Vision-Based Structural Damage Identification in Vibrating Beams via Dynamic Mode Decomposition

TL;DR

This paper introduces a novel, data-driven method using Dynamic Mode Decomposition (DMD) to identify structural damage in vibrating beams from high-speed video, enabling non-contact, interpretable damage detection.

Contribution

The study develops a DMD-based framework that extracts modal features from video data for damage detection, validated through numerical simulations and real experiments.

Findings

DMD effectively reconstructs and predicts system responses from partial video data.

The damage index based on DMD features distinguishes healthy and damaged states.

Results show consistent damage detection across simulations and experiments.

Abstract

Structural damage detection using non-contact sensing remains a challenging problem in structural health monitoring. This study presents a data-driven framework based on Dynamic Mode Decomposition (DMD) for extracting structural dynamics directly from high-speed video recordings of vibrating structures. Within this approach, the underlying dynamics are approximated by a linear operator, whose spectral decomposition yields modal frequencies and corresponding spatial mode shapes, enabling a physically interpretable representation of the system response. The proposed methodology is evaluated through both numerical and experimental investigations. First, a cantilever beam model is simulated in ANSYS under healthy and damaged conditions. DMD is applied to partial observation data to reconstruct and predict the system response, while the extracted modal features are analyzed to characterize damage-induced variations. Second, high-speed video recordings of the beam are processed into spatiotemporal snapshot matrices, allowing DMD to recover full-field dynamic behavior without contact sensors. To enable quantitative assessment, a damage index is formulated based on DMD-derived modal features, capturing deviations in both frequency content and spatial characteristics. The results demonstrate consistent and distinguishable patterns between healthy and damaged states across both simulation and experiments, highlighting the capability of DMD as a robust and interpretable tool for non-contact damage detection using video data.