Fragility assessment approach of deepwater drilling risers subject to harsh environments using Bayesian regularization artificial neural network

Abstract

The drilling risers are the most critical and vulnerable connection of floating drilling platform and subsea wellhead. In order to improve the operation efficiency, the operators have attempted to suspend the drilling operations and keep the drilling risers connected to the wellhead to survive in the storm, thus the fragility of the drilling risers under storm is of paramount importance to drilling operations. This paper is aimed at proposing an efficient and robust BRANN-based non-intrusive approach for the fragility assessment of the deepwater drilling riser subject to storms. The proposed approach, which could effectively reflect the non-linear relationship between the input and output data, can generate thousands of non-numerical data under limited Finite Element Analysis (FEA) of the drilling risers, while the Monte Carlo Simulation (MCS) could be further incorporated to calculate the fragility curve. A case study was conducted to demonstrate the characteristics with respect to significantly computational reduction of the proposed approach compared to the conventional MCS method, and the proposed approach was verified to be robust and efficient in assessing the fragility of the drilling risers under storms. The related conclusions could be used to provide reference for operations of drilling risers under harsh environment.