期刊
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
卷 68, 期 10, 页码 10087-10096出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2020.3020252
关键词
Forestry; Feature extraction; Fault diagnosis; Machine learning; Circuit faults; Microsoft Windows; Training; Analog circuits; deep forest (DF); diagnosis; failure; fault
资金
- Natural Science Foundation of China [61672430]
- Shaanxi Key Research and Development Program [S2019-YF-ZDCXL-ZDLGY-0227]
- Aeronautical Science Fund [BK1829-02-3009]
- NWPU Basic Research Fund [3102018jcc001]
- Key Research and Development Program of Shaanxi [2019ZDLGY14-02-01]
- Shenzhen Fundamental Research Program [JCYJ20190806152203506]
- Aeronautical Science Foundation of China [ASFC2018ZC53026]
The article discusses the application of deep learning in the field of circuit system fault diagnosis, introducing the limitations of traditional deep learning methods, as well as the advantages of the deep forest model and the proposed improved algorithm NPIDF.
Electronics-rich analog systems are difficult to diagnose owing to their complex working mechanisms and the variability of the working environment. In recent years, deep learning has been gradually applied to the field of circuit system fault diagnosis because of its strong ability to mine the intrinsic characteristics of signals. However, the traditional deep learning method requires a lot of effort to achieve satisfactory results due to large number of parameters, complex models, slow training speed, and large datasets. The key factors for the success of traditional deep learning methods are layer-by-layer processing, feature transformation within the model, and sufficient model complexity. Deep forest (DF) is a new feature learning model that inherits the three characteristics of the traditional deep learning model but is that it is not based on neural network. It has fewer hyperparameters, a simpler model, faster training speed. In this article, an improved DF algorithm based on nonparametric predictive inference (NPI) is proposed, named NPIDF, which can better deal with small sample data. In two typical analog filter circuit fault diagnosis experiments, it is proved that DF and NPIDF achieve good diagnosis effect, and NPIDF performance is better, showing a greater advantage in small sample data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据