Task-sequencing meta learning for intelligent few-shot fault diagnosis with limited data
Abstract
Recently, deep learning-based intelligent fault diagnosis methods have been developed rapidly, which rely on massive data to train the diagnosis model. However, it is usually difficult to collect sufficient failure data in practical industrial production, thus limits the application of intelligent diagnosis methods. To address the few-shot fault diagnosis problem, a task-sequencing meta-learning method is proposed in this article. First, the meta-learning model is trained over a series of learning tasks to obtain knowledge about how to diagnosis. Thus, the learned knowledge can help adapt and generalize with a few examples when dealing with new tasks that have never been encountered. Then, considering the difference and connection between different failures and diagnosis tasks, a task-sequencing algorithm is proposed to sort meta training tasks from easy to difficult, which followed the way human acquire knowledge. After evaluating the difficulty of each task, the proposed method learns simple tasks first and generalizes the learned knowledge to complex tasks. Better knowledge adaptability is obtained by gradually increasing the task difficulty. Finally, utilizing gradient-based meta learning, the initialization parameters are trained by a small number of gradient steps. The effectiveness of the proposed method is validated by a practice rolling bearing dataset and a power system dataset. The experiment results illustrate that the proposed method can identify new categories with only several samples. In addition, it also shows advantages in fault diagnosis when the categories are fine-grained according to the working conditions. Therefore, the proposed method is suitable for solving the few-shot problem in practice and complicated fault diagnosis.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
As evidenced by recent models like 1.6 trillion parameter Switch Transformer and 8x7B parameter Mixtra, MoE-based designs are rapidly redefining frontiers of model scale and performance across diverse language tasks.
“As evidenced by recent models like the 1.6 trillion parameter Switch Transformer [285] and the 8x7B parameter Mixtra [286], MoEbased designs are rapidly redefining the frontiers of model scale and performance across diverse language tasks.”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [286]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · see citing works
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1× · see citing works
“Consideringthehumanlearningprocessgenerally followstheorderfromeasytodifficult,curriculumlearning[34] advocatesthatthemodelshouldstartlearningfromeasysamples and gradually transition to complex samples.”
BackgroundOptimization as a Model for Few-Shot Learning
Ravi, S., & Larochelle, H. (2017) · International Conference on Learning Representations · Cited by 2,766 · see citing works
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
Wang, K., Liew, J. H., Zou, Y., Zhou, D., & Feng, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00929 · Cited by 1,581 · see citing works
Lessmeier, C., Kimotho, J. K., Zimmer, D., & Sextro, W. (2016) · PHM Society European Conference · doi:10.36001/phme.2016.v3i1.1577 · Cited by 1,421 · see citing works
Meta-Transfer Learning for Few-Shot Learning
Sun, Q., Liu, Y., Chua, T., & Schiele, B. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00049 · Cited by 1,366 · see citing works
Rethinking Few-Shot Image Classification: A Good Embedding is All You Need?
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_16 · Cited by 952 · see citing works
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDPreprint
Ge, Y., Zhu, F., Chen, D., Zhao, R., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02713 · Cited by 458 · see citing works
Self-citationLiu, R., Wang, F., Yang, B., & Qin, S. J. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2941868 · Cited by 454 · see citing works
Self-citationLimited Data Rolling Bearing Fault Diagnosis With Few-Shot Learning
Zhang, A., Li, S., Cui, Y., Yang, W., Dong, R., & Hu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2934233 · Cited by 422 · see citing works
Classification of Imbalanced Data by Oversampling in Kernel Space of Support Vector Machines
Mathew, J., Pang, C. K., Luo, M., et al. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2751612 · Cited by 314 · see citing works
MetaGAN: an adversarial approach to few-shot learning
Zhang, R., Che, T., Zoubin Ghahramani, A., Bengio, Y., & Song, Y. (2018) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 311 · see citing works
Few-shot transfer learning for intelligent fault diagnosis of machine
Wu, J., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2020) · Measurement · doi:10.1016/j.measurement.2020.108202 · Cited by 306 · see citing works
Gearbox Fault Diagnosis Using a Deep Learning Model With Limited Data Sample
Saufi, M. S. R. M., Ahmad, Z. A., Leong, M. S., & Lim, M. H. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2967822 · Cited by 275 · see citing works
A novel gas turbine fault diagnosis method based on transfer learning with CNN
Zhong, S., Fu, S., & Lin, L. (2019) · Measurement · doi:10.1016/j.measurement.2019.01.022 · Cited by 273 · see citing works
Metric-based meta-learning model for few-shot fault diagnosis under multiple limited data conditions
Wang, D., Zhang, M., Xu, Y., Lu, W., Yang, J. J., & Zhang, T. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107510 · Cited by 253 · see citing works
Few-Shot Learning via Saliency-Guided Hallucination of Samples
Zhang, H., Zhang, J., & Koniusz, P. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00288 · Cited by 247 · see citing works
He, Z., Shao, H., Wang, P., Lin, J. (., Cheng, J., & Yang, Y. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105313 · Cited by 235 · see citing works
Braun, D. A., Mehring, C., & Wolpert, D. M. (2010) · Behavioural Brain Research · doi:10.1016/j.bbr.2009.08.031 · Cited by 210 · see citing works
Meta-neural networks that learn by learning
Naik, D., & Mammone, R. J. (2003) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1992.287172 · Cited by 191 · see citing works
On the Optimization of a Synaptic Learning Rule
Samy Bengio, A., Bengio, Y., Cloutier, J., & Gescei, J. (2013) · doi:10.4324/9780203773833-22 · Cited by 181 · see citing works
Graph Few-Shot Learning via Knowledge Transfer
Yao, H., Zhang, C., Wei, Y., Jiang, M., Wang, S., Huang, J., Chawla, N. V., & Li, Z. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6142 · Cited by 165 · see citing works
Mechanical fault diagnosis and prediction in IoT based on multi-source sensing data fusion
Huang, M., Liu, Z., & Tao, Y. (2019) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2019.101981 · Cited by 164 · see citing works
Few-Shot Adaptive Faster R-CNN
Wang, T., Zhang, X., Yuan, L., & Feng, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00734 · Cited by 158 · see citing works
Hierarchically Structured Meta-learningPreprint
Yao, H., Wei, Y., Huang, J., & Li, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.05301 · Cited by 154 · see citing works
Martin-Diaz, I., Moríñigo-Sotelo, D., Duque-Pérez, Ó., et al. (2016) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2016.2618756 · Cited by 150 · see citing works
Peng, P., Zhang, W.-J., Zhang, Y., Xu, Y., Wang, H., & Zhang, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.04.075 · Cited by 119 · see citing works
Wang, F., Liu, R., Hu, Q., & Chen, X. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3003353 · Cited by 116 · see citing works
Self-citationZhou, Q., Li, Y., Tian, Y. P., & Jiang, L. (2020) · Measurement · doi:10.1016/j.measurement.2020.107880 · Cited by 98 · see citing works
Xing, S., Lei, Y., Yang, B., & Lü, N. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3063975 · Cited by 81 · see citing works
TaskNorm: Rethinking Batch Normalization for Meta-LearningPreprint
Bronskill, J. F., Gordon, J. A. R., Requeima, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03284 · Cited by 30 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102 · see citing works
“This technique involves mastering the optimization process and is critical in situations with limited data availability, to ensure models can quickly adapt and perform across diverse tasks, essential in the current data-driven landscape [253], [254].”
Background
- Authors
- Hu, Y., Liu, R., Li, X., Chen, D., & Hu, Q.
- Affiliations
- Tianjin University (CN)
- Venue
- IEEE Transactions on Industrial Informatics
- Published
- 2022-06
- Volume
- 18
- Issue
- 6
- Pages
- 3894-3904
- ISSN
- 1551-3203 (ISSN-L)
- 1941-0050
- OpenAlex
- W3200647619
- Cited by
- 180
- References
- 33
- Citations by year
- 2026: 26 · 2025: 42 · 2024: 61 · 2023: 38 · 2022: 12 · 2021: 1
- FWCI
- 12.47
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Informatics (publishedVersion)
- Funders
- National Natural Science Foundation of China (61925602)
- National Science and Technology Major Project (2017-I-0007-0008)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- few-shot learning, meta-learning, task sequencing, fault diagnosis, limited training data, task difficulty estimation, gradient-based meta-learning, rolling bearing fault diagnosis, power system fault diagnosis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
