Using implicit correlations among synchronized vibration signals from pixels to improve the accuracy of structural damage detection

In recent years, deep neural networks have been used increasingly to process vibration signals for detecting structural damage. However, the effectiveness of deep neural networks relies on having many vibration signals, which are difficult to acquire in practical engineering scenarios. To address this limitation, a phase-based motion estimation (PME) technique has been introduced, which treats each pixel as an independent sensor, enabling the extraction of millions of vibration signals from a single video. PME not only provides sufficient training data for deep neural networks but also ensures that the signals obtained from multiple pixels are perfectly synchronized in the temporal domain. The implicit correlations among synchronized signals from multiple pixels (i.e., pixel-dependencies) have the potential to enhance damage detection. However, it remains challenging to use the pixel-dependencies effectively to facilitate damage detection. To address this issue, a multi-feature-attention network is proposed. Innovatively, the contribution of pixel-dependencies to damage detection is quantified. By assigning greater attention weights to pixel-dependencies with greater contributions, the network achieves a substantial improvement in damage detection performance. The effectiveness of the proposed method was validated by successfully detecting subtle bolt looseness in a steel structure, showcasing its superior performance in structural damage detection tasks.