Interfacial stress analysis in damaged RC beams reinforced whit FRP using artificial neural network method

Concrete is the most widely used material in the construction industry across the globe. Its properties, combined with varying climatic and usage conditions, contribute to common issues in reinforced concrete structures, such as cracks, corrosion, and other forms of degradation. Rather than opting for demolition, it is often more efficient and cost-effective to rehabilitate and reinforce existing concrete elements using fiber-reinforced polymer (FRP) plates. Concurrently, the rapid advancements in programming and computational techniques have opened new avenues for engineers to incorporate artificial intelligence (AI) into construction practices. This paper presents an innovative approach that harnesses the power of artificial neural networks (ANN) to predict interfacial shear stresses and normal stresses in damaged reinforced concrete (RC) structures that are strengthened with externally bonded prestressed composite plates. The study takes into account a comprehensive range of factors that influence variations in normal and shear stresses. By implementing AI through ANN techniques, we can simulate the predictive capabilities of the human brain, effectively forecasting stress variations and providing solutions to complex structural problems. This biologically inspired methodology enhances the accuracy and reliability of our predictions. It has been found that this prediction method yields fairly acceptable results based on a reference database used for the prediction program. The results indicate that this AI-driven approach not only offers a viable alternative to traditional methods but also holds significant promise for future applications in the field of structural engineering.