Hybrid RBF-based prediction algorithms for evaluation of the compressive strength of HPC enhanced with blast furnace slag and fly ash

Shanwei  Zhang

doi:10.6180/jase.202511_28(11).0016

Hybrid RBF-based prediction algorithms for evaluation of the compressive strength of HPC enhanced with blast furnace slag and fly ash

Research Categories

Pearson Correlation Coefficient plot.

Shanwei Zhang

College of Design, Chongqing College of Finance and Economics, Yongchuan 402160, Chongqing, China

Received: September 16, 2024
Accepted: January 23, 2025
Publication Date: March 16, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202511_28(11).0016

The compressive strength (CS) of high-performance concrete (HPC) amended with blast furnace slag (BFS) and fly ash (FA) is estimated using a unique method in this study using a radial basis function (RBF) neural network. Herein, RBF was paired with the Chimp Optimization Algorithm (ChOA) and the Equilibrium Optimizer (EO) to determine the most important parameters of the RBF method that might be optimized, abbreviated as ChRB and EORB. The suggested algorithms were evaluated concerning 1030 experimental samples, eight input variables (HPC age, water, blast furnace slag, cement content, superplasticizer, fly ash, and fine and coarse aggregates), and the target CS as the forecasting. Accurate forecasting of CS enables construction sites to monitor and verify that concrete mixes satisfy strength specifications prior to pouring, therefore mitigating structural problems. This not only lowers carbon emissions but also promotes the use of industrial byproducts in building, in accordance with sustainable construction objectives. Precise CS forecasts facilitate the design of robust and resilient buildings, particularly for infrastructure projects exposed to significant loads or severe conditions. The results indicate that both hybrid ChRB and EORB analyses perform well in productivity for train and test portions. The EORB included lower index values than the ChRB. Based on the comparison results with the existing literature, it is obvious that the produced EORB outperforms all existing literature. In summary, the suggested approach is the EORB framework designed for estimating the CS of HPC enhanced with FA, and BFS.

Keywords: Compressive strength; Radial basis function neural network; High-performance concrete; Blast furnace slag; Fly ash

[1] I.-C. Yeh, (1998) “Modeling concrete strength with augment-neuron networks" Journal of Materials in Civil Engineering 10: 263–268. DOI: 10.1061/(ASCE)0899-1561(1998)10:4(263).
[2] I.-C. Yeh, (2006) “Analysis of strength of concrete using design of experiments and neural networks" Journal of Materials in Civil Engineering 18: 597–604. DOI: 10.1061/(ASCE)0899-1561(2006)18:4(597).
[3] I.-C. Yeh, (2003) “Prediction of strength of fly ash and slag concrete by the use of artificial neural networks" J. Chin. Inst. Civil Hydraul. Eng 15: 659–663.
[4] I.-C. Yeh, (1999) “Design of high-performance concrete mixture using neural networks and nonlinear program ming" Journal of Computing in Civil Engineering 13: 36–42. DOI: 10.1061/(ASCE)0887-3801(1999)13:1(36).
[5] S. Lee, N.-H. Nguyen, A. Karamanli, J. Lee, and T. P. Vo, (2023) “Super learner machine-learning algorithms for compressive strength prediction of high performance concrete" Structural Concrete 24: 2208–2228. DOI: 10.1002/suco.202200424.
[6] D. V. Dao, H. Adeli, H.-B. Ly, L. M. Le, V. M. Le, T.-T. Le, and B. T. Pham, (2020) “A sensitivity and ro bustness analysis of GPR and ANN for high-performance concrete compressive strength prediction using a Monte Carlo simulation" Sustainability 12: 830. DOI: 10.3390/su12030830.
[7] N.-H. Nguyen, T. P. Vo, S. Lee, and P. G. Asteris, (2021) “Heuristic algorithm-based semi-empirical formu las for estimating the compressive strength of the nor mal and high performance concrete" Construction and Building Materials 304: 124467. DOI: 10.1016/j.conbuildmat.2021.124467.
[8] P. G. Asteris, A. D. Skentou, A. Bardhan, P. Samui, and K. Pilakoutas, (2021) “Predicting concrete com pressive strength using hybrid ensembling of surrogate machine learning models" Cement and Concrete Re search 145: 106449. DOI: 10.1016/j.cemconres.2021.106449.
[9] S. M. Mousavi, P. Aminian, A. H. Gandomi, A. H. Alavi, and H. Bolandi, (2012) “A new predictive model for compressive strength of HPC using gene expression programming" Advances in Engineering Software 45: 105–114. DOI: 10.1016/j.advengsoft.2011.09.014.
[10] A. Cevik and A. F. Cabalar, (2009) “Modelling damp ing ratio and shear modulus of sand–mica mixtures using genetic programming" Expert Systems with Applica tions 36: 7749–7757. DOI: 10.1016/j.eswa.2008.09.010.
[11] A.Baykaso˘ glu, H. Güllü, H. Çanakçı, and L. Özbakır, (2008) “Prediction of compressive and tensile strength of limestone via genetic programming" Expert Systems with Applications 35: 111–123. DOI: 10.1016/j.eswa.2007.06.006.
[12] A. H. Gandomi, A. H. Alavi, M. R. Mirzahosseini, and F. M. Nejad, (2011) “Nonlinear genetic-based mod els for prediction of flow number of asphalt mixtures" Journal of Materials in Civil Engineering 23: 248–263. DOI: 10.1061/(ASCE)MT.1943-5533.0000154.
[13] A.H.AlaviandA.H.Gandomi,(2011) “A robust data mining approach for formulation of geotechnical engineer ing systems" Engineering Computations 28: 242–274. DOI: 10.1108/02644401111118132.
[14] C. Ferreira, (2001) “Gene expression programming: a new adaptive algorithm for solving problems" arXiv preprint cs/0102027: DOI: 10.48550/arXiv.cs/0102027.
[15] A. H.GandomiandA.H.Alavi, (2012) “A new multi gene genetic programming approach to non-linear system modeling. Part II: geotechnical and earthquake engineer ing problems" Neural Computing and Applications 21: 189–201. DOI: 10.1007/s00521-011-0735-y.
[16] A. H.GandomiandA.H.Alavi, (2012) “A new multi gene genetic programming approach to nonlinear system modeling. Part I: materials and structural engineering problems" Neural Computing and Applications 21: 171–187. DOI: 10.1007/s00521-011-0734-z.
[17] J. R. Koza, (1992) “Genetic programming: on the pro gramming of computers by means of natural selection Cambridge" MA: MIT Press.[Google Scholar]:
[18] M. H. Rafiei, W. H. Khushefati, R. Demirboga, and H. Adeli, (2017) “Novel Approach for Concrete Mixture Design Using Neural Dynamics Model and Virtual Lab Concept." ACI Materials Journal 114: DOI: 10.14359/51689485.
[19] T. Nguyen, A. Kashani, T. Ngo, and S. Bordas, (2019) “Deep neural network with high-order neuron for the pre diction of foamed concrete strength" Computer-Aided Civil and Infrastructure Engineering 34: 316–332. DOI: 10.1111/mice.12422.
[20] M.H.Rafiei, W.H.Khushefati, R. Demirboga, and H. Adeli, (2017) “Supervised deep restricted Boltzmann ma chine for estimation of concrete" ACI Materials Journal 114: 237. DOI: 10.14359/51689560.
[21] P. G.Asteris, P. C. Roussis, and M. G. Douvika, (2017) “Feed-forward neural network prediction of the mechanical properties of sandcrete materials" Sensors 17: 1344. DOI: 10.3390/s17061344.
[22] M.R. Kaloop, D. Kumar, P. Samui, J. W. Hu, and D. Kim, (2020) “Compressive strength prediction of high performance concrete using gradient tree boosting ma chine" Construction and Building Materials 264: 120198. DOI: 10.1016/j.conbuildmat.2020.120198.
[23] H. I. Erdal, (2013) “Two-level and hybrid ensembles of decision trees for high performance concrete compressive strength prediction" Engineering Applications of Ar tificial Intelligence 26: 1689–1697. DOI: 10.1016/j.engappai.2013.03.014.
[24] M.-Y. Cheng, P. M. Firdausi, and D. Prayogo, (2014) “High-performance concrete compressive strength predic tion using Genetic Weighted Pyramid Operation Tree (GWPOT)" Engineering Applications of Artificial Intelligence 29: 104–113. DOI: 10.1016/j.engappai.2013.11.014.
[25] J.-S. Chou and A.-D. Pham, (2013) “Enhanced artificial intelligence for ensemble approach to predicting high per formance concrete compressive strength" Construction and Building Materials 49: 554–563. DOI: 10.1016/j.conbuildmat.2013.08.078.
[26] H.I. Erdal, O. Karakurt, and E. Namli, (2013) “High performance concrete compressive strength forecasting us ing ensemble models based on discrete wavelet transform" Engineering Applications of Artificial Intelligence 26: 1246–1254. DOI: 10.1016/j.engappai.2012.10.014.
[27] S. Rajasekaran and S. Lavanya, (2007) “Hybridization of genetic algorithm with immune system for optimiza tion problems in structural engineering" Structural and Multidisciplinary Optimization 34: 415–429. DOI: 10.1007/s00158-006-0084-0.
[28] I.-C. Yeh, (2007) “Modeling slump flow of concrete using second-order regressions and artificial neural networks" Cement andconcrete composites 29: 474–480. DOI: 10.1016/j.cemconcomp.2007.02.001.
[29] S.-C. Lee, (2003) “Prediction of concrete strength using artificial neural networks" Engineering structures 25: 849–857. DOI: 10.1016/S0141-0296(03)00004-X.
[30] S. Rajasekaran, D. Suresh, and G. A. V. Pai, (2002) “Application of sequential learning neural networks to civil engineering modeling problems" Engineering with Computers 18: 138–147. DOI: 10.1007/s003660200012.
[31] S. Rajasekaran and R. Amalraj, (2002) “Predictions of design parameters in civil engineering problems using SLNN with a single hidden RBF neuron" Computers & structures 80: 2495–2505. DOI: 10.1016/S0045-7949(02)00213-4.
[32] B. K. R. Prasad, H. Eskandari, and B. V. V. Reddy, (2009) “Prediction of compressive strength of SCC and HPCwith high volume fly ash using ANN" Construc tion and Building Materials 23: 117–128. DOI: 10.1016/j.conbuildmat.2008.01.014.
[33] J. Kasperkiewicz, J. Racz, and A. Dubrawski, (1995) “HPC strength prediction using artificial neural network" Journal of Computing in Civil Engineering 9: 279 284. DOI: 10.1061/(ASCE)0887-3801(1995)9:4(279).
[34] T. Ji, T. Lin, and X. Lin, (2006) “A concrete mix propor tion design algorithm based on artificial neural networks" Cement and Concrete Research 36: 1399–1408. DOI: 10.1016/j.cemconres.2006.01.009.
[35] A. A.Basma, S. A. Barakat, and S. Al-Oraimi, (1999) “Prediction of cement degree of hydration using artificial neural networks" ACI Materials Journal 96: 167–172. DOI: 10.14359/441.
[36] I.-C. Yeh, (1998) “Modeling of strength of high performance concrete using artificial neural networks" Cement and Concrete research 28: 1797–1808. DOI: 10.1016/S0008-8846(98)00165-3.
[37] M. A. Hir, M. Zaheri, and N. Rahimzadeh, (2023) “Prediction of rural travel demand by spatial regression and artificial neural network methods (Tabriz County)" Journal of transportation research (Tehran) 20: 367 386. DOI: 10.22034/tri.2022.312204.2970.
[38] P. L. J. Domone and M. N. Soutsos, (1994) “Approach to the proportioning of high-strength concrete mixes" Concrete international 16: 26–31.
[39] S. M. Mousavi, A. H. Gandomi, A. H. Alavi, and M. Vesalimahmood, (2010) “Modeling of compressive strength of HPC mixes using a combined algorithm of ge netic programming and orthogonal least squares" Struc tural Engineering and Mechanics, An Int’l Journal 36: 225–241. DOI: 10.12989/sem.2010.36.2.225.
[40] R. A. Cook, C. Goodspeed, and S. Vanicar. High performance concrete defined for highway structures. 1998.
[41] M.Khishe and M. R. Mosavi, (2020) “Chimp optimiza tion algorithm" Expert systems with applications 149: 113338. DOI: 10.1016/j.eswa.2020.113338.
[42] N. Leema, H. K. Nehemiah, and A. Kannan, (2016) “Neural network classifier optimization using differential evolution with global information and back propagation al gorithm for clinical datasets" Applied Soft Computing 49: 834–844. DOI: 10.1016/j.asoc.2016.08.001.