HierMUD: Hierarchical Multi-task Unsupervised Domain Adaptation between Bridges for Drive-by Damage Diagnosis
This addresses the practical challenge of bridge health monitoring for infrastructure managers by enabling damage diagnosis across bridges without costly labeled data, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of expensive labeled data requirements for bridge damage diagnosis using drive-by vehicle vibrations by introducing a hierarchical multi-task unsupervised domain adaptation framework that transfers models between bridges without target labels. The framework achieves 95% damage detection accuracy, 93% localization accuracy, and up to 72% quantification accuracy, representing approximately 2x improvements over baseline methods.
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. To this end, we introduce a new framework that transfers the model learned from one bridge to diagnose damage in another bridge without any labels from the target bridge. 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 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 baseline methods.