DOI QR코드

DOI QR Code

잔여 유효 수명 예측 모형과 최소 수리 블록 교체 모형에 기반한 비용 최적 예방 정비 방법

Cost-optimal Preventive Maintenance based on Remaining Useful Life Prediction and Minimum-repair Block Replacement Models

  • 주영석 (한양대학교 기술경영전문대학원) ;
  • 신승준 (한양대학교 산업융합학부)
  • Choo, Young-Suk (Graduate School of Technology and Innovation Management, Hanyang University) ;
  • Shin, Seung-Jun (School of Interdisciplinary Industrial Studies, Hanyang University)
  • 투고 : 2022.06.14
  • 심사 : 2022.08.24
  • 발행 : 2022.09.30

초록

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

키워드

과제정보

This research was supported by the Ministry of SMEs and Startups, Republic of Korea, under 'Continuous Process Manufacturing Standardization of Shared Data between Facilities/Factories/Businesses in Characteristic Industries' in 'Smart Manufacturing Innovation R&D Program' (RS-2022-00140694).

참고문헌

  1. Aydemir, G. and Acar, B., Anomaly monitoring improves remaining useful life estimation of industrial machinery, Journal of Manufacturing Systems, 2020, Vol. 56, pp. 463-469. https://doi.org/10.1016/j.jmsy.2020.06.014
  2. Basri, E.I., Abdul Razak, I.H., Ab-Samat, H., and Kamaruddin, S., Preventive maintenance (PM) planning: a review, Journal of Quality in Maintenance Engineering, 2017, Vol. 23, No. 2, pp. 114-143. https://doi.org/10.1108/JQME-04-2016-0014
  3. Biggio, L. and Kastanis, I., Prognostics and health management of industrial assets: Current progress and road ahead, Frontiers in Artificial Intelligence, 2020, Vol. 3, 578613. https://doi.org/10.3389/frai.2020.578613
  4. Cailian, L. and Chun, Z., Life prediction of battery based on random forest optimized by genetic algorithm, IEEE International Conference on Prognostics and Health Management (ICPHM), 2020, 19950220.
  5. Chen, T. and Guestrin, C., XGBoost: A scalable tree boosting system, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794.
  6. Chen, X., Jin, G., Qiu, S., Lu, M., and Yu, D., Direct remaining useful life estimation based on random forest regression, Global Reliability and Prognostics and Health Management (PHM-Shanghai), 2020, 20297708.
  7. Dong, W., Liu, s., Cao, Y., and Bae S.J., Time-based replacement policies for a fault tolerant system subject to degradation and two types of shocks, Quality and Reliability Engineering International, 2020, Vol. 36, No. 7, pp. 2338-2350. https://doi.org/10.1002/qre.2700
  8. Dong, X., Yu, Z., Cao, W., Shi, Y., and Ma, Q., A survey on emsemble learing, Frontiers of Computer Science, 2020, Vol. 14, No. 2, pp. 241-258. https://doi.org/10.1007/s11704-019-8208-z
  9. Han, Y.C. and Kim, J.Y., Developing a XGBoost trading system based on N-period volatility labeling in the stock market, Journal of the Korean Data & Information Science Society, 2021, Vol. 32, No. 5, pp. 1049-1070. https://doi.org/10.7465/jkdi.2021.32.5.1049
  10. Han, Y.J. and Joe, I.W., Prediction of Ad Clicks Using Early Stop Based on XGBoost, The Journal of Korean Institute of Communications and Information Sciences, 2021, Vol. 46, No. 6, pp. 993-1000. https://doi.org/10.7840/kics.2021.46.6.993
  11. Kim, R., Kim., K.M., and Ahn, J..H., Comparison between random forest and recurrent neural network for photovoltaic power forecasting, Journal of Korean Society of Environmental Engineers, 2021, Vol. 45, No. 3, pp. 347-355.
  12. Lee, Y.D., Lim, M.K., and Choi, D.G., Short-term load forecasting for an individual building using shape-based clustering and random forest, Journal of the Korean Operations Research and Management Science Society, 2020, Vol. 37, No.4, pp. 21-31.
  13. Lei, Y., Li, N., Guo, L., Li N., Yan, T., and Lin, J., Machinery health prognostics: A systematic review from data acquisition to RUL prediction, Mechanical Systems and Signal Processing, 2018, Vol. 104, pp. 799-834. https://doi.org/10.1016/j.ymssp.2017.11.016
  14. Li, F., Zhang, L., Chen, B., Gao, D., Cheng, Y., Zhang, X., Yang, Y., Gao, K., Huang, Z., and Peng, J., A Light Gradient Boosting Machine for Remaining Useful Life Estimation of Aircraft Engines, 21st International Conference on Intelligent Transportation Systems (ITSC), 2018, 18308685.
  15. Lim, J.H., Won, D.Y., Sim, H.S., Park, C.H., Koh, K.J., Kang, J.G., and Kim, Y.S., A study on condition-based maintenance policy using minimum-repair block replacement, Journal of Applied Reliability, 2018, Vol. 18, No. 2, pp. 114-121. https://doi.org/10.33162/JAR.2018.06.18.2.114
  16. Liu, L., Wang, L., and Yu, Z., Remaining useful life estimation of aircraft engines based on deep convolution neural network and lightGBM combination model, International Journal of Computational Intelligence Systems, 2021, Vol. 14, 165. https://doi.org/10.1007/s44196-021-00020-1
  17. Nakagawa, T., Asummary of block replacement policies, Operations Research, 1979, Vol. 13, No. 4, pp. 351-361. https://doi.org/10.1051/ro/1979130403511
  18. Patil, S., Patil, A., Handikherkar, V., Desai, S., Phalle, V.M., and Kazi, F.S., Remaining useful life (rul) prediction of rolling element bearing using random forest and gradient boosting technique, International Mechanical Engineering Congress and Exposition, IMECE 2018-87623, 2018.
  19. Que, Z. and Xu, Z., A data-driven health prognostics approach for steam turbines based on XGBoost and DTW, IEEE Access, 2019, Vol. 7, pp. 93131-93138. https://doi.org/10.1109/ACCESS.2019.2927488
  20. Rebaiaia, M.L. and Ait-kadi, D., Maintenance policies with minimal repair and replacement on failures: analysis and comparison, International Journal of Production Research, 2020, Vol. 59, No. 23, pp. 6995-7017. https://doi.org/10.1080/00207543.2020.1832275
  21. Rebaiaia, M.L., Ait-Kadi, D., and Jamshidi, A., Periodic replacement strategies: optimality conditions and numerical performance comparisons, International Journal of Production Research, 2017, Vol. 55, No. 23, pp. 7135-7152. https://doi.org/10.1080/00207543.2017.1349953
  22. Seo, S.G., Kim, H.G., Bae, S.J., and Yun, W.Y., Reliability engineering, (3rd ed), Gyomoonsa, 2020.
  23. Shi, J., Yu, T., Goebel, K., and Wu, D., Remaining useful life prediction of bearings using ensemble learning: The impact of diversity in base learners and features, Journal of Computing and Information Science in Engineering, 2021, Vol. 21, No. 2, 021004. https://doi.org/10.1115/1.4048215
  24. Tong, Z., Miao, J., Tong, S., and Lu, Y., Early prediction of remaining useful life for Lithium-ion batteries based on a hybrid machine learning method, Journal of Cleaner Production, 2021, Vol. 317, 128265. https://doi.org/10.1016/j.jclepro.2021.128265
  25. Wang, X., Zeng, D., Dai, H., and Zhu, Y., Making the right business decision: Forecasting the binary NPD strategy in Chinese automotive industry with machine learning methods, Technological Forecasting & Social Change, 2020, Vol. 155, 120032. https://doi.org/10.1016/j.techfore.2020.120032
  26. Wu, J.Y., Wu, M., Chen, Z., Li, X., and Yan, R., A joint classification-regression method for multi-stage remaining useful life prediction, Journal of Manufacturing Systems, 2021, Vol. 58, pp. 109-119. https://doi.org/10.1016/j.jmsy.2020.11.016
  27. Yun, Y., Kim, S., Cho, S.H., and Choi, J.H., Neural network based aircraft engine health management using C-MAPSS data, Journal of Aerospace System Engineering, 2019, Vol. 13, No, 6, pp. 17-25. https://doi.org/10.20910/JASE.2019.13.6.17