel S., Bader N., Glodowski Ja. [et al.]. Starvation and Re-lubrication in Oscillating Bearings:
Influence of Grease Parameters, Tribology Letters, 2022, Vol. 70, No. 4, pp. 1-14.
6. Drynochkin A.V., Alenina E.E., Trshkin A.G. Analiz sostoyaniya rossiyskikh predpriyatiy
podshipnikovoy podotrasli i smezhnykh otrasley promyshlennosti [Analysis of the state of Russian enterprises
in the bearing sub-industry and related industries], Izvestiya MGTU «MAMI» [News of
MSTU "MAMI"], 2012, No. 2 (14), pp. 8-13.
7. Babaev A.M., Shemyakina M.A., Lyashov M.V. Obzor klassicheskikh metodov mashinnogo
obucheniya v kontekste resheniya zadach klassifikatsii [Review of classical machine learning methods
in the context of solving classification problems], Forum molodykh uchenykh [Forum of Young Scientists],
2018, No. 11 (27), pp. 137-142.
8. Kumar Gupta K. Muzakkir S.M. A Model for Prediction of Outer Race Defects of Rolling Contact
Bearing based on Vibration Data Using Machine Learning Algorithms, Tribology in Industry, 2023,
Vol. 45, No. 4, pp. 676-685.
9. Kamiel B.P., Anjarico F., Sudarisman S. Deteksi cacat bantalan gelinding berbasis Algoritma decision
trees Dan parameter Statistik, Jurnal Rekayasa Mesin, 2023, Vol. 14, No. 3, pp. 835-844.
10. Vishwendra M. A., Salunkhe P.S., Patil Sh.V. [et al.]. A Novel Method to Classify Rolling Element
Bearing Faults Using K-Nearest Neighbor Machine Learning Algorithm, ASCE-ASME Journal of Risk
and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, 2022, Vol. 8, No. 3.
11. Ul'yanov N.V., Akhmedova Sh.A. Vvedenie v analiz dannykh [Introduction to data analysis],
Aktual'nye problemy aviatsii i kosmonavtiki [Current problems of aviation and astronautics], 2022,
No. 2, pp. 357-359.
12. Yeray Mezquita, Ricardo S. Alonso, Roberto Casado-Vara, Javier Prieto & Juan Manuel Corchado.
A Review of k-NN Algorithm Based on Classical and Quantum Machine Learning, Distributed Computing
and Artificial Intelligence, Special Sessions, 17th International Conference, 2020, pp. 189-198.
13. Stryukov R.K, Shashkin A.I. O modernizatsii metoda blizhayshikh sosedey [On the modernization of
the nearest neighbors method], Vestnik VGU, seriya: sistemnyy analiz i informatsionnye tekhnologii
[Vestnik VSU, series: system analysis and information technologies], 2015, No. 1, pp. 114-120.
14. Annaeva M., Atanapesova A. Odnofaktornyy dispersionnyy analiz: metody i primenenie v statistike
[One-factor analysis of variance: methods and application in statistics], Vsemirnyy uchenyy [World
Scientist], 2023, No. 9 (1), pp. 267-271.
15. Le Minh Nhut, Le Ha Dong Quan. Study on Chiller Fault Detection and Diagnosis Method Based on
KNN Algorithm and ANOVA, International Journal of Mechanical Engineering and Robotics Research,
2023, pp. 223-230.
16. Borisov P.D., Kosolapov Yu.V. Sposob otsenki pokhozhesti programm metodami mashinnogo
obucheniya [A method for assessing the similarity of programs using machine learning methods],
Tr. Instituta sistemnogo programmirovaniya RAN [Proceedings of the Institute of System Programming
of the Russian Academy of Sciences], 2022, № 5 (34), pp. 63-75.
17. Cuentas S., Peñabaena-Niebles R., Garcia E. Support vector machine in statistical process monitoring:
a methodological and analytical review, The International Journal of Advanced Manufacturing Technology,
2017, Vol. 91, No. 1, pp. 485-500.
18. Nemat Saberi A., Belahcen A., Sobra Ja., Vaimann T. LightGBM-Based Fault Diagnosis of Rotating
Machinery Under Changing Working Conditions Using Modified Recursive Feature Elimination,
IEEE Access, 2022, Vol. 10, pp. 81910-81925.
19. Escanilla N.S., Hellerstein L., Kleiman R., Kuang Z., Shull JD, Page D. Recursive Feature Elimination
by Sensitivity Testing, 17th IEEE International Conference on Machine Learning and Applications,
2018, pp. 40-47.
20. Pyrko S.A., Mitioglo A.M., Ishmet'ev E.N. Avtonomnye izmeritel'nye moduli dlya sistem diagnostiki
elektrodvigateley [Autonomous measuring modules for electric motor diagnostic systems], Vestnik
Magnitogorskogo gosudarstvennogo tekhnicheskogo universiteta im. G.I. Nosova [Bulletin of Magnitogorsk
State Technical University named after. G.I. Nosova], 2020, Vol. 18, No. 1, pp. 80-89.
