Ge Yang

Ge Yang

Auto-generated profile, based on publicly available information

Ge Yang

Systems Engineering Research Institute, China State Shipbuilding Corporation Limited,Beijing,China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 April 2021 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
YGYang Ge
Yang Ge
LYLihui Yang
Lihui Yang
XMXikui Ma
Xikui Ma
In this article, a model-based sensorless control method which incorporates the orthogonal master-slave adaptive notch filter (ANF) for surface mounted permanent magnet synchronous motor is proposed. Since the rotor position estimation is seriously affected by the harmonics of estimated back-electromotive force (EMF), the orthogonal master-slave ANF is designed to deal with this problem. The orthogonal master-slave ANF is developed based on the ANF with frequency adaptation. The theoretical analysis indicates that the orthogonal master-slave ANF can accurately track the specific harmonics and the fundamental wave of back-EMF. Both the satisfactory harmonics elimination and the fast response speed of filter can also be achieved at the same time. Besides, the proposed frequency adaptation algorithm overcomes the dependence of frequency convergence on the signal amplitude and the problem of “double-frequency oscillation” in the estimated frequency. And since the use of frequency adaptation, the phase-locked loop is unnecessary, which simplifies the system and enhances the reliability. The corresponding experimental results under different conditions demonstrate the effectiveness and the superiority of the proposed method.

17 June 2022
Verified
Conference Paper
Closed access
SLShan Li
Shan Li
GYGe Yang
Ge Yang
SWShang Wu
Shang Wu
KZKaina Zhang
Kaina Zhang
YLYichen Liu
Yichen Liu
CZChenqian Zhao
Chenqian Zhao
Synthetic aperture radar (SAR) image classification usually relies on sample-based training. Mid-level features are widely used because SAR samples are scarce and objects exhibit complex visual appearances and strong variability. The common mid-level feature model is unsupervised, and the classification results are not robust. In this paper, we introduce mid-level features referred to as attributes. We propose a label-based attributes (L-Attribute) learning model that is based on solving mixed constrained optimization problems. We build discriminative image representations by learning a multi-kernel mapping between the input image features and the attribute space. To solve feature variability, we propose a label-based feature aggregation method to ensure that the attribute representations of the same class are similar and that different classes are far apart. In addition, we enforce that these learned attributes are highly discriminative and easy to predict. The framework is very effective and well generalized in scarce datasets.