Micrographic Evaluation of Carbon Nanotube Cement Composites via Machine Learning and Convolutional Neural Networks
Source abstract
Abstract
Carbon nanotube (CNT)/cement composite is a promising material for structural health monitoring, where CNT dispersion and content critically affect the conductive network for self-sensing. Still, a simple method to assess low CNT levels is lacking, limiting their large-scale production. This study applied machine learning (ML) and convolutional neural networks (CNN) to predict these factors from optical microscopic images. A custom 2D-CNN directly learned spatial features from cropped images, reaching higher accuracy (0.993) and F1-score (0.953) in distinguishing dispersion methods (shear-mixed or sonicated) and classifying CNT contents (0–0.4 wt%) compared to baseline ML models. Support vector machine (SVM) and light gradient-boosting machine (LGBM) achieved decent accuracy (0.980) and F1-scores (0.928–0.938) using color histograms but less consistent performance to random data splits. These models can be integrated into concrete production, particularly batch verification and surface inspection, enabling scalable quality control of CNT/cement composites.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Smart Materials for Construction · Innovative concrete reinforcement materials · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (57)
Show source-provided references
1. Awad, M., & Khanna, R. (2015). Support vector machines for classification. In C. A. Berkeley (Ed.), Efficient learning machines (pp. 39–66). Apress.10.1007/978-1-4302-5990-9_3 ↗
2. Azimi, S. M., Britz, D., Engstler, M., Fritz, M., & Mücklich, F. (2018). Advanced steel microstructural classification by deep learning methods. Scientific Reports, 8, 2128. https://doi.org/10.1038/s41598-018-20037-510.1038/s41598-018-20037-5 ↗
3. Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 110, 346–359. https://doi.org/10.1016/j.cviu.2007.09.01410.1016/j.cviu.2007.09.014 ↗
4. Bian, Y., Xing, T., Jiao, K., Kong, Q., Wang, J., Yang, X., Yang, S., Jiang, Y., Shen, R., Shen, H., & Kuang, C. (2022). Computational portable microscopes for point-of-care-test and tele-diagnosis. Cells, 11, 3670. https://doi.org/10.3390/cells1122367010.3390/cells11223670 ↗
5. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on computational learning theory, Pittsburgh, PA, pp. 144–152. https://doi.org/10.1145/130385.13040110.1145/130385.130401 ↗
6. Castañeda-Saldarriaga, D. L., Alvarez-Montoya, J., Martínez-Tejada, V., & Sierra-Pérez, J. (2021). Toward structural health monitoring of civil structures based on self-sensing concrete nanocomposites: A validation in a reinforced-concrete beam. International Journal of Concrete Structures and Materials, 15, 3. https://doi.org/10.1186/s40069-020-00451-810.1186/s40069-020-00451-8 ↗
7. Cha, Y., Choi, W., & Büyüköztürk, O. (2017). Deep learning‐based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 32, 361–378. https://doi.org/10.1111/mice.1226310.1111/mice.12263 ↗
8. Cha, Y., Choi, W., Suh, G., Mahmoudkhani, S., & Büyüköztürk, O. (2018). Autonomous structural visual inspection using region‐based deep learning for detecting multiple damage types. Computer-Aided Civil and Infrastructure Engineering, 33, 731–747. https://doi.org/10.1111/mice.1233410.1111/mice.12334 ↗
9. Collins, F., Lambert, J., & Duan, W. H. (2012). The influences of admixtures on the dispersion, workability, and strength of carbon nanotube–OPC paste mixtures. Cement and Concrete Composites, 34, 201–207. https://doi.org/10.1016/j.cemconcomp.2011.09.01310.1016/j.cemconcomp.2011.09.013 ↗
10. Common rules for precast concrete products. Withdrawn, 2018.
11. D’Alessandro, A., Tiecco, M., Meoni, A., & Ubertini, F. (2021). Improved strain sensing properties of cement-based sensors through enhanced carbon nanotube dispersion. Cement and Concrete Composites, 115, Article 103842. https://doi.org/10.1016/j.cemconcomp.2020.10384210.1016/j.cemconcomp.2020.103842 ↗
12. Ding, S., Ruan, Y., Yu, X., Han, B., & Ni, Y.-Q. (2019). Self-monitoring of smart concrete column incorporating CNT/NCB composite fillers modified cementitious sensors. Construction and Building Materials, 201, 127–137. https://doi.org/10.1016/j.conbuildmat.2018.12.20310.1016/j.conbuildmat.2018.12.203 ↗
13. Dorko, & Schmid. (2003). Selection of scale-invariant parts for object class recognition. In: Proceedings ninth IEEE international conference computer vision, Vol. 1, pp. 634–639. https://doi.org/10.1109/ICCV.2003.123840710.1109/ICCV.2003.1238407 ↗
14. Du, M., Jing, H., Gao, Y., Su, H., & Fang, H. (2020). Carbon nanomaterials enhanced cement-based composites: Advances and challenges. Nanotechnology Reviews, 9, 115–135. https://doi.org/10.1515/ntrev-2020-001110.1515/ntrev-2020-0011 ↗
15. Durmaz, A. R., Müller, M., Lei, B., Thomas, A., Britz, D., Holm, E. A., Eberl, C., Mücklich, F., & Gumbsch, P. (2021). A deep learning approach for complex microstructure inference. Nature Communications, 12, 6272. https://doi.org/10.1038/s41467-021-26565-510.1038/s41467-021-26565-5 ↗
16. Flah, M., Suleiman, A. R., & Nehdi, M. L. (2020). Classification and quantification of cracks in concrete structures using deep learning image-based techniques. Cement and Concrete Composites, 114, Article 103781. https://doi.org/10.1016/j.cemconcomp.2020.10378110.1016/j.cemconcomp.2020.103781 ↗
17. Green, M. J. (2010). Analysis and measurement of carbon nanotube dispersions: Nanodispersion versus macrodispersion. Polymer International, 59, 1319–1322. https://doi.org/10.1002/pi.287810.1002/pi.2878 ↗
18. Haque, M. I. U., Dubey, A. K., Danciu, I., Justice, A. C., Ovchinnikova, O. S., & Hinkle, J. D. (2023). Effect of image resolution on automated classification of chest X-rays. Journal of Medical Imaging. https://doi.org/10.1117/1.JMI.10.4.04450310.1117/1.JMI.10.4.044503 ↗
19. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep residual learning for image recognition. https://doi.org/10.48550/ARXIV.1512.0338510.48550/ARXIV.1512.03385 ↗
20. ISO/IEC. (2002). Information technology—Multimedia content description interface—Part 3: Visual. https://webstore.iec.ch/preview/info_isoiec15938-3%7Bed1.0%7Den.pdf. Accessed October 29, 2023.
21. Janković, N. Z., & Plata, D. L. (2019). Engineered nanomaterials in the context of global element cycles. Environmental Science : Nano, 6, 2697–2711. https://doi.org/10.1039/C9EN00322C10.1039/C9EN00322C ↗
22. Jung, M., Park, J., Hong, S., & Moon, J. (2022). The critical incorporation concentration (CIC) of dispersed carbon nanotubes for tailoring multifunctional properties of ultra-high performance concrete (UHPC). Journal of Materials Research and Technology, 17, 3361–3370. https://doi.org/10.1016/j.jmrt.2022.02.10310.1016/j.jmrt.2022.02.103 ↗
23. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In: Proceedings of the 31st international conference neural information processing systems (pp. 3149–3157). Curran Associates Inc.
24. Kim, H. K., Park, I. S., & Lee, H. K. (2014). Improved piezoresistive sensitivity and stability of CNT/cement mortar composites with low water–binder ratio. Composite Structures, 116, 713–719. https://doi.org/10.1016/j.compstruct.2014.06.00710.1016/j.compstruct.2014.06.007 ↗
25. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In: Proceedings of the 26th international conference on neural information processing systems (Vol. 1, pp. 1097–1105). Curran Associates Inc.
26. Kunjan, S., Grummett, T. S., Pope, K. J., Powers, D. M. W., Fitzgibbon, S. P., Bastiampillai, T., Battersby, M., & Lewis, T. W. (2021). The necessity of leave one subject out (LOSO) cross validation for EEG disease diagnosis. In M. Mahmud, M. S. Kaiser, S. Vassanelli, Q. Dai, & N. Zhong (Eds.), Brain informatics (pp. 558–567). Springer.10.1007/978-3-030-86993-9_50 ↗
27. Li, G. Y., Wang, P. M., & Zhao, X. (2007). Pressure-sensitive properties and microstructure of carbon nanotube reinforced cement composites. Cement and Concrete Composites, 29, 377–382. https://doi.org/10.1016/j.cemconcomp.2006.12.01110.1016/j.cemconcomp.2006.12.011 ↗
28. Lowe, D. G. (2004). Distinctive image features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60, 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.9410.1023/B:VISI.0000029664.99615.94 ↗
29. Lundberg, S., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. https://doi.org/10.48550/ARXIV.1705.0787410.48550/ARXIV.1705.07874 ↗
30. Mahadevan, A., & Mathioudakis, M. (2024). Cost-aware retraining for machine learning. Knowledge-Based Systems, 293, Article 111610. https://doi.org/10.1016/j.knosys.2024.11161010.1016/j.knosys.2024.111610 ↗
31. Manual for quality control for plants and production of structural precast concrete products (5th ed.). Precast/Prestressed Concrete Institute, Chicago, Illinois, 2021.
32. Materazzi, A. L., Ubertini, F., & D’Alessandro, A. (2013). Carbon nanotube cement-based transducers for dynamic sensing of strain. Cement and Concrete Composites, 37, 2–11. https://doi.org/10.1016/j.cemconcomp.2012.12.01310.1016/j.cemconcomp.2012.12.013 ↗
33. McNally, T., & Pötschke, P. (Eds.). (2011). Polymer-carbon nanotube composites: Preparation, properties and applications. Woodhead Publishing.
34. Meoni, A., D’Alessandro, A., Downey, A., García-Macías, E., Rallini, M., Materazzi, A. L., Torre, L., Laflamme, S., Castro-Triguero, R., & Ubertini, F. (2018). An experimental study on static and dynamic strain sensitivity of embeddable smart concrete sensors doped with carbon nanotubes for SHM of large structures. Sensors, 18, 831. https://doi.org/10.3390/s1803083110.3390/s18030831 ↗
35. Murala, S., Maheshwari, R. P., & Balasubramanian, R. (2012). Directional local extrema patterns: A new descriptor for content based image retrieval. International Journal of Multimedia Information Retrieval, 1, 191–203. https://doi.org/10.1007/s13735-012-0008-210.1007/s13735-012-0008-2 ↗
36. Nalon, G. H., Ribeiro, J. C. L., Araújo, E. N. D. D., Pedroti, L. G., Carvalho, J. M. F. D., Santos, R. F., & Aparecido-Ferreira, A. (2020). Effects of different kinds of carbon black nanoparticles on the piezoresistive and mechanical properties of cement-based composites. Journal of Building Engineering, 32, Article 101724. https://doi.org/10.1016/j.jobe.2020.10172410.1016/j.jobe.2020.101724 ↗
37. Nam, I. W., Souri, H., & Lee, H. K. (2016). Percolation threshold and piezoresistive response of multi-wall carbon nanotube/cement composites. Smart Structures and Systems, 18, 217–231. https://doi.org/10.12989/SSS.2016.18.2.21710.12989/SSS.2016.18.2.217 ↗
38. Park, J., Jung, M., Lee, Y., Hwang, H.-Y., Hong, S., & Moon, J. (2023). Quantified analysis of 2D dispersion of carbon nanotubes in hardened cement composite using confocal Raman microspectroscopy. Cement and Concrete Research, 166, Article 107102. https://doi.org/10.1016/j.cemconres.2023.10710210.1016/j.cemconres.2023.107102 ↗
39. Qian, H., Li, Y., Yang, J., Xie, L., & Tan, K. H. (2022). Image-based microstructure classification of mortar and paste using convolutional neural networks and transfer learning. Cement and Concrete Composites, 129, Article 104496. https://doi.org/10.1016/j.cemconcomp.2022.10449610.1016/j.cemconcomp.2022.104496 ↗
40. Rao, R. K., Sindu, B. S., & Sasmal, S. (2023). Real-time monitoring of structures under extreme loading using smart composite-based embeddable sensors. Journal of Intelligent Material Systems and Structures, 34, 1073–1096. https://doi.org/10.1177/1045389X22112858610.1177/1045389X221128586 ↗
41. Ren, B., Wang, H., Wang, D., Guan, T., & Zheng, X. (2023). Vision method based on deep learning for detecting concrete vibration quality. Case Studies in Construction Materials, 18, Article e02132. https://doi.org/10.1016/j.cscm.2023.e0213210.1016/j.cscm.2023.e02132 ↗
42. Scrivener, K., Snellings, R., & Lothenbach, B. (Eds.). (2017). A practical guide to microstructural analysis of cementitious materials. CRC Press.
43. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International conference on computer vision (ICCV), Venice, Italy, pp. 618–626. https://doi.org/10.1109/ICCV.2017.7410.1109/ICCV.2017.74 ↗
44. Sheiati, S., Nguyen, H., Kinnunen, P., & Ranjbar, N. (2023). Cementitious phase quantification using deep learning. Cement and Concrete Research, 172, Article 107231. https://doi.org/10.1016/j.cemconres.2023.10723110.1016/j.cemconres.2023.107231 ↗
45. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. https://doi.org/10.48550/ARXIV.1409.155610.48550/ARXIV.1409.1556 ↗
46. Statista. (n.d.). Carbon nanotube market value by world region 2026. https://www.statista.com/statistics/1037740/global-carbon-nanotube-market-value-by-region/. Accessed November 7, 2023.
47. Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society. Series b, Statistical Methodology, 36, 111–133. https://doi.org/10.1111/j.2517-6161.1974.tb00994.x10.1111/j.2517-6161.1974.tb00994.x ↗
48. Suchorzewski, J., Prieto, M., & Mueller, U. (2020). An experimental study of self-sensing concrete enhanced with multi-wall carbon nanotubes in wedge splitting test and DIC. Construction and Building Materials, 262, Article 120871. https://doi.org/10.1016/j.conbuildmat.2020.12087110.1016/j.conbuildmat.2020.120871 ↗
49. Tafesse, M., Lee, N. K., Alemu, A. S., Lee, H. K., Kim, S. W., & Kim, H.-K. (2021). Flowability and electrical properties of cement composites with mechanical dispersion of carbon nanotube. Construction and Building Materials, 293, Article 123436. https://doi.org/10.1016/j.conbuildmat.2021.12343610.1016/j.conbuildmat.2021.123436 ↗
50. Tampu, I. E., Eklund, A., & Haj-Hosseini, N. (2022). Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images. Scientific Data, 9, 580. https://doi.org/10.1038/s41597-022-01618-610.1038/s41597-022-01618-6 ↗
51. Tuan, N. M., Hau, Q. V., Chin, S., & Park, S. (2021). In-situ concrete slump test incorporating deep learning and stereo vision. Automation in Construction, 121, Article 103432. https://doi.org/10.1016/j.autcon.2020.10343210.1016/j.autcon.2020.103432 ↗
52. Varma, S., & Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics, 7, 91. https://doi.org/10.1186/1471-2105-7-9110.1186/1471-2105-7-91 ↗
53. Yavuz, A., Yilmaz, M., & Yilmaz, N. F. (2025). Large-scale production of CNT reinforced PVC-based artificial leather. Diamond and Related Materials, 158, Article 112619. https://doi.org/10.1016/j.diamond.2025.11261910.1016/j.diamond.2025.112619 ↗
54. Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? https://doi.org/10.48550/ARXIV.1411.179210.48550/ARXIV.1411.1792 ↗
55. Yu, X., & Kwon, E. (2009). A carbon nanotube/cement composite with piezoresistive properties. Smart Materials and Structures, 18, Article 055010. https://doi.org/10.1088/0964-1726/18/5/05501010.1088/0964-1726/18/5/055010 ↗
56. Zaki, M., Sharma, S., Gurjar, S. K., Goyal, R., & Jayadeva, N. M. A. K. (2023). Cementron: Machine learning the alite and belite phases in cement clinker from optical images. Construction and Building Materials, 397, Article 132425. https://doi.org/10.1016/j.conbuildmat.2023.13242510.1016/j.conbuildmat.2023.132425 ↗
57. Zhang, Q., Huang, J., Zhao, M., Qian, W., & Wei, F. (2011). Carbon nanotube mass production: Principles and processes. Chemsuschem, 4, 864–889. https://doi.org/10.1002/cssc.20110017710.1002/cssc.201100177 ↗