APPLICATION OF ANFIS FOR EVALUATING THE STRENGTH OF THE CONCRETE ROAD DURING CONSTRUCTION

Abstract

The quality of rigid pavement road during construction is an important process for construction supervision. Even though many methods have been proposed, they are based on field test (Destructive and Non-destructive) and there has not been an intelligence-based approach for predicting the quality of concrete. This paper proposes, by applying the principles of the Adaptive Neuro-Fuzzy Inference system (ANFIS), an ANFIS based approach for predicting the quality of concrete of rigid pavement. The total number of 40 examples of coring rigid pavement were acquired from the Department of Rural Roads for study in this research, 36 examples of which were used to train for construction of a new prediction model for the quality of concrete of rigid pavement. The model was then used to predict the quality of concrete of the remaining four examples. A comparison was made between the predicted results and the practical measurements. The comparison results showed that the proposed ANFIS based approach was accurate enough and could be applied for predicting the quality of concrete of rigid pavement.