基于机器学习的UHPC抗压强度预测及配合比优化

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



基于机器学习的UHPC抗压强度预测及配合比优化

Prediction of compressive strength and optimization of mix proportion based on machine learning UHPC

2024年第7期

机器学习；试验设计；支持向量回归；粒子群优化；超高性能混凝土；紧密堆积模型

Machine learning; Design of experiment; Support vector regression; Particle swarm optimization; Ultra-high performance concrete(UHPC); Compact packing model

2024年第7期

10.19761/j.1000-4637.2024.07.007.07

国家重点研发计划项目（2018YFC0705405）。

康志坚，李火星

筑友智造智能科技有限公司，湖南长沙 410005

康志坚，李火星

康志坚,李火星.基于机器学习的UHPC抗压强度预测及配合比优化[J].混凝土与水泥制品,2024(7):7-13.

KANG Z J,LI H X.Prediction of compressive strength and optimization of mix proportion based on machine learning UHPC[J].China Concrete and Cement Products,2024(7):7-13.

浏览量:

1000

摘要：结合试验设计、机器学习及紧密堆积模型提出了一种超高性能混凝土（UHPC）抗压强度预测和配合比优化方法，并对比了预测结果与实测结果。此外，还将支持向量回归-粒子群优化算法（SVR-PSO）模型与其他常见抗压强度预测模型进行了对比，并基于SVR-PSO模型设计开发了图形用户界面预测软件。结果表明：SVR-PSO模型在稳定性和预测精度方面具有明显优势，抗压强度预测值和实测值误差在5%以内；采用所提出的UHPC配合比设计方法，可基于原材料数据快速生成满足抗压强度要求的UHPC配合比。 Abstract: A method for predicting the compressive strength and optimizing the mix proportion of ultra-high performance concrete (UHPC) was proposed by combining experimental design, machine learning technology, and compact packing model, and the predicted results were compared with the measured results. In addition, the support vector regression-particle swarm optimization algorithm(SVR-PSO) model was compared with other common compressive strength prediction models, and a graphical user interface prediction software was designed and developed based on the SVR-PSO model. The results show that the SVR-PSO model has significant advantages in stability and prediction accuracy, with an error of less than 5% between the predicted and measured compressive strength values. The proposed UHPC mix proportion design method can quickly generate UHPC mix proportions that meet the compressive strength requirements based on raw material datas.

英文名 : Prediction of compressive strength and optimization of mix proportion based on machine learning UHPC

刊期 : 2024年第7期

关键词 : 机器学习；试验设计；支持向量回归；粒子群优化；超高性能混凝土；紧密堆积模型

Key words : Machine learning; Design of experiment; Support vector regression; Particle swarm optimization; Ultra-high performance concrete(UHPC); Compact packing model

刊期 : 2024年第7期

DOI : 10.19761/j.1000-4637.2024.07.007.07

文章编号 :

基金项目 : 国家重点研发计划项目（2018YFC0705405）。

作者 : 康志坚，李火星

单位 : 筑友智造智能科技有限公司，湖南长沙 410005

康志坚，李火星

康志坚,李火星.基于机器学习的UHPC抗压强度预测及配合比优化[J].混凝土与水泥制品,2024(7):7-13.

KANG Z J,LI H X.Prediction of compressive strength and optimization of mix proportion based on machine learning UHPC[J].China Concrete and Cement Products,2024(7):7-13.





摘要

参数

结论

参考文献

引用本文

Abstract: A method for predicting the compressive strength and optimizing the mix proportion of ultra-high performance concrete (UHPC) was proposed by combining experimental design, machine learning technology, and compact packing model, and the predicted results were compared with the measured results. In addition, the support vector regression-particle swarm optimization algorithm(SVR-PSO) model was compared with other common compressive strength prediction models, and a graphical user interface prediction software was designed and developed based on the SVR-PSO model. The results show that the SVR-PSO model has significant advantages in stability and prediction accuracy, with an error of less than 5% between the predicted and measured compressive strength values. The proposed UHPC mix proportion design method can quickly generate UHPC mix proportions that meet the compressive strength requirements based on raw material datas.

扫二维码用手机看

[1] 黄政宇,许卓.碳纤维织物增强UHPFRC(PE)薄板抗弯性能试验研究[J].铁道科学与工程学报,2018,15(2):450-457.
[2] 邵旭东,莫然,曹君辉,等.钢-UHPC轻型组合桥面受模拟行车扰动后抗裂性能研究[J].湖南大学学报(自然科学版)中文版,2022,49(3):1-13.
[3] 曾丹,刘扬,曹磊.钢-UHPC组合结构新型剪力件的抗剪性能[J].浙江大学学报(工学版),2021,55(9):1714-1724,1771.
[4] 魏久淇,李磊,王世合,等.超高性能混凝土临空板接触爆炸破坏效应实验研究[J].爆炸与冲击,2022,42(4):28-35.
[5] GHAFARI E,BANDARABADI M,COSTA H,et al.Prediction of fresh and hardened state properties of UHPC: Comparative study of statistical mixture design and an artificial neural network model[J].Journal of Materials in Civil Engineering,2015(11):0001270.
[6] ZARANDI M H F,TURKSEN I B,SOBHANI J,et al.Fuzzy polynomial neural networks for approximation of the compressive strength of concrete[J].Applied Soft Computing,2008,8(1):488-498.
[7] 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.
[8] 张清华,程震宇,廖贵星,等.波形顶板-UHPC组合桥面板优化设计[J].西南交通大学学报,2018,53(4):670-678.
[9] ABELLAN J.FOLD K.Validation neural network approach for predicting the one-day compressive strength of UHPC[J].Advances in Civil Engineering Materials,2021,55:142736.
[10] AMINI P A,ZHANG S,HUANG D,et al.Application of artificial neural networks and multiple linear regression on local bond stress equation of UHPC and reinforcing steel bars[J].Scientific Reports,2021,11(1):15061.
[11] FAN D Q,RUI Y,LIU K N,et al.Optimized design of steel fibres reinforced ultra-high performance concrete(UHPC) composites: Towards to dense structure and efficient fibre application[J].Construction and Building Materials,2021,273:1-13.
[12] VAPNIK V N.Statistical Learning Theory[J].Ann Arbor, 1998,1001(48):9.
[13] 曹斐,周彧,王春晓,等.一种改进的支持向量回归的混凝土强度预测方法[J].硅酸盐通报,2021,40(1):90-97.
[14] KHAZAEUU A,GHALEHNOVI M.Bearing stiffness of UHPC; An experimental investigation and a comparative study of regression and SVR-ABC models[J].Journal of Advanced Concrete Technology,2018,16(3):145-158.
[15] CHAABENE W B,FLAB M,NEHDI M L.Machine learning prediction of mechanical properties of concrete: critical review[J].Construction and Building Materials,2020,260:1-18.
[16] JIANG C S,LIANG G Q.Modeling shear strength of medium to ultra-high strength concrete beams with stirrups using SVR and genetic algorithm[J].Soft Computing,2021,25(16):10661-10675.
[17] 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.
[18] YASEEN Z M,TRAN M T,KIM S,et al.Shear strength prediction of steel fiber reinforced concrete beam using hybridintelligence models: A new approach[J].Engineering Structures,2018,177:244-255.
[19] ABUODEH O,ABDALLA J A,HAWILEH R A.Prediction of compressive strength of ultra-high performance concrete using SFS and ANN[C]//Institute of Electrical and Electronic Engineers(IEEE).2019 8th International Conference on Modeling Simulation and Applied Optimization(ICMSAO).America:IEEE,2019:978-981.
[20] MARANA A,JAMALI A,NEHDI M L.Predicting ultra-high performance concrete compressive strength using tabular generative adversarial networks[J].Materials,2020,13(47):1-24.
[21] HAECKER B C J.An argument for using coarse cements in high-performance concretes[J].Cement and Concrete Research,1999,98:1-4.
[22] 黄伟,孙伟.石灰石粉掺量对超高性能混凝土水化演变的影响[J].东南大学学报(自然科学版),2017,47(4):751-759.
[23] FAN D,YU R,FU S,et al.Precise design and characteristics prediction of ultra-high performance concrete(UHPC) based on artificial intelligence techniques[J].Cement and Concrete Composites,2021,10:104171.
[24] 肖俊璋,肖俊光.回归饱和设计值得商榷的问题[J].植物营养与肥料学报,2011,17(5):1274-1277.
[25] KENNEDY J,EBERHART R.Particle swarm optimization[C]//Institute of Electrical and Electronic Engineers(IEEE).95th international Conference on Neural Networks.America:IEEE,1995:468-488.
[26] LI L G,KWAN A K H.Packing density of concrete mix under dry and wet conditions[J].Powder Technology,2014,253:514-521.
[27] 高云,杜春苗,李栋,等.水胶比对高强混凝土力学性能影响的实验研究[J].西安建筑科技大学学报(自然科学版),2020,52(5):653-659.
[28] 申艳军,张欢,潘佳,等.混凝土界面过渡区微-细观结构识别及形成机制研究进展[J].硅酸盐通报,2020,39(10):3055-3069.
[29] 杨玉柱,黄维蓉,耿嘉庆,等.基于半经验的UHPC配合比设计方法[J].材料导报,2021,35(增刊2):188-193.
[30] LARRARD D F.Concrete mixture proportioning: A scientific approach[M].London:CRC Press,1999.
[31] WOMG V,KWAN A K H.A 3-parameter model for packing density prediction of ternary mixes of spherical particles[J].Powder Technology,2014,268(1):357-367.
[32] 高国华,黄卫东,李传海.纳米SiO₂增强骨料裹浆对混凝土抗冻性能的改善[J].建筑材料学报,2021,24(1):45-53.

上一个

碳酸盐环境下隧道衬砌混凝土的腐蚀研究及防治措施

下一个

打印路径对3D打印混凝土构件力学性能的影响

头部文案

基于机器学习的UHPC抗压强度预测及配合比优化

相关文件