Email this article Predicting compressive strength of heavyweight concrete using deep neural networks and Box–Behnken design
DOI: https://doi.org/10.20528/cjcrl.2025.04.002
View Counter: Abstract | 552 times | ‒ Full Article | 216 times |
Full Text:
PDFAbstract
This study investigates the prediction and evaluation of compressive strength in heavyweight concrete incorporating magnetite and steel slag, using two advanced modeling techniques: Deep Artificial Neural Networks (DANN) and Box-Behnken Response Surface Methodology (BBRSM). A total of 324 concrete specimens were prepared based on 36 unique mix designs. Non-destructive testing methods ultrasonic pulse velocity (UPV) and Schmidt rebound hammer (SRH) were employed to characterize material properties. The 28-day compressive strength of each sample was determined following ASTM C39 standards. Data from UPV and SRH tests, along with mix parameters such as the water-cement ratio, were used as inputs for both models. The DANN model, developed using a hybrid architecture combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), achieved superior predictive performance, with a coefficient of determination (R²) of 0.9951 and a root mean square error (RMSE) of 0.0314 MPa. This corresponds to a coefficient of variation of just 0.045%, with a standard deviation error of 0.02% relative to the mean compressive strength of approximately 70 MPa. In contrast, the BBRSM model, employing a sixth-degree polynomial equation, yielded an R² of 0.9628 and a standard deviation of residuals of 1.36 MPa (about 1.94% of the average strength). The findings highlight the enhanced accuracy and efficiency of the Hybrid DANN model over the BBRSM approach. While both techniques offer practical, cost-effective alternatives to experimental testing, the DANN model is particularly well-suited for capturing complex nonlinear behaviors, whereas BBRSM remains valuable for optimization-oriented analysis.
Keywords
References
Abbass W, Aslam F, Ahmed M, Ahmed A, Alyousef R, Mohamed A (2023). Predicting the performance of existing pre-cast concrete pipes using destructive and non-destructive testing techniques. Heliyon, 9(4), e15471.
Angiulli G, Burrascano P, Ricci M, Versaci M (2024a). Advances in the integration of artificial intelligence and ultrasonic techniques for monitoring concrete structures: A comprehensive review. Journal of Composites Science, 8(12), 531.
Angiulli G, Calcagno S, La Foresta F, Versaci M (2024b). Concrete compressive strength prediction using combined non-destructive methods: A calibration procedure using preexisting conversion models based on Gaussian process regression. Journal of Composites Science, 8(8), 300.
Ansari MA, Ansari SS, Ghazi MS, Saqib M, Ibrahim SM, Saquib M (2024). Incorporating non-destructive UPV into machine learning models for predicting compressive strength in SCM concrete. Materials Today: Proceedings, 4, 59–67.
Asri Y, Benaicha M, Zaher M, Hafidi Alaoui A (2022). Prediction of the compressive strength of self-compacting concrete using artificial neural networks based on rheological parameters. Structural Concrete, 23(6), 3864–3876.
Asteris PG, Kolovos KG, Douvika MG, Roinos K (2016). Prediction of self-compacting concrete strength using artificial neural networks. European Journal of Environmental and Civil Engineering, 20(sup1), s102–s122.
Asteris PG, Skentou AD, Bardhan A, Samui P, Lourenço PB (2021). Soft computing techniques for the prediction of concrete compressive strength using non-destructive tests. Construction and Building Materials, 303, 124450.
Benaicha M (2024). AI-driven prediction of compressive strength in self-compacting concrete: Enhancing sustainability through ultrasonic measurements. Sustainability, 16(15), 6644.
Boccacci G, Frasca F, Bertolin C, Siani AM (2024). Diagnosis of historic reinforced concrete buildings: A literature review of non-destructive testing (NDT) techniques. Procedia Structural Integrity, 55, 160–167.
Chou J-S, Pham A-D (2015). Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength. Construction and Building Materials, 49, 554–563.
Feng D-C, Liu Z-T, Wang X-D, Chen Y, Chang J-Q, Wei D-F, Jiang Z-M (2020). Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach. Construction and Building Materials, 230, 117000.
Iqbal MF, Liu Q-F, Azim I, Zhu X, Yang J, Javed MF, Rauf M (2020). Prediction of mechanical properties of green concrete incorporating waste foundry sand based on gene expression programming. Journal of Hazardous Materials, 384, 121322.
Jibril MM, Zayyan MA, Malami SI, Usman AG, Salami BA, Rotimi A, Abba SI (2023). Implementation of nonlinear computing models and classical regression for predicting compressive strength of high-performance concrete. Applied Engineering Sciences, 15, 100133.
Kouddane B, Sbartaï ZM, Elachachi SM, Lamdouar N (2023). New multi-objective optimization to evaluate the compressive strength and variability of concrete by combining non-destructive techniques. Journal of Building Engineering, 77, 107526.
Lai MH, Wu KJ, Cheng X, Ho JCM, Wu JP, Chen JH, Zhang AJ (2022). Effect of fillers on the behaviour of heavy-weight concrete made by iron sand. Construction and Building Materials, 332, 127357.
Mirzaie Aliabadi M, Derakhshan Nezhad AH, Shahidzadeh MS, Dadpur A (2024). Date palm fibers to improve tensile strength in self‑compacting concrete with silica fume. Civil Engineering Infrastructures Journal, In Press.
Moura MAN, Moreno AL, Ferreira GCS (2023). Ultrasonic testing on evaluation of concrete residual compressive strength: A review. Construction and Building Materials, 373, 130887.
Murty KSS, Rama Rao GV, Adiseshu S (2024). Experimental study on the effect of colloidal nano silica in self-compacting concrete containing ground granulated blast furnace slag. Research on Engineering Structures and Materials, 10(2), 1467–1481.
Pal A, Ahmed KS, Hossain FZ, Alam MS (2023). Machine learning models for predicting compressive strength of fiber-reinforced concrete containing waste rubber and recycled aggregate. Journal of Cleaner Production, 423, 138673.
Pazouki G, Tao Z, Saeed N, Kang W-H (2023). Using artificial intelligence methods to predict the compressive strength of concrete containing sugarcane bagasse ash. Construction and Building Materials, 409, 134047.
Ramkumar KB, Rajkumar KPR, Ahmmad SN, Murugesan J (2020). A review on performance of self-compacting concrete – Use of mineral admixtures and steel fibres with artificial neural network application. Construction and Building Materials, 261, 120215.
Roshan-Tabari, F., Toopchi-Nezhad, H., & Hashemi-Motlagh, G. (2024). Development and testing of a novel high-damping chlorobutyl rubber for structural viscoelastic damper devices. Civil Engineering Infrastructures Journal, 57(2), 337–355.
Reddy AN, Reddy GGK, Reddy PN, Reddy KS, Kavyateja BV (2024). Analyzing the impact of nano-sized silica on composite concrete: A static approach utilizing response surface method. Research on Engineering Structures and Materials, 10(2), 165–178.
Sadowski L, Nikoo M (2020). Non-destructive estimation of concrete compressive strength using ultrasonic pulse velocity and artificial neural network. Measurement, 152, 107328.
Sathiparan N, Jeyananthan P (2023). Prediction of masonry prism strength using machine learning technique: Effect of dimension and strength parameters. Materials Today Communications, 35, 106282.
Sathiparan N, Jeyananthan P, Subramaniam DN (2024). Surface response regression and machine learning techniques to predict the characteristics of pervious concrete using non-destructive measurement: Ultrasonic pulse velocity and electrical resistivity. Measurement, 225, 114006.
Sayyar-Roudsari S, Shalbaftabar A, Damirchilo F, Taslimian R, Abu-Lebdeh T, Hamoush S, Yi S (2024). Defect classification of reinforced concrete structures with nondestructive tests using statistical and machine learning methods. American Journal of Engineering and Applied Sciences, 17(3), 102–115.
Shahidzadeh MS, Derakhshan Nezhad AH, Mirzaie Aliabadi M (2024a). Analyzing and examining the impact of various fiber types on the mechanical and functional characteristics of UHPC. Research on Engineering Structures and Materials, 11(3), 1219–1244.
Shahidzadeh MS, Mirzaie Aliabadi M, Mansouri Far H, Derakhshan Nezhad AH (2024b). Mechanical and rheological performance of plastic concrete: Investigation of several properties. Research on Engineering Structures and Materials, In Press.
Silva FAN, Delgado JMPQ, Cavalcanti RS, Azevedo AC, Guimarães AS, Lima AGB (2021). Use of nondestructive testing of ultrasound and artificial neural networks to estimate compressive strength of concrete. Buildings, 11(2), 44.
Wang L, Yi S, Yu Y, Gao C, Samali B (2024). Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning. Mechanical Systems and Signal Processing, 221, 111719.
Yang X, Yang H, Zhang S (2019). Rate-dependent constitutive models of S690 high- strength structural steel. Construction and Building Materials, 198(7), 597–607.
Yang H, Zhang JC, Du GF, Mao ZH (2021). Experimental study on the behavior of cross-shaped concrete-filled steel tubular intermediate long columns under axial compression. Progress in Steel Building Structures, 23(7), 49-57.
Yılmaz S, Özdemir E, Firat M, Ateş A (2022). Economic analysis and economic leakage level in water loss management and paths for future evaluation: A review. Civil Engineering Infrastructures Journal, 55(2), 195–209.
Yousef I, Al-Nawaiseh M, Al-Rawashdeh M (2024). Seismic assessment of base‑isolated structure under a sequence of near‑fault earthquake records. Civil Engineering Infrastructures Journal, 57(2), 267–285.
Zhang Y, Aslani F, Lehane B (2021a). Compressive strength of rubberized concrete: Regression and GA-BPNN approaches using ultrasonic pulse velocity. Construction and Building Materials, 307, 124951.
Zhang Y, Ma J, Zhang Y, Wang L (2021b). Prediction of compressive strength of high-performance concrete using machine learning algorithms. Journal of Materials in Civil Engineering, 33(10), 04021294.
Zheng Y, Lin Y, Ma S (2024). Axial compressive behavior of stiffened and multi-cell cross-shaped CFST stub columns. Constructional Steel Research, 213, 108399.
Zhu Y, Gardner L, Yang H (2023). Experimental investigation into the transverse impact performance of high-strength circular CFST members. Thin-Walled Structures, 189(3), 110923.
