.png){kind=icon}
.png){kind=icon}
Return
Capacitance Prediction Using Multicascade Convolutional Neural Network for Efficient Wireless Power Transfer
.png){kind=icon}
PRE
AI
DOI：10.1109/LAWP.2024.3390201.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The efficiency of the wireless power transfer (WPT) is significantly impacted by misalignment between the transmitting and receiving coils due to impedance mismatching. To tackle this issue, an efficient power transfer solution is proposed, employing a capacitance prediction method based on a multi-cascade convolutional neural network. In the letter, the impedance-matching characteristic of a magnetic coupling resonant WPT system with an impedance-matching network is analyzed. After that, a neural network-driven approach is introduced to establish a mapping between reflection impedance and the optimal capacitance, and the impedance-matching performance of the system is assessed in the presence of coil misalignments. To validate the effectiveness of the proposed approach, tests are conducted and measurements demonstrate a significant improvement in power transfer efficiency.
Keywords:
Coils
Capacitance
Impedance
Impedance matching
Capacitors
Wireless power transfer
Feature extraction
multicascade convolutional neural network
wireless power transfer (WPT)
Journal
IF:
4.8
Papers:
1.0W
Citations:
2.8W