A cross-condition concurrent fault diagnosis framework for the marine gas turbine propulsion system

PDF(9956 KB)

Journal of Dalian Maritime University ›› 2025, Vol. 51 ›› Issue (4) : 58-66.

SANG Peisheng¹, TAN Yanghui^*1, GAO Qiang¹, ZHANG Jundong², GAO Ya¹, ZHANG Yunzhou¹

Author information +

History +

Abstract

Aiming at the problem that traditional ship machinery fault diagnosis methods usually only focus on a single fault scenario and lack the ability to diagnose concurrent faults across domains, an intelligent fault diagnosis framework based on fully connected multilabel domain adaptive neural network (FMANN) was proposed. Firstly, the joint domain adaptation method was introduced to achieve the fault feature transfer under different working conditions, effectively solving the problem of small sample fault diagnosis under target working conditions. Secondly, by introducing a multilabel classification method to capture the complex relationships among different faults, the migration diagnosis of concurrent faults has been achieved. Finally, the performance of several common domain adaptation methods under this framework was compared and analyzed, and the effectiveness and robustness of the proposed framework were verified by using the degradation dataset of a certain ship gas turbine propulsion system.

Key words

ship gas turbine / propulsion system / cross-condition concurrent fault / intelligent fault diagnosis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

SANG Peisheng, TAN Yanghui, GAO Qiang, ZHANG Jundong, GAO Ya , ZHANG Yunzhou. A cross-condition concurrent fault diagnosis framework for the marine gas turbine propulsion system[J]. Journal of Dalian Maritime University. 2025, 51(4): 58-66

References

[1]WANG M Q, CAO H, AI Z, et al. Fault diagnosis of ship ballast water system based on support vector machine optimized by improved sparrow search algorithm[J]. IEEE Access, 2024, 12: 17045-17057.

[2]AI Z R, CAO H, WANG J H, et al. Research method for ship engine fault diagnosis based on multi-head graph attention feature fusion[J]. Applied Sciences, 2023, 13(22): 12421-12441.

[3]戈淳, 闫灶宇, 商嘉桐, 等. 基于多域信息融合与改进ELM的船舶电机轴承故障诊断[J]. 中国舰船研究, 2025, 20(2): 68-76.

GE C, YAN Z Y, SHANG J T, et al. Fault diagnosis of ship motor bearings based on multi-domain information fusion and improved ELM [J]. Chinese Journal of Ship Research, 2025, 20(2): 68-76.(in Chinese)

[4]MA F X, QI L, YE S X, et al. Research on fault diagnosis algorithm of ship electric propulsion motor[J]. Applied Sciences, 2023, 13(6): 4064-4085.

[5]李维波, 高峰, 肖朋, 等. 基于WOA-RF算法的船舶柴发配电系统故障诊断[J]. 中国舰船研究, 2025, 20(2): 77-88.

LI W B, GAO F, XIAO P, et al. Fault diagnosis of ship diesel power distribution system based on WOA-RF algorithm [J]. Chinese Journal of Ship Research, 2025, 20(2): 77-88. (in Chinese)

[6]TAN Y H, ZHANG J D, TIAN H, et al. Multi-label classification for simultaneous fault diagnosis of marine machinery: a comparative study[J]. Ocean Engineering, 2021, 239: 109723.

[7]彭俏, 马杰, 刘明辉, 等. 基于知识矩阵推理的小型模块化反应堆并发故障诊断方法研究 [J]. 核动力工程, 2024, 45(3): 170-173.

PENG Q, MA J, LIU M H, et al. Research on small modular reactor concurrent fault diagnosis method based on knowledge matrix reasoning [J] Nuclear Power Engineering, 2024, 45(3): 170-173. (in Chinese)

[8]YE Q, LIU C H. Simultaneous fault diagnosis based on hierarchical multi-label classification and sparse Bayesian extreme learning machine[J]. Applied Sciences, 2023, 13(4): 2376.

[9]TIAN Y, MENG H, LING Y. Joint learning networks of low-level and high-level features for multi-label ship recognition in complex backgrounds[J]. Applied Intelligence, 2023, 53: 24327-24345.

[10]GUO Y, ZHANG J D. Fault diagnosis of marine diesel engines under partial set and cross working conditions based on transfer learning[J]. Journal of Marine Science Engineering, 2023, 11(8): 1527.

[11]WANG L D, CAO H, CUI Z C, et al. A fault diagnosis method for marine engine cross working conditions based on transfer learning[J]. Journal of Marine Science and Engineering, 2024, 12(2): 270.

[12]肖扬, 王华庆, 李华, 等. 基于精细复合缩放多尺度加权排列熵的跨域故障诊断方法[J]. 机械工程学报, 2025, 61(11): 1-12.

XIAO Y, WANG H Q, LI H, et al. Cross-domain fault diagnosis method based on refined composite zoom multi-scale weighted permutation entropy [J]. Journal of Mechanical Engineering, 2025, 61(11): 1-12. (in Chinese)

[13]CIPOLLINI F, ONETO L, CORADDU A, et al. Condition-based maintenance of naval propulsion systems with supervised data analysis[J]. Ocean Engineering, 2018, 149: 268-278.

[14]CIPOLLINI F, ONETO L, CORADDU A, et al. Condition-based maintenance of naval propulsion systems: data analysis with minimal feedback[J]. Reliability Engineering & System Safety, 2018, 177: 12-23.

[15]CORADDU A, ONETO L, GHIO A, et al. Machine learning approaches for improving condition-based maintenance of naval propulsion plants[J]. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 2014, 230(1): 136-153.

[16]DING Y, MA L, MA J, et al. A generative adversarial network-based intelligent fault diagnosis method for rotating machinery under small sample size conditions[J]. IEEE Access, 2019, 7: 149736-149749.

[17]GRETTON A, BORGWARD K M, RASCH J M, et al. A kernel two-sample test[J]. Journal of Machine Learning Research (JMLR), 2012, 13(25): 723-773.

[18]GONG M M, ZHANG K, LIU T L, et al. Domain adaptation with conditional transferable components[C]//Proceedings of The 33rd International Conference on Machine Learning. New York:JMLR,2016, 48: 2839-2848.

[19]GRETTON A,SRIPERUMBUDUR B, SEJDINOVIC D, et al. Optimal kernel choice for large-scale two-sample tests[J]. Advances in Neural Information Processing Systems, 2012, 25: 1205-1213.

[20]LI F Y, MA X, WANG Y Q. A multi-label method of state partition and fault diagnosis based on binary relevance algorithm[C]//2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS). IEEE,2020: 567-572.