Compressive strength of masonry made of clay bricks and cement mortar: Estimation based on Neural Networks and Fuzzy Logic

Abstract

The use of mathematical tools such as Artificial Neural Networks and Fuzzy Logic has been shown to be useful for solving complex engineering problems, without the need to reproduce the phenomenon under study, when the only information available consists of the parameters of the problem and the desired results. Based on a collection of 96 laboratory tests, this paper uses Artificial Neural Networks and Fuzzy Logic to determine the compressive strength of a masonry structure composed of clay bricks and cement mortar, by using only two parameters: the compressive strength of the mortar and that of the bricks. These mathematical techniques are an alternative to the complex analytical formulas dependent on a large number of parameters and to empirical formulas, which, even though simple, often give unrealistic values. The results obtained are compared to the calculation methods proposed by other authors and other standards and demonstrate the suitability of using Neural Networks and Fuzzy Logic to predict the compressive strength of masonry.