基于多种机器学习模型的混凝土力学性能预测及对比研究

头部文案

发布时间：2020-01-06 00:00:00

全国建材科技期刊
全国中文核心期刊
中国科技论文统计源期刊
万方数据-数字化期刊群入网期刊
中国学术期刊（光盘版）全文收录期刊

华东地区优秀科技期刊
江苏省期刊方阵“双效期刊”
中国期刊网全文收录期刊
中国科技期刊数据库全文收录期刊



基于多种机器学习模型的混凝土力学性能预测及对比研究

Prediction and comparative study of concrete mechanical properties based on multiple machine learning models

2025年第1期

机器学习；混凝土；力学性能；预测；XGBoost模型；神经网络；支持向量机

Machine learning; Concrete; Mechanical property; Prediction; XGBoost model; Neural network; Support vector machine

2025年第1期

10.19761/j.1000-4637.2025.01.034.07

上海市社会发展科技攻关项目（20dz1202103）。

杨光，杨利香

上海市建筑科学研究院有限公司，上海 200032

杨光，杨利香

杨光,杨利香.基于多种机器学习模型的混凝土力学性能预测及对比研究[J].混凝土与水泥制品,2025(1):34-40.

YANG G,YANG L X.Prediction and comparative study of concrete mechanical properties based on multiple machine learning models[J].China Concrete and Cement Products,2025(1):34-40.

浏览量:

1000

摘要：选择了BP神经网络模型、支持向量机、XGBoost模型这3种机器学习模型构建了混凝土原材料用量与28 d抗压强度之间的预测模型，比较了各模型的拟合度、泛化能力和预测误差。结果表明：XGBoost模型在拟合度和泛化能力方面表现较为优秀，是构建混凝土原材料用量与28 d抗压强度之间预测关系的最佳模型。 Abstract: Three machine learning algorithms, namely BP neural network model, support vector machine, and XGBoost model were selected to construct a prediction model between the amount of concrete raw materials and the 28 d compressive strength. The fitting degree, generalization ability, and prediction error of each model were compared. The results show that the XGBoost model performs well in terms of fitting and generalization ability, and it is the best model for predicting the relationship between the amount of concrete raw materials and the 28 d compressive strength.

英文名 : Prediction and comparative study of concrete mechanical properties based on multiple machine learning models

刊期 : 2025年第1期

关键词 : 机器学习；混凝土；力学性能；预测；XGBoost模型；神经网络；支持向量机

Key words : Machine learning; Concrete; Mechanical property; Prediction; XGBoost model; Neural network; Support vector machine

刊期 : 2025年第1期

DOI : 10.19761/j.1000-4637.2025.01.034.07

文章编号 :

基金项目 : 上海市社会发展科技攻关项目（20dz1202103）。

作者 : 杨光，杨利香

单位 : 上海市建筑科学研究院有限公司，上海 200032

杨光，杨利香

杨光,杨利香.基于多种机器学习模型的混凝土力学性能预测及对比研究[J].混凝土与水泥制品,2025(1):34-40.

YANG G,YANG L X.Prediction and comparative study of concrete mechanical properties based on multiple machine learning models[J].China Concrete and Cement Products,2025(1):34-40.





摘要

参数

结论

参考文献

引用本文

Abstract: Three machine learning algorithms, namely BP neural network model, support vector machine, and XGBoost model were selected to construct a prediction model between the amount of concrete raw materials and the 28 d compressive strength. The fitting degree, generalization ability, and prediction error of each model were compared. The results show that the XGBoost model performs well in terms of fitting and generalization ability, and it is the best model for predicting the relationship between the amount of concrete raw materials and the 28 d compressive strength.

扫二维码用手机看

[1] 赵日宏.某工程大体积混凝土施工质量与安全保证措施研究[J].建筑安全,2019,34(10):28-30.
[2] ZHANG X,AKBER M Z,ZHENG W.Prediction of seven-day compressive strength of field concrete[J].Construction and Building Materials,2021,305:124604.
[3] 宋颖彤,胡骏,胡家兵,等.采用成熟度理论预测海工混凝土抗压强度[J].新型建筑材料,2017,44(9):15-18.
[4] ZEYAD A M,TAYEH B A,ADESINA A,et al.Review on effect of steam curing on behavior of concrete[J].Cleaner Materials,2022,3:100042.
[5] MILLER D,HO N M,TALEBIAN N.Monitoring of in-place strength in concrete structures using maturity method—An overview[J].Structures,2022,44:1081-1104.
[6] 刘盼.超声脉冲测速法无损检测水工混凝土质量分析应用[J].黑龙江水利科技,2022,50(12):167-169.
[7] 吕春梅.新拌混凝土质量现场检测技术的应用研究[J].福建建材,2016(4):13-15.
[8] 胡定宇.基于机器学习和优化算法的混凝土性能预测及配合比设计[D].重庆:重庆交通大学,2022.
[9] 陈子祎,刘文白.基于智能算法的河港码头混凝土碳化深度预测[J].混凝土,2022(7):178-182.
[10] AKPINAR P,KHASHMAN A.Intelligent classification system for concrete compressive strength[J].Procedia Computer Science,2017,120:712-718.
[11] OMRAN B A,CHEN Q,JIN R.Comparison of data mining techniques for predicting compressive strength of environmentally friendly concrete[J].Journal of Computing in Civil Engineering,2016,30(6):04016029.
[12] NADERPOUR H,RAFIEAN A H,FAKHARIAN P.Compressive strength prediction of environmentally friendly concrete using artificial neural networks[J].Journal of Building Engineering,2018,16:213-219.
[13] 杨雅勋,张伟德,于海波,等.基于改进支持向量机的超声参数与受载混凝土应力状态研究[J].振动与冲击,2023,42(2):175-181,224.
[14] JUNCAI X,QINGWEN R,ZHENZHONG S.Prediction of the strength of concrete radiation shielding based on LS-SVM[J].Annals of Nuclear Energy,2015,85:296-300.
[15] CHOU J S,CHIU C K,FARFOURA M,et al.Optimizing the prediction accuracy of concrete compressive strength based on a comparison of data-mining techniques[J].Journal of Computing in Civil Engineering,2011,25(3):242-253.
[16] 张研,王鹏鹏,吴哲康.基于相关向量机模型的混凝土综合性能预测[J].硅酸盐通报,2022,41(1):118-125,152.
[17] 陈卫卫,王卫星,张仁瑞,等.基于机器学习XGBoost、引导滤波及矩的自由落体岩石块度在线检测[J].兰州大学学报(自然科学版),2021,57(5):701-710.
[18] 刘尚昂.基于XGBoost算法的建筑工程造价预测研究[D].北京:北京建筑大学,2022.
[19] 佟大威,杨传会,余佳,等.基于XGBoost-PSO的混凝土重力坝体型多目标优化设计[J].河海大学学报(自然科学版),2023,51(3):91-98.
[20] 徐秀华.海水环境灌注桩高性能混凝土配合比设计及应用[J].混凝土与水泥制品,2016(9):15-18.
[21] 周思屹.大掺量粉煤灰对砂浆和混凝土性能影响的试验研究[D].郑州:华北水利水电大学,2020.
[22] 王俊杰.粉煤灰和矿渣粉在云南省高速公路工程混凝土中的应用研究[D].西安:西安建筑科技大学,2019.
[23] 石玉光,白雪燕.复合掺合料对混凝土基本性能的影响研究[J].混凝土与水泥制品,2022(11):84-88.
[24] 廖灵青.大掺量矿物掺合料混凝土抗氯盐侵蚀性能研究[D].南宁:广西大学,2016.
[25] 叶宇巡,马成畅,黄达.废胎橡胶用量对保温砂浆导热系数的影响与神经网络预测[J].新型建筑材料,2014,41(5):92-95,100.
[26] MOHAMED O,KEWALRAMANI M,ATI M,et al.Application of ANN for prediction of chloride penetration resistance and concrete compressive strength[J].Materialia,2021,17:101123.
[27] SONEBI M,CEVIK A,GRUNEWALD S,et al.Modelling the fresh properties of self-compacting concrete using support vector machine approach[J].Construction and Building Materials,2016,106:55-64.
[28] 郭磊,高航,田青青,等.基于XGBoost-LSTM的CSG抗压强度预测[J].建筑材料学报,2023,26(6):631-637.
[29] NGUYEN N H,ABELLAN-GARCIA J,LEE S,et al.Efficient estimating compressive strength of ultra-high performance concrete using XGBoost model[J].Journal of Building Engineering,2022,52:104302.
[30] YAN H,HE Z,GAO C,et al.Investment estimation of prefabricated concrete buildings based on XGBoost machine learning algorithm[J].Advanced Engineering Informatics,2022,54:101789.

上一个

高耐久补偿收缩混凝土试验研究及工程应用

下一个

无

头部文案

基于多种机器学习模型的混凝土力学性能 预测及对比研究

相关文件

基于多种机器学习模型的混凝土力学性能预测及对比研究