Innovative Structural Health Monitoring Using a Hybrid Intelligence Framework

ABSTRACT The technique of examining and monitoring the state of infrastructure is known as structural health monitoring. Artificial intelligence (AI) is important in structural health monitoring (SHM) because it enables faster, more precise, and automated processing of data collected from sensors and other monitoring systems. In this study, we created and validated a unique artificial algae–based Boltzmann prediction system (AAbBPS) for SHM that can automatically evaluate structural member health. This research proposed new methodologies and methods for forecasting the fracture depth and damage index of a structure utilizing a novel Boltzmann prediction system. The structural member's properties are then tweaked to detect failures. In the last phase, the structural problems are categorized. In the end, AAbBPS stability was assessed utilizing performance metrics of accuracy and error rates. The present study provides an accuracy of 99.96%, an f ‐score of 99.91%, a recall of 99.98%, a precision of 99.94%, and an error rate of 0.3%.