Local shear connectors damage detection for a concrete-steel composite beam using acceleration time series

Abstract

Shear connectors in composite structures are of great importance to provide composite action and damage or failure of the connectors will affect the mechanical properties. In this paper, a nonparametric connector damage detection methodology with neural network was proposed. Vibration tests on the composite beam before and after loosening or removing some connectors were implemented and the corresponding acceleration responses were acquired. Using acceleration time series at certain locations of a substructure of the intact composite beam, nonparametric base-line model based on neural network was established. When the connectors are loosened or removed, the acceleration response measurements of the structure close to the connectors to be monitored do not meet the output of the corresponding neural network model. The difference between the output and the measurement provides an index for damage detection of the connector. Results show that the proposed nonparametric method is effective to detect damage of shear connectors for composite structures solely using acceleration time series.