Forecasting of the remaining useful life in conditions of small data sample
- Authors: Zadiran K.S.1, Shcherbakov M.V.1, Sai C.K.1
-
Affiliations:
- Volgograd state technical university
- Issue: No 102 (2023)
- Pages: 99-113
- Section: Control systems diagnosis and reliability
- URL: https://medbiosci.ru/1819-2440/article/view/363794
- DOI: https://doi.org/10.25728/ubs.2023.102.6
- ID: 363794
Cite item
Full Text
Abstract
In the article a method for forecasting the residual life of equipment using deep learning is proposed. The method is applicable in cases with a small amount of information about data failures, where existing classical methods may not provide the required accuracy. The process of maintaining the equipment in working condition is one of the most important processes in the operation of the equipment. At the same time, the maintenance process often suffers from inefficiency. Therefore, forecasting methods were developed, on the basis of which the concept of proactive maintenance process management was built, which allows optimizing the structure and costs of equipment management throughout the life cycle. However, these methods may show insufficient accuracy if there is not enough data to train them, for example, due to the rarity of equipment failures. To solve this problem, a new prediction method based on deep learning is proposed that can improve the prediction accuracy. In this method, the continuous prediction of the remaining service life over the entire interval is replaced by a model for generating signals containing the calculated prediction.
About the authors
Konstantin Sergeevich Zadiran
Volgograd state technical university
Email: konstantin.zadiran@gmail.com
Volgograd
Maxim Vladimirovich Shcherbakov
Volgograd state technical university
Email: maxim.shcherbakov@vstu.ru
Volgograd
Cuong Kvong Sai
Volgograd state technical university
Email: svcuonghvktqs@gmail.com
Volgograd
References
1. ГУНИНА И.А., ШКАРУПЕТА Е.В., РЕШЕТОВ В.В. Прорывное технологическое развитие промышленных комплексов в условиях цифровой трансформации // Ин-новационные кластеры цифровой экономики: теория и практика. – 2018. – С. 535–554. 2. КУПРИЯНОВСКИЙ В.П., НАМИОТ Д.Е., ДРОЖЖИ-НОВ В.И., КУПРИЯНОВСКАЯ Ю.В., ИВАНОВ М.О. Интернет вещей на промышленных предприятиях // International Journal of Open Information Technologies. – 2016. – №12. – С. 156–161. 3. ЛЫСЕНКО С.В., ТЕН Э.В. Об оценке остаточного ре-сурса башенных кранов // Проблемы современной науки и образования. – 2016. – №1. – С. 98–102. 4. САЙ ВАН КВОНГ, ЩЕРБАКОВ М.В. Метод прогнози-рования остаточного ресурса на основе обработки данных многообъектных сложных систем // Прикаспий-ский журнал: управление и высокие технологии. – 2019. – №1(45). – C. 33–44. 5. ШИЛОВА Е.В., ДЬЯКОВ А.Р. О феномене четвертой промышленной революции и его влиянии на экономику и управление // Вестник Прикамского социального инсти-тута. – 2018. – №3(81). – С. 86–95. 6. A Grammar Of Data Manipulation – Dplur. – URL: https://dplyr.tidyverse.org (дата обращения: 03.04.2022). 7. CERNUDA C. On the relevance of preprocessing in predic-tive maintenance for dynamic systems // In: Lughofer E., Sayed-Mouchaweh M. (Eds.). Predictive Maintenance in Dynamic Systems. Cham, Springer. – 2019. – P. 53–93. 8. CHENG J.C., CHEN W., CHEN K., WANG Q. Data-driven predictive maintenance planning framework for MEP com-ponents based on BIM and IoT using machine learning al-gorithms // Automation in Construction. – 2020. – Vol. 112. – P. 1– 21. 9. CHE-SHENG H., JEHN-RUEY J. Remaining useful life esti-mation using long short-term memory deep learning // IEEE Int. Conf. on Applied System Invention (ICASI–2018), Chi-ba, Japan. – 2018. – P. 58–61. 10. CRAN – Packages. – URL: https://cran.r-project.org/web/packages/ (дата обращения: 03.04.2022). 11. Forecast Package – RDocumentation. – URL: https://www.rdocumentation.org/packages/forecast (дата обраще-ния: 03.04.2022). 12. GOEBEL K., SAHA B., SAXENA A., CELAYA J.R., CHRISTOPHERSEN J.P. Prognostics in battery health man-agement // IEEE Instrumentation & Measurement Magazine. – 2008. – Vol. 8. – P. 33–40. 13. HUANG Z.Y., XU Z.G., WANG W.H., SUN Y.X. Remain-ing usefullife prediction for a nonlinear heterogeneous Wie-ner process model withan adaptive drift // IEEE Trans. Rel. – June, 2015. – Vol. 64, No. 2. – P. 687–700. 14. Identify and replace outliers in time series. – URL: https://pkg.robjhyndman.com/forecast/reference/tsoutliers.html (дата обращения: 03.04.2022). 15. LEI Y., LI N., GONTARZ S., LIN J, RADKOWSKI S., DYBALA J. A Model-Based Method for Remaining Useful Life Prediction of Machinery // IEEE Trans. on Reliability. – 2017. – Vol. 65. – P. 1314–1326. 16. LI X., DING Q., SUN J. Remaining useful life estimation in prognostics using deep convolution neural networks // Re-liab. Eng. Syst. Saf. – 2018. – Vol. 172. – P. 1–11. 17. LIU J., WANG W., MA F., YANG Y.B., YANG C.S. A da-ta-model-fusionprognostic framework for dynamic system state forecasting // Eng. Appl.Artif. Intell. – June, 2012. – Vol. 25, No. 4. – P. 814–823. 18. PATIL S., PATIL A., HANDIKHERKAR V., DESAI S., PHALLE V. M., KAZI F. S. Remaining Useful Life (RUL) Prediction of Rolling Element Bearing Using Random Forest and Gradient Boosting Technique // ASME 2018 Interna-tional Mechanical Engineering Congress and Exposition. – 2018. – P. 1–7. 19. RAN Y., ZHOU X., LIN P., WEN Y., DENG R. A Survey of Predictive Maintenance: Systems, Purposes and Approaches // IEEE communications Surveys & Tutorials. – 2019. – P. 1–36. 20. SHCHERBAKOV M.V. A Survey of Forecast Error Measures // World Applied Sciences Journal (WASJ). – 2013. – No. 24. – P. 171–176. 21. XIONGZI C., JINSONG Y., DIYIN T. YINGXUN W. Re-maining useful life prognostic estimation for aircraft subsys-tems or components: A review // 10th IEEE Int. Conf. on Electronic Measurement & Instruments (ICEMI). – 2011. – Vol. 2. – P. 94. 22. YAN M., WANG X., WANG B., CHANG M., MUHAM-MAD I. Bearing remaining useful life prediction using sup-port vector machine and hybrid degradation tracking model // ISA Trans. – 2020. – Vol. 98. – P. 471–482. 23. YU J. Remaining useful life prediction for lithium-ion batter-ies using a quantum particle swarm optimization-based par-ticle filter // Quality Engineering. – 2017. – Vol 29. – P. 536–546. 24. ZHANG Z., SI X., HU C., LEY Y. Degradation data analy-sis and remaining useful life estimation: A review on Wiener-process-based methods // European Journal of Operational Research. – 2018. – Vol. 271(3). – P. 775–796.
Supplementary files
