Title: Application of artificial neural network for interpreting ultrasonic readings of concrete

Authors: Alexandre Lorenzi, Joao Campagnolo, Luiz Carlos P. Silva Filho

Addresses: Universidade Federal do Rio Grande do Sul, Laboratorio d Ensaios e Modelos Estruturais (LEME), Av. Osvaldo Aranha, 99 CEP 90035-190 Centro, Porto Alegre, RS, Brazil. ' Universidade Federal do Rio Grande do Sul, Laboratorio de Ensaios e Modelos Estruturais (LEME), Av. Osvaldo Aranha, 99 CEP 90035-190 Centro, Porto Alegre, RS, Brazil. ' Universidade Federal do Rio Grande do Sul, Laboratorio de Ensaios e Modelos Estruturais (LEME), Av. Osvaldo Aranha, 99 CEP 90035-190 Centro, Porto Alegre, RS, Brazil

Abstract: 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.

Keywords: concrete; neural networks; strength; ultrasonic methods; artificial neural networks; non-destructive testing.

DOI: 10.1504/IJMPT.2006.008980

International Journal of Materials and Product Technology, 2006 Vol.26 No.1/2, pp.57 - 70

Published online: 10 Feb 2006 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article