RESEARCH PAPER
Optimal Imperfect Predictive Maintenance Based on Interval Remaining Useful
Life Prediction
1
School of Mechanical Engineering, Southeast University, China
2
College of Design and Engineering, National University of Singapore, Singapore
Submission date: 2024-11-22
Final revision date: 2025-01-14
Acceptance date: 2025-03-28
Online publication date: 2025-04-02
Publication date: 2025-04-02
Corresponding author
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(4):203458
HIGHLIGHTS
- A PdM framework combines interval RUL prediction with maintenance policy optimization
- BiTCN with multi-head attention significantly improves RUL prediction accuracy
- ABKDE is used to estimate the prediction uncertainty
- DCS optimizes hyperparameters of RUL prediction model and decision variables of PdM
- Case studies demonstrate outstanding performance of the proposed approach
KEYWORDS
differential creative search (DCS)bidirectional temporal convolutional network (BiTCN)adaptive bandwidth kernel density estimationinterval RUL predictionpredictive maintenance (PdM)
TOPICS
ABSTRACT
Predictive maintenance is essential in prognostics and health management, where prediction of remaining useful life (RUL) plays a key role. However, various challenges exist in deep learning-based RUL prediction models, including hyperparameter tuning, uncertainty, and applying RUL for maintenance. To address such issues, this paper proposes a novel PdM framework by combining interval RUL prediction with maintenance policy optimization. A bidirectional temporal convolutional network with multi-head attention method is adopted for RUL prediction, and a physical model can integrate the predicted RUL intervals for maintenance decision-making. Moreover, the differential creative search algorithm is introduced to optimize hyperparameters and decision maintenance variables. A case study is conducted with the C-MPASS aero engine dataset. The results show that the proposed model can reduce RMSE by over 3.20% and 3.68% on the FD002 and FD004 datasets, respectively. Sensitivity analysis also confirms its robust performance despite the variations in maintenance costs or times.
ACKNOWLEDGEMENTS
This work is supported by the National Natural Science Foundation of China (Grant No. 72471055) and the China Scholarship Council.
REFERENCES (51)
1.
Zio E. Prognostics and health management (PHM): Where are we and where do we (need to) go in theory and practice. Reliability Engineering & System Safety 2022; 218: 108119, https://doi.org/10.1016/j.ress....
2.
Fang P Y, Sui X X, Zhang A H, et al. Fusion model based RUL prediction method of lithium-ion battery under working conditions. Eksploatacja i Niezawodność 2024; 26(3): https://doi.org/10.17531/ein/1....
3.
Pinciroli L, Baraldi P, Zio E. Maintenance optimization in industry 4.0. Reliability Engineering & System Safety 2023; 234: 109204, https://doi.org/10.1016/j.ress....
4.
Zhou Z, Bai M, Long Z, Liu J, Yu D. An adaptive remaining useful life prediction model for aeroengine based on multi-angle similarity. Measurement 2024; 226: 114082, https://doi.org/10.1016/j.meas....
5.
Levitin G, Yu L, Dai Y. Optimizing corrective maintenance for multistate systems with storage. Reliability Engineering & System Safety 2024; 244: 109951, https://doi.org/10.1016/j.ress....
6.
Liu P, Wang G, Tan Z. Calendar-time-based and age-based maintenance policies with different repair assumptions. Applied Mathematical Modelling 2024; 129: 592-611, https://doi.org/10.1016/j.apm.....
7.
Sharma J, Mittal M L, Soni G. Condition-based maintenance using machine learning and role of interpretability: A review. International Journal of System Assurance Engineering and Management 2024; 15(4): 1345-1360, https://doi.org/10.1007/s13198....
8.
Hong G, Song W, Gao Y, Zio E, Kudreyko A. An iterative model of the generalized Cauchy process for predicting the remaining useful life of lithium-ion batteries. Measurement 2022; 187: 110269, https://doi.org/10.1016/j.meas....
9.
Wang T, Li X, Wang W, Du J, Yang X. A spatiotemporal feature learning-based RUL estimation method for predictive maintenance. Measurement 2023; 214: 112824, https://doi.org/10.1016/j.meas....
10.
Wang Z, Zhao W, Li Y, Dong L, Wang J, Du W, Jiang X. Adaptive staged RUL prediction of rolling bearing. Measurement 2023; 222: 113478, https://doi.org/10.1016/j.meas....
11.
Nunes P, Santos J, Rocha E. Challenges in predictive maintenance–A review. CIRP Journal of Manufacturing Science and Technology 2023; 40: 53-67, https://doi.org/10.1016/j.cirp....
12.
Cao X, Shi X, Zhao J, Duan Y, Yang X. Dynamic grouping maintenance optimization by considering the probabilistic remaining useful life prediction of multiple equipment. Eksploatacja i Niezawodność 2024; 26(3): https://doi.org/10.17531/ein/1....
13.
Truong T T, Airao J, Hojati F, Ilvig C F, Azarhoushang B, Karras P, Aghababaei R. Data-driven prediction of tool wear using Bayesian regularized artificial neural networks. Measurement 2024; 238: 115303, https://doi.org/10.1016/j.meas....
14.
Xiang S, Qin Y, Luo J, Pu H, Tang B. Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction. Reliability Engineering & System Safety 2021; 216: 107927, https://doi.org/10.1016/j.ress....
15.
Li T, Zhou Z, Li S, Sun C, Yan R, Chen X. The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study. Mechanical Systems & Signal Processing 2022; 168: 108653, https://doi.org/10.1016/j.ymss....
16.
Yu W, Kim IY, Mechefske C. Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme. Mechanical Systems & Signal Processing 2019; 129: 764-780, https://doi.org/10.1016/j.ymss....
17.
Liu J Q, Pan C L, Lei F, et al. Fault prediction of bearings based on LSTM and statistical process analysis. Reliability Engineering & System Safety 2021; 214: 107646, https://doi.org/10.1016/j.ress....
18.
Zhou J H, Qin Y, Luo J, et al. Dual-thread gated recurrent unit for gear remaining useful life prediction. IEEE Transactions on Industrial Informatics 2023; 19(7): 8307-8318, https://doi.org/10.1109/TII.20....
19.
Wang L, Cao H, Xu H, Liu H. A gated graph convolutional network with multi- sensor signals for remaining useful life prediction. Knowledge-Based Systems 2022; 252: 109340, https://doi.org/ 10.1016/j.knosys.2022.109340.
20.
Li X, Ding Q, Sun J. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliability Engineering & System Safety 2018; 172: 1-11, https://doi.org/10.1016/j.ress....
21.
Yang B, Liu R, Zio E. Remaining useful life prediction based on a double convolutional neural network architecture. IEEE Transactions on Industrial Electronics 2019; 66(12): 9521-9530, https://doi.org/10.1109/TIE.20....
22.
Wang P, Zhang X, Zhang G. Remaining useful life prediction of lithium-ion batteries based on ResNet-Bi-LSTM-Attention model. Energy Storage Science and Technology 2023; 12(4): 1215, https://doi.org/10.19799/j.cnk....
23.
He K, Su Z, Tian X, et al. RUL prediction of wind turbine gearbox bearings based on self-calibration temporal convolutional network. IEEE Transactions on Instrumentation and Measurement 2022; 71: 1-12, https://doi.org/10.1109/TIM.20....
24.
Cao Y, Ding Y, Jia M, et al. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings. Reliability Engineering & System Safety 2021; 215: 107813, https://doi.org/10.1016/j.ress....
25.
Rahman M S, Colbourne B, Khan F. Conceptual development of an offshore resource centre in support of remote harsh environment operations. Ocean Engineering 2020; 203: 107236, https://doi.org/10.1016/j.ocea....
26.
Shen J Y, Cui L R, Ma Y Z. Availability and optimal maintenance policy for systems degrading in dynamic environments. European Journal of Operational Research 2019; 276(1): 133-143, https://doi.org/10.1016/j.ejor....
27.
Huang C G, Huang H Z, Li Y F, et al. A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing. Journal of Manufacturing Systems 2021; 61: 757-767, https://doi.org/10.1016/j.jmsy....
28.
Huang C G, Huang H Z, Li Y F, et al. Fault prognosis using deep convolutional neural network and bootstrap-based method. 2020 IEEE 18th International Conference on Industrial Informatics (INDIN) 2021: 742-747, https://doi.org/10.1109/INDIN4....
29.
Guo J Y, Wang J, Wang Z Y, et al. A CNN–BiLSTM-Bootstrap integrated method for remaining useful life prediction of rolling bearings. Quality and Reliability Engineering International 2023; 39(5): 1796-1807, https://doi.org/10.1002/qre.33....
30.
Chen C, Shi J T, Lu N Y, et al. Data-driven predictive maintenance strategy considering the uncertainty in remaining useful life prediction. Neurocomputing 2022; 494: 79-88, https://doi.org/10.1016/j.neuc....
31.
Chen C, Tao G Y, Shi J T, et al. A lithium-ion battery degradation prediction model with uncertainty quantification for its predictive maintenance. IEEE Transactions on Industrial Electronics 2024; 71(4): 3650-3661, https://doi.org/10.1109/TIE.20....
32.
Zhang M, Wang D, Amaitik N, et al. A distributional perspective on remaining useful life prediction with deep learning and quantile regression. IEEE Open Journal of Instrumentation and Measurement 2022; 1: 1-13, https://doi.org/10.1109/OJIM.2....
33.
Erden C. Genetic algorithm-based hyperparameter optimization of deep learning models for PM2.5 time-series prediction. International Journal of Environmental Science and Technology 2023; 20(3): 2959-2982, https://doi.org/10.1109/OJIM.2....
34.
Taş G, Bal C, Uysal A. Performance comparison of lithium polymer battery SOC estimation using GWO-BiLSTM and cutting-edge deep learning methods. Electrical Engineering 2023; 105(5): 3383-3397, https://doi.org/10.1007/s13369....
35.
Che Z, Peng C, Yue C. Optimizing LSTM with multi-strategy improved WOA for robust prediction of high-speed machine tests data. Chaos, Solitons & Fractals 2024; 178: 114394, https://doi.org/10.1016/j.chao....
36.
Duankhan P, Sunat K, Chiewchanwattana S, et al. The differentiated creative search (DCS): Leveraging differentiated knowledge-acquisition and creative realism to address complex optimization problems. Expert Systems with Applications 2024; 123734, https://doi.org/10.1016/j.eswa....
37.
Zhang Y R, Su C, Wu J J, et al. Trend-augmented and temporal-featured transformer network with multi-sensor signals for remaining useful life prediction. Reliability Engineering & System Safety 2024; 241: 109662, https://doi.org/10.1016/j.ress....
38.
Liu L, Song X, Zhou Z. Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture. Reliability Engineering & System Safety 2022; 221: 108330, https://doi.org/10.1016/j.ress....
39.
Wang L, Cao H, Xu H, Liu H. A gated graph convolutional network with multisensor signals for remaining useful life prediction. Knowledge-Based Systems 2022; 252: 109340, https://doi.org/10.1016/j.knos....
40.
Chen C, Shi J T, Shen M Q, et al. A predictive maintenance strategy using deep learning quantile regression and kernel density estimation for failure prediction. IEEE Transactions on Instrumentation and Measurement 2023; 72: 1-12, https://doi.org/10.1109/TIM.20....
41.
Shoorkand H D, Nourelfath M, Hajji A. A hybrid CNN-LSTM model for joint optimization of production and imperfect predictive maintenance planning. Reliability Engineering & System Safety 2024; 241: 109707, https://doi.org/10.1016/j.ress....
42.
de Pater I, Reijns A, Mitici M. Alarm-based predictive maintenance scheduling for aircraft engines with imperfect remaining useful life prognostics. Reliability Engineering & System Safety 2022; 221: 108341, https://doi.org/10.1016/j.ress....
43.
Kong Z, Cui Y, Xia Z, Lv H. Convolution and long short-term memory hybrid deep neural networks for remaining useful life prognostics. Applied Sciences-Basel 2019; 9(19): 4156, https://doi.org/10.3390/app919....
44.
Zhang J, Jiang Y, Wu S, Li X, Luo H, Yin S. Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism. Reliability Engineering & System Safety 2022; 221: 108297, https://doi.org/ 10.1016/j.ress.2021.108297.
45.
Liu L, Song X, Zhou Z. Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture. Reliability Engineering & System Safety 2022; 221: 108330, https://doi.org/ 10.1016/j.ress.2022.108330.
46.
Zhang J, Li X, Tian J, Luo H, Yin S. An integrated multi-head dual sparse self- attention network for remaining useful life prediction. Reliability Engineering & System Safety 2023; 235: 109247, https://doi.org/10.1016/j.ress....
47.
Xiong J, Zhou J, Ma Y, Zhang F, Lin C. Adaptive deep learning-based remaining useful life prediction framework for systems with multiple failure patterns. Reliability Engineering & System Safety 2023; 235: 109244, https://doi.org/ 10.1016/j.ress.2023.109244.
48.
Vakharia V, Shah M, Nair P, et al. Estimation of lithium-ion battery discharge capacity by integrating optimized explainable-ai and stacked lstm model. Batteries 2023, 9, 125, https://doi.org/10.3390/batter....
49.
Wang, S M, Ma C M, Xu Y X, et al. A hyperparameter optimization algorithm for the lstm temperature prediction model in data center. Scientific Programming 2022, 6519909, https://doi.org/10.1155/2022/6....
50.
Dave V, Borade H, Agrawal H, et al. Deep learning-enhanced small-sample bearing fault analysis using Q-transform and HOG image features in a GRU-XAI framework. Machines 2024, 12, 373, https://doi.org/10.3390/machin....
51.
Song S S, Zhang S Q, Dong W, et al. Multi-source information fusion meta learning network with convolutional block attention module for bearing fault diagnosis under limited dataset. Structural Health Monitoring-An International Journal 2024, 23(2): 818-835, https://doi.org/10.1177/147592....
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
