Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

CFD-Powered Ship Trim Optimization: Integrating ANN for User-Friendly Software Tool Development

Version 1 : Received: 18 June 2024 / Approved: 18 June 2024 / Online: 18 June 2024 (12:03:33 CEST)

How to cite: Vasilev, M.; Kalajdžić, M.; Ivković, I. CFD-Powered Ship Trim Optimization: Integrating ANN for User-Friendly Software Tool Development. Preprints 2024, 2024061253. https://doi.org/10.20944/preprints202406.1253.v1 Vasilev, M.; Kalajdžić, M.; Ivković, I. CFD-Powered Ship Trim Optimization: Integrating ANN for User-Friendly Software Tool Development. Preprints 2024, 2024061253. https://doi.org/10.20944/preprints202406.1253.v1

Abstract

This study presents a comprehensive approach to trim optimization as a energy efficiency improvement measure, focusing on reducing fuel consumption for one RO-RO car carrier. Utilizing Computational Fluid Dynamics (CFD) software, the methodology incorporates Artificial Neural Networks (ANN) to develop a mathematical model for estimating key parameters such as brake power, daily fuel oil consumption (DFOC) and propeller speed. The complex ANN model is then integrated into a user-friendly software tool for practical engineering applications. The research outlines a seven-phase trim optimization process and discusses its potential extension to other types of ships, aiming to establish a universal methodology for CFD-based engineering analyses. Based on trim optimization results, the biggest DFOC goes up to 10.5% at 7.5m draft and up to 8% for higher drafts. Generally, in every considered case, it is recommended to sail with the trim towards the bow, meaning that the ship’s weight (ballast) should be adjusted to tilt slightly forward.

Keywords

EEDI; EEXI; CII; CFD; ANN; trim optimization

Subject

Engineering, Marine Engineering

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.