基于机器学习预测超高性能混凝土的抗压强度

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



基于机器学习预测超高性能混凝土的抗压强度

Prediction of compressive strength of ultra-high performance concrete based on machine learning

2025年第3期

机器学习；超高性能混凝土；抗压强度；钢纤维；预测

Machine learning; Ultra-high performance concrete; Compressive strength; Steel fiber; Prediction

2025年第3期

10.19761/j.1000-4637.2025.03.001.07

国家自然科学基金项目（51708349）；浙江省自然科学基金项目（LY20E080017）；温州市科协服务科技创新项目（kjfw53）。

欧阳利军1，石永超1，丁斌2，*，谢冰清1

1.上海理工大学环境与建筑学院，上海 200093； 2.温州职业技术学院建筑工程学院，浙江温州 325035

欧阳利军1，石永超1，丁斌2，*，谢冰清1

欧阳利军,石永超,丁斌,等.基于机器学习预测超高性能混凝土的抗压强度[J].混凝土与水泥制品,2025(3):1-7.

OUYANG L J,SHI Y C,DING B,et al.Prediction of compressive strength of ultra-high performance concrete based on machine learning[J].China Concrete and Cement Products,2025(3):1-7.

浏览量:

1000

摘要：收集了国内外已发表文献的168组试验数据并建立数据库，以15个影响因素为输入变量，抗压强度为输出变量，建立了决策树（DT）、随机森林（RF）、极端梯度提升树（XGBoost）三种机器学习模型对UHPC的抗压强度进行预测，并采用SHAP算法对模型进行了解释。结果表明：三种模型的预测误差百分比均在15%以内，模型预测收敛性较高，预测值和试验值相近，均具有较好的精度，其中，XGBoost模型的预测精度最高；在所选15个影响因素中，钢纤维掺量对UHPC抗压强度的影响最大；基于机器学习预测UHPC抗压强度具有一定的准确性和可靠性。 Abstract: A comprehensive database was constructed by collecting 168 sets of experimental data from both domestic and international literature. Using 15 influencing factors as input variables and compressive strength as output variable, three machine learning models of decision tree(DT), random forest(RF), and extreme gradient boosting tree(XGBoost) were developed to predict the compressive strength of UHPC. The SHAP framework was employed to interpret the three models. The results show that the prediction error percentages for all three models are within 15%, demonctrating high convergence and accuracy. The predicted values are similar to the experimental values and have good accuracy. Among them, the XGBoost model has the highest prediction accuracy. Among the 15 selected influencing factors, the steel fiber content has the most impact on the compressive strength of UHPC. It is confirmed that machine learning-based predictions of UHPC compressive strength possess a certain level of accuracy and reliability.

英文名 : Prediction of compressive strength of ultra-high performance concrete based on machine learning

刊期 : 2025年第3期

关键词 : 机器学习；超高性能混凝土；抗压强度；钢纤维；预测

Key words : Machine learning; Ultra-high performance concrete; Compressive strength; Steel fiber; Prediction

刊期 : 2025年第3期

DOI : 10.19761/j.1000-4637.2025.03.001.07

文章编号 :

基金项目 : 国家自然科学基金项目（51708349）；浙江省自然科学基金项目（LY20E080017）；温州市科协服务科技创新项目（kjfw53）。

作者 : 欧阳利军1，石永超1，丁斌2，*，谢冰清1

单位 : 1.上海理工大学环境与建筑学院，上海 200093； 2.温州职业技术学院建筑工程学院，浙江温州 325035

欧阳利军1，石永超1，丁斌2，*，谢冰清1

欧阳利军,石永超,丁斌,等.基于机器学习预测超高性能混凝土的抗压强度[J].混凝土与水泥制品,2025(3):1-7.

OUYANG L J,SHI Y C,DING B,et al.Prediction of compressive strength of ultra-high performance concrete based on machine learning[J].China Concrete and Cement Products,2025(3):1-7.





摘要

参数

结论

参考文献

引用本文

Abstract: A comprehensive database was constructed by collecting 168 sets of experimental data from both domestic and international literature. Using 15 influencing factors as input variables and compressive strength as output variable, three machine learning models of decision tree(DT), random forest(RF), and extreme gradient boosting tree(XGBoost) were developed to predict the compressive strength of UHPC. The SHAP framework was employed to interpret the three models. The results show that the prediction error percentages for all three models are within 15%, demonctrating high convergence and accuracy. The predicted values are similar to the experimental values and have good accuracy. Among them, the XGBoost model has the highest prediction accuracy. Among the 15 selected influencing factors, the steel fiber content has the most impact on the compressive strength of UHPC. It is confirmed that machine learning-based predictions of UHPC compressive strength possess a certain level of accuracy and reliability.

扫二维码用手机看

[1] MASSICOTTE B,DAGENAIS M A,LAGIER F.Performance of UHPFRC jackets for the seismic strengthening of bridge piers[J].Materials and Structures,2013,145:1-11.
[2] YOO D Y,BANTHIA N.Mechanical properties of ultra-high-performance fiber-reinforced concrete: A review[J].Cement and Concrete Composites,2016,73:267-280.
[3] ABELLANGARCíA J,NUNEZ-LOPEZ A,TORRES-CASTELLANOS N,et al.Effect of FC3R on the properties of ultra-high-performance concrete with recycled glass[J].Dyna,2019,86:84-93.
[4] ALDAHDOOH M,BUNNORI N M,JOHARI M M.Evaluation of ultra-high-performance-fiber reinforced concrete binder content using the response surface method[J].Materials and Design,2013,52:957-965.
[5] YU R,SPIESZ P,BROUWERS H.Effect of nano-silica on the hydration and microstructure development of ultra-high performance concrete (UHPC) with a low binder amount[J].Construction and Building Materials,2014,65:140-150.
[6] SALEHI H,BURGUENO R.Emerging artificial intelligence methods in structural engineering[J].Engineering Structures,2018,171:170-189.
[7] EL-ASRI Y,AICHA M B,ZAHER M,et al.Prediction of compressive strength of self-compacting concrete using four machine learning technics[J].Materials Today:Proceedings,2022,57:859-866.
[8] 刘德胜.基于机器学习算法的混凝土28 d抗压强度预测[J].混凝土与水泥制品,2022(9):20-24.
[9] 马高,刘康.基于BP神经网络CFRP约束混凝土抗压强度预测[J].湖南大学学报(自然科学版)中文版,2021,48(9):88-97.
[10] GUCLUER K,OZBEYAZ A,GOYMEN S,et al.A comparative investigation using machine learning methods for concrete compressive strength estimation[J].Materials Today Communications,2021,27:102278.
[11] SOLHMIRZAEI R,SALEHI H,KODUR V.Predicting flexural capacity of ultra-high-performance concrete beams: machine learning-based approach[J].Journal of Structural Engineering,2022,148(5):022031.
[12] KOU S C,XING F.The effect of recycled glass powder and reject fly ash on the mechanical properties of fibre-reinforced ultra high performance concrete[J].Advances in Materials Science and Engineering,2012,2012:263243.
[13] 高绪明.钢纤维对超高性能混凝土性能影响的研究[D].长沙:湖南大学,2013.
[14] AHMAD S,HAKEEM I,MASLEHUDDIN M.Development of UHPC mixtures utilizing natural and industrial waste materials as partial replacements of silica fume and sand[J].The Scientific World Journal,2014,2014:713531.
[15] YU R,SPIESZ P,BROUWERS H.Mix design and properties assessment of ultra-high performance fibre reinforced concrete (UHPFRC)[J].Cement and Concrete Research,2014,56:29-39.
[16] YU R,SPIESZ P,BROUWERS H.Development of an eco-friendly ultra-high performance concrete(UHPC) with efficient cement and mineral admixtures uses[J].Cement and Concrete Composites,2015,55:383-394.
[17] YU R,SPIESZ P,BROUWERS H.Development of ultra-high performance fibre reinforced concrete(UHPFRC): Towards an efficient utilization of binders and fibres[J].Construction and Building Materials,2015,79:273-282.
[18] 何稳.钢纤维在超高性能混凝土中增强增韧作用的研究[D].长沙:湖南大学,2015.

[19] WU Z M,SHI C J,HE W,et al.Effects of steel fiber content and shape on mechanical properties of ultra high performance concrete[J].Construction and building materials,2016,103:8-14.
[20] PYO S，KIM H K.Fresh and hardened properties of ultra-high performance concrete incorporating coal bottom ash and slag powder[J].Construction and Building Materials,2017,131:459-466.
[21] WU Z M,KHAYAT K,HENRI K,et al.Effect of nano-SiO2 particles and curing time on development of fiber-matrix bond properties and microstructure of ultra-high strength concrete[J].Cement and Concrete Research,2017,95:247-256.
[22] WU Z M,SHI C J,HE W.Comparative study on flexural properties of ultra-high performance concrete with supplementary cementitious materials under different curing regimes[J].Construction and Building Materials,2017,136:307-313.
[23] ZHANG J,ZHAO Y,LI H.Experimental investigation and prediction of compressive strength of ultra-high performance concrete containing supplementary cementitious materials[J].Advances in Materials Science and Engineering,2017,12:4563164.
[24] 吴峥.钢纤维对超高性能混凝土裂后性能的影响[D].长沙:湖南大学,2017.
[25] CHEN T,GAO X,REN M.Effects of autoclave curing and fly ash on mechanical properties of ultra-high performance concrete[J].Construction and Building Materials,2018,158:864-872.
[26] MENG W,KHAYAT K H.Effect of hybrid fibers on fresh properties, mechanical properties, and autogenous shrinkage of cost-effective UHPC[J].Journal of Materials in Civil Engineering,2018,30(4):018030.
[27] 欧阳利军,钱鹏,高皖扬,等.养护制度对超高性能混凝土高温损伤后残余力学性能的影响[J].工业建筑,2020,50(8):92-100.
[28] TRAN V Q,DANG V Q,HO L S.Evaluating compressive strength of concrete made with recycled concrete aggregates using machine learning approach[J].Construction and Building Materials,2022,323:126578.
[29] SAFAVIAN S R,LANDGREBE D.A survey of decision tree classifier methodology[J].IEEE Transactions on Systems Man and Cybernetics,1991,21(3):660-674.
[30] FAWAGREH K,GABER M M,ELYAN E.Random forests:from early developments to recent advancements[J].Systems Science and Control Engineering: An Open Access Journal,2014,2(1):602-609.
[31] RAMRAJ S,UZIR N,SUNIL R,et al.Experimenting XGBoost algorithm for prediction and classification of different datasets[J].International Journal of Control Theory and Applications,2016,9(40):651-662.
[32] LUNDBERG S M,LEE S I.A unified approach to interpreting model predictions[J].Advances in Neural Information Processing Systems,2017,30:4768-4777.
[33] LUNDBERG S M,ERION G,CHEN H,et al.From local explanations to global understanding with explainable AI for trees[J].Nature machine intelligence,2020,2(1):56-67.
[34] LARSEN I L,THORSTENSEN R T.The influence of steel fibres on compressive and tensile strength of ultra high performance concrete: A review[J].Construction and Building Materials,2020,256:119459.
[35] YANG J,CHEN B,NUTI C.Influence of steel fiber on compressive properties of ultra-high performance fiber-reinforced concrete[J].Construction and Building Materials,2021,302:124104.
[36] 李新星,李水生.粉煤灰和石英粉对超高性能混凝土性能的影响[J].混凝土与水泥制品,2023(12):11-16.
[37] SOLIMAN N A,TAGNIT-HAMOU A.Using particle packing and statistical approach to optimize eco-efficient ultra-high-performance concrete[J].ACI Materials Journal,2018,115(5):795-798.
[38] AHMED T,ELCHALAKANI M,KARRECH A,et al.Development of ECO-UHPC with very-low-C3A cement and ground granulated blast-furnace slag[J].Construction and Building Materials,2021,284:122787.
[39] NATH P,SARKER P.Effect of fly ash on the durability properties of high strength concrete[J].Procedia Engineering,2011,14:1149-1156.
[40] JING R,LIU Y,YAN P Y.Uncovering the effect of fly ash cenospheres on the macroscopic properties and microstructure of ultra-high performance concrete[J].Construction and Building Materials,2021,286:122977.

上一个

先张法预应力混凝土竹节管桩抗剪性能试验研究

下一个

硫铝酸盐水泥砂浆的水下不分散性能研究

头部文案

基于机器学习预测超高性能混凝土的抗压强度

相关文件