Amirkabir Journal of Civil Engineering

Amirkabir Journal of Civil Engineering

Damage Classification in Hollow Cement Mortar Specimens Using Machine Learning Algorithms

Document Type : Research Article

Authors
abolfazl faghihi 1
hamed mola davoodi 2
1 Mining Engineering department; Amirkabir University
2 Mining Engineering Department; Amirkabir University of Technology
10.22060/ceej.2026.25032.8377
Abstract
This study investigates the effectiveness of non-destructive ultrasonic testing for detecting and classifying damage in cement mortar specimens with different mix designs. To this end, a set of specimens with varying cement content (CC) were prepared and tested in both undamaged and damaged states. Ultrasonic signal data, after preprocessing and the extraction of statistical and time–frequency features, were used as inputs to three machine-learning algorithms: K-Nearest Neighbors (KNN), Naïve Bayes, and Random Forest. Analysis results indicated that the Naïve Bayes classifier, owing to its ability to handle independent and uncorrelated features of the ultrasonic data, outperformed the other methods and yielded the highest classification performance, achieving an accuracy of 99.00 ± 3.16% and a recall of 97.50 ± 7.91%. The main innovation of this research is the combination of machine-learning approaches with non-destructive methods to analyze energy variations in ultrasonic signals and to enable early damage detection in cement mortars with different cement content ratios. This data-driven, reproducible analytical framework not only improves the accuracy and reliability of damage identification but is also extensible for health monitoring and continuous assessment of concrete structures at practical scales, serving as an effective tool to enhance the durability and safety of civil infrastructure.
Keywords
Ultrasonic Testing, Machine Learning, K-Nearest Neighbors (KNN), Naï
ve Bayes, Random Forest
Subjects
[1]         J. Chakraborty and M. Stolinski, “Signal-level fusion approach for embedded ultrasonic sensors in damage detection of real RC structures,” Mathematics, vol. 10, no. 5, p. 724, 2022.
[2]         F. A. J. Mohamad et al., “NDT-Defect Detection on Concrete using Ultrasonic: A Review,” J. Tomogr. Syst. Sensors Appl., 2021.
[3]         G. Karaiskos, A. Deraemaeker, D. G. Aggelis, and D. Van Hemelrijck, “Monitoring of concrete structures using the ultrasonic pulse velocity method,” Smart Mater. Struct., vol. 24, no. 11, p. 113001, 2015, doi: 10.1088/0964-1726/24/11/113001.
[4]         L. Ge et al., “High-resolution ultrasonic imaging technology for the damage of concrete structures based on total focusing method,” Comput. Electr. Eng., vol. 105, p. 108526, 2023.
[5]         R. Jones, “The ultrasonic testing of concrete,” Ultrasonics, vol. 1, no. 2, pp. 78–82, 1963, doi: 10.1016/0041-624X(63)90058-1.
[6]         I. Ivanchev and V. Slavchev, “About the possible limitations in the usage of the non-destructive ultrasonic pulse velocity method for assessment of cracks in reinforced concrete structures, subjected to direct environmental exposure,” Buildings, vol. 9, no. 9, p. 202, 2019, doi: 10.3390/buildings9090202.
[7]         A. Lorenzi, J. Campagnolo, and L. C. P. Silva Filho, “Application of artificial neural network for interpreting ultrasonic readings of concrete,” Int. J. Mater. Prod. Technol., vol. 26, no. 1–2, pp. 57–70, 2006, doi: 10.1504/IJMPT.2006.008980.
[8]         R. Jones, “Non-destructive testing of concrete,” (No Title), 1962.
[9]         J. Xu and H. Wei, “Ultrasonic testing analysis of concrete structure based on S transform,” Shock Vib., vol. 2019, pp. 1–9, 2019.
[10]       K. Komlos, S. Popovics, T. Nürnbergerová, B. Babal, and J. S. Popovics, “Ultrasonic pulse velocity test of concrete properties as specified in various standards,” Cem. Concr. Compos., vol. 18, no. 5, pp. 357–364, 1996.
[11]       J. Wang, M. Chen, N. Zhu, and H. Liu, “A damage zone detection method in concrete hydraulic structures based on multi-frequency ultrasonic characteristics,” Sci. Rep., vol. 15, no. 1, p. 11173, 2025.
[12]       L. Wang, S. Yi, Y. Yu, C. Gao, and B. Samali, “Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning,” Mech. Syst. Signal Process., vol. 221, p. 111719, 2024.
[13]       T. Hu, J. Zhao, R. Zheng, P. Wang, X. Li, and Q. Zhang, “Ultrasonic based concrete defects identification via wavelet packet transform and GA-BP neural network,” PeerJ Comput. Sci., vol. 7, p. e635, 2021.
[14]       M. D. E. Candelaria, N. M. M. Chua, and S.-H. Kee, “Evaluation of heat-induced damage in concrete using machine learning of ultrasonic pulse waves,” Materials (Basel)., vol. 15, no. 22, p. 7914, 2022.
[15]       S. Grabke, F. Clauß, K.-U. Bletzinger, M. A. Ahrens, P. Mark, and R. Wüchner, “Damage detection at a reinforced concrete specimen with coda wave interferometry,” Materials (Basel)., vol. 14, no. 17, p. 5013, 2021.
[16]       J. A. Mukhti, K. P. V Robles, K.-H. Lee, and S.-H. Kee, “Evaluation of early concrete damage caused by chloride-induced steel corrosion using a deep learning approach based on RNN for ultrasonic pulse waves,” Materials (Basel)., vol. 16, no. 9, p. 3502, 2023.
[17]       A. Faghihi and H. Molladavoodi, “Damage detection in cement mortar samples using wavelet transform analysis of non-destructive ultrasonic test results,” 2025.
[18]       M. N. A. B. G. Taj, N. Alruwais, H. M. Alshahrani, J. Vijayalakshmi, N. Shanmugapriya, and S. Jayaprakash, “Precision crack analysis in concrete structures using CNN, SVM, and KNN: a machine learning approach,” Matéria (Rio Janeiro), vol. 29, p. e20240551, 2024.
[19]       D. W. Dunker and J. Farny, “Your Pipe Lining Has a New Cement—ASTM C150 Compared to ASTM C595,” in Pipelines 2024, pp. 312–320.
[20]       S. A. Proceq, “Operating Instructions Pundit Lab,” Pundit Lab+ Ultrason. Instrum., vol. 32, 2017.
[21]       N. S. M. Ravi Kumar, T. Barkavi, and C. Natarajan, “Structural health monitoring: detection of concrete flaws using ultrasonic pulse velocity,” J. Build. Pathol. Rehabil., vol. 3, pp. 1–9, 2018.
[22]       S. Hannachi and M. N. Guetteche, “Review of the ultrasonic pulse velocity Evaluating concrete compressive strength on site,” in Proceedings of Scientific Cooperation International Workshops on Engineering Branches, Istanbul, Turkey, 2014, no. August, pp. 103–112.
[23]       I. H. Sarker, “Machine learning: algorithms, real-world applications and research directions. SN Comput Sci 2: 160.” ed, 2021.
[24]       F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[25]       K. Fernandes, P. Vinagre, and P. Cortez, “A proactive intelligent decision support system for predicting the popularity of online news,” in Progress in Artificial Intelligence: 17th Portuguese Conference on Artificial Intelligence, EPIA 2015, Coimbra, Portugal, September 8-11, 2015. Proceedings 17, 2015, pp. 535–546.
[26]       I. H. Sarker, A. S. M. Kayes, and P. Watters, “Effectiveness analysis of machine learning classification models for predicting personalized context-aware smartphone usage,” J. Big Data, vol. 6, no. 1, pp. 1–28, 2019.
[27]       B. Mahesh, “Machine learning algorithms-a review,” Int. J. Sci. Res. (IJSR).[Internet], vol. 9, no. 1, pp. 381–386, 2020.
[28]       M. Hofmann and R. Klinkenberg, RapidMiner: Data mining use cases and business analytics applications. CRC Press, 2016.
Amirkabir Journal of Civil Engineering
Volume 57, Issue 12
March 2026
Pages 2055-2078