Citation: | Peiqi WANG, Changqing SHEN, Bojian CHEN, Juanjuan SHI, Weiguo HUANG, Zhongkui ZHU. Generic meta-transfer learning model with special neuronal processing parameters for few-shot fault bearing diagnosis[J]. Journal of Advanced Manufacturing Science and Technology , 2023, 3(3): 2023007. doi: 10.51393/j.jamst.2023007 |
The society is now in the data-rich environment, and deep learning is widely used in bearing fault diagnostic technology due to the advancement of information technology. These methods typically need a large amount of data to support. However, in some practical cases, only few of samples are frequently available when a fault occurs rather than adequate data to be analyzed. This situation indicates that bearing fault diagnostic problems are frequently fewshot problems. In this work, a generic meta-transfer learning model with special neuronal processing parameters (MSNPP) is proposed. MSNPP avoids the issue of overfitting commonly encountered in traditional meta-learning approaches when solving few-shot problems and maintains excellent performance when extracting features with deep networks. Moreover, MSNPP discovers the connection between different tasks by analyzing a few samples and quickly adapts to new tasks. In MSNPP, a technique known as neuron transfer (NT) is used to manipulate neurons by scaling and shifting them. The scaling and shifting parameters are used as meta-learning hyperparameters to transfer within different tasks, which is the work of NT. Experimental result shows that MSNPP prevents the issue of overfitting in conventional meta-learning approaches and achieves satisfactory accuracy and robustness when solving few-shot problems in fault diagnosis.
[1] |
. Liu D, Shi J, Liao ZR, et al. Prognostics and health management for electromechanical system: A review. Journal of Advanced Manufacturing Science and Technology 2022; 2(4): 2022015.
|
[2] |
. Zhou T, Hu MH, He Y, et al. Vibration features of rotor unbalance and rub-impact compound fault. Journal of Advanced Manufacturing Science and Technology 2022; 2(1): 2022002.
|
[3] |
. Hou JJ, Ma B, Liang LB, et al. An early warning method for mechanical fault detection based on adversarial auto-encoders. Journal of Advanced Manufacturing Science and Technology 2022; 2(2): 2022006.
|
[4] |
. Yang B, Lei YG, Li X, et al. Deep targeted transfer learning along designable adaptation trajectory for fault diagnosis across different machines. IEEE Transactions on Industrial Electronics 2023; 70(9): 9463-9473.
|
[5] |
. Shi HT, Shang YJ. Initial fault diagnosis of rolling bearing based on second-order cyclic autocorrelation and DCAE combined with transfer learning. IEEE Transactions on Instrumentation and Measurement 2021; 71: 1-18.
|
[6] |
. Zhang XY, Chen G, Hao TF, et al. Rolling bearing fault convolutional neural network diagnosis method based on casing signal. Journal of Mechanical Science and Technology 2020; 34(6): 2307-2316.
|
[7] |
. Manjit K, Dilbag S. Fusion of medical images using deep belief networks. Cluster Computing 2020; 23: 1439–1453.
|
[8] |
. Li SM, Xin Y, Li XQ, et al. A review on the signal processing methods of rotating machinery fault diagnosis. 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC); 2019 May 24-26; Chongqing, China; 2019. p. 1559-1565.
|
[9] |
. Zhao Z, Li TF, Wu JY, et al. Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study. ISA Trans 2020; 107: 224–255.
|
[10] |
. Vinyals O, Blundell C, Lillicrap T, et al. Matching networks for one shot learning. NIPS 2016: Neural Information Processing Systems 29; 2016 Dec 5-10; Barcelona, Spain; 2016. p. 29.
|
[11] |
. Chen ZY, Wang YH, Wu, J, et al. Wide residual relation network-based intelligent fault diagnosis of rotating machines with small samples. Sensors 2022; 22(11): 4161.
|
[12] |
. Finn C, Abbeel P, Levine S. Model-agnostic metalearning for fast adaptation of deep networks. PMLR 2017: Proceedings of the 34th International Conference on Machine Learning; 2017 Jul 7-10; Amsterdam, Netherlands; 2017. p. 1126-1135.
|
[13] |
. Fu QM, Wang ZC, Fang NG, et al. MAML2: meta reinforcement learning via meta-learning for task categories. Frontiers of Computer Science 2023; 17: 174325.
|
[14] |
. Feng Y, Chen JL, Xie JS, et al. Meta-learning as a promising approach for few-shot cross-domain fault diagnosis: Algorithms, applications, and prospects. Knowledge-Based Systems 2022; 235: 107646.
|
[15] |
. Wang YQ, Yao QM, Kwok JT, et al. Generalizing from a Few Examples: A Survey on Few-shot Learning. ACM Computing Surveys 2021; 53(3): 1- 34.
|
[16] |
. Wang D, Zhang M, Xu YC, et al. Metric-based meta-learning model for few-shot fault diagnosis under multiple limited data conditions. Mechanical Systems and Signal Processing 2021; 155: 107510.
|
[17] |
. Zhang TC, Chen JL, Li FD, et al. Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions. ISA Transactions 2022; 119: 152-171.
|
[18] |
. Sun QR, Liu YY, Chua TS, et al. Meta-transfer learning for few-shot learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2019 Jun 15-20; Longbeach, CA, USA; 2019. p. 403-412.
|
[19] |
. Wu JY, Zhao ZB, Sun C, et al. Few-shot transfer learning for intelligent fault diagnosis of machine. Measurement 2020; 166: 108202.
|
[20] |
. Feng Y, Chen JL, Zhang TC, et al. Semi-supervised meta-learning networks with squeeze-andexcitation attention for few-shot fault diagnosis. ISA Transactions 2022; 120: 383-401.
|
[21] |
. Chen JJ, Hu WH, Cao D, et al. A Meta-learning method for electric machine bearing fault diagnosis under varying working conditions with limited data. IEEE Transactions on Industrial Informatics 2023; 19(3): 2552-2564.
|
[22] |
. Hu XJ, Ding XX, Bai DP. A compressed modelagnostic meta-learning model based on pruning for disease diagnosis. Journal of Circuits, Systems and Computers 2022; 32(2): 2350022.
|
[23] |
. Li CAJ, Li SB, Zhang AS, et al. Meta-learning for few-shot bearing fault diagnosis under complex working conditions. Neurocomputing 2021; 439: 197-211.
|