Using artificial neural network and non-destructive test for crack detection in concrete surrounding the embedded steel reinforcement

Bond between steel and concrete is one of the key aspects of structural design and its performance evaluation. In the past much research work has been focused on understanding bond deterioration owing to corrosion of reinforcement, however, there exists no nondestructive method to access the bond condition. In this regard, the presented experimental research work details the development of a nondestructive testing method to estimate the crack condition of concrete surrounding the steel reinforced by using ultrasonic pulse velocity test. In addition, a multilayer feedforward back propagation perceptron artificial neural network (ANN) is developed in order to avoid simplification assumptions for developing models to predict the cracking, owing to the nonlinear complex stress distribution at the steel-concrete interface. The ANN is used to predict the crack width and to conduct sensitivity analysis of the various factors influencing the bond deterioration. A high accuracy level is achieved between the predicted and the experimental values with R-2 of 0.97 and the most influential parameter is highlighted.

Automated summary

This study developed a nondestructive testing method to evaluate the crack condition of steel reinforced concrete, and utilized an artificial neural network to predict crack width and conduct sensitivity analysis on factors influencing bond deterioration, achieving a high accuracy level with an R-2 value of 0.97.