MACHINE LEARNING CLASSIFICATION TECHNIQUES TO PREDICT IN SITU COMPRESSIVE STRENGTH OF REINFORCED CONCRETE USING NDT DATA
DOI:
https://doi.org/10.4314/njt.2025.5155Keywords:
Classification Techniques, ; Compressive Strength, Schmidt Rebound Hammer, Steel Reinforced Concrete, Ultrasonic Pulse Velocity.Abstract
Steel Reinforced Concrete (RC) is widely used in the construction industry due to its effective compressive and tensile strengths. This composite nature allows for withstanding diverse loading conditions. Assessing the structural condition of RC is essential for determining the extent of repair and retrofitting required for aged structures. Non-destructive testing (NDT) methods are commonly employed for this purpose. The objective of this study is to develop suitable correlations between compressive strengths of RC (fRC) and results obtained from two ND Tests - Schmidt rebound hammer (RS) test and Ultrasonic pulse velocity (Ѵ) test using machine learning techniques (ML) on the software platform of MATLAB. The experimental program involved casting 450 RC specimens, which included beam specimens with dimensions 70 cm × 15 cm × 15 cm and standard cube specimens with dimensions 15 cm × 15 cm × 15 cm, using concrete grades ranging from M25 to M35. The beams were reinforced with 2.68% longitudinal steel and provided with nominal concrete covers of 20 mm and 40 mm. NDT measurements (RS and Ѵ) were taken on the beam specimens, while compressive strength was determined from the companion cube specimens via destructive compression testing. The collected data were then analyzed using MATLAB’s Classification Learner app. A Support Vector Machine (SVM) model was used to establish the correlation between RS and fRC, while a Decision Tree classifier refined the Ѵ dataset with an accuracy of 99%. Using the ML approach, the data were effectively segregated through the developed models, which were further utilized to estimate the actual compressive strength of RC from NDT results. The study demonstrates that ML-based models can reliably estimate in-situ compressive strength from NDT results, yielding a practical approach for structural health assessment of RC.
References
REFERENCES
[1] Alwash, M., Breysse, D., and Sbartai, Z. M., “Non-destructive strength evaluation of concrete: Analysis of some key factors using synthetic simulations”, Construction and Building Materials, 99: 235–245, 2015. https://doi.org/10.1016/j.conbuildmat.2015.09.014
[2] Panedpojaman, P., and Tonnayopas, D., “Rebound hammer test to estimate compressive strength of heat-exposed concrete”, Construction and Building Materials, 172: 387–395, 2018. https://doi.org/10.1016/j.conbuildmat.2018.03.236
[3] Mehta, P. K., and Monteiro, P. J. M., Concrete: Microstructure, Properties, and Materials, 4th ed., McGraw-Hill Education, New York, USA, 2014.
[4] Masi, A., Chiauzzi, L., and Manfredi, V., “Criteria for identifying concrete homogeneous areas for the estimation of in-situ strength in RC buildings”, Construction and Building Materials, 121: 576–587, 2016. https://doi.org/10.1016/j.conbuildmat.2016.06.014
[5] Rathod, H., and Gupta, R., “Two-dimensional non-destructive testing data maps for reinforced concrete slabs with simulated damage”, Data in Brief, 25: 104127, 2019. https://doi.org/10.1016/j.dib.2019.104127
[6] Pfändler, P., Bodie, K., Crotta, G., Pantic, M., Siegwart, R., and Angst, U., “Non-destructive corrosion inspection of reinforced concrete structures using an autonomous flying robot”, Automation in Construction, 158: 105241, 2024. https://doi.org/10.1016/j.autcon.2023.105241
[7] Kencanawati, N. N., Akmaluddin, Marlitasari, R., and Paedullah, G., “Study on robustness of rebound hammer and ultrasonic pulse velocity measurement in several concrete damage levels”, IOP Conference Series: Earth and Environmental Science, 708(1): 012012, 2021. https://doi.org/10.1088/1755-1315/708/1/012012
[8] Al-Neshawy, F., Ferreira, M., and Puttonen, J., “NDT assessment of a thick-walled reinforced concrete mock-up of NPP concrete structures”, Proceedings of NDT-CE 2022 - International Symposium on Nondestructive Testing in Civil Engineering, Zurich, Switzerland, 2022.
[9] Bureau of Indian Standards (BIS), IS 455:1989 – Portland Slag Cement—Specification (Fourth Revision), New Delhi, India: BIS, 1989.
[10] Bureau of Indian Standards (BIS), IS 383:2016 – Specification for Coarse and Fine Aggregates for Concrete (Third Revision), New Delhi, India: BIS, 2016.
[11] Bureau of Indian Standards (BIS), IS 10262:2019 – Concrete Mix Proportioning Guidelines (Second Revision), New Delhi, India: BIS, 2019.
[12] Bureau of Indian Standards (BIS), IS 456:2000 – Plain and Reinforced Concrete – Code of Practice (Fourth Revision), New Delhi, India: BIS, 2000.
[13] Bureau of Indian Standards (BIS), IS 1199 (Part 5):2018 – Fresh Concrete—Method of Sampling, Testing and Analysis, Part 5: Making and Curing of Test Specimens, New Delhi, India: BIS, 2018.
[14] Bureau of Indian Standards (BIS), IS 516 (Part 1):2021 – Testing of Strength of Hardened Concrete, Section 1: Compressive, Flexural and Split Tensile Strength, New Delhi, India: BIS, 2021.
[15] Bureau of Indian Standards (BIS), IS 516 (Part 5/Sec 4):2020 – Hardened Concrete – Methods of Test, Part 5: Non-destructive Testing of Concrete, Section 4: Rebound Hammer Test, New Delhi, India: BIS, 2020.
[16] Bureau of Indian Standards (BIS), IS 516 (Part 5/Sec 1):2018 – Hardened Concrete – Methods of Test, Part 5: Non-destructive Testing of Concrete, Section 1: Ultrasonic Pulse Velocity Test, New Delhi, India: BIS, 2018.
[17] Cortes, C., and Vapnik, V., “Support vector networks”, Machine Learning, 20(3): 273–297, 1995. https://doi.org/10.1007/BF00994018
[18] Ng, A., Machine Learning Notes, Stanford University, 2023. https://stanford.edu/materials/aimlcs229/cs229-notes1.pdf
[19] Zhang, T., and Zhou, Z.-H., “Optimal margin distribution machine”, arXiv preprint, arXiv:1604.03348, 2016. https://arxiv.org/abs/1604.03348
[20] Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, Cambridge, MA, USA, 2016. https://www.deeplearningbook.org
[21] Cristianini, N., and Shawe-Taylor, J., An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, Cambridge, UK, 2000. https://doi.org/10.1017/CBO9780511801389
[22] Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., and Lin, C.-J., “LIBLINEAR: A library for large linear classification”, Journal of Machine Learning Research, 9: 1871–1874, 2008.
[23] Quinlan, J. R., “Induction of decision trees”, Machine Learning, 1(1): 81–106, 1986. https://doi.org/10.1007/BF00116251
[24] MathWorks, “Regression Learner App – Perform regression analysis using machine learning”, MATLAB Documentation, The MathWorks, Inc., Natick, MA, USA, 2023. https://www.mathworks.com/help/stats/regression-learner-app.html
[25] Shirdel, M., Di Mauro, M., and Liotta, A., “Worthiness Benchmark: A novel concept for analyzing binary classification evaluation metrics”, Information Sciences, 678: 120882, 2024. https://doi.org/10.1016/j.ins.2024.120882
[26] MathWorks, “Classification Learner App – Train classification models to predict data”, MATLAB Documentation, The MathWorks, Inc., Natick, MA, USA, 2023. https://www.mathworks.com/help/stats/classification-learner-app.html
[27] Bensaber, A., Boudaoud, Z., Toubal Seghir, N., Czarnecki, S., and Sadowski, Ł., “The assessment of concrete subjected to compressive and flexural preloading using nondestructive testing methods: Correlation between concrete strength and combined method (SonReb)”, Measurement, 222: 113659, 2023. https://doi.org/10.1016/j.measurement.2023.113659
[28] Agarwal, G., Tu, W., Sun, Y., and Kong, L., “Flexible quantile contour estimation for multivariate functional data: Beyond convexity”, Computational Statistics & Data Analysis, 168: 107400, 2022. https://doi.org/10.1016/j.csda.2021.107400
[29] Bayode, O., Aiyelokun, O., Osanyinlokun, O., and Adanikin, A., “Enhancing road crash prediction: A comparative study of machine learning algorithms and safety performance functions on the Lagos-Ibadan Expressway”, Nigerian Journal of Technology, 44(2): 215–221, 2025. https://doi.org/10.4314/njt.v44i2.5
[30] Omonayin, E., Akande, O. N., Muhammad, A., and Enemuo, S., “Evaluating deep learning models for real-time waste classification in smart IoT environment”, Nigerian Journal of Technology, 44(2): 357–366, 2025. https://doi.org/10.4314/njt.v44i2.18
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Nigerian Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The contents of the articles are the sole opinion of the author(s) and not of NIJOTECH.
NIJOTECH allows open access for distribution of the published articles in any media so long as whole (not part) of articles are distributed.
A copyright and statement of originality documents will need to be filled out clearly and signed prior to publication of an accepted article. The Copyright form can be downloaded from http://nijotech.com/downloads/COPYRIGHT%20FORM.pdf while the Statement of Originality is in http://nijotech.com/downloads/Statement%20of%20Originality.pdf
For articles that were developed from funded research, a clear acknowledgement of such support should be mentioned in the article with relevant references. Authors are expected to provide complete information on the sponsorship and intellectual property rights of the article together with all exceptions.
It is forbidden to publish the same research report in more than one journal.
How to Cite
