RESUMEN
Analysing concrete microscopic images is difficult because of its highly heterogeneous composition and the different scales involved. This article presents an open-source deep learning-based algorithm dedicated to air-void detection in concrete microscopic images. The model, whose strategy is presented alongside concrete compositions information, is built using the Mask R-CNN model. Model performances are then discussed and compared to the manual air-void enhancement technique. Finally, the selected open-source strategy is exposed. Overall, the model shows a good precision (mAP = 0.6452), and the predicted air void percentage agrees with experimental measurements highlighting the model's potential to assess concrete durability in the future.
Analyzing concrete microscopic images is difficult because of its highly heterogeneous composition and the different scales involved, e.g. cement paste, sand, and aggregates are the major phases at a microscopic scale. However, characterizing concrete microstructure is of paramount importance to assess its mechanical properties and durability. For example, air voids decrease the mechanical properties but can increase the resistance to freeze-thaw if correctly distributed and of small size. This article presents an open-source deep learning-based algorithm dedicated to air-void detection in concrete microscopic images. The model, whose strategy is presented alongside concrete compositions information, is built using the Mask R-CNN model. Model performances are then discussed and compared to the manual air-void enhancement technique, which involves coloring concrete surfaces and filling air voids with fine powder before taking images. Finally, the selected open-source strategy is exposed. Overall, the model shows a good precision (mAP = 0.6452), and the predicted air void percentage agrees with experimental measurements highlighting the model's potential to assess concrete durability in the future.
