Application of adaptive neuro-fuzzy technique to predict the unconfined compressive strength of PFA-sand-cement mixture

The paper addresses the application of an adaptive neuro-fuzzy (ANFIS) computing technique to predict the unconfined compressive strength of the pulverized fuel ash-cement-sand mixture. A series of unconfined compressive tests were performed on several mixtures of cement, pulverized fuel ash (PFA), and sand for checking and training data for the ANFIS network. Although some mathematical functions were applied to model the unconfined compressive strength of the construction materials, numerous setbacks of the models were observed. The artificial neural network (ANN) can be used as an analytical method for various prediction purposes because it provides the benefit of independency on the knowledge of internal system parameters, compressed compact solution in terms of multi-variable problems and rapid computation. The ANFIS is a particular class of the ANN family with attractive estimation and learning potentials. This provides a suitable platform when the analysis is aimed to counter the uncertainties in a system. The ANFIS RMSE was 0.0617 for prediction of the unconfined compressive strength of the pulverized fuel ash-cement-sand mixture. (C) 2015 Elsevier B.V. All rights reserved.