Development of Deep Neural Network-Based Strain Values Prediction Models for Full-Scale Reinforced Concrete Frames Using Highly Flexible Sensing Sheets

Abstract

Structural Health monitoring systems (SHM) are commonly used to identify and assess structural damage. In terms of damage detection, SHM needs to periodically collect data from sensors placed in the structure as damage-sensitive features. These include abnormal changes due to strain fields and abnormal symptoms of the structure, such as damage and deterioration. At present, large-scale deployment of sensors in existing structures to cover large areas is still difficult to overcome, while increasing maintenance costs. In this study, a strain sensing sheet with high tensile strength is used to collect the strain data set generated on the concrete surface of the full-scale reinforced concrete (RC) frame structure when the cyclic load is applied to its limit. On this basis, two prediction models of deep neural network for frame beam and frame column are established. The training results show that they can predict the strain value accurately and have good generalization ability. These two deep neural network prediction models will also be deployed in SHM systems in the future as part of the intelligent strain sensor system.