Dynamic Inductive Power Transfer Systems With Reflexive Tuning Networks Designed by Machine Learning
Date of Award:
5-2023
Document Type:
Dissertation
Degree Name:
Doctor of Philosophy (PhD)
Department:
Electrical and Computer Engineering
Committee Chair(s)
Regan Andrew Zane
Committee
Regan Andrew Zane
Committee
Abhilash Kamineni
Committee
Nicholas S. Flann
Committee
Hongjie Wang
Committee
Marv Halling
Abstract
This dissertation proposes a new way to make dynamic wireless charging systems more affordable. Instead of using one inverter for each transmitter coil, as is typically done, the proposed system uses a single inverter that is connected to multiple transmitter coils. This approach is made possible by reflexive tuning, which allows for high currents to be achieved only on the transmitter coil in use. The system was tested with a 50kW prototype, designed using a combination of neural networks and genetic algorithms. The prototype was tested on both automated rail and vehicle systems. The measured dc-dc efficiency with single and four transmitter coils are 90.0% and 87.9%, respectively.
Checksum
6a028ace2eb0d4b5dfa0467b3593074d
Recommended Citation
Inoue, Shuntaro, "Dynamic Inductive Power Transfer Systems With Reflexive Tuning Networks Designed by Machine Learning" (2023). All Graduate Theses and Dissertations, Spring 1920 to Summer 2023. 8760.
https://digitalcommons.usu.edu/etd/8760
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .