Enhancing acoustic emission analysis for corrosion damage detection in reinforced concrete by k-nearest neighbors method

The Acoustic Emission (AE) method is considered a significant tool for detecting damage in reinforced concrete structures caused by reinforcement corrosion. However, processing a large amount of AE data using traditional analysis methods is time-consuming. Therefore, integrating machine learning (ML) techniques into this process offers a more logical and effective solution to expedite data analysis and enhance damage detection accuracy. This study aims to train an ML model for detecting corrosion damage in reinforced concrete structures using an AE dataset. In pursuit of this goal, it seeks to enhance source localization that contributes to identifying crack patterns through signal-based analysis methods. AE data obtained from a reinforced concrete structural element subjected to accelerated corrosion testing in laboratory conditions have undergone detailed analyses with the ML model. In this context, an ML model capable of learning signals with various wave characteristics and parameters has been successfully integrated into the source localization algorithm, significantly improving AE source localization outcomes. Furthermore, this method is critical for structural safety as it enables the early detection of reinforcement corrosion and precise localization of cracks. The integration of this machine learning model with AE data serves as a valuable tool developed for more effective monitoring of damage in structures.