TY - JOUR
T1 - Automated estimation of cementitious sorptivity via computer vision
AU - Kabir, Hossein
AU - Wu, Jordan
AU - Dahal, Sunav
AU - Joo, Tony
AU - Garg, Nishant
N1 - The authors gratefully acknowledge the partial support received from the Department of Civil and Environmental Engineering at the University of Illinois Urbana-Champaign, as it was essential to the successful completion of this study. Special thanks are extended to Ishita Purwar and Ahmed Ibrahim for their contributions to annotating natural images and creating synthetic models. The authors recognize the assistance of Ishaan Murarka during mass measurements of paste samples. The authors also express appreciation to Jordan Ouellet, Nischal Kanel, and Aysan Farajnia for their role in casting mortar and concrete samples, which was vital for validating the proof of concept. The authors thank Muhammad Farjad Iqbal for assisting with the particle size analysis of anhydrous cement powders. Finally, the authors extend their gratitude to Brielle Feng for her assistance with the graphical design of a few schematics in the paper and to Sara Perez for proofreading the manuscript.
PY - 2024/12
Y1 - 2024/12
N2 - Monitoring water uptake in cementitious systems is crucial to assess their durability against corrosion, salt attack, and freeze-thaw damage. However, gauging absorption currently relies on labor-intensive and infrequent weight measurements, as outlined in ASTM C1585. To address this issue, we introduce a custom computer vision model trained on 6234 images, consisting of 4000 real and 2234 synthetic, that automatically detects the water level in prismatic samples absorbing water. This model provides accurate and frequent estimations of water penetration values every minute. After training the model on 1440 unique data points, including 15 paste mixtures with varying water-to-cement ratios from 0.4 to 0.8 and curing periods of 1 to 7 days, we can now predict initial and secondary sorptivities in real time with high confidence, achieving R² > 0.9. Finally, we demonstrate its application on mortar and concrete systems, opening a pathway toward low-cost and automated durability assessment of construction materials.
AB - Monitoring water uptake in cementitious systems is crucial to assess their durability against corrosion, salt attack, and freeze-thaw damage. However, gauging absorption currently relies on labor-intensive and infrequent weight measurements, as outlined in ASTM C1585. To address this issue, we introduce a custom computer vision model trained on 6234 images, consisting of 4000 real and 2234 synthetic, that automatically detects the water level in prismatic samples absorbing water. This model provides accurate and frequent estimations of water penetration values every minute. After training the model on 1440 unique data points, including 15 paste mixtures with varying water-to-cement ratios from 0.4 to 0.8 and curing periods of 1 to 7 days, we can now predict initial and secondary sorptivities in real time with high confidence, achieving R² > 0.9. Finally, we demonstrate its application on mortar and concrete systems, opening a pathway toward low-cost and automated durability assessment of construction materials.
UR - http://www.scopus.com/inward/record.url?scp=85209382707&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85209382707&partnerID=8YFLogxK
U2 - 10.1038/s41467-024-53993-w
DO - 10.1038/s41467-024-53993-w
M3 - Article
C2 - 39548066
AN - SCOPUS:85209382707
SN - 2041-1723
VL - 15
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 9935
ER -