Studying the impact of aggregates and mix volumetric properties on the moisture resistance of asphalt concrete using a feed-Forward artificial neural network

Several studies have reported the effect of various additives on the mois-ture resistance of AC, but limited studies explored the impact of aggregate's properties on the moisture sensitivity of AC. In this study, the influence of aggregate properties and mix's volumetric properties on the moisture sensitivity of AC was studied. The moisture sensitivity of the AC was based on Retained Stability Index (RSI). The study utilised results from 319 plant-produced asphalt mixtures. The RSI was modelled as a function of aggre-gates and mix's variables using Artificial Neural Network (ANN). The vari-ables studied include air voids (AV), void in mineral aggregates (VMA), clay lump (CL), Los Angeles's abrasion (LA), soundness value (SV), sand equiv-alence value (SEV), gradation and mix type. Profile method along with weight-connection relative importance ranking were employed to analyse the influence of the input variables on the RSI. The relationship between these variables and the RSI fits higher order polynomial functions.

Automated summary

Several studies have focused on the impact of additives on the moisture resistance of AC, but few have explored the influence of aggregate properties. This study investigates the effect of aggregate properties and mix volumetric properties on the moisture sensitivity of AC. The study uses 319 plant-produced asphalt mixture samples and models the moisture sensitivity based on the Retained Stability Index (RSI) using Artificial Neural Network (ANN). The relationship between the variables and RSI follows higher order polynomial functions.