PREDICTION OF THE REMAINING USEFUL LIFE OF TECHNOLOGICAL EQUIPMENT USING THE DEEP LEARNING METHOD LSTM
Abstract
The relevance of this study stems from the widespread implementation of predictive maintenance sys-tems. In modern industrial settings, accurately predicting the remaining service life (RUL) of critical equip-ment is particularly important. However, traditional data analysis methods demonstrate significant limita-tions when working with multivariate non-stationary time series characterized by high levels of noise and complex nonlinear dependencies. This leads to significant forecast errors, suboptimal repair planning, and an increased risk of sudden failures, which can cause significant economic losses and disrupt production processes. The goal of this study was to develop an improved RUL prediction model based on deep recur-rent neural networks. To achieve this goal, the following tasks were sequentially addressed: detailed analy-sis and multi-stage preprocessing of multivariate monitoring data; and design of a specialized two-layer LSTM architecture with integrated regularization mechanisms. The methods and approaches included the use of a unique methodology combining cascaded LSTM layers with normalization and dropout regulariza-tion. The model was trained on the NASA Turbofan Engine Degradation Simulation dataset using the state-of-the-art Adam optimizer and an early stopping strategy to prevent overfitting. Particular attention was paid to developing specialized preprocessing algorithms that effectively handle noisy time series and pre-serve long-term dependencies in the data. The main results of the experiments demonstrate high forecast accuracy. Detailed visual analysis of the time series confirmed the precise correspondence of the predicted values with the actual wear trajectories of mechanical components. The findings of the study demonstrate the high practical effectiveness of the developed model for solving current industrial forecasting problems. The feasibility of successful integration of the model into modern predictive maintenance systems for pro-cess equipment was established. The practical significance of the work lies in the potential for significant optimization of maintenance costs and minimization of the risk of critical failures. Prospects for further research include the development of hybrid architectures, the integration of attention mechanisms, and the adaptation of the model to various types of industrial equipment
References
1. Si X.-S., Wang W., Hu C.-H., & Zhou D.-H. Remaining useful life estimation – A review on the statisti-cal data driven approaches. European Journal of Operational Research, 16 August 2011, Vol. 213, Is-sue 1, pp. 1-14. DOI: 10.1016/j.ejor.2010.11.018.
2. Hochreiter S., & Schmidhuber J. Long short-term memory, Neural Computation, 15 November 1997, Vol. 9, Issue 8, pp. 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.
3. Gers F.A., Schmidhuber J., & Cummins F. Learning to forget: Continual prediction with LSTM, Neural Computation, 2000, Vol. 12, Issue 10, pp. 2451-2471. DOI: 10.1162/089976600300015015.
4. Saxena A., Goebel K., Simon D. and Eklund N. Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation, 2008 International Conference on Prognostics and Health Management, Denver, 6-9 October 2008, pp. 1-9. Available at: https://doi.org/10.1109/phm.2008.4711414.
5. Ren S., Sun Y., Cui J., Zhang L. A Deep Learning Approach for Remaining Useful Life Estimation of Bearings // Journal of Manufacturing Systems, 2018, Vol. 48, pp. 71-77. DOI: 10.1016/j.jmsy.2018.04.003.
6. Li X., Ding Q., Sun J.Q. Remaining Useful Life Estimation in Prognostics Using Deep Convolution Neural Networks, Reliability Engineering & System Safety, 2018, Vol. 172, pp. 1-11. DOI: 10.1016/j.ress.2017.11.021.
7. Wu Y., Yuan M., Dong S., Lin L., Liu Y. Remaining Useful Life Estimation of Engineered Systems Us-ing Vanilla LSTM Neural Networks, Neurocomputing, 2018, Vol. 275, pp. 167-179. DOI: 10.1016/j.neucom.2017.05.063
8. Zheng S., Ristovski K., Farahat A., Gupta C. Long Short-Term Memory Network for Remaining Useful Life Estimation // Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management (ICPHM). Dallas, TX, USA, 2017, pp. 88-95. DOI: 10.1109/ICPHM.2017.7998311.
9. Lei Y., Li N., Guo L., Li N., Yan T., 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. DOI: 10.1016/j.ymssp.2017.11.016.
10. Si X.-S., Wang W., Hu C.-H., Zhou D.-H. Remaining Useful Life Estimation – A Review on the Statisti-cal Data Driven Approaches, European Journal of Operational Research, 2011, Vol. 213, No. 1,
pp. 1-14. DOI: 10.1016/j.ejor.2010.11.018.
11. Zhang C., Lim P., Qin A.K., Tan K.C. Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics, IEEE Transactions on Neural Networks and Learning Systems, 2019, Vol. 30, No. 12, pp. 3816-3831. DOI: 10.1109/TNNLS.2018.2868936.
12. Zhao R., Yan R., Wang J., Mao K. Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks, Sensors, 2017, Vol. 17, No. 2, Art. № 273. DOI: 10.3390/s17020273.
13. Sateesh Babu G., Zhao P., Li X.-L. Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life, Database Systems for Advanced Applications: DASFAA 2016 International Workshops. Lecture Notes in Computer Science. 2016, Vol. 9643, pp. 214–228. DOI: 10.1007/978-3-319-32025-0_11.
14. Wang J., Yan R., Li X. A Hybrid Deep Learning Model for Predictive Maintenance of Rotating Machin-ery Based on LSTM and Transformer, Mechanical Systems and Signal Processing, 2023,
Vol. 189, Art. No. 110069. DOI: 10.1016/j.ymssp.2022.110069.
15. Lei Y., Yang B., Jiang X. Remaining Useful Life Prediction of Bearings Using a Novel Health Indicator and a Deep Temporal Convolutional Network, IEEE Transactions on Industrial Informatics, 2022, Vol. 18, No. 9, pp. 6001-6010. DOI: 10.1109/TII.2022.3142618.
16. Raddatz M.S., Sousa J.B.G. Explainable AI for LSTM-Based Remaining Useful Life Prediction: An Application to the C-MAPSS Dataset, Journal of Intelligent Manufacturing, 2024, Vol. 35, No. 2,
pp. 345-361. DOI: 10.1007/s10845-023-02147-8.
17. Liao H., Wang Z., Zhao Y. Digital Twin-Driven Remaining Useful Life Prediction Using a Physics-Informed LSTM Network, Reliability Engineering & System Safety, 2023, Vol. 239, Art. No. 109560. DOI: 10.1016/j.ress.2023.109560.
18. Guo L., Li Y., Li N. A Comparative Study of LSTM, GRU and Attention Mechanisms for Remaining Useful Life Prediction, Engineering Applications of Artificial Intelligence, 2022, Vol. 116, Art.
No. 105472. DOI: 10.1016/j.engappai.2022.105472.
19. Zhang K., Wang T., Chen Z. A Self-Attentive LSTM Approach for RUL Prediction with Adaptive Fea-ture Extraction, IEEE Access, 2021, Vol. 9, pp. 154233-154245. DOI: 10.1109/ACCESS.2021.3127890.
20. Sansawat A., Zhang L., Wang P. A Survey on Deep Learning for Predictive Maintenance in Industry 4.0: Methods, Challenges and Future Directions, Computers & Industrial Engineering, 2024, Vol. 187, Art. No. 109810. DOI: 10.1016/j.cie.2023.109810.
