Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Review of computational mechanics, optimization, and machine learning tools for digital twins applied to infrastructures

Stavroulakis Georgios, Charalampidi Varvara, Koutsianitis Panagiotis

Full record


URI: http://purl.tuc.gr/dl/dias/303838EF-62DD-4BE7-8E89-4634758A23A7
Year 2022
Type of Item Review
License
Details
Bibliographic Citation G. E. Stavroulakis, B. G. Charalambidi, and P. Koutsianitis, “Review of computational mechanics, optimization, and machine learning tools for digital twins applied to infrastructures,” Appl. Sci., vol. 12, no. 23, Nov. 2022, doi: 10.3390/app122311997. https://doi.org/10.3390/app122311997
Appears in Collections

Summary

This review discusses the links between the newly introduced concepts of digital twins and more classical finite element modeling, reduced order models, parametric modeling, inverse analysis, machine learning, and parameter identification. The purpose of this article is to demonstrate that development, as almost always is the case, is based on previously developed tools that are currently exploited since the technological tools for their implementation are available and the needs of their usage appear. This fact has rarely been declared clearly in the available literature. The need for digital twins in infrastructures arises due to the extreme loadings applied on energy-related infrastructure and to the higher importance that fatigue effects have. Digital twins promise to provide reliable and affordable models that accompany the structure throughout its whole lifetime, make fatigue and degradation prediction more reliable, and support effective predictive maintenance schemes.

Available Files

Services

Statistics