Improving Driveability Predictions for Offshore Piles using Bayesian Optimisation

Buckley, R. , Chen, Y., Sheil, B., Suryasentana, S., Randolph, M. and Doherty, J. (2023) Improving Driveability Predictions for Offshore Piles using Bayesian Optimisation. In: 9th International SUT OSIG Conference “Innovative Geotechnologies for Energy Transition”, London, UK, 12-14 Sep 2023,

Abstract

Pile driveability predictions require information on the pile geometry, impact hammer and the soil resistance to driving (SRD). Current methods to predict SRD are based on databases of long slender piles and have been shown to provide poor predictions when applied to geometries outside of their original calibration spaces. New, robust and adaptable methods are required to predict SRD for current offshore pile geometries. An optimisation framework to update uncertain model parameters in existing axial static design methods to calibrate SRD is described. The optimisation is undertaken using a robust Bayesian approach to dynamically update uncertain variables during driving. The framework is demonstrated using a case study from a German offshore wind site. The static method is shown to perform well for piles with geometries that reflect the underlying database such that only minimal optimisation is required. For larger diameter piles, relative to the prior best estimate, optimised results are shown to provide significant improvements in the mean calculations, and associated variance, of pile driveability as more data is acquired. When compared with results determined using the conventional design approach used by industry, the optimised parameters provided notable improvements in the agreement between measured and calculated values. The optimised parameters can be used to predict SRD in similar profiles where large datasets are available, the demonstrated framework may be used to develop new SRD methods.

• Item Type: Conference Proceedings
• Additional Information: The Authors acknowledge the support of the Supergen Offshore Renewable Energy (ORE) Hub Flexible funding for the iDrive project. Sheil was also supported by the RAEng Fellowship Scheme.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Buckley, Dr Roisin
• Authors: Buckley, R., Chen, Y., Sheil, B., Suryasentana, S., Randolph, M., and Doherty, J.
• College/School: College of Science and Engineering > School of Engineering > Infrastructure and Environment

Related URLs

• Organisation

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
314446		iDrive: Intelligent Driveability Forecasting for Offshore Wind Turbine Monopile Foundations	Roisin Buckley	Engineering and Physical Sciences Research Council (EPSRC)	R74903	ENG - Infrastructure & Environment