Multi-Objective Power Electronics System Design and Optimization, A Machine Learning Approach

Graduate Thesis Or Dissertation

Public Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/g445cn28c

Descriptions

Attribute Name	Values
Creator	Jackson, Derek
Abstract	The integration of power electronics within the energy and transportation sectors enlists a demand for the rapid development of energy-eﬃcient electrical systems. While model-based design and physics-based simulations are eﬀective ways to handle the multi-disciplinary and multi-objective (MO) design of these complex systems, design exploration remains a time-consuming procedure. A recently developed machine learning (ML) framework that outperforms other optimization algorithms in both accuracy and speed is one promising solution. This thesis presents the integration of the ML framework into the MO design process for power electronic systems. The autonomy and eﬃciency of the ML approach enables development of low-cost and energy-eﬃcient systems by reducing the required time and resources. A discussion of electrical system design, modeling, and optimization theory will lay the groundwork for demonstrating the proposed ML approach.
License	All rights reserved
Resource Type	Masters Thesis
Date Issued	2021-06-11
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Electrical and Computer Engineering
Degree Grantor	Oregon State University
Commencement Year	2021
Advisor	Cao, Yue
Academic Affiliation	Electrical Engineering and Computer Science
Rights Statement	In Copyright
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]
Embargo reason	Pending Publication
Embargo date range	2021-06-11 to 2023-06-10

Parents:

This work has no parents.

In Collection:

Thumbnail	Title	Date Uploaded	Visibility	Actions
	JacksonDerekM2021.pdf	2021-06-11	Public	Download