PERFORMANCE AND ACCURACY OF REAL-TIME MONITORING-BASED AI/ML TECHNIQUES IN STRUCTURAL HEALTH MONITORING (SHM)

Abstract

Structural health monitoring, or SHM, is an important tool for making sure that civil infrastructure is safe, long-lasting, and in good shape. Real-time monitoring systems, along with artificial intelligence (AI) and machine learning (ML), have opened up new ways to quickly and accurately find and diagnose structural damage. This study looks at how well AI and ML algorithms could be used to keep an eye on big structures by simulating how well they work and how accurate they are in real-time SHM systems. We use simulation methods to see how useful AI/ML models might be for finding problems early on, checking their accuracy, and speeding up the SHM decision-making process. A review of traditional research has shown that AI/ML-based monitoring can make SHM systems more reliable, lower costs, and improve their ability to predict when maintenance is needed.