Propulsion shafting is a vital component of the ship power system, and its failure seriously affects navigation safety. Leveraging multi-sensor data for more reliable diagnostics is imperative. Transfer learning techniques have demonstrated considerable benefits in ship fault diagnosis, but in multi-sensor scenarios, extracting domain-invariant and discriminative features remains a challenge. To tackle this issue, this study develops a three-stage adversarial training framework for the first time. The framework effectively fuses the bearing housing vibration response information and shaft displacement information to discriminate the alignment status of the propulsion shafting. One-dimensional signals are transformed into two-dimensional images using the Hilbert symmetrized dot pattern to enhance image textures. The Vision Transformer architecture is employed to ensure the optimal integration of multi-sensor vision information. Subsequently, combining the data distributional discrepancy measurement theory and the pseudo-label strategy, a subdomain matching method is presented based on the progressive training paradigm. Meanwhile, a dynamic pseudo-label rectification strategy is designed to guide the primary network for more precise matching. The experimental results confirm the effectiveness of the proposed framework, which outperforms other leading methods. It offers a scalable solution for the intelligent operation and maintenance of propulsion shafting, with significant engineering application value.
NeupaneDBouadjenekMRDazeleyR, et al. Data-driven machinery fault diagnosis: a comprehensive review. Neurocomputing2025; 627: 129588.
3.
FengWQMousaviZLinJF, et al. Compound damage detection using wavelet transform and deep neural network trained on healthy and single damage states: validation on a laboratory-scale offshore jacket model. Struct Health Monit2025. DOI: 10.1177/14759217251313496.
4.
HasanAAsfihaniTOsenO, et al. Leveraging digital twins for fault diagnosis in autonomous ships. Ocean Eng2024; 292: 116546.
5.
GuYKZengLQiuGQ.Bearing fault diagnosis with varying conditions using angular domain resampling technology, SDP and DCNN. Measurement2020; 156: 107616.
6.
GuoWShiYT.A visual faulty feeder detection method for power distribution network based on spatial image generation and deep learning. IET Gener Transm Distrib2023; 17(24): 5430-5445.
7.
YinWZXiaHHuangXY, et al. A composite fault diagnosis method for nuclear power plant rotor system based on symmetrized dot pattern and residual neural network. Ann Nucl Energy2025; 211: 111029.
8.
ShanSJLiuJBWuSG, et al. A motor bearing fault voiceprint recognition method based on Mel-CNN model. Measurement2023; 207: 112408.
9.
ZhangYCJiJCRenZH, et al. Multi-sensor open-set cross-domain intelligent diagnostics for rotating machinery under variable operating conditions. Mech Syst Signal Process2023; 191: 110172.
10.
LiuDDCuiLLWangG, et al. Interpretable domain adaptation transformer: a transfer learning method for fault diagnosis of rotating machinery. Struct Health Monit2024; 24(2): 1187–1200.
11.
CheCCWangHWXiongML, et al. Few-shot fatigue damage evaluation of aircraft structure using neural augmentation and deep transfer learning. Eng Fail Anal2023; 148: 107185.
12.
ZhangXMMaZMJiangYY.Fault diagnosis of high-speed motorized spindles based on lumped parameter model and enhanced transfer learning. Struct Health Monit2024. DOI: 10.1177/14759217241255285.
13.
GaoDLYangCJTangXY, et al. Fault diagnosis of blast furnace based on incomplete multi-source domain adaptation with feature fusion. Adv Eng Inform2024; 62(D): 102946.
14.
AzamfarMSinghJLiX, et al. Cross-domain gearbox diagnostics under variable working conditions with deep convolutional transfer learning. J Vib Control2021; 27(7–8): 854–864.
15.
ChenGWTangQLiH, et al. Rigid-flexible coupling dynamic-assisted imbalanced fault diagnosis for helicopter tail transmission system. Measurement2025; 242(B): 115934.
16.
LuNCuiZYHuHY, et al. Multi-view and multi-level network for fault diagnosis accommodating feature transferability. Expert Syst Appl2023; 213(B): 119057.
17.
LiuBYanCFHeC, et al. An interpretable physics-informed subdomain moment-enhanced adaptation network for unsupervised transfer fault diagnosis of rolling bearing. Adv Eng Inform2025; 67: 103491.
18.
LiSJiangQBXuYD, et al. Digital twin-assisted interpretable transfer learning: a novel wavelet-based framework for intelligent fault diagnostics from simulated domain to real industrial domain. Adv Eng Inform2024; 62(B): 102681.
19.
MingZTangBPDengL, et al. Digital twin-assisted fault diagnosis framework for rolling bearings under imbalanced data. Appl Soft Comput2024; 168: 112528.
20.
LiuXFJinYYangF, et al. Twin data multimode collaborative transfer learning for bearing failure diagnosis. Eng Appl Artif Intell2024; 137(A): 109142.
21.
WuZHJiangHKLuTF, et al. A deep transfer maximum classifier discrepancy method for rolling bearing fault diagnosis under few labeled data. Knowl Based Syst2020; 196: 105814.
22.
JiaSXWangJRHanBK, et al. A novel transfer learning method for fault diagnosis using maximum classifier discrepancy with marginal probability distribution adaptation. IEEE Access2020; 8: 71475-71485.
23.
LinZHYangZGSituRW, et al. Improving maximum classifier discrepancy by considering joint distribution for domain adaptation. Proc Int Conf Web Inf Syst Eng2018; 11234: 253–268.
24.
HuJYuYHYangJG, et al. Research on the generalisation method of diesel engine exhaust valve leakage fault diagnosis based on acoustic emission. Measurement2023; 210: 112560.
25.
LiuXLLiuFZHanTZ, et al. Novel source domain filtering dual classifier network with adaptive pseudo label refinement for partial domain fault diagnosis. Neurocomputing2025; 620: 129260.
26.
SunYWTaoHFStojanovicV.Pseudo-label guided dual classifier domain adversarial network for unsupervised cross-domain fault diagnosis with small samples. Adv Eng Inform2025; 64: 102986.
27.
XiaMLiTXuL, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Trans Mech2018; 23(1): 101–110.
28.
ChenFZhaoZGHuXX, et al. 2025. A nonlinear dynamics method using multi-sensor signal fusion for fault diagnosis of rotating machinery. Adv Eng Inform2025; 65(B): 103190.
29.
ShaoHDLinJZhangLW, et al. A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance. Inform Fusion2021; 74: 65–76.
30.
DongYTJiangHKWangX, et al. An interpretable integration fusion time-frequency prototype contrastive learning for machine fault diagnosis with limited labeled samples. Inform Fusion2025; 124: 103340.
31.
HasanMJIslamMMKimJM.Multi-sensor fusion-based time-frequency imaging and transfer learning for spherical tank crack diagnosis under variable pressure conditions. Measurement2021; 168: 108478.
32.
LiSFengKXuYD, et al. Cross-modal zero-sample diagnosis framework utilizing non-contact sensing data fusion. Inform Fusion2024; 110: 102453.
33.
WangQBYuLYHaoL, et al. An adaptive transfer fault detection method for rotary machine with multi-sensor information fusion. J Intell Manuf2024; 35(6): 1–16.
34.
LiuZJYangXHXieYC, et al. Multi-sensor cross-domain fault diagnosis method for leakage of ship pipeline valves. Ocean Eng2024; 299: 117211.
35.
LiSJiJFengK, et al. Composite neuro-fuzzy system-guided cross-modal zero-sample diagnostic framework using multisource heterogeneous noncontact sensing data. IEEE Trans Fuzzy Syst2025; 33(1): 302–313.
36.
ShenJXSongDMaTC, et al. Blade crack detection based on domain adaptation and autoencoder of multidimensional vibro-acoustic feature fusion. Struct Health Monit2023; 2(5): 3498–3513.
37.
XuYJWangTZDialloDB, et al. A confidence-guided DS fault diagnosis method for tidal stream turbines blade. Ocean Eng2024; 311(1): 118807.
38.
MaDLiuZHGaoQH, et al. Few-shot fault diagnosis of EHA based on MTF-ResNet-MA and dual-attribute adaptive decision-level fusion. Measurement2025; 247: 116787.
SaitoKWatanabeKUshikuY.Maximum classifier discrepancy for unsupervised domain adaptation. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit2018; 1: 3723–3732.
41.
HuangKRenZJZhuLB, et al. A three-stage bearing transfer fault diagnosis method for large domain shift scenarios. Reliab Eng Syst Saf2025; 254(B): 110641.
42.
MaXJHuangHXWangYS, et al. Normalized loss functions for deep learning with noisy labels. Proc Int Conf Mach Learn2020; 119: 6543–6553.
43.
WangYSMaXJChenZY, et al. Symmetric cross entropy for robust learning with noisy labels. Proc IEEE/CVF Int Conf Comput Vis2019; 1: 322–330.
44.
WangHXuJYanR, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE Trans Instrum Meas2020; 69(5): 2377–2389.
45.
YangFTianXTMaLP, et al. An optimized variational mode decomposition and symmetrized dot pattern image characteristic information fusion-Based enhanced CNN ball screw vibration intelligent fault diagnosis approach. Measurement2024; 229: 114382.
ZhuWYShiBQFengZP.A transfer learning method using high-quality pseudo labels for bearing fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1–11.
48.
RezaeianjouybariBShangY.A novel deep multi-source domain adaptation framework for bearing fault diagnosis based on feature-level and task-specific distribution alignment. Measurement2021; 178: 109359.
49.
LiuYWangYChowTWS, et al. Deep adversarial subdomain adaptation network for intelligent fault diagnosis. IEEE Trans Industr Inform2022; 18(9): 6038–6046.
50.
HanTLiuCYangWG, et al. Deep transfer network with joint distribution adaptation: a new intelligent fault diagnosis framework for industry application. ISA Trans2020; 97: 269–281.
