Abstract
Deep learning methods have demonstrated promising performance in fault diagnosis tasks. Although the scarcity of data in industrial scenarios limits the practical application of such methods, transfer learning effectively tackles this issue through cross-machine knowledge transfer. Nevertheless, the cross-machine few-shot problem, which is a more general industrial scenario, has been rarely investigated. Existing studies have not considered the cross-machine domain shift problem, which results in poor testing performance. This paper proposes an augmentation-based discriminative meta-learning method to address this issue. In the meta-training process, signal transformation is proposed to increase the meta-task diversity for more robust feature learning, and multi-scale learning is combined for more adaptive feature embedding. In the meta-testing process, limited labeled fault information is used to promote model generalization in the target domain through quasi-meta-training based on data augmentation. Furthermore, a novel hyperbolic prototypical loss is proposed for more discriminative feature representation and separable category prototypes by designing a hyperbolic decision boundary. Cross-machine few-shot diagnosis experiments were conducted using three datasets from different machines, namely, the bearing, motor, and gear datasets. The effectiveness of the proposed method was verified through ablation and comparison studies.
References
Zhou H, Huang X, Wen G, et al. Convolution enabled transformer via random contrastive regularization for rotating machinery diagnosis under time-varying working conditions. Mech Syst Signal Process, 2022, 173: 109050
Yang C, Zhou K, Liu J. SuperGraph: Spatial-temporal graph-based feature extraction for rotating machinery diagnosis. IEEE Trans Ind Electron, 2022, 69: 4167–4176
Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap. Mech Syst Signal Process, 2020, 138: 106587
Jin Y R, Qin C J, Zhang Z N, et al. A multi-scale convolutional neural network for bearing compound fault diagnosis under various noise conditions. Sci China Tech Sci, 2022, 65: 2551–2563
Wang L, Liu Z, Cao H, et al. Subband averaging kurtogram with dual-tree complex wavelet packet transform for rotating machinery fault diagnosis. Mech Syst Signal Process, 2020, 142: 106755
Huang H R, Li K, Su W S, et al. An improved empirical wavelet transform method for rolling bearing fault diagnosis. Sci China Tech Sci, 2020, 63: 2231–2240
Wang J, Du G, Zhu Z, et al. Fault diagnosis of rotating machines based on the EMD manifold. Mech Syst Signal Process, 2020, 135: 106443
Xu L, Pennacchi P, Chatterton S. A new method for the estimation of bearing health state and remaining useful life based on the moving average cross-correlation of power spectral density. Mech Syst Signal Process, 2020, 139: 106617
Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring. Mech Syst Signal Process, 2019, 115: 213–237
Zhao B, Zhang X, Zhan Z, et al. Deep multi-scale separable convolutional network with triple attention mechanism: A novel multi-task domain adaptation method for intelligent fault diagnosis. Expert Syst Appl, 2021, 182: 115087
Zhang W, Peng G L, Li C H, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors, 2017, 17: 425
Jimenez-Guarneros M, Morales-Perez C, Rangel-Magdaleno J J. Diagnostic of combined mechanical and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN. IEEE Trans Ind Inf, 2022, 18: 4688–4697
Chao Q, Gao H H, Tao J F, et al. Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals. Sci China Tech Sci, 2022, 65: 470–480
Zhang W, Li C H, Peng G L, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mech Syst Signal Proc, 2018, 100: 439–453
Jiang G, He H, Yan J, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Trans Ind Electron, 2019, 66: 3196–3207
Xing S, Lei Y, Yang B, et al. Adaptive knowledge transfer by continual weighted updating of filter kernels for few-shot fault diagnosis of machines. IEEE Trans Ind Electron, 2022, 69: 1968–1976
Li W, Huang R, Li J, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges. Mech Syst Signal Process, 2022, 167: 108487
Yan R, Shen F, Sun C, et al. Knowledge transfer for rotary machine fault diagnosis. IEEE Sens J, 2020, 20: 8374–8393
Di Z Y, Shao H D, Xiang J W. Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions. Sci China Tech Sci, 2021, 64: 481–492
Guo L, Lei Y, Xing S, et al. Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Ind Electron, 2019, 66: 7316–7325
Zhu J, Chen N, Shen C. A new multiple source domain adaptation fault diagnosis method between different rotating machines. IEEE Trans Ind Inf, 2021, 17: 4788–4797
Yu Y, Guo L, Tan Y, et al. Multisource partial transfer network for machinery fault diagnostics. IEEE Trans Ind Electron, 2022, 69: 10585–10594
Deng Y, Huang D, Du S, et al. A double-layer attention based adversarial network for partial transfer learning in machinery fault diagnosis. Comput Industry, 2021, 127: 103399
Wu J, Zhao Z, Sun C, et al. Few-shot transfer learning for intelligent fault diagnosis of machine. Measurement, 2020, 166: 108202
Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the International Conference on Machine Learning (ICML). Sydney, 2017
Hu Y, Liu R, Li X, et al. Task-sequencing meta learning for intelligent few-shot fault diagnosis with limited data. IEEE Trans Ind Inf, 2022, 18: 3894–3904
Wang D, Zhang M, Xu Y C, et al. Metric-based meta-learning model for few-shot fault diagnosis under multiple limited data conditions. Mech Syst Signal Proc, 2021, 155: 107510
Feng Y, Chen J, Zhang T, et al. Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis. ISA Trans, 2022, 120: 383–401
Xu J, Shi Y, Yuan X, et al. Cross-category mechanical fault diagnosis based on deep few-shot learning. IEEE Sens J, 2021, 21: 27698–27709
Luo M, Xu J, Fan Y, et al. TRNet: A cross-component few-shot mechanical fault diagnosis. IEEE Trans Ind Inf, 2023, 19: 6883–6894
Vinyals O, Blundell C, Lillicrap T P, et al. Matching networks for one shot learning. In: Proceedings of the Advances in Neural Information Processing Systems. Barcelona, 2016
Tseng H Y, Lee H Y, Huang J B, et al. Cross-domain few-shot classification via learned feature-wise transformation. arXiv: 2001.08735
Hu S X, Li D, Stuhmer J, et al. Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference. In: Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, 2022. 9058–9067
Yu S, Wang M, Pang S, et al. TDMSAE: A transferable decoupling multi-scale autoencoder for mechanical fault diagnosis. Mech Syst Signal Process, 2023, 185: 109789
Peng D, Wang H, Liu Z, et al. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition. IEEE Trans Ind Inf, 2020, 16: 4949–4960
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016. 770–778
Bai S J, Zico Kolter J, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv: 1803.01271
Wang B, Lei Y, Li N, et al. Multiscale convolutional attention network for predicting remaining useful life of machinery. IEEE Trans Ind Electron, 2021, 68: 7496–7504
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning (ICML). Lille, 2015. PMLR 448–456
Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning. In: Guyon I, Luxburg U V, Bengio S, et al, eds. Advances in Neural Information Processing Systems. Curran Associates, Inc. Long Beach, 2017
Case western reserve university bearing data center. http://csegroups.case.edu/bearingdatacenter/home
Pandhare V, Li X, Miller M, et al. Intelligent diagnostics for ball screw fault through indirect sensing using deep domain adaptation. IEEE Trans Instrum Meas, 2021, 70: 1–11
Qin C, Jin Y, Zhang Z, et al. Anti-noise diesel engine misfire diagnosis using a multi-scale CNN-LSTM neural network with denoising module. CAAI Trans Intel Tech, 2023, doi: I10.1049/cit2.12170
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the National Natural Science Foundation of China (Grant No. 51975356), and Shanghai Municipal Science and Technology Major Project (Grant No. 2021SHZDZX0102).
Rights and permissions
About this article
Cite this article
Xia, P., Huang, Y., Wang, Y. et al. Augmentation-based discriminative meta-learning for cross-machine few-shot fault diagnosis. Sci. China Technol. Sci. 66, 1698–1716 (2023). https://doi.org/10.1007/s11431-022-2380-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-022-2380-0