Application of artificial neural networks for approximating a ship's heave and pitch motions in head waves

• Main Author: Tan, Calvin Xin Chong
• Other Authors: Liu Shukui
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Mechanical engineering
• Online Access: https://hdl.handle.net/10356/150376
• Institution: Nanyang Technological University

Machine learning technologies, specifically neural networks, is becoming a very popular tool amongst engineers to seek practical solutions to complex engineering problems. Naval architects are interested in predicting the performance of their vessels, during the design phase in realistic seaway conditions, using limited available ship information. This report presents an attempt to apply artificial neural networks to approximate the heave and pitch motions of a ship in head waves at design speed using ship main particulars and wave parameters. With advancements in machine learning technologies, auto-machine learning tool is used to identify a most efficient neural network structure for the best prediction accuracy. The model’s performance will be evaluated to identify the strengths and weaknesses in the methodology.