In the practical application of bearing fault diagnosis, the data imbalance problems caused by the lack of available fault data lead to inaccurate diagnosis. The high cost and difficulty of obtaining fault samples has become an obstacle to the development of intelligent diagnosis technology. Aiming at the problem of data imbalance caused by small samples, this paper proposes a data generation method called FEF_WGAN_GP based on Wasserstein generative adversarial networks with gradient penalty (WGAN_GP) and feature Euclidean distance filtering (FEF) theory. Firstly, WGAN_GP is used to obtain signals with similar distribution to the small sample data, which can alleviate the imbalance of the dataset. Then, the FEF method is used to filter the generated data in order to obtain a higher quality of the samples. In the test validation part, not only the used dataset is evaluated to obtain a more reasonable dataset, but also the generated signals are evaluated from multiple perspectives. In addition, this paper evaluates the effects of the number, length and signal-to-noise ratio of the parent data on the quality of the generated signals, as well as the effect of the setting of the threshold of the data filtering method on the accuracy of the classifier. The experimental results indicate that this method performs well in processing unbalance fault data. It has better stability and diagnostic accuracy than the current stable method.
ChengYLinMWuJ, et al. Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowl Based Syst2021; 216(1): 106796.
2.
KongYQinZWangT, et al. An enhanced sparse representation-based intelligent recognition method for planet bearing fault diagnosis in wind turbines. Renew Energy2021; 173: 987–1004.
3.
AinapureALiXSinghJ, et al. Enhancing intelligent cross-domain fault diagnosis performance on rotating machines with noisy health labels. Procedia Manuf2020; 48: 940–946.
4.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
5.
DongYLiYZhengH, et al. A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: solving the small sample problem. ISA Trans2022; 121: 327–348.
6.
YangCZhouKLiuJ.SuperGraph: spatial-temporal graph-based feature extraction for rotating machinery diagnosis. IEEE Trans Ind Electron2022; 69: 4167–4176.
7.
HanHCuiXFanY, et al. Least squares support vector machine (LS-SVM)-based chiller fault diagnosis using fault indicative features. Appl Therm Eng2019; 154: 540–547.
8.
Namigtle-JiménezAEscobar-JiménezRFGómez-AguilarJF, et al. Online ANN-based fault diagnosis implementation using an FPGA: application in the EFI system of a vehicle. ISA Trans2020; 100: 358–372.
9.
LuNXiaoHSunY, et al. A new method for intelligent fault diagnosis of machines based on unsupervised domain adaptation. Neurocomputing2021; 427: 96–109.
10.
JingLZhaoMLiP, et al. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Measurement2017; 111: 1–10.
11.
DengZWangZTangZ, et al. A deep transfer learning method based on stacked autoencoder for cross-domain fault diagnosis. Appl Math Comput2021; 408: 126318.
12.
ZhangYJiJMaB.Fault diagnosis of reciprocating compressor using a novel ensemble empirical mode decomposition-convolutional deep belief network. Measurement2020; 156: 107619.
13.
YaoDLiBLiuH, et al. Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit. Measurement2021; 175: 109166.
14.
XiangSQinYLuoJ, et al. Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction. Reliab Eng Syst Saf2021; 216: 107927.
15.
NiQJiJCFengK.Data-driven prognostic scheme for bearings based on a novel health indicator and gated recurrent unit network. IEEE Trans Ind Inform2023; 19: 1301–1311.
16.
ZhangTChenJLiF, et al. Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Trans2022; 119: 152–171.
17.
WangTWangJWuY, et al. A fault diagnosis model based on weighted extension neural network for turbo-generator sets on small samples with noise. Chin J Aeronaut2020; 33: 2757–2769.
18.
HuKHuangYHuangW, et al. Deep supervised learning using self-adaptive auxiliary loss for COVID-19 diagnosis from imbalanced CT Images. Neurocomputing2021; 458: 232–245.
19.
NieYZamzamASBrandtA.Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks. Sol Energy2021; 224: 341–354.
20.
LiZHuangMLiuG, et al. A hybrid method with dynamic weighted entropy for handling the problem of class imbalance with overlap in credit card fraud detection. Expert Syst Appl2021; 175: 114750.
21.
LiuYZhouYLiuX, et al. Wasserstein GAN-Based small-sample augmentation for New-Generation Artificial Intelligence: a case study of cancer-staging data in Biology. Engineering2019; 5: 156–163.
22.
WangZHuangHWangY.Fault diagnosis of planetary gearbox using multi-criteria feature selection and heterogeneous ensemble learning classification. Measurement2021; 173: 108654.
23.
HouXZhangTJiL, et al. Combating highly imbalanced steganalysis with small training samples using feature selection. J Vis Commun Image Represent2017; 49: 243–256.
24.
GotAMoussaouiAZouacheD.Hybrid filter-wrapper feature selection using whale optimization algorithm: a multi-objective approach. Expert Syst Appl2021; 183: 115312.
25.
AlibeigiMHashemiSHamzehA.DBFS: an effective density based feature selection scheme for small sample size and high dimensional imbalanced data sets. Data Knowl Eng2012; 81-82: 67–103.
26.
KimK.Normalized class coherence change-based k NN for classification of imbalanced data. Pattern Recognition2021; 120: 108126.
27.
ChenRZhuJHuX, et al. Fault diagnosis method of rolling bearing based on multiple classifier ensemble of the weighted and balanced distribution adaptation under limited sample imbalance. ISA Trans2021; 114: 434–443.
28.
DuHZhangYGangK, et al. Online ensemble learning algorithm for imbalanced data stream. Appl Soft Comput2021; 107: 107378.
29.
ZhuHLiuGZhouM, et al. A Noisy-sample-removed under-sampling scheme for imbalanced classification of Public Datasets. IFAC-PapersOnLine2020; 53: 624–629.
30.
RoyACruzRMOSabourinR, et al. A study on combining dynamic selection and data preprocessing for imbalance learning. Neurocomputing2018; 286: 179–192.
31.
GaoXRenBZhangH, et al. An ensemble imbalanced classification method based on model dynamic selection driven by data partition hybrid sampling. Expert Syst Appl2020; 160: 113660.
32.
WeiJHuangHYaoL, et al. New imbalanced bearing fault diagnosis method based on sample-characteristic oversampling TechniquE (SCOTE) and multi-class LS-SVM. Appl Soft Comput2021; 101: 107043.
33.
SoltanzadehPHashemzadehM.RCSMOTE: range-controlled synthetic minority over-sampling technique for handling the class imbalance problem. Inf Sci2021; 542: 92–111.
34.
LiuSJiangHWuZ, et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis. Measurement2021; 168: 108371.
35.
ZhaoYHaoKTangXS, et al. A conditional variational autoencoder based self-transferred algorithm for imbalanced classification. Knowl Based Syst2021; 218: 106756.
36.
ZhangCZhouYChenY, et al. Over-sampling algorithm based on VAE in imbalanced classification. In: LuoMZhangM (ed.) CLOUD 2018: Cloud computing – CLOUD 2018, Springer: Seattle, WA, June 2018, pp.334–344. https://doi.org/10.1007/978-3-319-94295-7_23
37.
LiuJZhangCJiangX.Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet. Mech Syst Signal Process2022; 168: 108664.
38.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial networks. arXiv:1406.2661, 2014.
39.
ShaoSWangPYanR.Generative adversarial networks for data augmentation in machine fault diagnosis. Comput Ind2019; 106: 85–93.
40.
WangYRSunGDJinQ.Imbalanced sample fault diagnosis of rotating machinery using conditional variational auto-encoder generative adversarial network. Appl Soft Comput2020; 92: 106333.
41.
ZareapoorMShamsolmoaliPYangJ.Oversampling adversarial network for Class-imbalanced fault diagnosis. Mech Syst Signal Process2021; 149: 107175.
42.
ArjovskyMChintalaSBottouL, et al. Wasserstein GAN. arXiv:1701.07875, 2017.
43.
GulrajaniIAhmedFArjovskyM, et al. Improved training of Wasserstein GANs, arXiv:1704.00028, 2017.
OdenaADumoulinVOlahC.Deconvolution and checkerboard artifacts. Distill2016; 1(10): e3.
46.
ChenQWeiHRashidM, et al. Kernel extreme learning machine based hierarchical machine learning for multi-type and concurrent fault diagnosis. Measurement2021; 184: 109923.
LiuTChenJDongG, et al. The fault detection and diagnosis in rolling element bearings using frequency band entropy. Proc IMechE, Part C: J Mechanical Engineering Science2013; 227: 87–99.
49.
QiuHLeeJLinJ, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics. J Sound Vib2006; 289: 1066–1090.
50.
YangCMaJWangX, et al. A novel based-performance degradation indicator RUL prediction model and its application in rolling bearing. ISA Trans2022; 121: 349–364.
