Vaseiko, Bohdan (2020) WEC Optimization via Machine Learning. Integration Project, Industrial Engineering and Management.
|
Text
BaIP IEM B. Vaseiko .pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
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 |