A heuristic optimization method based on a global search strategy for predicting ultra-high performance concrete’s uniaxial compressive strength using Kernel extreme learning machine

Abstract

Accurately predicting the uniaxial compressive strength of ultra-high-performance concrete is vital for optimizing material design and ensuring cost-effective construction. However, existing predictive models often fail to capture the nonlinear relationships inherent in complex UHPC datasets and suffer from extended training times, thereby limiting their accuracy and practical utility. From the perspective of artificial intelligence, this study proposes an enhanced predictive framework that integrates a kernel extreme learning machine with a globally strengthened whale optimization algorithm. The proposed framework introduces three novel mechanisms—adaptive inertia weight, variable helix search, and optimal neighborhood perturbation—designed to improve the algorithm’s global search capability, convergence speed, and solution stability. From the engineering application perspective, the proposed model is applied to three UHPC datasets to predict uniaxial compressive strength. Prior to modeling, feature normalization is employed to reduce the impact of dimensional inconsistency among input variables. Experimental results demonstrate the model’s superior predictive precision, achieving $R^2$ values of 0.8823, 0.8906, and 0.8951 across the datasets. These findings confirm that the integration of advanced AI optimization techniques significantly enhances the performance of predictive models in civil engineering, offering a reliable and efficient approach for ultra-high-performance concrete strength estimation in design and construction workflows.

Keywords

Ultra-high performance concrete / Uniaxial compressive strength / Whale optimization algorithm / Kernel extreme learning machine / Global search

References

[1] Aiyer BG, Kim D, Karingattikkal N, Samui P, Rao PR. Prediction of compressive strength of self-compacting concrete using least square support vector machine and relevance vector machine. KSCE Journal of Civil Engineering, 2014, 18: 1753-1758.

[2] Akeed MH, Qaidi S, Ahmed HU, Faraj RH, Mohammed AS, Emad W, Tayeh BA, Azevedo AR. Ultra-high performance fiber-reinforced concrete Part IV: Durability properties, cost assessment, applications, and challenges. Case Studies in Construction Materials, 2022, 17: 01271

[3] Aziz T, Aziz H, Mahapakulchai S, Charoenlarpnopparut C. Optimizing compressive strength prediction using adversarial learning and hybrid regularization. Scientific Reports, 2024, 14. ArticleID: 18338

[4] Chou JS, Chiu CK, Farfoura M, Al-Taharwa I. Optimizing the prediction accuracy of concrete compressive strength based on a comparison of data-mining techniques. Journal of Computing in Civil Engineering, 2011, 25: 242-253.

[5] Du G, Liu X, Zhu Y, Li D, Xing X. Experimental study on the performance of steel fiber shotcrete in tunnels and its engineering applications. Chinese Journal of Rock Mechanics and Engineering, 2008, 27: 1448-1454

[6] El Asri Y, Aicha MB, Zaher M, Alaoui AH. Prediction of compressive strength of self-compacting concrete using four machine learning technics. Materials Today: Proceedings, 2022, 57: 859-866

[7] Faramarzi A, Heidarinejad M, Mirjalili S, Gandomi AH. Marine predators algorithm: A nature-inspired metaheuristic. Expert Systems with Applications, 2020, 152. ArticleID: 113377

[8] Gholampour A, Mansouri I, Kisi O, Ozbakkaloglu T. Evaluation of mechanical properties of concretes containing coarse recycled concrete aggregates using multivariate adaptive regression splines (mars), m5 model tree (m5tree), and least squares support vector regression (lssvr) models. Neural Computing and Applications, 2020, 32: 295-308.

[9] Gilan SS, Jovein HB, Ramezanianpour AA. Hybrid support vector regression-particle swarm optimization for prediction of compressive strength and rcpt of concretes containing metakaolin. Construction and Building Materials, 2012, 34: 321-329.

[10] Golafshani EM, Behnood A. Application of soft computing methods for predicting the elastic modulus of recycled aggregate concrete. Journal of Cleaner Production, 2018, 176: 1163-1176.

[11] Huang, G. B., Zhu, Q. Y., & Siew, C. K., (2004). Extreme learning machine: a new learning scheme of feedforward neural networks, In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541), IEEE. (pp.985–990).

[12] Javed MF, Fawad M, Lodhi R, Najeh T, Gamil Y. Forecasting the strength of preplaced aggregate concrete using interpretable machine learning approaches. Scientific Reports, 2024, 14. ArticleID: 8381

[13] Joshi DA, Menon R, Jain R, Kulkarni A. Deep learning based concrete compressive strength prediction model with hybrid meta-heuristic approach. Expert Systems with Applications, 2023, 233. ArticleID: 120925

[14] Karaboga D, Gorkemli B, Ozturk C, Karaboga N. A comprehensive survey: Artificial bee colony (abc) algorithm and applications. Artificial Intelligence Review, 2014, 42: 21-57.

[15] Kennedy, J., & Eberhart, R., (1995). Particle swarm optimization, In Proceedings of ICNN’95-international conference on neural networks, IEEE. (pp.1942–1948).

[16] Khandagale, H., Salunkhe, M. S., Kamble, V. K., Manjarekar, A. A., Halkarnikar, P., & Redekar, S. S., (2024). Optimizing concrete compressive strength prediction: A comparative study of machine learning algorithms, In 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT), IEEE. (pp. 1–6).

[17] Li P, Zhang Z, Gu J. Prediction of concrete compressive strength based on ISAA-BPnn-Adaboost. Materials, 2024, 17. ArticleID: 5727

[18] Li Y, Zhong R, Yu J, Song J, Wang Q, Chen C, Li X, Liu E. Uniaxial compressive strength of concrete inversion using machine learning and computational intelligence approach. Results in Engineering, 2025, 26. ArticleID: 105627

[19] Mirjalili S, Lewis A. The whale optimization algorithm. Advances in Engineering Software, 2016, 95: 51-67.

[20] Mirjalili S, Mirjalili SM, Lewis A. Grey wolf optimizer. Advances in Engineering Software, 2014, 69: 46-61.

[21] Nili M, Afroughsabet V. Property assessment of steel-fibre reinforced concrete made with silica fume. Construction and Building Materials, 2012, 28: 664-669.

[22] Pham AD, Hoang ND, Nguyen QT. Predicting compressive strength of high-performance concrete using metaheuristic-optimized least squares support vector regression. Journal of Computing in Civil Engineering, 2016, 30: 06015002.

[23] Wang, R., (2023). Research on Strength Prediction and Application of Steel Fiber Shotcrete. Master’s thesis. Kunming University of Science and Technology.

[24] Xu L, Fan D, Liu K, Xu W, Yu R. A machine learning framework for intelligent development of ultra-high performance concrete (UHPC): From dataset cleaning to performance predicting. Expert Systems with Applications, 2024, 242. ArticleID: 122790

[25] Xu, Y., Deng, B., Wu, & L., (2024). Comparison of compressive strength prediction models for recycled aggregate concrete prepared with blast furnace slag and fly ash. Mineral Comprehensive Utilization , 1–9 http://kns.cnki.net/kcms/detail/51.1251.TD.20231010.1247.006.html. online First, Accessed on 13 Jul 2024.

[26] Xue, J. (2020). Research and Application of a New Swarm Intelligence Optimization Technique. Ph.d. thesis. Donghua University.

[27] Yang, X., Guan, W., Liu, & Yuqi, E. A. (2015). Interval prediction method of wind power based on kernel extreme learning machine model optimized by particle swarm optimization. Proceedings of the Chinese Society for Electrical Engineering, 35, 146–153. https://doi.org/10.13334/j.0258-8013.pcsee.2015.S.020

[28] Yeh IC. Modeling concrete strength with augment-neuron networks. Journal of Materials in Civil Engineering, 1998, 10: 263-268.

[29] Yeh IC. Modeling of strength of high-performance concrete using artificial neural networks. Cement and Concrete Research, 1998, 28: 1797-1808.

[30] Zhang Y, Ren W, Chen Y, Mi Y, Lei J, Sun L. Predicting the compressive strength of high-performance concrete using an interpretable machine learning model. Scientific Reports, 2024, 14: 28346.

RIGHTS & PERMISSIONS

The Author(s)