In this paper, a Back Propagation Neural Network (BPNN) is used to predict crack pattern for masonry panels with opening subjected to lateral loading. The cellular automata method is used to digitalize the panels, including two steps - dividing a panel into a certain number of cells and calculating cell state values by use of a Von Neumann neighborhood model. These digitalized values are used as input data of NN model, respectively. All the experimental data is collected, including panel configuration, material property, opening ratio and location, state values, and crack pattern. The NN model is trained repeatedly, taking part of the data as a training set, to determine parameters, and the rest of the data is taken to check the model. Well-trained NN models can predict the crack pattern of any other panel. The results show that NN method is suitable for prediction of crack pattern. Comparing the two ways of prediction, the Fragility Coefficient Method gets a more precise pattern. The predicted cracks are distributed successively in some specific areas, especially in high similarity, compared with experimental crack pattern.
Full Text (PDF)