No abstract

No abstract

This paper presents a study about a Machine Learning approach for modeling the stiffness of different high-modulus asphalt concretes (HMAC) prepared in the laboratory with harder paving grades or polymer-modified bitumen which were designed with or without reclaimed asphalt (RA) content. Notably, the mixtures considered in this study are not part of purposeful experimentation in support of modeling, but practical solutions developed in actual mix design processes. Since Machine Learning models require a careful definition of the network hyperparameters, a Bayesian optimization process was used to identify the neural topology, as well as the transfer function, optimal for the type of modeling needed. By employing different performance metrics, it was possible to compare the optimal models obtained by diversifying the type of inputs. Using variables related to the mix composition, namely bitumen content, air voids, maximum and average bulk density, along with a categorical variable that distinguishes the bitumen type and RAP percentages, successful predictions of the Stiffness have been obtained, with a determination coefficient (R2) value equal to 0.9909. Nevertheless, the use of additional input, namely the Marshall stability or quotient, allows the Stiffness prediction to be further improved, with R2 values equal to 0.9938 or 0.9922, respectively. However, the cost and time involved in the Marshall test may not justify such a slight prediction improvement.

The paper presents the influence of laboratory aging simulation on fracture properties determined on 150 variants of asphalt mixtures. The fracture properties were determined by two different test approaches—semi-circular bending test (SCB test) and three-point bending test on beam specimens (3-PB test). The aging was simulated according to one of the methods defined in EN 12697-52 (storage of test specimens in chamber at temperature of 85 °C for 5 days). The evaluated group of variants covered asphalt mixtures for all road layers. The group was further divided according to used bituminous binder (unmodified vs. modified) and reclaimed asphalt content. The results showed that strength parameters (flexural strength and fracture toughness) increase with aging. It further shows that fracture work provides more complex information about the cracking behavior. For the aging indexes, it was found that for mixtures with modified binders and mixtures which did not contain reclaimed asphalt (RA), the values were higher. The aging indexes for fracture work showed different results for both performed tests.

Recently, environmental concerns have become a primary driving force in most countries and industries dealing with natural resources. As a part of this category, asphalt pavement industry is trying to implement more green and sustainable features in its products, while maintaining the mechanical and performance-based properties of the resulting asphalt mixtures. Among potential recycled materials, vehicle tires and aged asphalt pavement have been demonstrated to show economic, ecological, and behavioral improvements in the mixtures. However, mixtures with a high content of reclaimed asphalt (RA) and crumb rubber present some limitations. Therefore, using another group of additives, i.e., a warm mix asphalt (WMA) additive, has been considered. The presented paper investigates the use of an elevated content of RA with different crumb rubber modified binders and (in some mixtures) a warm mix additive in an asphalt concrete (AC) binder mix. Regular empirical tests have been conducted and more advanced performance or functional characteristics, i.e., stiffness, thermal induced cracking, resistance to permanent deformation, complex modulus have been determined and evaluated. Selected results are presented in the paper.