As monitoring systems become an integral part of intelligent infrastructure, there is a growing need for autonomous approaches that can operate reliably and deliver meaningful results with limited human supervision. This special session invites work in automated and long-term vibration-based monitoring of structures. Submissions are encouraged that address challenges and success stories related to large data volumes, environmental and operational variability, system scalability, and automated interpretation of results and performance metrics that support informed decision-making on structural condition. Both theoretical contributions, methodological developments, and real-world case studies are welcome, reflecting current practice as well as future directions.

Topics of interest may include:

• Automated operational modal analysis and modal tracking
• Long-term trend detection in dynamic response and modal parameters
• Environmental and operational variability modeling and compensation
• Autonomous monitoring systems and decision-making frameworks
• Field applications and large-scale case studies
• Machine-learning approaches to long-term and large-scale monitoring
• Uncertainty quantification for automated monitoring results
• Lifecycle-oriented monitoring strategies and decision support for maintenance

Keywords: Structural Health Monitoring, Operational Modal Analysis, Automated Modal Identification and Tracking, Machine Learning, Data-Driven Methods

Track chairs

Øyvind Wiig Petersen, Norwegian University of Science and Technology

Gunnstein Thomas Frøseth, Norwegian University of Science and Technology

Davide Raviolo, Norwegian University of Science and Technology