This study investigates the use of artificial intelligence (AI) to optimize fiber-reinforced polymer (FRP) composites in the retrofitting of concrete structures, aiming to enhance structural performance, durability, and cost-efficiency. Traditional retrofitting techniques using FRP often involve trial-and-error approaches, which can result in overdesign or material inefficiencies. This research introduces an AI-based optimization framework that integrates machine learning algorithms with structural engineering principles to systematically analyze and recommend the best retrofit configurations. The AI model evaluates multiple design parameters, including FRP thickness, fiber orientation, adhesive properties, and environmental exposure conditions, to find solutions that maximize strengthening effectiveness while minimizing material use and installation costs. Validation against experimental and numerical data demonstrates the model’s accuracy and practical applicability. The results indicate significant improvements in load-carrying capacity and service life extension for retrofitted concrete elements, as well as reduction in overall retrofit costs. By harnessing AI, this study offers a novel, data-driven approach to advancing FRP retrofitting strategies, fostering more sustainable and economical infrastructure preservation methods that align with modern engineering demands.
You may also start an advanced similarity search for this article.