This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
University of Coimbra , Coimbra , Portugal
University of Coimbra , Coimbra , Portugal
University of Coimbra , Coimbra , Portugal
Artificial intelligence (AI) is emerging as a powerful tool in structural engineering, enabling data-driven alternatives to traditional analytical and numerical methods. In steel structures, AI has been applied to design optimisation, structural health monitoring, and reliability assessment; however, its application to modelling nonlinear joint behaviour remains limited. This paper reviews AI methods in steel structures, outlining their purpose, capabilities, and current challenges. Focus is given to steel joints, where accurate prediction of moment–rotation (M–θ) response is essential. A framework combining Genetic Algorithms (GA) for component characterisation and Physics-Informed Neural Networks (PINNs) for surrogate modelling and joint behaviour prediction is presented. The approach enables fast and physically consistent prediction of full nonlinear joint behaviour, supporting advanced AI structural design.
artificial intelligence, steel structures, steel joints, genetic algorithms, physics-informed neural networks, nonlinear behaviour
This work was supported by the Innovation Pact “R2UTechnologies | Modular Systems” (C644876810-00000019), by the “R2UTechnologies” Consortium, co-financed by NextGenerationEU through the “Agendas for Business Innovation” investment of the Portuguese Recovery and Resilience Plan (PRR).
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
