Modelling of Asphalt's Adhesive Behaviour Using Classification and Regression Tree (CART) Analysis.

Md Arifuzzaman,Okan Sirin,Md Shah Alam,Uneb Gazder,Abdullah Al Mamun

doi:10.1155/2019/3183050

Abstract

The modification by polymers and nanomaterials can significantly improve different properties of asphalt. However, during the service life, the oxidation affects the constituents of modified asphalt and subsequently results in deviation from the desired properties. One of the important properties affected due to oxidation is the adhesive properties of modified asphalt. In this study, the adhesive properties of asphalt modified with the polymers (styrene-butadiene-styrene and styrene-butadiene) and carbon nanotubes were investigated. Asphalt samples were aged in the laboratory by simulating the field conditions, and then adhesive properties were evaluated by different tips of atomic force microscopy (AFM) following the existing functional group in asphalt. Finally, a predictive modelling and machine learning technique called the classification and regression tree (CART) was used to predict the adhesive properties of modified asphalt subjected to oxidation. The parameters that affect the behaviour of asphalt have been used to predict the results using the CART. The results obtained from CART analysis were also compared with those from the regression model. It was observed that the CART analysis shows more explanatory relationships between different variables. The model can predict accurately the adhesive properties of modified asphalts considering the real field oxidation and chemistry of asphalt at a nanoscale.

Highlights

Academic Editor: Amparo Alonso-Betanzos e modification by polymers and nanomaterials can significantly improve different properties of asphalt
A predictive modelling and machine learning technique called the classification and regression tree (CART) was used to predict the adhesive properties of modified asphalt subjected to oxidation. e parameters that affect the behaviour of asphalt have been used to predict the results using the CART. e results obtained from CARTanalysis were compared with those from the regression model
This study predicted the adhesive properties of oxidized asphalt using a predictive modelling and machine learning technique, i.e., the classification and regression tree (CART). e model addresses the adhesive properties of modified asphalt simulating the real field oxidation and chemistry of asphalt at a nanoscale

Summary

Research Article

Modelling of Asphalt’s Adhesive Behaviour Using Classification and Regression Tree (CART) Analysis. In addition to providing different aforementioned properties, it is observed that the use of SB and SBS significantly affects the adhesive properties of asphalt [7]. Some of the studies that addressed the adhesive properties of the PMA [23,24,25] or CMA [26, 27] considered the effect of moisture rather than oxidization In this regard, this study predicted the adhesive properties of oxidized asphalt (modified by polymers and CNTs) using a predictive modelling and machine learning technique, i.e., the classification and regression tree (CART). It can be seen from the figure that the PMA will be modified using two different types of CNTs (each one comprises three different percentages). Once the PMA is modified by a CNT (named PCA), the samples are divided into two groups, such as fresh and oxidized. e adhesive properties of each sample are analysed using five different tips of AFM. e parameters (percentage and type of CNT, functional group, polymer type, etc.) that affect the behaviour of asphalt have been used

Conclusion and recommendation Figure

Very tiny AFM tip Test sample

Test sample