In this paper, microscopic technique tests were carried out to observe and evaluate the degree of blending between reclaimed asphalt pavement (RAP) binder and virgin binder in hot mixed asphalt mixture. To this end, titanium dioxide (TiO2) was selected as a tracer to tag virgin binder. Scanning electron microscope/energy dispersive spectrometer (SEM/EDS) experiments were conducted on compacted recycled asphalt mixtures and virgin asphalt mixtures. The element mass ratio of titanium over sulfur (Ti:S) was proposed as an quantitative indicator of blending ratio to accurately evaluate the degree of partial blending between RAP and virgin binders. The SEM/EDS images visually displayed the partial blending in high RAP mixtures. Different partial blending patterns were observed under different handling processes. The results of EDS tests indicated that with the increase of the RAP content, the blending degree of virgin and aged binder decreased rapidly, and the homogeneity of blended binder became weakened. In addition, aging process and recycling agent could improve the efficiency of RAP binder as it is blended with virgin one, and it should be noted that the inter-diffusion of old and new binders need enough time. This methodology provides a systemic approach to determine the degree of binder blending in RAP mixture.
Inappropriate maintenance and rehabilitation strategies cause many problems such as maintenance budget waste, ineffective pavement distress treatments, and so forth. A method based on a machine learning algorithm called deep reinforcement learning (DRL) was developed in this presented research in order to learn better maintenance strategies that maximize the long-term cost-effectiveness in maintenance decisionmaking through trial and error. In this method, each single-lane pavement segment can have different treatments, and the long-term maintenance cost-effectiveness of the entire section is treated as the optimization goal. In the DRL algorithm, states are embodied by 42 parameters involving the pavement structures and materials, traffic loads, maintenance records, pavement conditions, and so forth. Specific treatments as well as do-nothing are the actions. The reward is defined as the increased or decreased cost-effectiveness after taking corresponding actions. Two expressways, the Ningchang and Zhenli expressways, were selected for a case study. The results show that the DRL model is capable of learning a better strategy to improve the long-term maintenance cost-effectiveness. By implementing the optimized maintenance strategies produced by the developed model, the pavement conditions can be controlled in an acceptable range.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.