Edge AI and IoT for Real-Time Structural Health Monitoring

Abstract

Structural Health Monitoring (SHM) is essential for assessing the safety, performance, and condition of civil infrastructure. However, conventional SHM approaches face challenges related to data volume, communication latency, scalability, and real-time processing. The integration of the Internet of Things (IoT), edge computing, and Artificial Intelligence (AI) provides a promising approach to intelligent and real-time SHM. This review examines the integration of IoT and Edge AI for civil infrastructure monitoring, covering sensing technologies, communication networks, edge-computing architectures, machine learning and deep learning, TinyML, edge hardware, and integrated edge-cloud frameworks. The review further discusses real-time damage detection, multimodal sensor fusion, digital twins, cybersecurity, and energy-efficient monitoring. Findings indicate that Edge AI can reduce latency and bandwidth requirements while enabling faster local decision-making; however, practical deployment remains challenged by computational and energy constraints, sensor noise, communication reliability, limited real-world datasets, model generalization, and the lack of standardized evaluation frameworks. Future research should focus on lightweight AI, TinyML, multimodal and self-supervised learning, energy-aware edge intelligence, secure communication, and edge-based digital twins. Overall, IoT and Edge AI offer significant potential for developing reliable, efficient, and intelligent real-time SHM systems.