Optimized Offshore Vessel Design Tool

Project background

An Offshore Vessel is operating under many different conditions. The performance of an offshore vessel is not solely dependent on one design aspect. Vessel’s main particulars are the result of the required capabilities and will affect the vessel’s operations. Stability, Resistance and Propulsion, DP performance, Workability, and Fuel economy typically contribute to the vessel’s achievements. This multi-objective optimization process is time-intensive, and automating it would provide vessel designers with greater opportunities to identify diverse Pareto optimal solutions.

Project goal

Based on the available data of different vessel types, a tool should be developed that is capable of optimizing the vessel for multiple objectives. When the database information is insufficient, the tool should be able to synthesize various aspects of the design (Generative AI) to complete the data needed for optimization. This tool should be able to evaluate critical performance metrics for offshore vessel designs, enabling multi-objective optimization. Key objectives include, among others: Greenhouse gas emissions, operational expenses, and vessel uptime.

The project goal is to overcome data limitations and deliver a robust, automated framework for vessel design optimization by leveraging both existing data and AI-based data synthesis.

Project tasks

The project tasks of this master thesis project is: 1 Investigate and structure the available data for different Offshore Vessel types, 2 Develop a tool to generate synthetic design and performance data and complete the database, 3 Validate the quality and reliability of generated data, 4 Implement an optimization routine capable of handling multi objective design criteria to create a series of designs based on this data.

Candidate Profile

We are looking for a motivated MSc student with:

< >Strong interest in ship design, optimization, and digital technologies.Familiarity with programming (Python or similar) and optimization algorithms.Curiosity about AI applications in engineering.Contact information

Supervisors TU Delft:

Austin Kana a.a.kana@tudelft.nl ––––– Roy de Winter r.dewinter@tudelft.nl

Supervisors Royal IHC

Shaurya Veer s.veer@royalihc.com ––––– Peter van der Hoek p.vanderhoek@royalihc.com

References

[1] Papanikolau, A, & Kana, A. A et al. (2024). Ship Design in the Era of Digital Transition: A state of the art report. Proceedings of 15th IMDC Conference 2024.

[2] Winter, R. de, & Back, T.H.W. et al. (2020). Optimizing Ships using the Holistic Accelerated Concept Design Methodology. Proceedings of the 14th PRADS Conference 2019.