
Conferencia: AI-Enhanced Structural Health Monitoring Through Multimodal Sensing, Computational Modeling, and Network Integration
Recent developments in artificial intelligence (AI) and advanced sensing technologies are transforming the field of Structural Health Monitoring (SHM). As infrastructure continues to age—particularly in Western countries with older built environments—SHM has become essential for evaluating and ensuring structural safety. While significant progress has been made in AI-driven data analysis and in the development of novel sensing solutions, such as self-sensing structural materials, effective prognosis in civil engineering remains elusive. A major challenge lies in the limited integration between data-driven insights and physics-based models.
To enable risk-informed decision-making at a territorial scale, SHM must evolve into a comprehensive, multi-scale framework—one that fuses multimodal sensor data with computational modeling, and expands the focus from individual structures to interconnected networks. This talk delves into the latest research from the University of Perugia, Italy, exploring the intersection of advanced sensing, AI-powered analytics, and computational techniques. Topics include smart masonry using self-sensing materials, deep learning and statistical pattern recognition for damage detection and classification, and the application of metamodeling and Bayesian inference for more robust structural assessment.