Pattern Recognition for Design Performance Prediction in Marine
During the design and development work of small boat design there is a reoccurring need to perform estimations on performance in view of client expectations. There are many simplified quasi-empirical methods available to the hull designer but few or even none cover a very wide scope of speed. It would be desirable to reach a fast understanding, with the capability of load and dimensional variations, of the performance estimation without having the limitation of choosing a speed window in the early design phase.
Volvo Penta is dedicated in supporting our customers beyond the products and one way is to provide simplified tools to estimate and predict performance and economy of customer applications. The system MPS (Marine Performance Software) is such a tool and it contains a multitude of test cases where real boats can be compared to new design estimations within the same tool.
This thesis will look into the possibility to expand the capability of the tool with a data-based (machine learning) approach based on knowledge that may be extracted from the embedded database.
Thesis scope of work
- Literature review, early design prediction methods for boats.
- Data analysis and data mining on the current database.
- Model development based historical data
- Testing and verification of the model: the model should be able to run in a test environment
- Two students
- Knowledge of statistical analysis and machine leaning,
- Knowledge of naval architecture and marine performance predictions is advantageous.
- Programming, Matlab, Simulink, or others
Thesis Level: Master (30 ECTS points)
Starting date: January 2020
Number of students: 2 students
Ethan Faghani, Chief Engineer-Automation and AI, Volvo Penta, 073-902-5306
Jon Wingren, Senior Sales&Application Engineer, Volvo Penta, 073-902-1625
With Volvo Penta, a world-leading supplier of engines and complete drive systems for marine and industrial applications, you will be part of a global and diverse team of highly skilled professionals who works with passion, trust each other and embraces change to stay ahead. We make our customers win.
We want to get to know you
An email confirmation will be sent as soon as you submit your application. After this, it is still possible to update your personal profile.
If selected for an interview, you will be contacted with information about the following process steps: second interview, assessments and references.
All candidates will be notified when a final candidate is selected for the job. You can choose for us to keep your resume in our database and activate a search agent that will look for other jobs that match your profile.
When you begin your employment, you will receive an introduction to help you quickly become part of the team and start working with your tasks in the best possible way.