An optimal aggregate size distribution is crucial for concrete strength and quality and can significantly reduce cement consumption and associated CO2 emissions. The composition of the aggregate mixtures used for concrete production is characterized by means of the sieve curve. This cumulative curve indicates the mass fraction of aggregate particles of different sizes in a mixture. The traditional method of aggregate grading includes separating of the particles with sieves of different mesh sizes, a process that is time-consuming and invasive. The smartphone app developed by the authors is capable of analysing photographs taken with a mobile phone camera in fractions of a second. It detects individual aggregate particles, calculates their size distribution and characterizes the particle shapes. Due to the non-contact technology, this method is particularly suitable for the continuous monitoring of aggregates on conveyor belts in concrete plants as well as for fast manual checks. Currently, the app is still in the early stages of development but can already be tested by interested parties (see below).
Subscribe to magazineContact
Sharik Siddiqi und Dr. Jan Rybizki, Institute for Applied Building Research gGmbH, Weimar, Germany Stefan Thor, Logikwerk GmbH, Meiningen, Germany References [1] Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., “You Only Look Once: Unified, Real-Time Object Detection”, <i>arXiv e-prints</i>, 2015. doi:10.48550/arXiv.1506.02640. [2] Terven, J. and Cordova-Esparza, D., “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS”, <i>arXiv e-prints</i>, 2023. doi:10.48550/ arXiv.2304.00501. [3] Coenen, M.; Beyer, D.; Heipke, C.; Haist, M. (2022): Learning to Sieve: Prediction of Grading Curves from Images of Concrete Ag- gregate, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-2-2022, pp. 227–235