Abstract

Monopile is a popular choice in the foundation supporting offshore wind turbines (OWTs), with local scour significantly impacting their lateral responses. Macro-element model, which encapsulates the response between the monopile and the surrounding seabed soils into a force-displacement relation, has been extensively developed to describe offshore foundations. However, such kind of models specifically targeting monopiles subjected to lateral loading in local scour remain underdeveloped. This work proposes a macro-element model with a succinct hyperbolic hardening relation for laterally loaded monopiles in local scour conditions, using the evolutionary polynomial regression (EPR) machine learning technique for easy and optimal design. First, the finite element model is verified and extended to generate force-displacement responses considering the monopile geometries, soil characteristics, and local scour geometries. These results are then utilised to determine the optimal hyperbolic hardening relation of the macro-element model. Next, the EPR technique is employed to determine the relationship between the hyperbolic hardening relation parameters and the influencing factors. Finally, the macro-element model is successfully evaluated by comparing with measurements from centrifuge tests and numerical solutions by finite element analysis, demonstrating its applicability in practical design and the ability to reproduce FEA results with a significant reduction in computational cost.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.