Few-shot Learning for Plastic Bearing Fault Diagnosis – An Integrated Image Processing and NLP Approach

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 26, 2023
David He Miao

Abstract

Plastic bearings have a wide range of industrial applications due to their many desirable properties such as lightweight, low friction coefficient, chemical resistance, and ability to operate without lubrication. Timely bearing fault diagnosis can prevent equipment failure and costly downtime.  In recent years, developing machine learning based bearing fault diagnosis with few labelled data has attracted a lot of attentions as datasets with fault labels are rare in many industrial applications.  One effective approach to meet the challenge is few-shot learning.  Among many approaches, utilizing a good pre-trained deep learning model to achieve few-shot learning is an effective and efficient alternative.  In this paper, a pre-trained deep learning model called CLIP that combines image processing and natural language processing (NLP) is adopted to few-shot learning for plastic bearing fault diagnosis.  We explore the feasibility of leveraging CLIP model in the realm of bearing fault diagnosis via few-shot learning. Specifically, we tackle the challenges posed by CLIP's creation of requisite text prompt embeddings for the diagnosis of mechanical faults, within a few-shot learning framework. Our investigation illuminates the remarkable capability of CLIP to adapt to new tasks with minimal examples, a feature we exploit to devise a solution for plastic bearing fault diagnosis. The effectiveness of the few-shot learning method with CLIP is demonstrated using vibration data collected from plastic bearing seeded fault tests in the laboratory.

How to Cite

He, D., & He, M. (2023). Few-shot Learning for Plastic Bearing Fault Diagnosis – An Integrated Image Processing and NLP Approach. Annual Conference of the PHM Society, 15(1). https://doi.org/10.36001/phmconf.2023.v15i1.3575
Abstract 166 | PDF Downloads 118

##plugins.themes.bootstrap3.article.details##

Keywords

Plastic bearing, fault diagnosis, CLIP, NLP, Few-shot learning, Transfer leraning

References
Liu, X., Zhang, Y., Liu, Y., Li, H., & Li, Z. (2021). Metalearning as a promising approach for few-shot crossdomain fault diagnosis: Algorithms, applications, and prospects. Neurocomputing, vol. 449, pp. 93-103. https://doi.org/10.1016/j.neucom.2021.05.086.

Yan, Y., Liu, Y., Liu, X., Chen, Y., Peng, Y., & Li, X. (2021). Few-shot learning under domain shift: Attentional contrastive calibrated transformer of time series for fault diagnosis under sharp speed variation. IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp. 2834-2844

Chen, W., (1991). Nonlinear Analysis of Electronic Prognostics. Doctoral dissertation. The Technical University of Napoli, Napoli, Italy.

Feng, Y., Chen, J., Xie, J., Zhang, T., Lv, H., & Pan, T. (2022). Meta-learning as a promising approach for fewshot cross-domain fault diagnosis: Algorithms, applications, and prospects. Knowledge-Based Systems, 237, 107165. https://doi.org/10.1016/j.knosys.2021.107165.

Hu, S. X., Li, D., Stühmer, J., Kim, M., & Hospedales, T. M. (2019). Pushing the limits of simple pipelines for fewshot learning: External data and fine-tuning make a difference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 11803- 11812). doi: 10.1109/CVPR.2019.01206.

Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. OpenAI. Retrieved from https://cdn.openai.com/papers/Learning_Transferable_Visual_Models_From_Natural_Language_Supervision.pdf.

He, D., Li, R., & Zhu, J. (2013). Plastic bearing fault diagnosis based on a two-step data mining approach. IEEE Transactions on Industrial Electronics, vol. 60, pp. 3429 – 3440.
Section
Technical Research Papers