Reliable fault detection in train transmission systems is essential for safe and efficient railway operation, yet it is challenged by variable operating conditions and scarce fault samples. To address these issues, a novel unified health domain relation learning (UHDRL) framework is proposed. Specifically, a pseudofault sample library is constructed to generate diverse synthetic fault examples, reducing UHDRL’s reliance on healthy samples. A unified health domain mechanism is designed to map the different operating conditions into a common feature space, thereby reducing distribution shifts caused by operating variations. Additionally, a health relation learning mechanism is proposed to construct feature pairs between healthy representations and pseudo-faults to uncover intrinsic and discriminative attributes of health states. Experiments on three train transmission systems, conducted under both deterministic and non-deterministic operating condition changes, demonstrate that UHDRL is highly adaptable and robust in zero-fault-sample settings, improving detection accuracy by over 12% compared with existing methods.
DingAQinYWangB, et al. Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systems. Mech Syst Signal Pr2024; 210: 111175.
2.
SongEZZhuRJYaoC, et al. Generalized zero-shot bearing compound fault diagnosis based on reserved gate pre-classifier and physical information semantics. Struct Health Monit. Epub ahead of print 10June2025. DOI: 10.1177/14759217251338329.
3.
WangHBYanCFZhaoYJ, et al. SEACKgram: a targeted method of optimal demodulation-band selection for compound faults diagnosis of rolling bearing. Struct Health Monit2025; 24(1): 223–242.
4.
LiYMengXYXuFY, et al. Intelligent fault diagnosis of hoisting systems under complex working conditions using deep graph convolutional generative adversarial networks with limited data. Struct Health Monit2025; 24(6): 3770–3791.
5.
RanGSLiXYLiM, et al. FD-Zero framework: LLM-based diagnosis framework for zero-shot mechanical time-domain signals. Struct Health Monit. Epub ahead of print 9September2025. DOI: 10.1177/14759217251366940.
6.
YeZZWuJHeXS, et al. Source-free domain adaptation framework for rotating machinery fault diagnosis by reliable self-learning and auxiliary contrastive learning. Reliab Eng Syst Safe2025; 262: 111228.
7.
KumarAParkashCXiangJW.A robust entropy-based sparsity measure for health monitoring of rotating machinery. Struct Health Monit. Epub ahead of print 10August2025. DOI: 10.1177/14759217251346390.
8.
KumarAWylomanskaAZimrozR, et al. Critical challenges and advances in vibration signal processing for non-stationary condition monitoring. Adv Eng Inform2025; 65: 103290.
9.
ZhaoJYHeDQJinZZ, et al. A new method for bearing remaining useful life prediction based on dynamic wavelet and physical information constraints. Expert Syst Appl2026; 296: 129023.
10.
ChenZYWuKWuJ, et al. Residual shrinkage transformer relation network for intelligent fault detection of industrial robot with zero-fault samples. Knowl Based Syst2023; 268: 110452.
11.
MaoZHWangHJiangB, et al. Graph convolutional neural network for intelligent fault diagnosis of machines via knowledge graph. IEEE T Ind Inform2024; 20(5): 7862–7870.
12.
ChenZYHuangHZDengZW, et al. Shrinkage mamba relation network with out-of-distribution data augmentation for rotating machinery fault detection and localization under zero-faulty data. Mech Syst Signal Pr2025; 224: 112145.
13.
KumarAXiangJW.Robust adaptive ridge detection for frequency tracking in heavy-noise environment. Adv Eng Inform2025; 68: 103774.
14.
ZhangQLiSCChin-HonT, et al. Fault impulse inference and cyclostationary approximation: a feature-interpretable intelligent fault detection method for few-shot unsupervised domain adaptation. Reliab Eng Syst Safe2025; 253: 110568.
15.
WangHWangSHYangRG, et al. An optimized dynamic model improved deep discriminative transfer learning network for fault detection in rotation vector reducers. Reliab Eng Syst Safe2024; 251: 110331.
16.
LuNHuHYYinT, et al. Transfer relation network for fault diagnosis of rotating machinery with small data. IEEE T Cybernetics2022; 52(11): 11927–11941.
17.
LuoJJShaoHDLinJ, et al. Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speeds. Reliab Eng Syst Safe2024; 245: 110001.
18.
ChenXRLiXYuSP, et al. Dynamic vision enabled contactless cross-domain machine fault diagnosis with neuromorphic computing. IEEE -CAA J Automatic2024; 11(3): 788–790.
19.
ZhangYCDingJLLiYB, et al. Multi-modal data cross-domain fusion network for gearbox fault diagnosis under variable operating conditions. Eng Appl Arti Intell2024; 133: 108236.
20.
GuoLLeiYGXingSB, et al. Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Ind Electron2019; 66(9): 7316–7325.
21.
HeCShiHMLiuXR, et al. Interpretable physics-informed domain adaptation paradigm for cross-machine transfer diagnosis. Knowl Based Syst2024; 288: 111499.
22.
SunSLWangTYYangHX, et al. An environmentally adaptive and contrastive representation learning method for condition monitoring of industrial assets. IEEE T Cybernetics2024; 54(3): 1484–1496.
23.
ZhouHXLeiZHZioE, et al. Conditional feature disentanglement learning for anomaly detection in machines operating under time-varying conditions. Mech Syst Signal Pr2023; 191: 110139.
24.
HuCYWuJYSunC, et al. Mutual information-based feature disentangled network for anomaly detection under variable working conditions. Mech Syst Signal Pr2023; 204: 110804.
25.
WuJYHuCYSunC, et al. Helicopter transmission system anomaly detection in variable flight regimes with decoupling variational autoencoder. Aerosp Sci Technol2024; 144: 108764.
26.
GaninYUstinovaEAjakanH, et al. Domain-adversarial training of neural networks. J Mach Learn Res2016; 17: 1–35.
27.
ZhangXLWangYQWeiSQ, et al. Multi-scale deep residual shrinkage networks with a hybrid attention mechanism for rolling bearing fault diagnosis. J Instrum2024; 19(5): P05015.
LessmeierCKimothoJKZimmerD, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. PHM Soc Euro Conf2016; 3: 1577.
30.
ZhuYCZhuangFZWangJD, et al. Deep subdomain adaptation network for image classification. IEEE T Neur Net Lear2021; 32(4): 1713–1722.
31.
ChenSMYuJBWangSJ.One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes. J Process Contr2020; 87: 54–67.
32.
ZhangZDengXG.Anomaly detection using improved deep SVDD model with data structure preservation. Pattern Recogn Lett2021; 148: 1–6.
