Deep learning-based fault diagnosis methods have achieved significant results. However, under actual working conditions, the inability of equipment to operate for long periods in a fault state results in a much smaller amount of collected fault data compared to normal data. This leads to existing fault diagnosis models being able to learn only limited diagnostic knowledge, causing a substantial decline in diagnostic accuracy. Therefore, a dilated dynamic supervised contrast learning framework for imbalanced data scenarios is proposed. In this framework, a dilated convolution network is designed as a feature extractor to enhance the feature extraction ability by changing the dilation rate. Then, the dynamic supervision loss function is designed, and the sample compensation factor of each category is given according to the frequency of sample used in the training process to enhance the contribution of the minority class and optimize the feature extractor. Finally, a dynamic cross-entropy loss function is designed to train the network and classifier to achieve accurate classification of faults. Experiments on two open-source datasets show the effectiveness of the proposed model framework.
GuXYuYGuoL, et al. CSWGAN-GP: a new method for bearing fault diagnosis under imbalanced condition. Measurement2023; 217: 113014.
2.
ShiMDingCWangR, et al. Graph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery. Reliab Eng Sys Saf2023; 240: 109601.
3.
FengK.Vibration based gear wear monitoring and prediction. UNSW Sydney, 2021.
4.
AnZWangHYanY, et al. Contrast learning with hard example mining for few-shot fault diagnosis of rolling bearings. Measur Sci Technol2024; 35(10): 106121.
5.
WangXJiangHMuM, et al. A trackable multi-domain collaborative generative adversarial network for rotating machinery fault diagnosis. Mech Sys Sig Process2025; 224: 111950.
6.
FengKJiJ CZhangY, et al. Digital twin-driven intelligent assessment of gear surface degradation. Mech Sys Sig Process2023; 186: 109896.
7.
QinYLiCCaoF, et al. A fault dynamic model of high-speed angular contact ball bearings. Mech Mach Theory2020; 143: 103627.
8.
ChengJYangYLiX, et al. Adaptive periodic mode decomposition and its application in rolling bearing fault diagnosis. Mech Sys Sig Process2021; 161: 107943.
9.
ZhangYGaoLWenX, et al. Intelligent fault diagnosis of machine under noisy environment using ensemble orthogonal contractive auto-encoder. Expert Sys Appl2022; 203: 117408.
10.
ChenMShaoHDouH, et al. Data augmentation and intelligent fault diagnosis of planetary gearbox using ILoFGAN under extremely limited samples. IEEE Transact Reliab2022; 72(3): 1029–1037.
11.
LiSPengYShenY, et al. Rolling bearing fault diagnosis under data imbalance and variable speed based on adaptive clustering weighted oversampling. Reliab Eng Sys Saf2024; 244: 109938.
12.
WeiJHuangHYaoL, et al. New imbalanced bearing fault diagnosis method based on Sample-characteristic Oversampling TechniquE (SCOTE) and multi-class LS-SVM. Appl Soft Comp2021; 101: 107043.
13.
LiuBTsoumakasG.Dealing with class imbalance in classifier chains via random undersampling. Knowl Based Sys2020; 192: 105292.
14.
ZhangJZouJSuZ, et al. A class-aware supervised contrastive learning framework for imbalanced fault diagnosis. Knowl Based Sys2022; 252: 109437.
15.
YanKLuCMaX, et al. Intelligent fault diagnosis for air handing units based on improved generative adversarial network and deep reinforcement learning. Exp Sys Appl2024; 240: 122545.
16.
LiJLiuTWuX.Research on bearing vibration signal generation method based on filtering WGAN_GP with small samples. Proceed Instit Mech Eng Part C J Mech Eng Sci2023; 237(20): 4911–4929.
17.
WangXJiangHWuZ, et al. Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis. Adv Eng Inform2023; 56: 102027.
18.
GulrajaniIAhmedFArjovskyM, et al. Improved training of wasserstein gans. Adv Neural Inform Process Sys2017; 30: 45.
19.
FengKXuYWangY, et al. Digital twin enabled domain adversarial graph networks for bearing fault diagnosis. IEEE Transact Ind Cyber-Phys Sys2023.
20.
ZhangTChenJLiF, et al. Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Transact2022; 119: 152–171.
21.
DongYJiangHMuM, et al. Multi-sensor data fusion-enabled lightweight convolutional double regularization contrast transformer for aerospace bearing small samples fault diagnosis. Adv Eng Inform2024; 62: 102573.
22.
XuKLiSJiangX, et al. A renewable fusion fault diagnosis network for the variable speed conditions under unbalanced samples. Neurocomputing2020; 379: 12–29.
23.
HeKFanHWuY, et al. Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020; 4: 9729–9738.
24.
OordALiYVinyalsO.Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
25.
ChaoQLuSLiuC, et al. Unsupervised learning to detect wear faults in axial piston pumps by the similarity of periodic discharge pressure ripples. Proceed Instit Mech Eng Part C J Mech Eng Sci2024; 3: 09544062241253710.
26.
DingYZhuangJDingP, et al. Self-supervised pretraining via contrast learning for intelligent incipient fault detection of bearings. Reliab Eng Sys Saf2022; 218: 108126.
27.
LinZTianCHouY, et al. Improving graph collaborative filtering with neighborhood-enriched contrastive learning. Proceedings of the ACM web conference 2022. 2022; 4: 2320–2329.
28.
YuFKoltunV.Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122, 2015.
29.
ZhengJPanHChengJ.Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines. Mech Sys Sig Process2017; 85: 746–759.
30.
AnZJiangXYangR, et al. Actively imaginative data augmentation for machinery diagnosis under large-speed-fluctuation conditions. IEEE Transact Indust Inform2022; 19(7): 8484–8495.
31.
SunYLiS.Bearing fault diagnosis based on optimal convolution neural network. Measurement2022; 190: 110702.
32.
HeJYinLLiuJ, et al. A fault diagnosis method for unbalanced data based on a deep cost sensitive convolutional neural network. IFAC-PapersOnLine2022; 55(3): 43–48.
33.
TangHLuSQianG, et al. IoT-based signal enhancement and compression method for efficient motor bearing fault diagnosis. IEEE Sens J2020; 21(2): 1820–1828.
34.
Van der MaatenLHintonG. Visualizing data using t-SNE. J Mach Learn Res2008; 9(11): 2579–2605.
35.
HuangHBaddourN.Bearing vibration data collected under time-varying rotational speed conditions. Data Brief2018; 21: 1745–1749.
