Prediction model for compressive strength of basic concrete mixture using artificial neural networks

In the present paper, we propose a prediction model for concrete compressive strength using artificial neural networks. In experimental part of the research, 75 concrete samples with various w/c ratios were exposed to freezing and thawing, after which their compressive strength was determined at different age, viz. 7, 20 and 32 days. In computational phase of the research, different prediction models for concrete compressive strength were developed using artificial neural networks with w/c ratio, age and number of freeze/thaw cycles as three input nodes. We examined three-layer feed-forward back-propagation neural networks with 2, 6 and 9 hidden nodes using four different learning algorithms. The most accurate prediction models, with the highest coefficient of determination (R (2) > 0.87), and with all of the predicted data falling within the 95 % prediction interval, were obtained with six hidden nodes using Levenberg-Marquardt, scaled conjugate gradient and one-step secant algorithms, and with nine hidden nodes using Broyden-Fletcher-Goldfarb-Shannon algorithm. Further analysis showed that relative error between the predicted and experimental data increases up to acceptable a parts per thousand 15 %, which confirms that proposed ANN models are robust to the consistency of training and validation output data. Accuracy of the proposed models was further verified by low values of standard statistical errors. In the final phase of the research, individual effect of each input parameter was examined using the global sensitivity analysis, whose results indicated that w/c ratio has the strongest impact on concrete compressive strength.