Automated, strain-based, output-only bridge damage detection

This paper presents a framework for automated damage detection using a continuous stream of structural health monitoring data. The study utilized measured strains from an optimized sensor set deployed on a double track, steel, railway, truss bridge. Stringer-floor beam connection deterioration, a common deficiency, was the focus of this study; however, the proposed methodology could be used to assess the condition of a wide range of structural elements and details. The framework utilized Proper Orthogonal Modes (POMs) as damage features and Artificial Neural Networks (ANNs) as an automated approach to infer damage location and intensity from the POMs. POM variations, which are traditionally input (load) dependent, were ultimately utilized as damage indicators. Input variability necessitated implementing ANNs to help decouple POM changes due to load variations from those caused by deficiencies, changes that would render the proposed framework input independent, a significant advancement. To develop an automated and efficient output-only damage detection framework, data cleansing and preparation were conducted prior to ANN training. Damage "scenarios" were artificially introduced into select output (strain) datasets recorded while monitoring train passes across the selected bridge. This information, in turn, was used to train ANNs using MATLABs Neural Net Toolbox. Trained ANNs were tested against monitored loading events and artificial damage scenarios. Applicability of the proposed, output-only framework was investigated via studies of the bridge under operational conditions. To account for the effects of potential deficiencies at the stringer-floor beam connections, measured signal amplitudes were artificially decreased at select locations. It was concluded that the proposed framework could successfully detect artificial deficiencies imposed on measured signals under operational conditions.