Sparse Auto-Encoder Networks to Detect and Localize Structural Changes in Metallic Bridges

The application of vibration monitoring integrated with sparse Auto-Encoder (SAE) networks is investigated in this paper with the objective of detecting and localizing structural anomalies or damages. Unlike previous studies on SAE networks, the methodology proposed is based on the definition of a single SAE model, trained with the signals simultaneously collected from several sensors. Once the SAE has been trained using measurements that represent the baseline (undamaged) condition of the structure, the network is likely to reconstruct well newly collected data if the structure maintains its intact condition. When damage or structural degradation processes start developing, an increase in the reconstruction error—defined as the residual between the original input and the reconstructed output—has to be expected, so that a deviation from the normal state is highlighted. Moreover, this rise in reconstruction errors is typically more significant near the damaged areas, allowing for precise localization of the affected zones. The performance and robustness of the proposed approach are illustrated and validated using experimental data from two real-world bridge structures.