Dr. Yolibeth Mejias, P. Eng., Sr. Project Engineer at the Ontario Ministry of Transportation
Application of Image analysis techniques to develop a quality control (QC) tool for automated optimum binder content (OBC) determination of Open-graded friction Course (OGFC) mixtures
In some transportation agencies including the Florida Department of Transportation (FDOT), open-graded friction course (OGFC) mixtures are designed by estimating the optimum binder content (OBC) based on visual inspection of the asphalt binder draindown (ABD) configuration of three OGFC samples placed on pie plates with pre-determined trial asphalt binder contents (AC). The inspection of the ABD configuration is performed by trained and experienced technicians who determine the OBC using perceptive interpolation or extrapolation based on the known AC values of the above samples.
In order to eliminate the human subjectivity involved in this method, the authors first developed an automated image processing-based methodology, an Artificial Intelligence (AI) application for prediction of the OBC using digital images of the pie plate specimens (PPS). In the extended research effort reported in this paper, a quality control tool (QCT) was developed for the aforementioned automated method (AI) to enhance its reliability when implemented by other agencies and contractors. QCT is developed using three quality control imaging parameters (QCIP), orientation, spatial distribution, and segregation of ABD configuration of PPS images. Then, the above QCIP were evaluated from PPS images of a variety of mixture designs produced using the FDOT visual method. The statistical and computer-generated, results indicated that the selected QCIP are adequate for the formulation of quality control criteria for PPS production. The authors believe that the developed QCT will enhance the reliability and accuracy of the automated OBC estimation image processing-based methodology.