Stiffness Modulus and Marshall Parameters of Hot Mix Asphalts: Laboratory Data Modeling by Artificial Neural Networks Characterized by Cross-Validation

Nicola Baldo,Matteo Miani,Evangelos Manthos

doi:10.3390/app9173502

Nicola Baldo, Matteo Miani + Show 1 more

Open Access

https://doi.org/10.3390/app9173502

Copy DOI

Abstract

The present paper discusses the analysis and modeling of laboratory data regarding the mechanical characterization of hot mix asphalt (HMA) mixtures for road pavements, by means of artificial neural networks (ANNs). The HMAs investigated were produced using aggregate and bitumen of different types. Stiffness modulus (ITSM) and Marshall stability (MS) and quotient (MQ) were assumed as mechanical parameters to analyze and predict. The ANN modeling approach was characterized by multiple layers, the k-fold cross validation (CV) method, and the positive linear transfer function. The effectiveness of such an approach was verified in terms of the coefficients of correlation ( R ) and mean square errors; in particular, R values were within the range 0.965 – 0.919 in the training phase and 0.881 – 0.834 in the CV testing phase, depending on the predicted parameters.

Highlights

Road pavements are transport infrastructures built with different types of hot mix asphalt (HMA), namely mixtures made of aggregates and bitumen, mixed at temperatures higher than 150 ◦ C
Annex (IT-CY), using the standard conditions: Temperature ofaggregates, 20 °C and a target evaluated for stiffness and the results are presented in Table S6 for HMAs with limestone and diabase deformation and rise time equal to 5 μm and 124 ms, respectively
Evaluated for stiffness and the results are presented in Table S6 for HMAs with limestone and diabase aggregates, 4.1

Summary

Introduction

Road pavements are transport infrastructures built with different types of hot mix asphalt (HMA), namely mixtures made of aggregates and bitumen, mixed at temperatures higher than 150 ◦ C. In order to withstand traffic loads and environmental conditions, such infrastructures have to be properly designed in terms of their thickness and material properties. With respect to the composition and mechanical characteristics of HMAs, experimental methods are currently used to design and optimize such bituminous mixtures [1,2,3,4,5,6]. For what concerns the bitumen content identification and the mixtures’ performance evaluation, quite onerous laboratory tests are necessary; such experimental procedures require experienced and skilled technicians. Any modification of the HMAs composition, in terms of type or quantity of bitumen, rather than of aggregates, requires new laboratory tests. A numerical model of HMAs’ mechanical behavior that could quickly elaborate a reliable prediction of the material’s response would allow a reduction in time and costs for the design of the mixture itself

Objectives

Methods

Results

Conclusion