Abstract
Concrete compressive strength is a critical property for structural performance and construction scheduling. Traditional non-destructive testing (NDT) methods, such as rebound hammer and ultrasonic pulse velocity, offer limited reliability and resolution, particularly at early ages. This study presents an AI-powered structural health monitoring (SHM) framework that integrates multi-type and multi-position piezoelectric (PZT) sensor networks with machine learning for in situ prediction of concrete compressive strength. Signals were collected from various PZT types positioned on the top, middle, bottom, and surface sides of concrete cubes during curing. A series of machine learning models were trained and evaluated using both the full and selected feature sets. Results showed that combining multiple PZT types and locations significantly improved prediction accuracy, with the best models achieving up to 95% classification accuracy using only the top 200 features. Feature importance and PCA analyses confirmed the added value of sensor heterogeneity. This study demonstrates that multi-sensor AI-enhanced SHM systems can offer a practical, non-destructive solution for real-time strength estimation, enabling earlier and more reliable construction decisions in line with industry standards.