This research is focused on the numerical analysis of steel structural elements subjected to fire. An experimental program will be designed, implemented, and evaluated, with its results serving for the validation of numerical simulations, the verification of computational procedures, and the development of artificial intelligence–based methods for the design of structural elements and their joints. The primary analytical tools employed will be the finite element method and advanced artificial intelligence techniques.
The objective of the study is to examine in detail the behavior of steel structural components, particularly open-web beams, at elevated temperatures resulting from fire. To achieve this, a combined approach will be adopted, integrating experimental testing, numerical simulations, and AI-based modeling. The project will encompass the design, execution, and evaluation of experiments investigating the mechanical response of structural elements under thermal loading. Subsequently, validated numerical models will be developed to facilitate the optimization of design solutions using machine learning methods and advanced AI algorithms.
The finite element method will enable a detailed description of the interactions between the mechanical behavior of elements and the performance of their joints under simultaneous thermal and mechanical loading. Special attention will be devoted to open-web beams with both constant and variable cross-sections, which are widely used in modern steel structures due to their favorable strength-to-weight ratio and high material efficiency. The research will further address the optimization of structural design not only in terms of load-bearing capacity and fire resistance but also with respect to environmental considerations, including CO₂ emissions associated with the production of structural elements and their overall environmental impact.
The expected contributions of the dissertation include the formulation of recommendations for numerical modeling procedures of steel structural elements, the identification of the scope of applicability of the proposed methods across various structural systems and fire load conditions, the development of AI-based models for the efficient design and dimensioning of open-web beams and their joints, and the refinement of analytical formulations through the integration of experimental data, numerical simulations, and computational analyses.
The results of the dissertation will advance the state of the art in the design and analysis of fire-resistant steel structures, contributing to safer, more reliable, and economically efficient construction under both standard operating conditions and extreme scenarios such as fire. In addition, the findings will provide a foundation for further research in structural engineering, fire safety, and the application of artificial intelligence in construction.
