A data-driven methodology for fragility assessment of hang-off deepwater drilling risers under emergency evacuation conditions

• Published in: Ocean engineering Vol. 315; p. 119777
• Main Authors: Zhang, Nan, Xu, Shaolun, Li, Xinhong, Yang, Mingyang, Chang, Yuanjiang, Liu, Xiuquan, Chen, Guoming
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2025
• Subjects: Data-driven; Drilling riser; Evacuation; Fragility; Hang-off; Hang-off; Data-driven; Evacuation; Drilling riser; Fragility
• ISSN: 0029-8018
• DOI: 10.1016/j.oceaneng.2024.119777

Emergency evacuation operations for hang-off drilling riser systems under extreme sea conditions are subjected to complex environmental and operational loads, increasing the risk of failure. Such failures can lead to severe economic losses and catastrophic accidents, emphasizing the need for robust fragility assessment of hang-off riser systems during evacuation scenarios. This study presents a robust and efficient data-driven methodology utilizing a Bayesian Regularization Artificial Neural Network for assessing the fragility of deepwater hang-off drilling risers under emergency evacuation conditions. The proposed model captures the intricate relationship between evacuation loads and riser responses, allowing robust predictions from limited simulation datasets. By integrating with logistic regression, the model facilitates the generation of accurate fragility curves. A detailed case study is conducted to demonstrate the effectiveness and feasibility of the proposed methodology, showing its superior capability in generating accurate fragility curves for both hard and soft hang-off drilling risers. The findings offer critical insights to enhance decision-making and safety protocols for hang-off drilling risers in challenging environments, supporting safer and more reliable evacuation operations. •A data-driven BRANN model is developed for fast, accurate prediction of dynamic responses in hang-off risers during evacuations.•A BRANN-based method efficiently assesses riser fragility, minimizing reliance on extensive numerical simulations.•A case study demonstrates the feasibility of computing fragility curves for risers under evacuation conditions.•Comparison of hard and soft hang-off modes highlights advantages of the soft mode during evacuations.