Fatigue Reliability of Offshore Wind Turbines using Gaussian Processes

Abstract

The fatigue limit state (FLS) often drives the design of offshore wind turbine (OWT) substructures. Numerical assessment of fatigue damage over the life of a structure is computationally expensive, due to the need for time-history simulation of a large number of environmental conditions. This makes structural reliability for FLS a challenging task as it also requires numerical sampling of random variables to model uncertainty in the estimation of fatigue damage. This paper proposes using Gaussian process regression to build surrogate models for fatigue damage caused by different environmental conditions. A case study demonstrates how the proposed approach reduces the computational effort required to evaluate the FLS. Finally, a structural reliability calculation using the surrogate model highlights the large scatter in fatigue life prediction due to parameter uncertainty.