Design of Seismic Retrofitting Systems for Reinforced Concrete Structures Using Modern Strengthening Methods and Artificial Intelligence Techniques

In this study, the design and optimization of seismic retrofitting systems for reinforced concrete structures are investigated using a novel, hybrid, and AI-based approach. These systems combine three advanced technologies: fiber-reinforced polymers (FRP), nonlinear dampers, and seismic isolators, which are simultaneously implemented with the aim of improving the seismic performance of structures. The main innovation of this research lies in the simultaneous and purposeful integration of these retrofitting methods using artificial intelligence algorithms. These algorithms include machine learning, genetic algorithms, and other evolutionary optimization techniques employed in the analysis and decision-making process. The primary objective of this study is to develop an intelligent retrofitting system capable of accurately identifying the weak points of a structure and recommending the optimal combination of retrofitting type, location, and quantity of materials. To achieve this, numerical modeling of the structure was first carried out using advanced analysis software, and a comprehensive database was then created from the results to train the AI algorithms. By evaluating various retrofitting scenarios and analyzing the dynamic responses of the structure under different seismic excitations, the algorithms were able to determine the most effective retrofitting patterns. The results of the analyses indicate that the proposed hybrid approach not only significantly reduces inter-story drifts and internal forces but also improves the overall seismic performance of the structure. A comparison between the proposed method and traditional retrofitting techniques shows that the suggested system is more efficient and, in particular, performs better in structures with complex geometry and dynamic behavior. Moreover, the application of artificial intelligence algorithms has accelerated the design process, reduced human errors, and enhanced the accuracy of the results. These features can play a crucial role in real-world retrofitting projects, leading to cost reduction and improved safety. Ultimately, the findings of this research can serve as a model for the development of modern seismic retrofitting technologies for reinforced concrete structures and represent a significant step toward improving the safety and resilience of structures in earthquake-prone areas

کلیدواژه ها:

Seismic Retrofitting ، Reinforced Concrete Structure ، FRP Fibers ، Dampers ، Artificial Intelligence ، Genetic Algorithm ، Neural Network.