Prediction of water absorption of recycled coarse aggregate based on deep learning image segmentation
-
Yixing Wei
,
Jianhong Yang
Abstract
To quickly measure the water absorption (WA) of Recycled Coarse Aggregates (RCA), we utilize a detection platform designed for RCA to collect two-dimensional images. Utilizing the RCA-net network, we segment the areas of the mortar and aggregate on the RCA surface. Segmentations allow us to extract critical parameters for characterizing the quality of RCA, the proportion of mortar area (PMA). Subsequently, we construct three regression functions between PMA and WA. The experimental results demonstrate that our proposed segmentation method effectively separates both adhered particles of RCA and distinct areas of mortar and aggregate on RCA surfaces. Next, sprinkling water on RCA surfaces can enhance the accuracy of the segmentation. Notably, within particle size ranges of 5–10 mm, 10–20 mm, and 20–31.5 mm, we all observed a significant linear relationship between PMA and WA. We used those linear relationships and the equivalent mass of RCA detected by the image method in each particle size range to construct the prediction model of water absorption. According to the validation result of 24 groups RCA, this model’s maximum relative error of RCA water absorption predicted value was 10.6 %. The detection time of this method is short, and the detection time of 2 kg RCA is 3.8 min, with an average computation time per image of merely 0.659 s. This efficiency fulfills the requirements for real-time industrial inspection.
Zusammenfassung
Um die Wasseraufnahme (WA) von recycelten groben Gesteinskörnungen (RCA) schnell zu messen, verwenden wir eine für RCA konzipierte Detektionsplattform zur Erfassung zweidimensionaler Bilder. Mithilfe des RCA-Netzes segmentieren wir die Bereiche des Mörtels und der Zuschlagstoffe auf der RCA-Oberfläche. Die Segmentierung ermöglicht es uns, kritische Parameter zur Charakterisierung der Qualität von RCA zu extrahieren, insbesondere den Anteil der Mörtelfläche (PMA). Anschließend konstruieren wir drei Regressionsfunktionen zwischen PMA und WA. Die experimentellen Ergebnisse zeigen, dass die von uns vorgeschlagene Segmentierungsmethode sowohl anhaftende Partikel von RCA als auch unterschiedliche Bereiche von Mörtel und Zuschlagstoffen auf RCA-Oberflächen effektiv trennt. Darüber hinaus kann die Besprühung der RCA-Oberflächen mit Wasser die Genauigkeit der Segmentierungsmethode verbessern. Innerhalb der Partikelgrößenbereiche von 5–10 mm, 10–20 mm und 20–31,5 mm konnten wir eine signifikante lineare Beziehung zwischen PMA und WA feststellen. Diese lineare Beziehung zwischen PMA und WA und die entsprechende Masse von RCA, die durch eine Bildanalyse getrennt für jeden Partikelgrößenbereich ermittelt wurde, erlaubt es ein Vorhersagemodell der Wasserabsorption zu generieren. Nach den Validierungsergebnissen von 24 RCA-Gruppen betrug der maximale relative Fehler dieses Modells bei der Vorhersage der Wasseraufnahme von RCA 10,6 %. Die Verarbeitungszeit dieser Methode ist kurz und beträgt für die Masse von 2 kg RCA nur 3,8 Minuten, mit einer durchschnittlichen Berechnungszeit pro Bild von nur 0,659 Sekunden. Diese Effizienz erfüllt die Anforderungen an eine industrielle Echtzeit-Inspektion.
Funding source: the Science and Technology Project of Quanzhou
Award Identifier / Grant number: 2022GZ3
Funding source: the Major Program of Industry and University Cooperation of Fujian Province
Award Identifier / Grant number: 2021H6029
About the authors
Yixing Wei received his B. Sc. Degree from Huaqiao University in 2021. He is currently a master student at Huaqiao University. His main research interests include quality evaluation by image method of recycled coarse aggregate.
Huaiying Fang received her Ph. D. degree from Huaqiao University in 2012. She is currently a professor at Huaqiao University. Her main research interests include system development for aggregate quality evaluation.
Jianhong Yang (Corresponding author) received his M. Sc. degree from Huaqiao University in 2004 and received his Ph. D. degree from Huaqiao University and Tohoku University in 2010. He is currently a professor at Huaqiao University. His main research interests include multimodal vision inspection method and system development and multi-platform based machine deep learning algorithms.
Guoyi Tan received his M. Sc. degree from Huaqiao University in 2023. His main research interests include method and system development for quality testing of recycled aggregate.
Feizhi Huang received his B. Sc. Degree from Fujian Agriculture and Forestry University in 2021. He is currently a master student at Huaqiao University. His main research interests include grading evaluation by image method of fine aggregate.
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission. The primary contributions of each author are as follows: Yixing Wei, Huaiying Fang, Guoyi Tan, Feizhi Huang: performed the investigation and formal analysis. Yixing Wei, Huaiying Fang: wrote the original draft. Jianhong Yang: provided the methodology and supervision. Jianhong Yang, Huaiying Fang: wrote review & editing.
-
Competing interests: The authors state no competing interests.
-
Research funding: The authors also would like to thank the financial support provided by the Major Program of Industry and University Cooperation of Fujian Province (2021H6029). The Science and Technology Project of Quanzhou (2022GZ3).
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
[1] K. Verian, W. Ashraf, and Y. Cao, “Properties of recycled concrete aggregate and their influence in new concrete production,” Resour., Conserv. Recycl., vol. 133, pp. 30–49, 2018. https://doi.org/10.1016/j.resconrec.2018.02.005.Search in Google Scholar
[2] T. Ye, J. Xiao, W. Zhao, Z. Duan, and Y. Xu, “Combined use of recycled concrete aggregate and glass cullet in mortar: strength, alkali expansion and chemical compositions,” J. Build. Eng., vol. 55, p. 104721, 2022. https://doi.org/10.1016/j.jobe.2022.104721.Search in Google Scholar
[3] H. Wu, H. Duan, L. Zheng, J. Wang, Y. Niu, and G. Zhang, “Demolition waste generation and recycling potentials in a rapidly developing flagship megacity of South China: prospective scenarios and implications,” Constr. Build. Mater., vol. 113, pp. 1007–1016, 2016. https://doi.org/10.1016/j.conbuildmat.2016.03.130.Search in Google Scholar
[4] L. Zheng, et al.., “Characterizing the generation and flows of construction and demolition waste in China,” Constr. Build. Mater., vol. 136, pp. 405–413, 2017. https://doi.org/10.1016/j.conbuildmat.2017.01.055.Search in Google Scholar
[5] Md. Uzzal Hossain, C. Poon, I. Lo, and J. Cheng, “Comparative environmental evaluation of aggregate production from recycled waste materials and virgin sources by LCA,” Resour., Conserv. Recycl., vol. 109, pp. 67–77, 2016. https://doi.org/10.1016/j.resconrec.2016.02.009.Search in Google Scholar
[6] P. Alaejos, M. de Juan, J. Rueda, R. Drummond, and I. Valero, “Quality assurance of recycled aggregates,” in Progress of Recycling in the Built Environment: Final Report of the RILEM Technical Committee 217-PRE, E. Vázquez, Ed., Dordrecht, Netherlands, Springer, 2013, pp. 229–273.10.1007/978-94-007-4908-5_6Search in Google Scholar
[7] K. Liang, et al.., “Theoretical analysis of water absorption kinetics of recycled aggregates immersed in water,” Constr. Build. Mater., vol. 302, p. 124156, 2021. https://doi.org/10.1016/j.conbuildmat.2021.124156.Search in Google Scholar
[8] M. Joseph, L. Boehme, Z. Sierens, and L. Vandewalle, “Water absorption variability of recycled concrete aggregates,” Mag. Concr. Res., vol. 67, no. 11, pp. 592–597, 2015. https://doi.org/10.1680/macr.14.00210.Search in Google Scholar
[9] Y. Zhao, W. Zeng, and H. Zhang, “Properties of recycled aggregate concrete with different water control methods,” Constr. Build. Mater., vol. 152, pp. 539–546, 2017. https://doi.org/10.1016/j.conbuildmat.2017.05.134.Search in Google Scholar
[10] K. McNeil and T. Kang, “Recycled concrete aggregates: a review,” Int. J. Concr. Struct. Mater., vol. 7, pp. 61–69, 2013. https://doi.org/10.1007/s40069-013-0032-5.Search in Google Scholar
[11] V. W. Y. Tam, X. F. Gao, C. M. Tam, and C. H. Chan, “New approach in measuring water absorption of recycled aggregates,” Constr. Build. Mater., vol. 22, pp. 364–369, 2008. https://doi.org/10.1016/j.conbuildmat.2006.08.009.Search in Google Scholar
[12] M. Sadagopan, K. Malaga, and A. Nagy, “Modified pycnometer method to measure the water absorption of crushed concrete aggregates,” J. Sustainable Cem.-Based Mater., vol. 9, no. 5, pp. 259–269, 2020. https://doi.org/10.1080/21650373.2020.1715902.Search in Google Scholar
[13] B. Damineli, M. Quattrone, S. Angulo, M. Taqueda, and V. John, “Rapid method for measuring the water absorption of recycled aggregates,” Mater. Struct., vol. 49, no. 10, pp. 4069–4084, 2016. https://doi.org/10.1617/s11527-015-0773-5.Search in Google Scholar
[14] M. Quattrone, B. Cazacliu, S. Angulo, E. Hamard, and A. Cothenet, “Measuring the water absorption of recycled aggregates, what is the best practice for concrete production?” Constr. Build. Mater., vol. 123, pp. 690–703, 2016. https://doi.org/10.1016/j.conbuildmat.2016.07.019.Search in Google Scholar
[15] A. D. Tegguer, “Determining the water absorption of recycled aggregates utilizing hydrostatic weighing approach,” Constr. Build. Mater., vol. 27, pp. 112–116, 2012. https://doi.org/10.1016/j.conbuildmat.2011.08.018.Search in Google Scholar
[16] F. Théréné, E. Keita, J. Naël-Redolfi, B. Pascal, L. Bonafous, and N. Roussel, “Water absorption of recycled aggregates: measurements, influence of temperature and practical consequences,” Cem. Concr. Res., vol. 137, p. 106196, 2020. https://doi.org/10.1016/j.cemconres.2020.106196.Search in Google Scholar
[17] A. Abbas, et al.., “Quantification of the residual mortar content in recycled concrete aggregates by image analysis,” Mater. Charact., vol. 60, no. 7, pp. 716–728, 2009. https://doi.org/10.1016/j.matchar.2009.01.010.Search in Google Scholar
[18] Y. Wang, J. Liu, P. Zhu, H. Liu, C. Wu, and J. Zhao, “Investigation of adhered mortar content on recycled aggregate using image analysis method,” J. Mater. Civ. Eng., vol. 33, no. 9, p. 04021225, 2021. https://doi.org/10.1061/(asce)mt.1943-5533.0003864.Search in Google Scholar
[19] G. Bonifazi, R. Palmieri, and S. Serranti, “Evaluation of attached mortar on recycled concrete aggregates by hyperspectral imaging,” Constr. Build. Mater., vol. 169, pp. 835–842, 2018. https://doi.org/10.1016/j.conbuildmat.2018.03.048.Search in Google Scholar
[20] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 3431–3440.10.1109/CVPR.2015.7298965Search in Google Scholar
[21] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234–241.10.1007/978-3-319-24574-4_28Search in Google Scholar
[22] L.-C. Chen, P. George, I. Kokkinos, K. Murphy, and A. Yuille, “DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834–848, 2017. https://doi.org/10.1109/tpami.2017.2699184.Search in Google Scholar PubMed
[23] L.-C. Chen, Y. Zhu, P. George, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Computer Vision – ECCV 2018: 15th European Conference, 2018, pp. 833–851.10.1007/978-3-030-01234-2_49Search in Google Scholar
[24] ASTM, Standard Method of Test for Specific Gravity and Absorption of Coarse Aggregate, ASTM Designation C 127-07, West Conshohocken, 2007.Search in Google Scholar
[25] A. Kirillov, et al.., “Segment anything,” 2023, https://arxiv.org/abs/2304.02643.10.1109/ICCV51070.2023.00371Search in Google Scholar
[26] B. Alexander, V. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. Kalinin, “Albumentations: fast and flexible image augmentations,” Information, vol. 11, no. 2, p. 125, 2020. https://doi.org/10.3390/info11020125.Search in Google Scholar
[27] M. de Juan and P. Gutiérrez, “Study on the influence of attached mortar content on the properties of recycled concrete aggregate,” Constr. Build. Mater., vol. 23, pp. 872–877, 2009. https://doi.org/10.1016/j.conbuildmat.2008.04.012.Search in Google Scholar
[28] X. Hu, H. Fang, J. Yang, L. Fan, W. Lin, and J. Li, “Online measurement and segmentation algorithm of coarse aggregate based on deep learning and experimental comparison,” Constr. Build. Mater., vol. 327, p. 127033, 2022. https://doi.org/10.1016/j.conbuildmat.2022.127033.Search in Google Scholar
[29] J. Yang, W. Yu, H. Fang, X. Huang, and S. Chen, “Detection of size of manufactured sand particles based on digital image processing,” PLOS One, vol. 13, no. 12, pp. 1–18, 2018. https://doi.org/10.1371/journal.pone.0206135.Search in Google Scholar PubMed PubMed Central
© 2024 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- Measurement systems and sensors with cognitive features III
- Research Articles
- Opportunities of artificial intelligence in the field of calibration services
- Neuronale Netze zur Startwertschätzung bei der Identifikation piezoelektrischer Materialparameter
- Spectral reconstruction using neural networks in filter-array-based chip-size spectrometers
- Prediction of water absorption of recycled coarse aggregate based on deep learning image segmentation
- Surface mortar detection and performance evaluation of recycled aggregates based on hyperspectral technology
- A comparative study of classification methods for state recognition in injection molding
Articles in the same Issue
- Frontmatter
- Editorial
- Measurement systems and sensors with cognitive features III
- Research Articles
- Opportunities of artificial intelligence in the field of calibration services
- Neuronale Netze zur Startwertschätzung bei der Identifikation piezoelektrischer Materialparameter
- Spectral reconstruction using neural networks in filter-array-based chip-size spectrometers
- Prediction of water absorption of recycled coarse aggregate based on deep learning image segmentation
- Surface mortar detection and performance evaluation of recycled aggregates based on hyperspectral technology
- A comparative study of classification methods for state recognition in injection molding
