Utilizing hybrid machine learning to estimate the Compressive Strength of High-Performance Concrete

Lili  GUO; Daming  FAN

doi:10.6180/jase.202411_27(11).0008

Utilizing hybrid machine learning to estimate the Compressive Strength of High-Performance Concrete

Material Engineering

Lili GUO¹This email address is being protected from spambots. You need JavaScript enabled to view it.and Daming FAN²

¹College of Mechanical and Engineering, Wuhan University of Engineering Science, 430200, China

²Department of Surveying and Mapping Information Engineering, Changjiang Institute of Technology,430200, China

Received: August 6, 2023
Accepted: November 28, 2023
Publication Date: January 27, 2024

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.202411_27(11).0008

This article examines the correlation between compressive strength (CS) and High-performance concrete (HPC) and its practical use in construction engineering. HPC is widely recognized for its remarkable attributes of strength and durability, which render it a high option for deployment in high-stress infrastructural systems like bridges and tunnels. The CS of concrete is a fundamental attribute critical in determining its capacity to maintain structural integrity and endurance over time. This paper investigates the efficacy of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model in forecasting the CS of HPC. The presented model coupled with three meta-heuristic algorithms, namely Chef-based optimization algorithm (COA), Henry Gas Solubility Optimization (HSO), and Artificial Ecosystem-Based Optimization (AEO), to improve the performance and accuracy of ANFIS. In addition, the prediction was applied by 344 datasets from published papers in two phases containing training (70%) and testing (30%). As a result, ANEB (ANFIS coupled with AEO) obtained suitable results with high R2 and less RMSE value compared to other models. This precision in forecasting permits engineers to design concrete structures that are not only more efficient but also cost-effective. The integration of ANFIS in the prediction of the CS of HPC has the potential to facilitate the development of more resilient and durable infrastructures, consequently yielding consequential advantages for the construction sector.

Keywords: High-performance concrete; Compressive strength; Adaptive Neuro-Fuzzy Inference System; Chef-based optimization algorithm; Henry Gas Solubility Optimization; Artificial Ecosystem-Based Optimization.

[1] C. Plati, (2019) “Sustainability factors in pavement materials, design, and preservation strategies: A literature review" Construction and Building Materials 211: 539–555.
[2] M. Nikoo, F. T. Moghadam, and Ł. Sadowski, (2015) “Prediction of concrete compressive strength by evolutionary artificial neural networks" Advances in Materials Science and Engineering 2015:
[3] F. Masoumi, S. Najjar-Ghabel, A. Safarzadeh, and B. Sadaghat, (2020) “Automatic calibration of the groundwater simulation model with high parameter dimensionality using sequential uncertainty fitting approach" Water Supply 20: 3487–3501.
[4] J.-S. Chou and A.-D. Pham, (2013) “Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength" Construction and Building Materials 49: 554–563.
[5] K. Ozawa, K. Maekawa, and H. Okamura, (1992) “Development of high performance concrete" Journal of the Faculty of Engineering, University of Tokyo, Series B;(Japan) 41:
[6] B. A. Graybeal. Material property characterization of ultra-high performance concrete. 2006.
[7] A. Azizi, A. Y. B. Ali, and L. W. Ping, (2015) “Modelling production uncertainties using the adaptive neurofuzzy inference system" South African Journal of Industrial Engineering 26: 224–234.
[8] B. Cetisli, (2010) “Development of an adaptive neurofuzzy classifier using linguistic hedges: Part 1" Expert Systems with Applications 37: 6093–6101.
[9] M. R. Akbarzadeh, H. Ghafourian, A. Anvari, R. Pourhanasa, and M. L. Nehdi, (2023) “Estimating Compressive Strength of Concrete Using Neural Electromagnetic Field Optimization" Materials 16: 4200.
[10] I.-C. Yeh, (1998) “Modeling of strength of highperformance concrete using artificial neural networks" Cement and Concrete research 28: 1797–1808.
[11] T.-P. Chang, F.-C. Chuang, and H.-C. Lin, (1996) “A mix proportioning methodology for high-performance concrete" Journal of the Chinese Institute of Engineers 19: 645–655.
[12] V. Afroughsabet, L. Biolzi, and T. Ozbakkaloglu, (2016) “High-performance fiber-reinforced concrete: a review" Journal of materials science 51: 6517–6551.
[13] S. Fallah and M. Nematzadeh, (2017) “Mechanical properties and durability of high-strength concrete containing macro-polymeric and polypropylene fibers with nano-silica and silica fume" Construction and building materials 132: 170–187.
[14] B. Sadaghat, G. G. Tejani, and S. Kumar, (2023) “Predict the Maximum Dry Density of soil based on Individual and Hybrid Methods of Machine Learning" Advances in Engineering and Intelligence Systems 2:
[15] P. G. Asteris, P. B. Lourenço, P. C. Roussis, C. E. Adami, D. J. Armaghani, L. Cavaleri, C. E. Chalioris, M. Hajihassani, M. E. Lemonis, and A. S. Mohammed, (2022) “Revealing the nature of metakaolinbased concrete materials using artificial intelligence techniques" Construction and Building Materials 322: 126500.
[16] G. Habert. “10 - Assessing the environmental impact of conventional and ‘green’ cement production”. In: Eco-efficient Construction and Building Materials. Ed. by F. Pacheco-Torgal, L. Cabeza, J. Labrincha, and A. de Magalhães. Woodhead Publishing, 2014, 199–238. DOI: https: //doi.org/10.1533/9780857097729.2.199.
[17] B. Sankar and P. Ramadoss, (2022) “Experimental and statistical investigations on alccofine based ternary blended high-performance concrete" International Journal of Engineering 35: 1629–1640.
[18] H. U. Ahmed, A. S. Mohammed, and A. A. Mohammed, (2022) “Proposing several model techniques including ANN and M5P-tree to predict the compressive strength of geopolymer concretes incorporated with nano-silica" Environmental Science and Pollution Research 29: 71232–71256.
[19] B. Sankar and P. Ramadoss, (2023) “Modeling the compressive strength of high-performance concrete containing metakaolin using distinctive statistical techniques" Results in Control and Optimization: 100241.
[20] N. S. Piro, A. S. Mohammed, and S. M. Hamad, (2023) “Evaluate and predict the resist electric current and compressive strength of concrete modified with GGBS and steelmaking slag using mathematical models" Journal of Sustainable Metallurgy 9: 194–215.
[21] S. Liao, G. Li, J. Li, D. Jiang, G. Jiang, Y. Sun, B. Tao, H. Zhao, and D. Chen, (2020) “Multi-object intergroup gesture recognition combined with fusion feature and KNN algorithm" Journal of Intelligent Fuzzy Systems 38: 2725–2735.
[22] M. Nematzadeh and S. Fallah-Valukolaee, (2017) “Effectiveness of fibers and binders in high-strength concrete under chemical corrosion" Structural Engineering and Mechanics, An Int’l Journal 64: 243–257.
[23] P. Rashiddadash, A. A. Ramezanianpour, and M. Mahdikhani, (2014) “Experimental investigation on flexural toughness of hybrid fiber reinforced concrete (HFRC) containing metakaolin and pumice" Construction and Building Materials 51: 313–320.
[24] A. Behnood, J. Olek, and M. A. Glinicki, (2015) “Predicting modulus elasticity of recycled aggregate concrete using M5 model tree algorithm" Construction and Building Materials 94: 137–147.
[25] E. Avci, (2008) “Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system" Applied Soft Computing 8: 225–231.
[26] M. Buragohain and C. Mahanta, (2008) “A novel approach for ANFIS modelling based on full factorial design" Applied soft computing 8: 609–625.
[27] A. Sengur, (2008) “Wavelet transform and adaptive neuro-fuzzy inference system for color texture classification" Expert Systems with Applications 34: 2120– 2128.
[28] A. Sengur, (2008) “An expert system based on principal component analysis, artificial immune system and fuzzy kNN for diagnosis of valvular heart diseases" Computers in biology and medicine 38: 329–338.
[29] A. S. Abdullah, F. A. Essa, and Z. M. Omara, (2021) “Effect of different wick materials on solar still performance–a review" International Journal of Ambient Energy 42: 1055–1082.
[30] F. A. Essa, M. A. Elaziz, and A. H. Elsheikh, (2020) “An enhanced productivity prediction model of active solar still using artificial neural network and Harris Hawks optimizer" Applied Thermal Engineering 170: 115020.
[31] F. A. Essa, A. H. Elsheikh, A. A. Algazzar, R. Sathyamurthy, M. K. A. Ali, M. A. Elaziz, and K. H. Salman, (2020) “Eco-friendly coffee-based colloid for performance augmentation of solar stills" Process Safety and Environmental Protection 136: 259–267.
[32] A. Eid, S. Kamel, A. Korashy, and T. Khurshaid, (2020) “An enhanced artificial ecosystem-based optimization for optimal allocation of multiple distributed generations" IEEE Access 8: 178493–178513.
[33] A. A. Ewees, L. Abualigah, D. Yousri, A. T. Sahlol, M. A. A. Al-Qaness, S. Alshathri, and M. A. Elaziz, (2021) “Modified artificial ecosystem-based optimization for multilevel thresholding image segmentation" Mathematics 9: 2363.
[34] A. Tharwat, (2019) “Parameter investigation of support vector machine classifier with kernel functions" Knowledge and Information Systems 61: 1269–1302.
[35] A. Tharwat, A. E. Hassanien, and B. E. Elnaghi, (2017) “A BA-based algorithm for parameter optimization of support vector machine" Pattern recognition letters 93: 13–22.
[36] A. F. Mirza, M. Mansoor, and Q. Ling, (2020) “A novel MPPT technique based on Henry gas solubility optimization" Energy Conversion and Management 225: 113409.
[37] D. Mohammadi, M. A. Elaziz, R. Moghdani, E. Demir, and S. Mirjalili, (2021) “Quantum Henry gas solubility optimization algorithm for global optimization" Engineering with Computers: 1–20.
[38] N. Pholdee, S. Bureerat, S. M. Sait, and V. Patel, (2020) “The Henry gas solubility optimization algorithm for optimum structural design of automobile brake components":
[39] E. Turajlic, E. Buza, and A. Akagic. “Honey Badger Algorithm and Chef-based Optimization Algorithm for Multilevel Thresholding Image Segmentation”. In: IEEE, 2022, 1–4.
[40] B. Abdollahzadeh, F. S. Gharehchopogh, and S. Mirjalili, (2021) “Artificial gorilla troops optimizer: a new nature-inspired metaheuristic algorithm for global optimization problems" International Journal of Intelligent Systems 36: 5887–5958.
[41] I. Ahmadianfar, O. Bozorg-Haddad, and X. Chu, (2020) “Gradient-based optimizer: A new metaheuristic optimization algorithm" Information Sciences 540: 131–159.
[42] M. A. Elaziz, D. Oliva, and S. Xiong, (2017) “An improved opposition-based sine cosine algorithm for global optimization" Expert Systems with Applications 90: 484–500.
[43] H. Yin, S. Liu, S. Lu, W. Nie, and B. Jia, (2021) “Prediction of the compressive and tensile strength of HPC concrete with fly ash and micro-silica using hybrid algorithms" Advances in Concrete Construction 12: 339.
[44] L. Huang, W. Jiang, Y. Wang, Y. Zhu, and M. Afzal, (2022) “Prediction of long-term compressive strength of concrete with admixtures using hybrid swarm-based algorithms" Smart Structures and Systems, An International Journal 29: 433–444.
[45] H. Cheng, S. Kitchen, and G. Daniels, (2022) “Novel hybrid radial based neural network model on predicting the compressive strength of long-term HPC concrete" Advances in Engineering and Intelligence Systems 1:
[46] H. Zhang, X. Gu, F. Zhang, and L. Zhang, (2023) “Development of a radial basis neural network for the prediction of the compressive strength of high-performance concrete" Multiscale and Multidisciplinary Modeling, Experiments and Design: 1–14.
[47] P. Weng, J. Xie, and Y. Zou, (2023) “Compressive strength prediction of admixed HPC concrete by hybrid deep learning approaches" Journal of Intelligent Fuzzy Systems: 1–14.