RESEARCH PAPER
A fault diagnosis method for marine diesel engine system components based on adversarial neural network
1
Marine Engineering Colloge, Dalian Maritime University, China
2
Ningbo Ocean Shipping CO., LTD, China
Submission date: 2025-08-03
Final revision date: 2025-09-17
Acceptance date: 2025-12-16
Online publication date: 2025-12-26
Publication date: 2025-12-26
HIGHLIGHTS
- A more accurate class-level matching strategy is developed.
- A shallow independent-deep shared strategy is designed.
- A progressive adversarial training diagnostic framework is proposed.
KEYWORDS
TOPICS
ABSTRACT
Diesel engine is the main power source of ships, and its failure seriously affects safe navigation. Transfer learning is an effective method to solve cross-domain diagnosis of marine diesel engine. However, when facing large domain shifts, relying solely on cross-domain consistent semantic information cannot achieve high-precision diagnosis of the target task. A diagnostic method for diesel engine has been proposed. The shallow independent - deep sharing mechanism is first designed to fully consider the specificity and commonality of different domains. Then, the reliable alignment of different classes of source and target domains is achieved based on domain alignment theory and pseudo-label strategy. The performance of the framework is rigorously evaluated by two real-world cases and its applicability across subsystems is verified. The results demonstrate that the average accuracy of the framework is over 93%, outperforming other methods by more than 1.55%. Even in tasks with large domain distribution discrepancies, the framework also enables robust feature transfer.
ACKNOWLEDGEMENTS
This study is sponsored by the National Natural Science Foundation of China (Grant No. 52471311), the China Scholarship Council scholarship program (Grant No. 202506570017), the Fundamental Research Funds for the Central Universities (Grant No. 3132025611).
REFERENCES (38)
1.
Guo Y, Zhang J, Sun B, Wang Y. A universal fault diagnosis framework for marine machinery based on domain adaptation. Ocean Eng 2024; 302: 117729, https://doi.org/10.1016/j.ocea....
2.
Liang Q, Knutsen K, Vanem E, Aesoy V, Zhang H. A review of maritime equipment prognostics health management from a classification society perspective. Ocean Eng 2024; 301: 117619, https://doi.org/10.1016/j.ocea....
3.
Lloyd’s List Intelligence, Ship Accident Data 2023, London, United Kingdom, Nov. 2023. Lloyd's List Intelligence (lloydslistintelligence.com).
4.
American Bureau of Shipping, Guidance Notes on Failure Mode and Effects Analysis (FMEA) for Classification, Houston, The USA, Jan. 2018.
5.
Lloyd’s List, Outlook 2021, Shipping Accelerates towards an Uncertain Future, London, United Kingdom, Jan. 2021.
6.
Yang N, Liu J, Ma H, Zhao W, Gao Y. Fault diagnosis of gear based on URP-CVAE-MGAN under imbalanced and small sample conditions. Eksploatacja i Niezawodność - Maintenance and Reliability 2025; 27(3): 199417, https://doi.org/10.17531/ein/1....
7.
Ge Y, Zhang F, Ren Y. A Federated Transfer Fault Diagnosis Method for Cross-Domain and Incomplete Data. Eksploatacja i Niezawodność - Maintenance and Reliability 2025; 27(2): 194182, https://doi.org/10.17531/ein/1....
8.
Dong X, Zeng H, Li C, Ye K, Lu Z. Health condition assessment of marine diesel engine sub-system based on PSO-BP neural network. Ships and Offshore Structures 2025; 1–17. https://doi.org/10.1080/174453....
9.
Liu Z, Yang X, Xie Y, Wu M, Li Z, Mu W, Liu G. Multisensor cross-domain fault diagnosis method for leakage of ship pipeline valves. Ocean Eng 2024; 299: 117211, https://doi.org/10.1016/j.ocea....
10.
Shahid S, Ko S, Kwon S. Real-time abnormality detection and classification in diesel engine operations with convolutional neural network. Expert Systems with Applications 2022; 192: 116233, https://doi.org/10.1016/j.eswa....
11.
Shi J, Ren Y, Tang H, Xiang J. Hydraulic directional valve fault diagnosis using a weighted adaptive fusion of multi-dimensional features of a multi-sensor. J. Zhejiang Univ. Sci. A 2022; 23(4): 257–271. https://doi.org/10.1631/jzus.A....
12.
Coraddu A, Oneto L, Ilardi D, Stoumpos S, Theotokatos G. Marine dual fuel engines monitoring in the wild through weakly supervised data analytics. Eng. Appl. Artif. Intell 2021; 100: 104179, https://doi.org/10.1016/j.enga....
13.
Qin H, Yang R, Guo C, Wang W. Fault diagnosis of electric rudder system using PSOFOA-BP neural network. Measurement 2021; 186: 110058, https://doi.org/10.1016/j.meas....
14.
Dibaj A, Ettefagh M, Hassannejad R, Ehghaghi M, A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults. Expert Systems with Applications 2021; 167: 114094, https://doi.org/10.1016/j.eswa....
15.
Xu X, Lin Y, Ye C. Fault diagnosis of marine machinery via an intelligent data-driven framework. Ocean Eng 2023; 289: 116302, https://doi.org/10.1016/j.ocea....
16.
Xu Z, Li C, Yang Y. Fault diagnosis of rolling bearing of wind turbines based on the variational mode decomposition and deep convolutional neural networks. Appl. Soft. Comput 2020; 95: 106515, https://doi.org/10.1016/j.asoc....
17.
Jiao J, Zhao M, Lin J, Liang K. Residual joint adaptation adversarial network for intelligent transfer fault diagnosis. Mech. Syst. Signal Process 2020; 145: 106962, https://doi.org/10.1016/j.ymss....
18.
Zhu J, Li O, Chen M, Hu B, Ma E. Rolling bearing fault diagnosis method based on adaptive signal diagnosis network and its application. Eksploatacja i Niezawodność – Maintenance and Reliability 2025; 27(2): 194673; https://doi.org/10.17531/ein/1....
19.
Gao Y, Li X. Fault Diagnosis of Centrifugal fan Bearings Based on I-CNN and JMMD in the Context of Sample Imbalance. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 26(4):191459, https://doi.org/10.17531/ein/1....
20.
Zhao W, Lv Y, Lee K, Li W. An intelligent data-driven adaptive health state assessment approach for rolling bearings under single and multiple working conditions. Computers & Industrial Engineering 2025; 203: 110988, https://doi.org/10.1016/j.cie.....
21.
Jiang F, Song H, Shen X. A novel fault transfer diagnosis method using CBAM-MobileNetV2 and its application to mine hoist main bearings under variable working conditions. J Mech Sci Technol. 2025; 39: 3091–3104, https://doi.org/10.1007/s12206....
22.
Zhang X, Yang K. Transformer fault diagnosis method based on MTF and GhostNet. Measurement, 2025; 249: 117056, https://doi.org/10.1016/j.meas....
23.
Cui Z, Lu Y, Yan X, Cui S. Compound fault diagnosis of diesel engines by combining generative adversarial networks and transfer learning. Expert Systems with Applications 2024; 251: 123969, https://doi.org/10.1016/j.eswa....
24.
Li C, Li G, Xing P, Cui D, Sui Y, Zhang H. A progressive domain separation network incorporating iris time-frequency maps for open-set diagnosis of ship propulsion shafting. Ocean Eng 2026; 343: 123219, https://doi.org/10.1016/j.ocea....
25.
Tang A, Wang M, Pan H. Angle-based transfer support matrix machine for roller bearing fault diagnosis under limited labeled data. Structural Health Monitoring 2024, doi:10.1177/14759217241298394.
26.
Zhang Y, Li C, Tang Y, Zhang X, Zhou F. A novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder and transfer learning. Journal of Manufacturing Systems 2024; 76: 443-456, https://doi.org/10.1016/j.jmsy....
27.
Li C, Li G, Xing P, Cui D, Sui Y, Zhang H. A semi-supervised learning framework fusing multi-sensor visual features for ship propulsion shafting fault diagnosis. Structural Health Monitoring 2025. https://doi.org/10.1177/147592....
28.
Huang M, Yin J, Yan S, Xue P. A fault diagnosis method of bearings based on deep transfer learning. Simulation Modelling Practice and Theory 2024; 122: 102659, https://doi.org/10.1016/j.simp....
29.
Hu J, Yu Y, Yang J, Jia H. Research on the generalisation method of diesel engine exhaust valve leakage fault diagnosis based on acoustic emission. Measurement. 2023; 210: 112560, https://doi.org/10.1016/j.meas....
30.
Hu L, Liu L, Yang J, Hu H, Zheng C, Yu Y. Fault diagnosis based on deep transfer learning for marine turbocharger. International Journal of Mechanical Sciences 2025; 300: 110444, https://doi.org/10.1016/j.ijme....
31.
Pei G, Zhu X, Wang X. A turn-based domain adversarial network for cross-domain fault diagnosis of diesel engine. J Mech Sci Technol. 2025; 39: 3079–3090, https://doi.org/10.1007/s12206....
32.
Li J, Deng W, Dang X, Zhao H. Cross-domain Adaptation fault diagnosis with Maximum classifier discrepancy and deep feature alignment under variable working conditions. IEEE Transactions on Reliability, https://doi.org/10.1109/TR.202....
33.
Saito K, Watanabe K, Ushiku Y. Maximum classifier discrepancy for unsupervised domain adaptation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2018; 201(4): 3723-3732, https://doi.org/10.1109/CVPR.2....
34.
Ghorvei M, Kavianpour M, Beheshti M, Ramezani A. Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis. Neurocomputing 2023; 517: 44-61, https://doi.org/10.1016/j.neuc....
35.
Fu S, Zou L, Wang Y, Lin L, Lu Y, Zhao M, Guo F, Zhong S. DCSIAN: A novel deep cross-scale interactive attention network for fault diagnosis of aviation hydraulic pumps and generalizable applications. Reliability Engineering & System Safety 2024; 249: 110246, https://doi.org/10.1016/j.ress....
36.
Gao C, Wang Z, Guo Y, Wang H, Yi H. MPINet: Multiscale physics-informed network for bearing fault diagnosis with small samples. IEEE Transactions on Industrial Informatics. 2024; 20(12): 14371-14380, https://doi.org/10.1109/TII.20....
37.
Li X, Jiang H, Liu S, Zhang J, Xu J. A unified framework incorporating predictive generative denoising autoencoder and deep coral network for rolling bearing fault diagnosis with unbalanced data. Measurement 2021; 178: 109345, https://doi.org/10.1016/j.meas....
38.
Jiang Q, Lin X, Lu X, Shen Y, Zhu Q, Zhang Q. Self-supervised learning-based dual-classifier domain adaptation model for rolling bearings cross-domain fault diagnosis. Knowledge-Based Systems 2024; 284: 111229, https://doi.org/10.1016/j.knos....
| 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.
