Date of Award:

8-2024

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Electrical and Computer Engineering

Committee Chair(s)

Todd K. Moon

Committee

Todd K. Moon

Committee

Mohammad Shekaramiz

Committee

Jacob H. Gunther

Committee

Jonathan Phillips

Abstract

In reaction to rising global temperatures and carbon dioxide emissions, many countries are looking to use energy sources other than fossil fuels. One such source of energy is wind energy, which can be harvested by wind turbines. By rotating at high speeds, the blades of these large turbines are able to convert wind energy to kinetic energy, which is then converted to electricity usable by the power grid. Traditional methods for inspecting these turbines for damages are expensive, unsafe, and susceptible to human error. These turbines are so tall and so large that inspectors run the risk of falling from large heights or being injured by falling turbine debris. It is also difficult to spot every damaged area on a blade so large. A solution to this problem is to have a drone fly up and take pictures of the blades. Afterwards, these pictures can be processed by a machine learning architecture, which is a specific type of AI (artificial intelligence). The AI will then tell the inspectors if damages exist on the blades. Wind turbines are normally turned off during inspection for the safety of the inspectors. If the turbines are left on during the inspection process to save money, the blades will likely be moving, so images of the blades may be blurry. This will make it more difficult for the AI to detect damages. This is why deblurring the images before further processing could be a great way to still have accurate results from the AI with rotating blades. In this study, the health of wind turbine blades is determined using specific machine architectures along with image deblurring techniques and a custom-made image set of wind turbine blades taken with a drone.

Checksum

c3800827c9c7068a2ff869d15008eabb

Download

Share

COinS

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 .