ABSTRACT
This paper focuses on opportunities that AI models bring to the monitoring and life cycle assessment of bridge structures. The paper examines different phases of data collection and generation and presents a holistic approach to curation of data. The paper then discusses various analytics that could be used to translate data to information that is useful in learning the fundamental characteristics of the structures and producing diagnostic measures for assessing the state of the structures. New classes of neural networks are developed to perform these analytical tasks accurately and in a scalable platform. These methods allow large volumes of data from various sources, including data from mobile sensors, to be utilized for assessment of critical structural systems.
