Session: 07-04-01 Structures in Ice

Submission Number: 157406

Machine Learning Based Computational Models for Increased Accuracy and Enabling Digital Twins 

Computational simulation approaches have long been a cornerstone of design in marine and offshore structures. More recently, they have also become essential for optimizing operations and ensuring sustainability. The digital twin (DT) framework has enabled to bridge the gap between simulation and its practical application in controlling, monitoring, and operating marine assets. However, the applications where complex non-linear problems are solved in real or close to real-time are still limited. It is proposed that this could be overcome by the recent rise of artificial intelligence (AI) and machine learning methods, which are promising technologies that can make current computational models more versatile. Namely, data-driven surrogate models or neural networks embedded in numerical algorithms enable the relegation of many computationally complex calculations into simple, functional forms, which opens a pathway to a new generation of digital twins. Memory-augmented neural networks offer a viable solution for applications involving memory-dependent problems, such as ship motion control or material fracture. These neural network models operate incrementally, much the same as the computational models they are inserted to. This work explores a critical yet underexamined aspect of these incremental machine learning models that is important when considering the pathway to real-time digital twins for ship motion control or non-linear structural analysis. 

Presenting Author: Mihkel Kõrgesaar Tallinn University of Technology

Presenting Author Biography: Professor Kõrgesaar research focuses on developing advanced, but computationally efficient simulation tools for non-linear response and limit state assessment of marine structures. The efficiency requirement stems from the sheer size of the engineering structures operating in marine environment meaning that most advanced methods known in literature are often prohibitively expensive to be applied to marine structures. Therefore, Kõrgesaar has developed ductile fracture criteria applicable to large shell elements and computational homogenization (equivalent single layer) approaches for assessing the ultimate strength of ship structures. In more broader terms, my interests are in the strength analysis of thin-walled structures, design and optimization, and limit states such as ultimate and accidental. I am also an active member of the International Ship Structures Committee III.1 Ultimate Strength.