Anisotropic masonry failure criterion using artificial neural networks

In the last decades, a plethora of advanced computational models and techniques have been proposed on the modeling, assessment and design of masonry structures. The successful application of such sophisticated models necessitates the development of reliable analytical models capable of describing the failure of masonry materials. Nevertheless, there is a lack of analytical models due to the anisotropic and brittle nature exhibited by the masonry materials. In the present paper, the use of neural networks (NNs) is proposed to approximate the failure surface of masonry materials in dimensionless form. The comparison of the derived results with experimental findings as well as analytical results demonstrates the promising potential of using NNs for the reliable and robust approximation of the masonry failure surface under biaxial stress.