Prediction and verification of compressive strength of historicalmasonry structures with artificial neural network

Compressive strength and modulus of elasticity are the key material properties of historical structures to adapt finite element model to obtain correct structural assessment. Generally, modulus of elasticity is adapted by multiplying compressive strength of the material. In this paper, it is aimed to predict compressive strength of historical masonry buildings by using material characteristics and physical characteristics. For this purpose, 21 historical masonry mosques, churches and cathedrals were selected. Unit weight, wall thickness, height of the structure, plan area and modulus of elasticity of the selected 21 historical structures are listed as material characteristics and physical characteristics for using compressive strength prediction. Artificial Neural Network model is used to predict compressive strength of 13 different historical structures. Performance of prediction is verified by using MATLAB among all 34 total historical structures. 0.83 Rsquare is obtained from the prediction model and total prediction performance is obtained from trained data 0.97 and 0.79 from all 34 data by using MATLAB.