ANN MODEL FOR PREDICTING COMPRESSIVE STRENGTH OF CONCRETE BUILDING USING NDT DATA
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Compressive strength of concrete is a key mechanical property for evaluating the safety and serviceability of existing reinforced concrete structures. Conventionally, core extraction is adopted to determine in-situ concrete strength; however, these methods are often costly, time-consuming, and may cause structural damage. As a result, non-destructive testing (NDT) techniques such as the Rebound Hammer Test and Ultrasonic Pulse Velocity (UPV) Test are widely used as alternatives. Individually, these methods suffer from limited accuracy due to material heterogeneity, surface conditions, and testing limitations. To improve reliability, the combined SonReb method, which integrates rebound number and ultrasonic pulse velocity, has been proposed.
This study develops an Artificial Neural Network model to predict compressive strength.how strong concrete will be by looking at UPV, bounce test results, and how old the material is. Data come straight from real-world inspections, then checked against drilled samples for accuracy. Several versions of the network get tested, yet the best one turns out to be a straightforward forward-moving designWith a setup of (3-64-32-16-1, ReLU, Adam), results showed strong performance: R² = 0.94, while RMSE= 2.5 MPa and MAE = 2.09 MPa.
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Lokhande, S., Ramteke, T., Wanve, H. & Naranaware, K. (2026). ANN Model for Predicting Compressive Strength of Concrete Building using NDT Data. International Journal of Science, Strategic Management and Technology, 02(04). https://doi.org/10.55041/ijsmt.v2i4.486
Lokhande, Sushma, et al.. "ANN Model for Predicting Compressive Strength of Concrete Building using NDT Data." International Journal of Science, Strategic Management and Technology, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.486.
Lokhande, Sushma,Tanisha Ramteke,Hemant Wanve, and Kshitij Naranaware. "ANN Model for Predicting Compressive Strength of Concrete Building using NDT Data." International Journal of Science, Strategic Management and Technology 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.486.
References
2.Alouan, , et al. (2025), Non-destructive concrete strength prediction using AI: a comparative study, ResearchGate.
3.Asteris et (2020) , Concrete compressive strength using artificial neural networks. ACM
4.Benzerzour, A., et al. (2022), Prediction of the compressive strength of waste-based concretes using artificial neural network, Materials 15, 7045.
5.Bilgehan, M., and P. Turgut (2010), Artificial neural network approach to predict compressive strength of concrete through ultrasonic pulse velocity, Res. Nondestruct. Eval. 21, 1–17.
6.Bonagura, M., and L. Nobile (2021), Artificial neural network approach for predicting concrete compressive strength by SonReb, Struct. Durab. Health Monit. 15, 125–137.
7.Chandak, N. R., and H. R. Kumavat (2020), SonReb method for evaluation of compressive strength of concrete, IOP Conf. Ser. Mater. Sci. Eng. 810, 012071.
8.Deshpande, N., S. Londhe, and S. Kulkarni (2014), Modeling compressive strength of recycled aggregate concrete by artificial neural network, model tree and non-linear regression, Int. J. Built Environ. 3, 187–198.
9.Empirical physics-informed neural networks (2025), Prediction of concrete strength using nondestructive testing.
10.Gangele, , and A. K. Patel (2020), Prediction of compressive strength by considering practical non- destructive test conditions using artificial neural network, J. Mater. Eng. Struct.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
