Gaussian mixture model for automated mode tracking for long-span bridges

Determination of the most meaningful structural modes and gaining insight into how these modes evolve in time are important issues for long-term structural health monitoring (SHM) of the long-span bridges. To address these issues, modal parameters identified throughout the life of the bridge need to be compared and linked with each other, which is the process of mode tracking. The modal frequencies for a long-span bridge are typically closely-spaced and sensitive to the environment (e.g., temperature, wind, traffic, etc.), which makes automated tracking of modal parameters a difficult process, often requiring human intervention. Machine learning methods are well-suited for uncovering complex underlying relationships between processes and thus have the potential to realize accurate and automated modal tracking. In this study, Gaussian mixture model (GMM), a popular unsupervised machine learning method, is employed to automatically determine and update baseline modal properties from the identified unlabeled modal parameters. On this foundation, a new mode tracking method is proposed for automated modal tracking for long-span bridges. A numerical example for a three-degree-of-freedom system is employed to validate the feasibility of using GMM to automatically determine the baseline modal properties. In future work, a comprehensive field monitoring study will be presesnted to validate the proposed method so as to provide a reliable tool for long-term structural health monitoring of the long-span bridge.