A systematic approach to structural maintenance: Integrating Non-Destructive Testing (NDT) data with Genetic Algorithm

Modern structural health monitoring systems became more precise and effective after scientists combined AI and Genetic Algorithms (GAs) technologies. Structural integrity assessment relies primarily on five Traditional Non-Destructive Testing (NDT) methods which include Ultrasonic Pulse Velocity (UPV) tests, Rebound Hammer (RH) tests, Half-Cell Potential (HCP) tests and Core Cutting tests and Carbonation Depth tests. The available detection methods create difficulties due to the unwanted data noise together with unpredictable accuracy levels throughout each assessment period and a lack of real-time investigation capability. The research evaluates how GAs enhance NDT procedures for optimizing structural maintenance operations. This study utilized MATLAB to process NDT data from six different sites which led to graphic outputs beneficial for GA-based computational evaluations. The GA adopted selection with crossover and mutation as techniques for precision refinement that fulfilled requirements of Indian Standard (IS) codes. GAs prove effective for maintenance strategy enhancement and prediction of structural deterioration and decision-making process improvement. Numerous field applications using GA techniques reach accuracy rates of 98% which suggests their suitability for on-site health monitoring operations. Recent research patterns show that GAs maintain their growing popularity for infrastructure maintenance applications because they offer affordable data-centered solutions. The research adds value to present-day developments of artificial intelligence-based structural health monitoring protocols that emphasize the combination of computational intelligence with standard NDT techniques. AI-based methods lead to major improvements in the sustainability and reliability of infrastructure which results in both extended structural safety and optimized maintenance operations.