高性能混凝土的早期抗压强度预测和极值寻优

摘要/Abstract

摘要： 高性能混凝土7 d抗压强度作为早期强度的重要指标,对建筑工程质量的影响不容忽视。为了实现高性能混凝土的抗压强度预测及极值寻优,本文基于Logistic混沌映射改进麻雀搜索算法(LCSSA)优化BP神经网络,建立LCSSA-BP预测模型。选取88组数据作为训练集、38组数据作为测试集,对比BP、支持向量机(SVM)、极限学习机(ELM)、人工蜂群算法优化BP神经网络(ABC-BP)、布谷鸟搜索算法优化BP神经网络(CS-BP)模型的预测结果。从数据集划分、输入变量数量的角度出发,验证了LCSSA-BP模型的预测精度。采用遗传算法进行抗压强度寻优,确定高性能混凝土配合比的最佳掺量。研究表明:相较于其他模型,LCSSA-BP模型具有更高的预测精度、更低的预测误差;当按照9-1划分训练集和测试集时,模型决定系数R²为0.975,相关系数R为0.987;综合考虑变量的关联度和数据分布特性,选取水泥、高炉矿渣、水、粗骨料和细骨料作为输入变量时,模型R²为0.954,R为0.977;遗传算法在高性能混凝土早期7 d抗压强度寻优和配合比设计方面具有较高的可行性和实用性。

关键词: 高性能混凝土, 早期抗压强度, 极值寻优, 配合比, LCSSA-BP, 遗传算法, 麻雀搜索算法

Abstract: 7 d compressive strength of high performance concrete, as an important indicator of early strength, has a significant impact on the quality of construction projects that cannot be ignored. In order to achieve high performance concrete compressive strength prediction and extreme value optimization, this paper optimised the BP neural network based on the logistic chaos mapping improved sparrow search algorithm (LCSSA), and established the LCSSA-BP prediction model. 88 sets of data were selected as the training set and 38 sets of data as the test set to compare the prediction results of BP,support vector machine (SVM), extreme learning machine (ELM), artificial bee colony algorithm-BP (ABC-BP) and cuckoo search-BP (CS-BP) models. The prediction accuracy of the LCSSA-BP model was verified from the perspectives of data set division and the number of input variables. Genetic algorithm was used for compressive strength optimization to determine the optimum mix proportion for high performance concrete. The study shows that compared with other models, the LCSSA-BP model has higher prediction accuracy and lower prediction error; when the training set and test set are divided according to 9-1, the determination coefficient R² of model is 0.975 and correlation coefficient R is 0.987; considering the correlation degree of the variables and the characteristics of the data distribution, when cement, blast furnace slag, water, coarse aggregate and fine aggregate are selected as input variables, the R² is 0.954, R is 0.977; the genetic algorithm has high feasibility and practicability in the optimization of high-performance concrete early 7 d compressive strength and mix proportion design.

Key words: high performance concrete, early compressive strength, extreme value optimization, mix proportion, LCSSA-BP, genetic algorithm, sparrow search algorithm

中图分类号:

TU528

范明辉, 杨普新, 李薇, 任文渊, 马驰骋. 高性能混凝土的早期抗压强度预测和极值寻优[J]. 硅酸盐通报, 2024, 43(12): 4339-4349.

FAN Minghui, YANG Puxin, LI Wei, REN Wenyuan, MA Chicheng. Early Compressive Strength Prediction and Extreme Value Optimization for High Performance Concrete[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2024, 43(12): 4339-4349.

参考文献

[1] SWAMY R N. High performance and durability through design[J]. Special Publication, 1996, 159: 209-230.
[2] BHARATKUMAR B H, NARAYANAN R, RAGHUPRASAD B K, et al. Mix proportioning of high performance concrete[J]. Cement and Concrete Composites, 2001, 23(1): 71-80.
[3] DUSHIMIMANA A, NIYONSENGA A A, NZAMURAMBAHO F. A review on strength development of high performance concrete[J]. Construction and Building Materials, 2021, 307: 124865.
[4] 王海英, 李子彤, 张英治, 等. 基于拌和生产数据的BP神经网络混凝土抗压强度预测[J]. 建筑科学与工程学报, 2024, 41(3): 18-25.
WANG H Y, LI Z T, ZHANG Y Z, et al. BP neural network prediction of concrete compressive strength based on mixing production data[J]. Journal of Architecture and Civil Engineering, 2024, 41(3): 18-25 (in Chinese).
[5] 李地红, 高群, 夏娴, 等. 基于BP神经网络的混凝土综合性能预测[J]. 材料导报, 2019, 33(增刊2): 317-320.
LI D H, GAO Q, XIA X, et al. Prediction of comprehensive performance of concrete based on BP neural network[J]. Materials Reports, 2019, 33(supplement 2): 317-320 (in Chinese).
[6] 王鹏辉, 乔宏霞, 冯琼, 等. 基于PSO-BPNN模型的氯氧镁水泥混凝土耐水性预测[J]. 建筑材料学报, 2024, 27(3): 189-196.
WANG P H, QIAO H X, FENG Q, et al. Prediction of water resistance of magnesium oxychloride cement concrete based on PSO-BPNN model[J]. Journal of Building Materials, 2024, 27(3): 189-196 (in Chinese).
[7] 汪声瑞, 胡畔, 陈思宝, 等. 基于耦合BAS-MLP的混凝土抗压强度预测[J]. 建筑材料学报, 2023, 26(7): 705-715.
WANG S R, HU P, CHEN S B, et al. Prediction of concrete compressive strength based on coupled BAS-MLP[J]. Journal of Building Materials, 2023, 26(7): 705-715 (in Chinese).
[8] 黄炜, 周烺, 葛培, 等. 基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究[J]. 材料导报, 2021, 35(15): 15026-15030.
HUANG W, ZHOU L, GE P, et al. A comparative study on compressive strength model of recycled brick aggregate concrete based on PSO-BP and GA-BP neural networks[J]. Materials Reports, 2021, 35(15): 15026-15030 (in Chinese).
[9] 邹翔, 殷松峰, 程跃, 等. 基于ISSA-BP神经网络的激光甲烷传感器温度补偿研究[J]. 光子学报, 2023, 52(8): 0814003.
ZOU X, YIN S F, CHENG Y, et al. Temperature compensation study of laser methane sensor based on ISSA-BP neural network[J]. Acta Photonica Sinica, 2023, 52(8): 0814003 (in Chinese).
[10] 孟志军, 刘淮玉, 安晓飞, 等. 基于SPA-SSA-BP的小麦秸秆含水率检测模型[J]. 农业机械学报, 2022, 53(2): 231-238+245.
MENG Z J, LIU H Y, AN X F, et al. Prediction model of wheat straw moisture content based on SPA-SSA-BP[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(2): 231-238+245 (in Chinese).
[11] 张良, 何山, 艾纯玉. 基于Sine-SSA-BP神经网络模型的风机叶根载荷预测[J]. 可再生能源, 2023, 41(10): 1322-1328.
ZHANG L, HE S, AI C Y. The wind turbine leaf root load prediction based on Sine-SSA-BP neural network model[J]. Renewable Energy Resources, 2023, 41(10): 1322-1328 (in Chinese).
[12] YEH I C. Concrete compressive strength[CP]. UCI Machine Learning Repository, 2007.
[13] 刘廷滨, 黄滔, 欧嘉祥, 等. 基于ANN和XGB算法的锈蚀钢筋混凝土高温粘结强度预测方法[J]. 工程力学, 2024, 41(增刊1): 300-309.
LIU T B, HUANG T, OU J X, et al. Prediction method of bond strength of corroded reinforced concrete at high temperature based on ANN and XGB algorithm[J]. Engineering Mechanics, 2024, 41(supplement 1): 300-309 (in Chinese).
[14] 吕庆, 刘月明, 张振峰, 等. 基于承钢生产数据预测烧结矿FeO含量[J]. 钢铁研究学报, 2018, 30(12): 957-962.
LYU Q, LIU Y M, ZHANG Z F, et al. Prediction of FeO content in sinter based on production data of Chengde Steel Mill[J]. Journal of Iron and Steel Research, 2018, 30(12): 957-962 (in Chinese).
[15] MUKHERJEE A, NAG BISWAS S. Artificial neural networks in prediction of mechanical behavior of concrete at high temperature[J]. Nuclear Engineering and Design, 1997, 178(1): 1-11.
[16] BAI J, WILD S, WARE J A, et al. Using neural networks to predict workability of concrete incorporating metakaolin and fly ash[J]. Advances in Engineering Software, 2003, 34(11/12): 663-669.
[17] 王述红, 董福瑞. 基于变形预测和参数反演的山岭隧道围岩稳定性分析[J]. 岩土工程学报, 2023, 45(5): 1024-1035.
WANG S H, DONG F R. Stability analysis of surrounding rock of mountain tunnels based on deformation prediction and parameter inversion[J]. Chinese Journal of Geotechnical Engineering, 2023, 45(5): 1024-1035 (in Chinese).
[18] 吕鑫, 慕晓冬, 张钧, 等. 混沌麻雀搜索优化算法[J]. 北京航空航天大学学报, 2021, 47(8): 1712-1720.
LYU X, MU X D, ZHANG J, et al. Chaos sparrow search optimization algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47(8): 1712-1720 (in Chinese).
[19] WANG K W, REN J, YAN J W, et al. Research on a concrete compressive strength prediction method based on the random forest and LCSSA-improved BP neural network[J]. Journal of Building Engineering, 2023, 76: 107150.
[20] 周新茂, 郑焮元, 于正鑫, 等. 基于相似日理论和LCSSA-BP的短期光伏发电功率预测[J]. 电网与清洁能源, 2022, 38(11): 88-97.
ZHOU X M, ZHENG X Y, YU Z X, et al. Short-term photovoltaic power prediction based on similarity day theory and LCSSA-BP[J]. Advances of Power System & Hydroelectric Engineering, 2022, 38(11): 88-97 (in Chinese).
[21] 胡明伟, 何国庆, 吴雯琳, 等. 基于改进Logistic-SSA-BP神经网络的地铁短时客流预测研究[J]. 重庆交通大学学报(自然科学版), 2023, 42(3): 90-97.
HU M W, HE G Q, WU W L, et al. Subway short-term passenger flow forecast based on improved logistic-SSA-BP neural network[J]. Journal of Chongqing Jiaotong University (Natural Science), 2023, 42(3): 90-97 (in Chinese).
[22] 陈庆, 马瑞, 蒋正武, 等. 基于GA-BP神经网络的UHPC抗压强度预测与配合比设计[J]. 建筑材料学报, 2020, 23(1): 176-183, 191.
CHEN Q, MA R, JIANG Z W, et al. Compressive strength prediction and mix proportion design of UHPC based on GA-BP neural network[J]. Journal of Building Materials, 2020, 23(1): 176-183, 191 (in Chinese).
[23] 韩建军, 赵道松, 李建平. 基于BP神经网络的垃圾飞灰混凝土抗压强度预测模型[J]. 混凝土, 2022(9): 78-81.
HAN J J, ZHAO D S, LI J P. Prediction model of compressive strength of garbage fly ash concrete based on BP neural network[J]. Concrete, 2022(9): 78-81 (in Chinese).
[24] 包子阳, 余继周, 杨杉. 智能优化算法及其MATLAB实例[M]. 北京: 电子工业出版社, 2021.
BAO Z Y, YU J Z, YANG S. Smart optimization algorithms and their MATLAB examples[M]. Beijing: Publishing House of Electronics Industry, 2021 (in Chinese).
[25] 董建军, 谢洪阳, 戴宜文, 等. 基于GA-BP算法的高炉矿渣-粉煤灰混凝土抗压强度预测[J]. 统计学与应用, 2022, 11(1): 27-37.
DONG J J, XIE H Y, DAI Y W, et al. Compressive strength prediction of blast furnace slag-fly ash concrete based on GA-BP algorithm[J]. Statistics and Application, 2022, 11(1): 27-37 (in Chinese).
[26] 朱燕丽, 马川义, 张吉哲, 等. 沥青胶浆-集料界面水盐侵蚀损伤与多因素影响规律研究[J/OL]. 材料导报, 1-21 (2024-04-17)[2024-06-05]. http://kns.cnki.net/kcms/detail/50.1078.TB.20240415.1544.029.html.
ZHU Y L, MA C Y, ZHANG J Z, et al. Experimental investigation of moisture-salt erosion and multiple factors influence on asphalt mortar-aggregate interface[J/OL]. Materials Reports, 1-21 (2024-04-17)[2024-06-05]. http://kns.cnki.net/kcms/detail/50.1078.TB.20240415.1544.029.html (in Chinese).
[27] 段妹玲, 张单, 袁锦虎, 等. 基于ISSA-GRU的混凝土抗压强度预测[J]. 硅酸盐通报, 2023, 42(7): 2392-2400.
DUAN M L, ZHANG D, YUAN J H, et al. Prediction of compressive strength of concrete based on ISSA-GRU[J]. Bulletin of the Chinese Ceramic Society, 2023, 42(7): 2392-2400 (in Chinese).
[28] 陈谦, 王朝辉, 傅豪, 等. 路用水性环氧树脂的拉伸强度预测和极值寻优[J]. 材料导报, 2021, 35(16): 16172-16177.
CHEN Q, WANG Z H, FU H, et al. Prediction and extreme value optimisation of tensile strength of waterborne epoxy resin for road[J]. Materials Guide, 2021, 35(16): 16172-16177 (in Chinese).