Application of deep learning in structural health management of concrete structures

Abstract

Structural health management constitutes an essential factor in ensuring the durability of concrete structures. Cracks in concrete, reinforcement corrosion, alkali-silica reaction, and efflorescence attacks are commonly concrete defects that can be identified visually. However, detection and classification of these defects in concrete bridges and other high-rise concrete structures are difficult and expensive process in manual approaches. In this research, a deep learning application is applied to detect and classify concrete defects. Concrete images from the public repository were used to create the explored database. The database was divided into training and validation subsets. The visual geometry group (Vgg19), neural search architecture (nasnetlarge), and residual inception block (vinceptionresnetv2) algorithms were used in analysing the images.  The results of the overall performance show that Vgg19 algorithm recorded higher accuracy in the detection and classification of concrete defects as compared to nasnetlarge and inceptionresnetv2 algorithms. The efficiency of the proposed approach was evaluated using a new dataset containing images of concrete defects. The outcome of this research strongly shows that deep learning models could enhance the efficiency of concrete structural health monitoring in a multi-classification scenario.