The compaction of a hot mix asphalt depends on a number of important factors whose control, during the execution of the pavement, is complex; however it is essential to achieve the results envisaged in the design with the least possible cost. Therefore, the evaluation of the effect of these variables on the material density is important as well as their quantification in real time. This research, starting from a survey of some environmental variables, together with the hot mix asphalt density using an electrical impedance device, through the application of a neuro-fuzzy technique, proposes a procedure to classify the most important features. These results can be rapidly deduced during the paving operations; calibrations required to correct the compaction can be applied on site without waiting further time necessary for the extraction of the cores and the subsequent laboratory analysis. In this way it is possible to identify with a better precision the aspects of the environmental context requiring more attention. In addition, the model permits the inclusion of new input variables and additional data that can be recorded in following phases.
The aim of this paper is the proposal of an expeditious procedure to be used during the execution of an asphalt layer for improving the compaction task. This procedure, based on a fuzzy clustering technique, starts from the knowledge of some information recorded by ordinary measuring instruments and provides an aid to the decision-maker on the number of roller passes needed to achieve a specific density at a certain temperature. This result can be deduced with great rapidity during the paving operations on site without waiting for the time spent in the core extraction and in the subsequent laboratory analysis. In this way it is possible to identify more precisely which aspects of the execution have to be corrected for performing the best compaction.
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.