基于Bi-LSTM与改进NSGAIII的混凝土配合比多目标优化

doi:10.11896/cldb.24090069

Abstract
Figure/Table
References
Related Citation (4)

Download:

Full Text ( PDF ) (8587KB)
Export: BibTeX | EndNote (RIS)

Abstract For the challenges of multi-variable, multi-objective, and nonlinear issues in concrete mix ratio optimization, a solution that combines a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network with an improved third-generation Non-dominated Sorting Genetic Algorithm (NSGAIII) is proposed. This approach first constructs a data-driven method using the Bi-LSTM model to predict compressive strength of concrete, accurately capturing the nonlinear relationship between mix ratios and compressive strength. On this basis, the NSGAIII algorithm is employed to optimize multiple objectives, including compressive strength, material cost, and carbon emissions. During the mix ratio optimization process, an enhanced strategy that incorporates adaptive mutation and endpoint perturbation is adopted to improve the multi-objective optimization performance of the NSGA-III algorithm. The results show that the Bi-LSTM model achieves accurate predictions of compressive strength, with a correlation coefficient of 0.95 between the predicted and actual values in the test dataset, a root mean square error of 5.3, and a mean absolute error of 4.1. The model outperforms other approaches in both prediction accuracy and generalization capability, especially in predicting compressive strength of concrete. The improved NSGAIII algorithm surpasses conventional methods such as multi-objective particle swarm optimization (MOPSO), NSGAII, and the standard NSGAIII in mix ratio optimization performance. These findings provide valuable reference for concrete mix ratio optimization design in engineering practice.

Key words： concrete mix design compressive strength prediction multi-objective optimization Bi-LSTM improved NSGAIII

Published: 10 October 2025 Online: 2025-09-24

CLC number:

TU528

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HUANG Binbin
	ZENG Lei
	WANG Chao
	SUN Liangfu
	HU Gaoxing

Cite this article:

HUANG Binbin,ZENG Lei,WANG Chao, et al. Multi-objective Optimization of Concrete Mixture Proportions Based on Bi-LSTM and Improved NSGAIII[J]. Materials Reports, 2025, 39(19): 24090069-8.

URL:

https://www.mater-rep.com/EN/10.11896/cldb.24090069 OR https://www.mater-rep.com/EN/Y2025/V39/I19/24090069

1 Zeng Z Y, Zhu Z Y, Yao W, et al. Construction and Building Materials, 2022, 329, 127082.
2 Toufigh V, Jafari A. Construction and Building Materials, 2021, 277, 122241.
3 Miao X, Chen B C, Zhao Y X. Journal of Building Engineering, 2024, 91, 109377.
4 Feng D C, Liu Z T, Wang X D, et al. Construction and Building Materials, 2020, 230, 117000.
5 Salami B A, Olayiwola T, Oyehan T A, et al. Construction and Building Materials, 2021, 301, 124152.
6 Ji T, Lin T W, Lin X J. Journal of Building Materials, 2005(6), 677 (in Chinese).
季韬, 林挺伟, 林旭健. 建筑材料学报, 2005(6), 677.
7 Han B, Ji K, Hu Y F, et al. Journal of Mining & Safety Engineering, 2021, 38(3), 584 (in Chinese).
韩斌, 吉坤, 胡亚飞, 等. 采矿与安全工程学报, 2021, 38(3), 584.
8 Daneshvar M H, Sarmadi H. Engineering Structures, 2022, 256, 114059.
9 Shan W C, Liu J P, Zhou J W. Engineering Structures, 2023, 284, 115980.
10 Liu Z P, Wang Q H, Fatahi B, et al. Engineering Structures, 2024, 310, 118083.
11 Wang P H, Qiao H X, Feng Q, et al. Journal of Building Materials, 2024, 27(3), 189 (in Chinese).
王鹏辉, 乔宏霞, 冯琼, 等. 建筑材料学报, 2024, 27(3), 189.
12 Ni T Y, Du X, Mo Y B, et al. Materials Reports, 2024, 38(10), 79 (in Chinese).
倪彤元, 杜鑫, 莫云波, 等. 材料导报, 2024, 38(10), 79.
13 Wu X G, Wang L, Chen H Y, et al. Materials Reports, 2022, 36(17), 115 (in Chinese).
吴贤国, 王雷, 陈虹宇, 等. 材料导报, 2022, 36(17), 115.
14 Wang S R, Hu P, Chen S B, et al. Journal of Building Materials, 2023, 26(7), 705 (in Chinese).
汪声瑞, 胡畔, 陈思宝, 等. 建筑材料学报, 2023, 26(7), 705.
15 Huang W, Zhou L, Ge P, et al. Materials Reports, 2021, 35(15), 15026 (in Chinese).
黄炜, 周烺, 葛培, 等. 材料导报, 2021, 35(15), 15026.
16 Bui D K, Nguyen T, Chou J S, et al. Construction and Building Materials, 2018, 180, 320.
17 Wang K W, Ren J, Yan J W, et al. Journal of Building Engineering, 2023, 76, 107150.
18 Zhang W M, Liu D W, Cao K P. Case Studies in Construction Materials, 2024, 21, e03416.
19 Zhang T R, Zhang Y Z, Wang Q H, et al. Journal of Building Engineering, 2023, 71, 106518.
20 Tran V Q, Dang V Q, Ho L S. Construction and Building Materials, 2022, 323, 126578.
21 Parichatprecha R, Nimityongskul P. Computers and Concrete, 2009, 6, 253.
22 Chen X D, Chen B, Liu G H. Journal of Hydroelectric Engineering, 2007(5), 59 (in Chinese).
陈晓东, 陈斌, 刘国华. 水力发电学报, 2007(5), 59.
23 Cheng M Y, Prayogo D, Wu Y W. Journal of Computing in Civil Engineering, 2014, 28, 06014003.
24 Sun B B, Wang P F, Guo J J, et al. Journal of Building Engineering, 2024, 96, 110653.
25 Wang J X, Wen Y J, Wu K G, et al. Journal of Energy Storage, 2024, 93, 112298.
26 Sun B, Niu N N. Ocean Engineering, 2024, 311, 118944.
27 Schmidhuber J, Hochreiter S. Neural Computation, 1997, 9, 1735.
28 Lu Y H, Tang L Q, Chen C B, et al. Engineering Structures, 2023, 285, 116000.
29 Deb K, Jain H. IEEE Transactions on Evolutionary Computation, 2013, 18, 577.
30 Zhang J F, Huang Y M, Wang Y H, et al. Construction and Building Materials, 2020, 253, 119208.
31 Ren Q B, Li W W, Li M C, et al. Journal of Hydraulic Engineering, 2022, 53(1), 98 (in Chinese).
任秋兵, 李文伟, 李明超, 等. 水利学报, 2022, 53(1), 98.
32 Golafshani E M, Behnood A. Cement and Concrete Composites, 2019, 96, 95.
33 Wang C, Yu T T, Curiel-Sosac J L, et al. Structural and Multidisciplinary Optimization, 2019, 60, 757.
34 Yeh I C. Cement and Concrete Research, 1998, 28, 1797.
35 Li Y, Zhang J P, He Y Z, et al. Construction and Building Materials, 2023, 409, 134098.