Journal
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Volume 69, Issue 10, Pages 10573-10584Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2022.3140403
Keywords
Data models; Fault diagnosis; Training; Feature extraction; Knowledge engineering; Monitoring; Representation learning; Few-shot learning; intelligent fault diagnosis; prior knowledge; self-supervised learning
Categories
Funding
- National Natural Science Foundation of China [91960106, 51875436, U1933101]
- China Postdoctoral Science Foundation [2020T130509, 2018M631145]
- Liuzhou Natural Science Foundation [2021AAA0112]
- Fundamental Research Funds for the Central Universities [XZY022020007, XZY022021006]
Ask authors/readers for more resources
Data-driven intelligent diagnosis models aim to extract health information from massive monitoring data, but the limited size of faulty monitoring data in engineering scenarios has made few-shot fault diagnosis an important research point. This study proposes a prior knowledge-augmented self-supervised feature learning framework to reduce the amount of training data required by integrating prior diagnosis knowledge.
Data-driven intelligent diagnosis models expect to mine the health information of machines from massive monitoring data. However, the size of faulty monitoring data collected in engineering scenarios is limited, which leads to few-shot fault diagnosis as a valuable research point. Fortunately, it is possible to reduce the required amount of training data by integrating prior diagnosis knowledge into diagnosis models. Inspired by this, we present a prior knowledge-augmented self-supervised feature learning framework for few-shot fault diagnosis. In the framework, 24 signal feature indicators are built to form prior features set based on existing diagnosis knowledge. Besides, a convolutional autoencoder is used to mine the general features, which are considered to potentially contain fault information that prior features do not possess. We design a self-supervised learning scheme for training the diagnosis model, which enables the model to learn both prior and general features served as proxy labels. As a result, the model is expected to mine richer features from limited monitoring data. The effectiveness of the proposed framework is verified using two mechanical fault simulation experiments. From the angle of prior diagnosis knowledge, the proposed framework provides a new perspective to the problem of few-shot intelligent diagnosis of machines.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available