Javascript must be enabled for the correct page display

WEC Optimization via Machine Learning

Vaseiko, Bohdan (2020) WEC Optimization via Machine Learning. Integration Project, Industrial Engineering and Management.

[img]
Preview
Text
BaIP IEM B. Vaseiko .pdf

Download (1MB) | Preview
[img] Text
toestemming.pdf
Restricted to Registered users only

Download (127kB)

Abstract

Sea and ocean waves are a promising source of renewable energy. The device that is used for converting wave power into electrical or mechanical energy is called wave energy converter (WEC). Ocean Grazer B.V. (OG) is a company that has patented a design for WEC called Ocean Grazer 3.0. In this design, OG is using a honeycomb-shaped grid of point absorbers (buoys). Each buoy is connected with a string to a piston, where the vertical movement of the buoy is converted into electric energy via a transmission system. The transmission ratio (TR) is a measure of added pumping force to the piston, in response to higher or lower energy waves. Ocean Grazer 3.0 has a design that allows tuning of the TR. Therefore, a fast computing algorithm is required that can predict the TR, which maximizes the power extraction of Ocean Grazer 3.0. With that said, a machine learning (ML) approach was used for optimizing the power output. Machine learning is an extension of artificial intelligence. An ML algorithm is designed to learn with minimum human interference, by recognizing the patterns within the input data. Consequently, the ML method called neural networks was used to construct an accurate predictor.

Item Type: Thesis (Integration Project)
Supervisor name: Vakis, A. and Geertsema, A.A.
Degree programme: Industrial Engineering and Management
Thesis type: Integration Project
Language: English
Date Deposited: 30 Jan 2020 13:52
Last Modified: 30 Jan 2020 13:52
URI: https://fse.studenttheses.ub.rug.nl/id/eprint/21478

Actions (login required)

View Item View Item