Physics-guided diagnosis framework for bridge health monitoring using raw vehicle accelerations

Damage detection of bridges using vibrations from a passing vehicle has received a lot of interest recently. Though non-modal parameter-based methods (e.g., data-driven approaches) have shown promising results in this context, their advancement towards a comprehensive and rigorous monitoring system is hampered by their overreliance on machine learning techniques. On this background, this paper proposes a novel automatic physics-guided diagnosis framework for bridge health monitoring utilizing only raw vehicle accelerations. First, numerical studies are conducted to investigate the relationship between vehicle time-domain signals and bridge damage, based on which a new damage index is proposed. At the same time, it also explores the identification of damage locations and proposes a location index. Second, a damage diagnosis framework, which consists of a data processing method and a physics-guided model, is designed to overcome deficiencies from a drive-by measurement and to automate the damage detection process. The proposed framework was validated using datasets acquired from laboratory experiments employing a scale vehicle model and a steel beam. The results affirmed the method's efficacy in damage indication, quantification, and localization. Moreover, the superiority of the proposed damage index and the rationale for the proposed physics-guided approach were also demonstrated through comparisons with machine learning-based methods.

Automated summary

This study proposes a novel automatic physics-guided diagnosis framework for bridge health monitoring using only raw vehicle accelerations. Numerical studies were conducted to investigate the relationship between vehicle time-domain signals and bridge damage, leading to the proposal of a new damage index and a location index. The proposed framework was validated through experiments and demonstrated its efficacy in damage indication, quantification, and localization. Comparisons with machine learning-based methods also showed the superiority of the proposed damage index and the rationale for the physics-guided approach.