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

Abstract

Several studies have reported the effect of various additives on the moisture 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 aggregates and mix’s variables using Artificial Neural Network (ANN). The variables studied include air voids $(AV)$, void in mineral aggregates $(VMA)$, clay lump $(CL)$, Los Angeles’s abrasion $(LA)$, soundness value (SV), sand equivalence 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.

KEYWORDS:

• Moisture resistance
• asphalt concrete
• aggregates
• artificial neural network
• moisture damage

Acknowledgments

The authors acknowledge the support provided by Municipality of Eastern Province, Dammam, KSA, and Imam Abdulrahman Bin Faisal University, Dammam, KSA, in carrying out this research.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.