A HIERARCHICAL DOMAIN-ADVERSARIAL AND MULTI-TASK LEARNING ALGORITHM FOR BRIDGE DAMAGE DIAGNOSIS USING A DRIVE-BY VEHICLE

Monitoring bridge health using vibrations of drive-by vehicles has various benefits, such as no need for directly installing and maintaining sensors on the bridge. However, many of the existing drive-by monitoring approaches are based on supervised learning models that require labeled data from every bridge of interest, which is expensive and time-consuming, if not impossible, to obtain. This labeling requirement is further exacerbated by having multiple diagnostic tasks (e.g., damage detection, localization, and quantification) because they have different learning difficulties. To this end, we introduce a multi-task domain adaptation framework that transfers the damage diagnosis model learned from one bridge to a new bridge without requiring any labels from the new bridge in any of the tasks. Our framework trains a hierarchical neural network model in an adversarial way to extract task-shared and task-specific features that are informative to multiple diagnostic tasks and invariant across multiple bridges. We evaluate our framework on experimental laboratory data collected from 2 bridges and 3 vehicles. We achieve accuracies of 95% for damage detection, 93% for localization, and up to 72% for quantification, which are ~2 times improvements from a baseline method.