Intelligent fault diagnosis methods are indispensable for ensuring the reliable operation of industrial equipment. Currently, the growing complexity of intelligent fault diagnostic methods has substantially increased the demand for training data. However, collecting and labeling data from industrial equipment is both time-consuming and costly, leading to challenges associated with small-sample conditions. This limitation poses a significant hurdle to the development of data-driven intelligent fault diagnosis methods. Inspired by the pre-training and fine-tuning paradigms used in large language models, this study proposes a novel generative adversarial fine-tuning (GAFT) framework for bearing fault diagnosis under small-sample conditions. The framework combines generative adversarial network (GAN)-TrAdaBoost and low-rank adaptation (LoRA) fine-tuning to improve data efficiency. GAN-TrAdaBoost employs synthetic data generated through GAN-based data augmentation to provide robust synthetic data support for the pre-trained model. These synthetic data are then fed into the diagnostic model, where TrAdaBoost dynamically adjusts the weights of synthetic data with varying fidelity. Following this, the diagnostic model undergoes fine-tuning using LoRA, which parameterizes weight updates through low-rank decomposition to reduce the ratio of trainable parameters. Comprehensive experiments on two rotational machinery datasets demonstrate that the proposed GAFT consistently outperforms state-of-the-art methods in both diagnostic accuracy and data efficiency. Through the provision of high-fidelity training data and the refinement of model architecture and fine-tuning techniques, this method delivers a scalable and effective framework for intelligent fault diagnosis in bearing systems.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
2.
LiuHYuanRLvY, et al. Multivariate phase space warping-based degradation tracking and remaining useful life prediction of rolling bearings. IEEE Trans Reliab2024; 73(3): 1592–1605.
3.
LiuHYuanRLvY, et al. Remaining useful life prediction of rolling bearings based on segmented relative phase space warping and particle filter. IEEE Trans Instrum Meas2022; 71: 1–15.
4.
LiWHuangRLiJ, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Signal Process2022; 167: 108487.
5.
LiuGShenWGaoL, et al. Knowledge transfer in fault diagnosis of rotary machines. IET Collaborat Intell Manuf2022; 4(1): 17–34.
6.
LiuHYuanRLvY, et al. Degradation tracking of rolling bearings based on local polynomial phase space warping. IEEE Trans Reliab2023; 73(2): 1380–1392.
7.
DongZJiangYJiaoW, et al. Double attention-guided tree-inspired grade decision network: a method for bearing fault diagnosis of unbalanced samples under strong noise conditions. Adv Eng Inform2025; 64: 103004.
8.
XiaoDHuangYQinC, et al. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis. Proc Inst Mech Eng C J Mech Eng Sci2019; 233(14): 5131–5143.
9.
HuXCaoYSunY, et al. Railway automatic switch stationary contacts wear detection under few-shot occasions. IEEE Trans Intell Transp Syst2021; 23(9): 14893–14907.
10.
RileyRDDebrayTPCollinsGS, et al. Minimum sample size for external validation of a clinical prediction model with a binary outcome. Stat Med2021; 40(19): 4230–4251.
11.
LiXHuYLiM, et al. Fault diagnostics between different type of components: a transfer learning approach. Appl Soft Comput2020; 86: 105950.
12.
YosinskiJCluneJBengioY, et al. How transferable are features in deep neural networks?Adv Neural Inform Process Syst2014; 27: 3320–3328.
13.
LongMCaoYWangJ, et al. Learning transferable features with deep adaptation networks. In: International conference on machine learning. PMLR, 2015, pp. 97–105.
14.
ZhangWLiX.Federated transfer learning for intelligent fault diagnostics using deep adversarial networks with data privacy. IEEE/ASME Trans Mechatron2021; 27(1): 430–439.
15.
LiangYWangYLiW, et al. Adaptive fault diagnosis of machining processes enabled by hybrid deep learning and incremental transfer learning. Comput Ind2025; 167: 104262.
16.
LinCKongYHanQ, et al. An information fusion-based meta transfer learning method for few-shot fault diagnosis under varying operating conditions. Mech Syst Signal Process2024; 220: 111652.
17.
ChenXLiuTFournier-VigerP, et al. A fine-grained self-adapting prompt learning approach for few-shot learning with pre-trained language models. Knowl Based Syst2024; 299: 111968.
18.
LiCZhangSQinY, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing2020; 407: 121–135.
19.
DingNQinYYangG, et al. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nat Mach Intell2023; 5(3): 220–235.
20.
TajbakhshNShinJYGuruduSR, et al. Convolutional neural networks for medical image analysis: full training or fine tuning?IEEE Trans Med Imaging2016; 35(5): 1299–1312.
21.
RadfordAWuJChildR, et al. Language models are unsupervised multitask learners. OpenAI Blog2019; 1(8): 9.
22.
ShaoSMcAleerSYanR, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform2018; 15(4): 2446–2455.
23.
ZhongHLvYYuanR, et al. Bearing fault diagnosis using transfer learning and self-attention ensemble lightweight convolutional neural network. Neurocomputing2022; 501: 765–777.
24.
XiaMShaoHWilliamsD, et al. Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliab Eng System Saf2021; 215: 107938.
25.
ZophBGhiasiGLinTY, et al. Rethinking pre-training and self-training. Adv Neural Inform Process Syst2020; 33: 3833–3845.
26.
LiZRenKJiangX, et al. Domain generalization using pretrained models without fine-tuning. arXiv preprint arXiv:2203.04600, 2022.
27.
ZhengHShenLTangA, et al. Learn from model beyond fine-tuning: a survey. arXiv preprint arXiv:2310.08184, 2023.
28.
LiYSongYJiaL, et al. Intelligent fault diagnosis by fusing domain adversarial training and maximum mean discrepancy via ensemble learning. IEEE Trans Ind Inform2020; 17(4): 2833–2841.
29.
ZhouFYangSFujitaH, et al. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowl Based Syst2020; 187: 104837.
30.
NeupaneDSeokJ.Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: a review. IEEE Access2020; 8: 93155–93178.
31.
GaoXDengFYueX.Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty. Neurocomputing2020; 396: 487–494.
32.
YangJLiuJXieJ, et al. Conditional GAN and 2-D CNN for bearing fault diagnosis with small samples. IEEE Trans Instrum Meas2021; 70: 1–12.
33.
LuDWengQ.A survey of image classification methods and techniques for improving classification performance. Int J Remote Sens2007; 28(5): 823–870.
34.
WeiDLiuKWangJ, et al. ResNet-18-based interturn short-circuit fault diagnosis of PMSMs with consideration of speed and current loop bandwidths. IEEE Trans Transp Electr2023; 10(3): 5805–5818.
35.
YuWLvP.An end-to-end intelligent fault diagnosis application for rolling bearing based on MobileNet. IEEE Access2021; 9: 41925–41933.
36.
HuBTangJWuJ, et al. An attention EfficientNet-based strategy for bearing fault diagnosis under strong noise. Sensors2022; 22(17): 6570.
37.
AmarnathMSugumaranVKumarH.Exploiting sound signals for fault diagnosis of bearings using decision tree. Measurement2013; 46(3): 1250–1256.
38.
YanXJiaM.A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing. Neurocomputing2018; 313: 47–64.
39.
WangZZhangQXiongJ, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests. IEEE Sens J2017; 17(17): 5581–5588.
40.
NiuJPanJQinZ, et al. Small-sample bearings fault diagnosis based on ResNet18 with pre-trained and fine-tuned method. Appl Sci2024; 14(12): 5360.
41.
LiuWXuZWangJ, et al. Efficient fine-tuned preventive monitoring models of bearing failures without prior on-site fault data. Measurement2025; 242: 116067.
42.
ChenJYanZLinC, et al. Aero-engine high speed bearing fault diagnosis for data imbalance: a sample enhanced diagnostic method based on pre-training WGAN-GP. Measurement2023; 213: 112709.
43.
ZhangQHeQQinJ, et al. Application of fault diagnosis method combining finite element method and transfer learning for insufficient turbine rotor fault samples. Entropy2023; 25(3): 414.
44.
VrbančičGPodgorelecV.Transfer learning with adaptive fine-tuning. IEEE Access2020; 8: 196197–196211.
45.
LvKYangYLiuT, et al. Full parameter fine-tuning for large language models with limited resources. arXiv preprint arXiv:2306.09782, 2023.
46.
LiXLLiangP.Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190, 2021.
47.
DixitSVermaNKGhoshAK.Intelligent fault diagnosis of rotary machines: Conditional auxiliary classifier GAN coupled with meta learning using limited data. IEEE Trans Instrum Meas2021; 70: 1–11.
48.
SongXLiuZWangZ.Rolling bearing fault diagnosis in electric motors based on IDIG-GAN under small sample conditions. Meas Sci Technol2024; 35(10): 106105.
49.
ZhangTChenJXieJ, et al. SASLN: signals augmented self-taught learning networks for mechanical fault diagnosis under small sample condition. IEEE Trans Instrum Meas2020; 70: 1–11.
50.
WangHLiPLangX, et al. FTGAN: a novel GAN-based data augmentation method coupled time–frequency domain for imbalanced bearing fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1–14.
