Data Informed Model Test Design With Machine Learning – An Example in Nonlinear Wave Load on a Vertical Cylinder

• Published in: Journal of Offshore Mechanics and Arctic Engineering
• Main Authors: Tang, Tianning, Ding, Haoyu, Dai, Saishuai, Chen, Xi, Taylor, Paul H., Zang, Jun, Adcock, Thomas A.A.
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2024
• Subjects: fluid structure interaction; hydrodynamics; machine learning; /dk/atira/pure/subjectarea/asjc/2200/2212; name=Ocean Engineering; /dk/atira/pure/subjectarea/asjc/2200/2210; name=Mechanical Engineering; Arctic
• Online Access: https://researchportal.bath.ac.uk/en/publications/45a111ac-45f8-45db-93ac-9bec921860be; https://doi.org/10.1115/1.4063942; https://purehost.bath.ac.uk/ws/files/319298494/Tim_JOMAE_arv.pdf; http://www.scopus.com/inward/record.url?scp=85206971383&partnerID=8YFLogxK

Model testing is common in coastal and offshore engineering. The design of such model tests is important such that the maximal information of the underlying physics can be extrapolated with a limited amount of test cases. The design of experiments also requires considering the previous similar experimental results and the typical sea-states of the ocean environments. In this study, we develop a model test design strategy based on Bayesian sampling for a classic problem in ocean engineering—nonlinear wave loading on a vertical cylinder. The new experimental design strategy is achieved through a GP-based surrogate model, which considers the previous experimental data as the prior information. The metocean data are further incorporated into the experimental design through a modified acquisition function. We perform a new experiment, which is mainly designed by data-driven methods, including several critical parameters such as the size of the cylinder and all the wave conditions. We examine the performance of such a method when compared to traditional experimental design based on manual decisions. This method is a step forward to a more systematic way of approaching test designs with marginally better performance in capturing the higher-order force coefficients. The current surrogate model also made several “interpretable” decisions which can be explained with physical insights.