New model of moisture susceptibility of nano silica-modified asphalt concrete using GMDH algorithm

Abstract

Abstract The primary objectives of the design and implementation of asphalt pavement on road and road surfaces are to achieve the best performance in different climatic conditions. Asphalt pavement performance depends on the adhesion and bonding of binder and aggregates that the moisture causes it to disappear and it results in bleeding and stripping. Although the moisture susceptibility mechanism is not fully known, factors such as binder properties, aggregates properties, asphalt mixture properties, quality control during congestion, the dynamic effect of traffic load and the type of anti-stripping additive play a significant role in creating a moisture susceptibility and aggravation of failures. In this paper, Group Method of Data Handling (GMDH)-type neural networks have been used for modeling and prediction of moisture susceptibility of nano silica-modified asphalt concrete. To achieve this goal, 5 types of mixtures with different percentage of nano-silica (0, 0.2, 0.4, 0.7 & 0.9%) were prepared and the moisture susceptibility of modified mixtures was evaluated. Results showed that nano-silica can improve the moisture susceptibility of asphalt mixtures. For modeling, the experimental data were divided into train and test sections (70% for training and 30% for testing). The predicted values were compared with those of experimental values in order to estimate the performance of the GMDH-neural network. The model values showed a very good regression with the experimental results.