Estimation of compressive strength of hollow concrete masonry prisms using artificial neural networks and adaptive neuro-fuzzy inference systems

This paper proposes the use of artificial neural networks and adaptive neuro-fuzzy inference systems for estimating the compressive strength of hollow concrete block masonry prisms. Three main influential parameters, namely the prisms' height-to-thickness ratio and the compressive strengths of hollow concrete blocks and mortars, were used as input to the models. The two models were trained and tested using 102 data sets obtained from the tests conducted by the authors as well as published technical literatures and then verified by comparison with other empirical calculation methods. The results showed that the proposed models have excellent prediction ability with insignificant error rates.