Research on the Bearing Lifespan Prediction Method for Ship Propulsion Shaft Systems Based on an Enhanced Domain Adversarial Neural Network
Abstract
:1. Introduction
2. Methodology Overview
2.1. Problem Description
2.2. Introduction to DANN Model
3. The Enhanced DANN Two-Stage Prediction Method
3.1. Feature Pre-Extraction Stage
3.2. Adaptation Stage of the Adversarial Domain
4. Experimental Study
4.1. Introduction to the Experimental Platform
4.1.1. Outline
4.1.2. Rotating Part
4.1.3. Loading Part
4.1.4. Measurement Part
4.1.5. Organization of Data
- -
- First operating conditions: 1800 rpm and 4000 N;
- -
- Second operating conditions: 1650 rpm and 4200 N;
- -
- Third operating conditions: 1500 rpm and 5000 N.
4.2. Data Preprocessing and Implementation Details
4.3. Life Prediction Process
4.4. Comparative Experiments
4.4.1. Introduction to Comparative Algorithms
4.4.2. Comparative Experiment Process and Result Analysis
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Han, H.; Lee, K.; Park, S. Estimate of the fatigue life of the propulsion shaft from torsional vibration measurement and the linear damage summation law in ships. Ocean Eng. 2015, 107, 212–221. [Google Scholar] [CrossRef]
- Murawski, L.; Charchalis, A. Simplified method of torsional vibration calculation of marine power transmission system. Mar. Struct. 2014, 39, 335–349. [Google Scholar] [CrossRef]
- Murawski, L. Axial vibrations of a propulsion system taking into account the couplings and the boundary conditions. J. Mar. Sci. Technol. 2004, 9, 171–181. [Google Scholar] [CrossRef]
- Murawski, L. Shaft Line Whirling Vibrations: Effects of Numerical Assumptions on Analysis Results. Mar. Technol. 2005, 42, 53–61. [Google Scholar] [CrossRef]
- Vizentin, G.; Vukelic, G.; Murawski, L. Marine Propulsion System Failures-A Review. J. Mater. Sci. Eng. 2020, 8, 662. [Google Scholar] [CrossRef]
- Ortolani, F.; Mauro, S.; Dubbioso, G. Investigation of the radial bearing force developed during actual ship operations. Part 2: Unsteady maneuvers. Ocean Eng. 2015, 106, 424–445. [Google Scholar] [CrossRef]
- Zhu, J.; Chen, N.; Shen, C. A new data-driven transferable remaining useful life prediction approach for bearing under different working conditions. Mech. Syst. Signal Proc. 2020, 139, 106602. [Google Scholar] [CrossRef]
- Li, X.; Ma, Y.; Zhu, J.J. An online dual filters RUL prediction method of lithium-ion battery based on unscented particle filter and least squares support vector machine. Measurement 2021, 184, 109935. [Google Scholar] [CrossRef]
- Zhu, R.; Chen, Y.; Peng, W.W.; Ye, Z.S. Bayesian deep-learning for RUL prediction: An active learning perspective. Reliab. Eng. Syst. Safe 2022, 228, 108758. [Google Scholar] [CrossRef]
- Wang, X.C.; Zhao, J.J. Research on IGBT Life Based on Wavelet Neural Network. Electr. Eng. 2020, 10, 114–116. [Google Scholar] [CrossRef]
- Zhou, T.T.; Zhu, X.M.; Wu, C.J. Marine propulsion shaft system fault diagnosis method based on partly ensemble empirical mode decomposition and SVM. J. Vibroeng. 2015, 17, 1783–1795. [Google Scholar]
- Li, X.; Ding, Q.; Sun, J.Q. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Safe 2018, 172, 1–11. [Google Scholar] [CrossRef]
- Kang, W.; Xiao, J.; Xiao, M.; Hu, Y.; Zhu, H.; Li, J. Research on remaining useful life prognostics based on fuzzy evaluation-Gaussian process regression method. IEEE Access 2020, 8, 71965–71973. [Google Scholar] [CrossRef]
- Wan, S.K.; Li, X.H.; Zhang, Y.F.; Liu, S.J.; Hong, J.; Wang, D.F. Bearing remaining useful life prediction with convolutional long short-term memory fusion networks. Reliab. Eng. Syst. Safe 2022, 224, 108528. [Google Scholar] [CrossRef]
- Ren, L.; Sun, Y.; Wang, H.; Zhang, L. Prediction of bearing remaining useful life with deep convolution neural network. IEEE Access 2018, 6, 13041–13049. [Google Scholar] [CrossRef]
- Song, X.W.; Liao, Z.Q.; Wang, H.F. Incrementally accumulated holographic SDP characteristic fusion method in ship propulsion shaft bearing fault diagnosis. Meas. Sci. Technol. 2022, 33, 045011. [Google Scholar] [CrossRef]
- Zou, D.L.; Lv, F.R.; Ta, N. Study on bearing force of marine propeller induced by longitudinal vibration of propulsion-shafting. Ships Offshore Struc. 2019, 15, 162–173. [Google Scholar] [CrossRef]
- Kuo, H.C.; Wu, L.J.; Chen, J.H. Neural-fuzzy fault diagnosis in a marine propulsion shaft system. J. Mater. Process. Technol. 2002, 122, 12–22. [Google Scholar] [CrossRef]
- Siahpour, S.; Li, X.; Lee, J. Deep learning-based cross-sensor domain adaptation for fault diagnosis of electro-mechanical actuators. Int. J. Dyn. Control 2020, 8, 1054–1062. [Google Scholar] [CrossRef]
- Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 2009, 22, 1345–1359. [Google Scholar] [CrossRef]
- Zhang, W.; Li, X.; Ma, H.; Luo, Z.; Li, X. Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning. IEEE Trans. Ind. Inform. 2021, 17, 7445–7455. [Google Scholar] [CrossRef]
- Zhang, W.; Li, X.; Ma, H.; Luo, Z.; Li, X. Federated learning for machinery fault diagnosis with dynamic validation and self-supervision. Knowl.-Based Syst. 2021, 213, 106679. [Google Scholar] [CrossRef]
- Ordóñez, C.; Lasheras, F.; O Sánchez. A hybrid ARIMA-SVM model for the study of the remaining useful life of aircraft engines. J. Comput. Appl. Math. 2019, 346, 184–191. [Google Scholar] [CrossRef]
- Li, W.; Liu, T. Time varying and condition adaptive hidden Markov model for tool wear state estimation and remaining useful life prediction in micro-milling. Mech. Syst. Signal Proc. 2019, 131, 689–702. [Google Scholar] [CrossRef]
- Sun, B.; Feng, J.; Saenko, K. Return of frustratingly easy domain adaptation. In Proceedings of the AAAI conference on Artificial Intelligence, Washington, DC, USA, 2 March 2016. [Google Scholar] [CrossRef]
- Ganin, Y.; Ustinova, E.; Ajakan, H.; Germain, P.; Larochelle, H.; Laviolette, F.O. Domain-adversarial training of neural networks. J. Mach. Learn. Res. 2016, 17, 1–35. [Google Scholar] [CrossRef]
- Wang, Y.; Sun, X.; Li, J.; Yang, Y. Intelligent fault diagnosis with deep adversarial domain adaptation. IEEE Trans. Instrum. Meas. 2021, 70, 1–9. [Google Scholar] [CrossRef]
- Li, X.; Zhang, W.; Ma, H.; Luo, Z.; Li, X. Data alignments in machinery remaining useful life prediction using deep adversarial neural networks. Knowl-Based Syst. 2020, 197, 105843. [Google Scholar] [CrossRef]
- Nectoux, P.; Gouriveau, R.; Medjaher, K. PRONOSTIA: An experimental platform for bearings accelerated degradation tests. In Proceedings of the IEEE International Conference on Prognostics and Health Management, PHM’12, Denver, CO, USA, 21 June 2012. [Google Scholar]
- Ding, N.; Li, H.L.; Yin, Z.W.; Jiang, F.M. A novel method for journal bearing degradation evaluation and remaining useful life prediction under different working conditions. Measurement 2021, 177, 109273. [Google Scholar] [CrossRef]
- Li, B.; Tang, B.P.; Deng, L.; Zhao, M.H. Self-Attention ConvLSTM and Its Application in RUL Prediction of Rolling Bearings. IEEE Trans. Instrum. Meas. 2021, 70, 3518811. [Google Scholar] [CrossRef]
Condition | Rotating Speed (rmp) | Radical Force (N) | Bearing Data |
---|---|---|---|
Condition 1 | 1800 | 4000 | bearing1-1–bearing1-7 |
Condition 2 | 1650 | 4200 | bearing2-1–bearing2-7 |
Condition 3 | 1500 | 5000 | bearing3-1–bearing3-3 |
Parameters From | Parameters | Value |
---|---|---|
Overall | Learning rate | 1 × 10−5 |
Batch size | 64 | |
Epochs | 4000 | |
Feature Extractor | Conv1 | 32 × 3 |
Conv2 | 16 × 3 | |
Conv3 | 1 × 3 | |
Neurons Number in FC1 | 30 | |
Predictor | Neurons Number in FC2 | 10 |
Output of the RUL predictor | 1 | |
Domain Discriminator | Neurons Number in FC3 | 100 |
Output of the Domain Discriminator | 2 |
Task | Source Data (Labeled) | Target Data (Unlabeled) | Notes |
---|---|---|---|
Task 1 | bearing2-1–bearing2-7 | bearing1-3 | Condition2→ Condition 1 |
Task 2 | bearing1-1–bearing1-7 | bearing2-3 | Condition 1→ Condition 2 |
Task 3 | bearing1-1–bearing1-7 | bearing3-3 | Condition 1→ Condition 3 |
Task | Method | R2 | MAE | MSE | RMSE |
---|---|---|---|---|---|
Task 1 | DANN | 0.3450 | 0.2831 | 0.0067 | 0.3262 |
Improved DANN | 0.9385 | 0.0572 | 0.0015 | 0.0732 | |
Task 2 | DANN | 0.2273 | 0.2447 | 0.0066 | 0.2939 |
Improved DANN | 0.9035 | 0.0672 | 0.0020 | 0.0898 | |
Task 3 | DANN | 0.1313 | 0.4625 | 0.0244 | 0.5078 |
Improved DANN | 0.8323 | 0.0913 | 0.0057 | 0.1182 |
Task | Method | R2 | MAE | MSE | RMSE |
---|---|---|---|---|---|
Task 1 | MK-MMD | 0.5855 | 0.1665 | 0.0041 | 0.1992 |
SA-ConvLSTM | 0.7817 | 0.1208 | 0.0029 | 0.1410 | |
Proposed | 0.9385 | 0.0572 | 0.0015 | 0.0732 | |
Task 2 | MK-MMD | 0.5631 | 0.1473 | 0.0044 | 0.1940 |
SA-ConvLSTM | 0.3400 | 0.1806 | 0.0055 | 0.2438 | |
Proposed | 0.9035 | 0.0672 | 0.0020 | 0.0898 | |
Task 3 | MK-MMD | 0.4194 | 0.2497 | 0.0138 | 0.2876 |
SA-ConvLSTM | 0.6183 | 0.1639 | 0.0097 | 0.2011 | |
Proposed | 0.8323 | 0.0913 | 0.0057 | 0.1182 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ren, F.; Du, J.; Chang, D. Research on the Bearing Lifespan Prediction Method for Ship Propulsion Shaft Systems Based on an Enhanced Domain Adversarial Neural Network. J. Mar. Sci. Eng. 2023, 11, 2128. https://doi.org/10.3390/jmse11112128
Ren F, Du J, Chang D. Research on the Bearing Lifespan Prediction Method for Ship Propulsion Shaft Systems Based on an Enhanced Domain Adversarial Neural Network. Journal of Marine Science and Engineering. 2023; 11(11):2128. https://doi.org/10.3390/jmse11112128
Chicago/Turabian StyleRen, Feixiang, Jiwang Du, and Daofang Chang. 2023. "Research on the Bearing Lifespan Prediction Method for Ship Propulsion Shaft Systems Based on an Enhanced Domain Adversarial Neural Network" Journal of Marine Science and Engineering 11, no. 11: 2128. https://doi.org/10.3390/jmse11112128