Prediction of early heat of hydration of plain and blended cements using neuro-fuzzy modelling techniques

In this study, a new approach based on an adaptive neuro-fuzzy inference system (ANFIS) was presented for the prediction of early heat of hydration of plain and blended cements. Two different type of model is trained and tested using these data. The data used in these models are arranged in a format of five input parameters that cover the additives percentage (AP), grinding type (GT) and finesses of cements (FC) and an output parameter which is heat of hydration of cements (HHC). The results showed that neuro-fuzzy models have strong potential as a feasible tool for evaluation of the effect of additives percentage, grinding type (GT) and finesses of cements on the early heat of hydration of cements. Some conclusions concerning the impacts of features on the prediction of early heat of hydration of plain and blended cements were obtained through analysis of the ANFIS. The results are highly promising, and a comparative analysis suggests that the proposed modelling approach outperforms ANN model in terms of training performances and prediction accuracies. The results show that the proposed ANFIS model can be used in the prediction of early heat of hydration of plain and blended cements.