Abstract
Reclaimed asphalt pavement (RAP) has grown in popularity in recent years due to its potential to blower costs and minimize negative effects on the environment. RAP incorporation, however, can also significantly influence the mechanical characteristics of asphalt mixtures, which can impact their general effectiveness and longevity. Due to their potential to improve the qualities of revitalized mixes with RAP, waste materials like waste engine oil (WEO) and waste cooking oil (WCO) have attracted interest for use in asphalt mixtures. This study focuses on predicting and optimizing the mechanical properties of revitalized asphalt mixtures using WCO and WEO along with RAP, particularly the modulus of resilience (MR) and indirect tensile strength (ITS). Classification and regression tree (CART) models were developed to forecast MR, ITS, and ITS loss% for asphalt mixes. It was found that the models could accurately predict the experimental data. With a WCO rejuvenator employed in less than or equal to 16.5% proportion, maximum MR and ITS were achieved. To get maximum MR, the asphalt content should not be more than 5.1%. On the other hand, WEO rejuvenator, asphalt content greater than 5.1%, and RAP content not greater than 45%, were used to achieve maximum durability (lowest ITS loss%). A 5% increase in the loss value is the result of choosing the design that provides the most strength. The study’s results encourage the adoption of environmentally friendly pavement building techniques by effectively reusing waste materials and improving the mechanical properties of revitalized asphalt mixtures.
| Original language | English |
|---|---|
| Article number | e02340 |
| Journal | Neural Computing and Applications |
| DOIs | |
| State | Accepted/In press - 2024 |
Bibliographical note
Publisher Copyright:© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.
Keywords
- Asphalt pavements
- CART model
- Machine learning
- Recycled asphalt pavement (RAP)
- Sustainable pavement construction
- Waste oil rejuvenators
ASJC Scopus subject areas
- Software
- Artificial Intelligence