Skip to Main Content
Skip Nav Destination
Asset Integrity Management of Critical Infrastructure
Editor
Mamdouh M. Salama
Mamdouh M. Salama
MMS4Aim LLC, USA
Search for other works by this author on:
Dragan Komljenovic
Dragan Komljenovic
Hydro-Québec, Canada
Search for other works by this author on:
Jovica R. Riznic
Jovica R. Riznic
Canadian Nuclear Safety Commission, Canada
Search for other works by this author on:
ISBN:
9780791887738
No. of Pages:
180
Publisher:
ASME
Publication date:
2024

A novel efficient risk-based tool for rapidly assessing the post-cyclonic structural integrity of flexible risers is demonstrated. Leveraging Machine Learning (ML) technology via an Artificial Neural Network (ANN), the predictive tool is trained by synthetic data for near-instantaneous integrity assessment. This tool is validated using an operational floating facility to demonstrate the effectiveness of ANNs as surrogate models. The probabilistic framework used enhances our understanding of structural failure risks, potentially reducing delays and production losses associated with confirming riser integrity after extreme events. Moreover, the adaptability of this approach extends its application to a wide range of other offshore structures beyond risers, making it a versatile and valuable tool for the offshore engineering industry.

This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal