Meidi Sun

ORCID: 0000-0002-2295-1953
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Machine Fault Diagnosis Techniques
  • Advanced Decision-Making Techniques
  • Gear and Bearing Dynamics Analysis
  • Engineering Diagnostics and Reliability
  • Silicon Carbide Semiconductor Technologies
  • Medical Imaging and Analysis
  • Multilevel Inverters and Converters
  • Machine Learning and ELM
  • Advanced DC-DC Converters
  • Image Processing and 3D Reconstruction
  • Induction Heating and Inverter Technology
  • 3D Shape Modeling and Analysis
  • Electromagnetic Compatibility and Noise Suppression
  • Domain Adaptation and Few-Shot Learning

Changsha University of Science and Technology
2022-2024

Hunan University
2018-2022

In intelligent fault diagnosis, transfer learning can reduce the requirement of sufficient labeled data and same distribution. However, for diagnosis a new machine, there are still some limitations, such as low accuracy or demand with information in machine. this article, we propose stack autoencoder algorithm based on class separation domain fusion (SAE-CSDF) to solve these problems. According characteristics bearing faults, proposed weighted strategy ensure direction balance process. The...

10.1109/tie.2021.3066933 article EN IEEE Transactions on Industrial Electronics 2021-03-23

Most of the mechanical fault diagnosis methods induction motors (IMs) are based on vibration signals. However, sensors expensive and require direct contact with IMs. This article proposes a data-driven method for IMs using stator current signals, which is more convenient low cost, since no additional required. Aiming at weak representation faults in an intelligent noise elimination reconstruction model proposed to improve signal-to-noise ratio. Through automatic feature extraction...

10.1109/tte.2022.3163612 article EN IEEE Transactions on Transportation Electrification 2022-03-30

Impedance-source inverters provide a promising single-stage power conversion with boost-buck capabilities and inverter legs short-circuit immunity. To achieve superior thermal output harmonic performance, two novel discontinuous modulation strategies for the three-phase quasi-Z source inverter, called maximum-boost space vector (SVM) simple-boost SVM respectively, are proposed in this article. By properly arranging shoot-through states clamping certain switch to positive or negative dc-link...

10.1109/tie.2021.3139185 article EN IEEE Transactions on Industrial Electronics 2022-01-06

10.1109/cac63892.2024.10864488 article EN 2021 China Automation Congress (CAC) 2024-11-01
Coming Soon ...