In steel structural engineering, artificial intelligence (AI) and machine learning (ML) are improving accuracy, efficiency, and automation. This review explores AI-driven approaches, emphasizing how AI models improve predictive capabilities, optimize performance, and reduce computational costs compared to traditional methods. Inverse Machine Learning (IML) is a major focus since it helps engineers to minimize reliance on iterative trial-and-error by allowing them to identify ideal material properties and geometric configurations depending on predefined performance targets. Unlike conventional ML models that focus mostly on forward predictions, IML helps data-driven design generation, enabling more adaptive engineering solutions. Furthermore, underlined is Explainable Artificial Intelligence (XAI), which enhances model transparency, interpretability, and trust of AI. The paper categorizes AI applications in steel construction based on their impact on design automation, structural health monitoring, failure prediction and performance evaluation throughout research from 1990 to 2025. The review explores challenges such as data limitations, model generalization, engineering reliability, and the need for physics-informed learning while examining AI’s role in bridging research and real-world structural applications. By integrating AI into structural engineering, this work supports the adoption of ML, IML, and XAI in structural analysis and design, paving the way for more reliable and interpretable engineering practices.

This study formulates numerical and analytical approaches to the self-equilibrium problem of novel units of tensegrity metamaterials composed of class θ = 1 tensegrity prisms. The freestanding configurations of the examined structures are determined for varying geometries, and it is shown that such configurations exhibit a large number of infinitesimal mechanisms. The latter can be effectively stabilized by applying self-equilibrated systems of internal forces induced by cable prestretching. The equilibrium equations of class θ = 1 tensegrity prisms are studied for varying values of two aspect parameters, and local solutions to the self-equilibrium problem are determined by recourse to Newton–Raphson iterations. Such a numerical approach to the form-finding problem can be easily generalized to arbitrary tensegrity systems. An analytical approach is also proposed for the class θ = 1 units analyzed in the present work. The potential of such structures for development of novel mechanical metamaterials is discussed, in the light of recent findings concerned with structural lattices alternating lumped masses and tensegrity units.

Composite modular panels are increasingly used in modern buildings, yet their layered behavior makes mechanical characterization and modeling difficult. This study presents a novel hybrid framework that integrates analytical, numerical, and AI-driven approaches for the mechanical characterization of composite panels. The system combines a layered concrete configuration with embedded steel reinforcement, and its performance was evaluated through experimental testing, analytical formulation, finite element simulations, and artificial intelligence techniques. Full-scale bending and shear tests were conducted and results in terms of displacements were compared with in silico simulations. The equivalent elastic modulus and thickness were suggested via a closed-form analytical procedure and validated numerically, showing less than 3% deviation from experiments. These equivalent parameters were used to simulate the dynamic response of a two-storey prototype building under harmonic excitation, with simulated modal periods differing by less than 10% from experimental data. To generalize the method, a parametric dataset of 218 panel configurations was generated by varying material and geometric properties. Machine learning models including Artificial Neural Network, Random Forest, Gradient Boosting, and Extra Trees were trained on this dataset, achieving R² > 0.98 for both targets. A graphical user interface was developed to integrate the trained models into an engineering tool for fast prediction of equivalent properties. The proposed methodology provides a unified and computationally efficient approach that combines physical accuracy with practical usability, enabling rapid design and optimization of composite panel structures.

Metallic thin-walled beams with continuously varying cross-sections loaded in compression are particularly sensitive to instability problems due to lateral-torsional buckling. Such a phenomenon depends on several parameters, including the cross-sectional properties along the entire length, material properties, load distribution, support, and restraint conditions. Due to the difficulty of obtaining analytic solutions for the problem under consideration, the present study takes a numerical approach based on a variational formulation of the lateral-torsional buckling problem of tapered C-beams. Numerical simulations are compared with experimental results on the buckling of a physical model of at thin-walled beam with uniformly varying cross-section, with the aim of assessing the accuracy of the proposed approach. The good agreement between numerical and experimental results and the reduced computational effort highlight that the proposed variational approach is a powerful tool, provided that the geometry of the structure and the boundary conditions are accurately modeled.