Deep learning-based damage estimation in concrete structures using acoustic emission data

Abstract

Conventional structural testing methods assess damaged condition of the structures and they generally base on subjective visual inspection. To take necessary precautions before/during a disaster, real-time monitoring of damage progression is very important especially for critical structures such as bridges, viaducts, tunnels, dams and nuclear power plants. Acoustic emission (AE) has been proved to be a successful method for this purpose and it is used to locate even invisible micro-level cracks in the structures. The most important feature that makes this technique advantageous over other non-destructive testing methods is that it continuously monitors damages in structures subjected to load by sensors converting the waves emitted from the damage into electrical signals. By analyzing the parameters of the recorded signals, critical information such as the type, location, origination-time, size and direction of the damage can be obtained. In this study, it was aimed to estimate damage status of the concrete members exposed to loading by developing a deep learning-based damage detection model. This model was developed by monitoring AE activities of concrete and reinforced concrete specimens with different strength, size, properties and loading conditions. Afterwards, a relationship was established between the properties and load levels of the specimens with features of the AE signals. The developed model was tested on reinforced concrete elements under load. The results show that the model is successful at estimating the damage level.