The intelligent deep learning algorithms have achieved a great success in bearing fault diagnosis. However, most of them rely on data-driven optimization or prior experience without considering physical fault characteristics. Moreover, it requires a large amount of labeled data with expensive computational resources for model training, which is not always available in insufficient training samples. To address these, this article proposes a meta-transfer learning method with nature language supervised pretraining for few-shot fault diagnosis of bearings. First, a physics-guided feature extraction backbone network is designed, which incorporates cepstrum and entropy to leverage periodic features of vibration signals. Furthermore, a meta-transfer learning on scaled sampling layers is achieved under limited training samples. Finally, to overcome the drawback of one-hot encoding for meta-transfer learning, a nature language supervised pretraining is devised to enhance the complex feature representation in the source domain. Several experiments are performed to verify the effectiveness of the proposed method. On the local dataset for meta-learning and meta-test, an accuracy of 95.9% is achieved in the 5-way-5-shot task mode.
FuLZhangPDingM, et al. A novel composite envelope negentropy deconvolution reconstruction method for fault diagnosis. IEEE Trans Instrum Meas2024; 73: 6500814.
2.
FuLMaJLiangZ, et al. Msncog: a lightweight faults diagnosis system based on multiscale transfer model for adaptive infrared perspective. IEEE Trans Instrum Meas2024; 73: 3510411.
3.
RuanDWangJYanJ, et al. CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis. Adv Eng Inform55; 2023: 101877.
4.
ZhangTXuFJiaM.A centrifugal fan blade damage identification method based on the multi-level fusion of vibro-acoustic signals and CNN. Measurement2022; 199: 111475.
5.
MiaoJWangJZhangD, et al. Improved generative adversarial network for rotating component fault diagnosis in scenarios with extremely limited data. IEEE Trans Instrum Meas2022; 71: 106542.
6.
TianYZhaoXHuangW.Meta-learning approaches for learning-to-learn in deep learning: a survey. Neurocomputing2022; 494: 203–223.
7.
NieXXieG.A fault diagnosis framework insensitive to noisy labels based on recurrent neural network. IEEE Sens J2021; 21(3): 2676–2686.
8.
HuangGLiuZMaatenLVD, et al. Densely connected convolutional networks. IEEE Conf Comput Vis Pattern Recognit2017; 1: 2261–2269.
9.
WangTXiaoYLiB, et al. Adaptive diagnosis for transformer with unknown faults based on antenna-augmented rfid sensor and deep learning. IEEE Sens J2023; 23(17): 20423–20436.
10.
DaveVBoradeHAgrawalH, et al. Deep learning-enhanced small-sample bearing fault analysis using q-transform and hog image features in a GRU-XAI framework. Machines2024; 12(6): 373.
11.
GaoDZhuYRenZ, et al. A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity. Knowl Based Syst2021; 231: 107413.
12.
DibajAEttefaghMMHassannejadR, et al. A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults. Exp Syst Appl2021; 167: 114094.
13.
ZhaoXYaoJDengW, et al. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network. IEEE Trans Neural Netw Learn Syst2023; 34(9): 6339–6353.
14.
DingXLinLHeD, et al. A weight multinet architecture for bearing fault classification under complex speed conditions. IEEE Trans Instrum Meas2021; 70: 1–11.
15.
WangGLiuDCuiL.Auto-embedding transformer for interpretable few-shot fault diagnosis of rolling bearings. IEEE Trans Reliab2023; 73: 1270–1279.
16.
FangHDengJBaiY, et al. CLFormer: a lightweight transformer based on convolutional embedding and linear self-attention with strong robustness for bearing fault diagnosis under limited sample conditions. IEEE Trans Instrum Meas2022; 71: 1–8.
17.
FangHDengJChenD, et al. You can get smaller: a lightweight self-activation convolution unit modified by transformer for fault diagnosis. Adv Eng Inform2023; 55: 101890.
18.
BaiYZhouMZhangW, et al. Augmentation pathways network for visual recognition. IEEE Trans Patt Anal Mach Intell2023; 45(8): 10580–10587.
19.
MengZLiQSunD, et al. An intelligent fault diagnosis method of small sample bearing based on improved auxiliary classification generative adversarial network. IEEE Sens J2022; 22(20): 19543–19555.
20.
WangRChenZZhangS, et al. Dual-attention generative adversarial networks for fault diagnosis under the class-imbalanced conditions. IEEE Sens J2022; 22(2): 1474–1485.
21.
ZhangTChenJLiF, et al. A small sample focused intelligent fault diagnosis scheme of machines via multimodules learning with gradient penalized generative adversarial networks. IEEE Trans Ind Electron2021; 68(10): 10130–10141.
22.
WangZWangJWangY.An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition. Neurocomputing2018; 310: 213–222.
23.
AkheniaPBhavsarKPanchalJ, et al. (2022) Fault severity classification of ball bearing using singan and deep convolutional neural network. Proc Inst Mech Eng C J Mech Eng Sci 2022; 236(7): 3864–3877.
24.
YangBLeiYJiaF, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process2019; 122: 692–706.
25.
LuWLiangBChengY, et al. Deep model based domain adaptation for fault diagnosis. IEEE Trans Ind Electron2017; 64(3): 2296–2305.
26.
LiCZhangSQinY, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing2020; 407: 121–135.
27.
GuKZhangYQiaoJ.Ensemble meta-learning for few-shot soot density recognition. IEEE Trans Ind Inform2021; 17(3): 2261–2270.
28.
LiCLiSZhangA, et al. Meta-learning for few-shot bearing fault diagnosis under complex working conditions. Neurocomputing2021; 439: 197–211.
29.
SuHXiangLHuA, et al. A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions. Mech Syst Signal Process2022; 169; 108765.
30.
WangHLiJWuH, et al. Pre-trained language models and their applications. Engineering2023; 25: 51–65.
31.
LiuDBaiLYuT.Generalized few-shot classification with knowledge graph. Neural Process Lett2023; 55(6): 7649–7666.
32.
WuYLiYZhaoT, et al. Improved prototypical network for active few-shot learning. Pattern Recognit Lett2023; 172: 188–194.
33.
GaoCChengGLiT, et al. Self-supervised pre-training for attention-based encoder-decoder ASR model. IEEE-ACM Trans Audio Speech Lang Process2022; 30: 1763–1774.
