Session: 06-17-02 AI Technology for Ocean Engineering II

Paper Number: 123234

123234 - Bucking Reliability Assessment of Offshore Fluid Tanks Subjected to External Pressure With Advanced Machine Learning Approaches 

Offshore fluid tanks are critical components of offshore oil and gas infrastructure and are often subjected to external pressures that may lead to catastrophic buckling failure. Reliable assessment of their structural integrity is paramount to ensure offshore operations' safety and environmental sustainability. Traditionally, reliability assessment relies on deterministic and conservative methods, which may not accurately capture uncertainties from the structural and environmental parameters. Furthermore, classical sampling-based approaches for the reliability assessment (e.g., Monte Carlo simulation) require many simulations/experiments, which is unrealistic for the actual engineer design and optimization process. To address this limitation, this study leverages state-of-the-art machine learning approaches to do buckling reliability assessments of offshore fluid tanks under external pressure. The uncertainties encompassing geometric characteristics, material properties, and external loads are considered for the reliability assessment. The buckling analysis is carried out by the finite element method. Advanced machine learning methods are applied for the reliability assessment. The results demonstrate that the machine learning approaches can significantly reduce the computational cost for the reliability assessment. The machine learning approaches enable an accurate and probabilistic assessment of the buckling reliability, offering insights into the safety margins and the risk of failure. By applying advanced machine learning techniques, this research enhances the reliability assessment of offshore fluid tanks subjected to external pressure, thus facilitating improved risk management and structural design optimization. The incorporation of probabilistic models and data-driven insights paves the way for a more efficient and precise evaluation of the structural integrity of offshore fluid tanks, ultimately enhancing the safety and sustainability of offshore operations.

Presenting Author: Chao REN University of Stavanger

Presenting Author Biography: Dr.Chao REN is a Post-doc researcher at the University of Stavanger in Norway. He got his Ph.D. in Insa Rouen Normandie, France. His work mainly relates to offshore energy and applying machine-learning approaches to offshore energy and structures.

Authors:

Chao REN University of Stavanger
Frank Eriksen Dynamic Well Solutions As
Stian Gundersen Dynamic Well Solutions AS
Yihan Xing University of Stavanger