Intelligent prediction of compressive strength of self-compacting concrete incorporating silica fume using hybrid IWOA-GPR model

被引:0
作者
Yu, Yang [1 ]
Wang, Guangyin [1 ]
Huseien, Ghasan Fahim [2 ]
Zou, Zhen [1 ]
Ding, Zhenghao [3 ]
Zhang, Chunwei [1 ]
机构
[1] Shenyang Univ Technol, Multidisciplinary Ctr Infrastruct Engn, Sch Architecture & Civil Engn, Shenyang 110870, Liaoning, Peoples R China
[2] Natl Univ Singapore, Sch Design & Environm, Dept Built Environm, Singapore 117566, Singapore
[3] Kyoto Univ, Dept Civil & Earth Resources Engn, Kyoto, Japan
来源
MATERIALS TODAY COMMUNICATIONS | 2025年 / 45卷
关键词
Self-compacting concrete; Compressive strength; Whale optimization algorithm; Gaussian process regression; Sensitivity analysis; SCC; MACHINE;
D O I
10.1016/j.mtcomm.2025.112282
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Self-compacting concrete (SCC) has been widely used due to its ability to fill complex molds without the need for mechanical vibration. However, the compressive strength of SCC is influenced by various factors, and traditional prediction methods often fail to provide accurate models. Gaussian process regression (GPR) demonstrates high accuracy when dealing with complex, high-dimensional data; however, the performance of the model is highly dependent on the selection of hyperparameters. To address these issues, this study proposes an improved whale optimization algorithm (IWOA) to optimize the hyperparameters of the GPR prediction model. Cement, water-tobinder ratio, silica fume (nano silica or/and micro silica), coarse aggregate, fine aggregate, superplasticizer, and viscosity-modifying agent are selected as inputs, with the 28-day compressive strength of SCC as the output. A nonlinear convergence factor is employed to enhance the global search capability, thereby improving the prediction accuracy and stability of the model. Finally, experimental data is used to compare the proposed method with various other prediction models, validating the superiority of the proposed approach. The results indicate that the IWOA-GPR model achieved a root mean squared error (RMSE) of 4.80 on the training set and 6.52 on the testing set, with a mean absolute error (MAE) of 3.05 and 4.67, respectively. The coefficient of determination (R2) on the testing set was 0.95, indicating excellent predictive performance. Compared to other models (BPNN, SVM, EDT, RF), the IWOA-GPR model demonstrated significant improvements in RMSE and MAE, with reductions of up to 25.77 % on the training set and 20.90 % on the testing set. Sensitivity analysis identified the water-to-binder ratio as the most critical factor (SHAP value = 8.2), followed by fine aggregate and cement content. These results validate the IWOA-GPR model as a robust tool for SCC strength prediction and mix optimization.
引用
收藏
页数:17
相关论文
共 45 条
  • [1] Observation of a broad 1-- resonant structure around 1.5 GeV/c2 in the K+K- mass spectrum in J/ψ→K+K-π0
    Ablikim, M.
    Bai, J. Z.
    Ban, Y.
    Cai, X.
    Chen, H. F.
    Chen, H. S.
    Chen, H. X.
    Chen, J. C.
    Chen, Jin
    Chen, Y. B.
    Chi, S. P.
    Chu, Y. P.
    Cui, X. Z.
    Dai, Y. S.
    Deng, Z. Y.
    Dong, L. Y.
    Dong, Q. F.
    Du, S. X.
    Du, Z. Z.
    Fang, J.
    Fang, S. S.
    Fu, C. D.
    Gao, C. S.
    Gao, Y. N.
    Gu, S. D.
    Gu, Y. T.
    Guo, Y. N.
    Guo, Y. Q.
    Guo, Z. J.
    Harris, F. A.
    He, K. L.
    He, M.
    Heng, Y. K.
    Hu, H. M.
    Hu, T.
    Huang, G. S.
    Huang, X. P.
    Huang, X. T.
    Ji, X. B.
    Jiang, X. S.
    Jiao, J. B.
    Jin, D. P.
    Jin, S.
    Jin, Yi
    Lai, Y. F.
    Li, G.
    Li, H. B.
    Li, H. H.
    Li, J.
    Li, R. Y.
    [J]. PHYSICAL REVIEW LETTERS, 2006, 97 (14)
  • [2] Total and initial fracture energies of self-compacting lightweight concrete containing silica fume and nano-silica
    Ahmadi, Seyed Hassan
    Mazloom, Moosa
    Salehi, Hasan
    [J]. ENGINEERING FRACTURE MECHANICS, 2024, 308
  • [3] Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models
    Asteris, Panagiotis G.
    Skentou, Athanasia D.
    Bardhan, Abidhan
    Samui, Pijush
    Pilakoutas, Kypros
    [J]. CEMENT AND CONCRETE RESEARCH, 2021, 145 (145)
  • [4] An experimental survey on combined effects of fibers and nanosilica on the mechanical, rheological, and durability properties of self-compacting concrete
    Beigi, Morteza H.
    Berenjian, Javad
    Omran, Omid Lotfi
    Nik, Aref Sadeghi
    Nikbin, Iman M.
    [J]. MATERIALS & DESIGN, 2013, 50 : 1019 - 1029
  • [5] Optimum Design of Single and Multiple Tuned Mass Dampers for Vibration Control in Buildings Under Seismic Excitation
    Brandao, Francisco da Silva
    de Almeida, Alex Koch
    Fadel Miguel, Leticia Fleck
    [J]. INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS, 2022, 22 (08)
  • [6] Research on New Adaptive Whale Algorithm
    Chen, Xuan
    [J]. IEEE ACCESS, 2020, 8 : 90165 - 90201
  • [7] Automated structural resilience evaluation based on a multi-scale Transformer network using field monitoring data
    Chen, Zepeng
    Liu, Qitian
    Ding, Zhenghao
    Liu, Feng
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2025, 222
  • [8] Efficient Image Encryption Scheme Using Novel 1D Multiparametric Dynamical Tent Map and Parallel Computing
    Daoui, Achraf
    Yamni, Mohamed
    Chelloug, Samia Allaoua
    Wani, Mudasir Ahmad
    El-Latif, Ahmed A. Abd
    [J]. MATHEMATICS, 2023, 11 (07)
  • [9] Optimal Design of Dampers for Multi-Mode Cable Vibration Control Based on Genetic Algorithm
    Di, Fangdian
    Chen, Lin
    Sun, Limin
    [J]. INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS, 2021, 21 (04)
  • [10] Clustering driven incremental learning surrogate model-assisted evolution for structural condition assessment
    Ding, Zhenghao
    Kuok, Sin-Chi
    Lei, Yongzhi
    Li, Yifei
    Yu, Yang
    Zhang, Guangcai
    Hu, Shuling
    Yuen, Ka-Veng
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2025, 224