Modeling of masonry failure surface under biaxial compressive stress using Neural Networks

Anisotropic Failure Criterion for Britle Materials Using Artificial Neural Networks

“…The methodology of the present work is similar to another study by the authors [11], that focused only on the compression-compression area, where both principal stresses were compressive, i.e. it focused on the third quadrant of the σΙ-σΙΙ plane (compression-compression), without having to do with the other three quadrants.…”

“…uniaxial σΙI), 0.1, 0.25, 0.5 and 1 were obtained from the results using the symmetry of the panels and the loading. The failure envelopes that Page obtained by plotting mean curves for each bed joint angle can be found in Page [17][18][19] and [11]. These failure envelopes are based on the peak strength values obtained from running bond masonry panel tests in which a uniform loading was applied proportionally.…”

“…The 'Clipper' saw has the capacity to hold impregnated diamond edge circular blades of varying thickness and diameters. Two days prior to the date of testing, the 'compressive edge' of the panel (the side on which the compressive loads was to be applied) was capped with 1:1 (cement:sand) mortar [11].…”

“…Using this information, the algorithm adjusts the weights of each connection in order to reduce the value of the error function by some small amount. The procedure is similar to the one used in a previous work by the authors [11], where more details can be found. The transfer function used in the present study is the hyperbolic tangent function, the same for all the hidden and the input layer, which yields output values in the interval [-1, 1], while its derivative yields output values in the interval [0, 1].…”

“…Detailed and in-depth state-of-the-art reports can be found in [6][7][8][9][10][11]. The successful implementation of these advanced models requires reliable analytical constitutive rules such as constitutive equation models of masonry material failure.…”