Project description
The purpose of the Ph. D. project is to develop advanced, data driven mathematical models for analyzing the dynamics of ocean-going vessels, especially with regard to modeling fuel efficiency. Traditionally physical models, e.g. hydrodynamics, the study of motions of liquids, have been used to model the dynamics and fuel efficiency of ships. However, these models are limited when it comes to modeling the real-life conditions of ocean-going vessels. Therefore, the goal of of this project is to develop powerful models, based on a machine-learning approach, that are able to adapt to actual conditions of the ships. Such models require inputs of (large amounts) of data, containing actual measurements of operational conditions from vessels.

Current paper in the working
Efficient Ship Propulsion through Modelling - This paper is expected to be finished before the end of this semester. It will present an accurate system for predicting an ocean going vessels speed and energy consumption given circumstances. The model however has some drawbacks especially related to dynamic changes in the controls, which are discussed.

Software
PyPR – Python Pattern Recognition - Part of the code used for the Ph. D. project has been assembled in a library called Python Pattern Recognition or PyPR. The code is likely to be licensed under GPLv3 or the Python License. PyPR is available on sourceforge, pypr.sourceforge.org.
The project is still in its early development stages, but some parts can be used now, such as the back-propagation neural network, K-means clustering, and Expectation Maximization of Gaussian Mixtures. The library is likely to change much over the next months, so if you use it in any project, then it would probably be best just to copy the code into your project until PyPR becomes more mature.

All feedback is appreciated.
Contact

Email: joanpeturpetersen_at_gmail.com
Tel: +298 59 15 55

Personal