Joao Luiz Campagnolo

Application of artificial neural network for interpreting ultrasonic readings of concrete

Concrete is an essential material for civil engineers. However, its properties can vary considerably, depending on the nature and proportions of the constituents, the construction methods and the loading and environmental conditions. Therefore, the development of methods to determine the state condition and ascertain the quality of concrete elements is critical. This paper describes a study carried out to evaluate the feasibility of developing Artificial Neural Networks (ANN) that use data about concrete properties and ultrasonic readings to estimate compressive strength. The results obtained indicate that the estimation power of a neural network can surpass that of traditional statistical techniques and that this might become a very interesting tool to model certain problems in civil engineering.

Development of artificial neural networks for interpreting ultrasonic pulse velocity tests in concrete

Nondestructive Testing (NDT) techniques are useful tools for analyzing reinforced concrete (RC) structures. The use of Ultrasonic Pulse Velocity (UPV) measurements enables monitoring changes in some critical characteristics of concrete over the service life of a structure. Nonetheless, the current techniques for UPV data analysis are largely based on the sensitivity of the professionals who apply these tests. For accurate diagnosis it is necessary to consider the different factors and conditions that can affect the results. In order to properly control and inspect RC facilities it is essential to develop appropriate strategies to make the task of data interpretation easier and more accurate. This study is based on the idea that using Artificial Neural Networks (ANNs) is a feasible way to generate workable estimation models correlating concrete characteristics, density and compressive strength. The study shows that this goal is achievable and indicates that neural models perform better than traditional statistical models.