基于机器学习的超高性能混凝土性能预测_《混凝土与水泥制品》杂志社

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



基于机器学习的超高性能混凝土性能预测

Performance prediction of ultra-high performance concrete based on machine learning

2024年第11期

超高性能混凝土（UHPC）；人工神经网络（ANN）；遗传算法（GA）；性能预测；抗压强度；流动度

Ultra-high performance concrete(UHPC); Artificial neural network(ANN); Genetic algorithm(GA); Performance prediction; Compressive strength; Fluidity

2024年第11期

10.19761/j.1000-4637.2024.11.049.06

桥梁智能与绿色建造全国重点实验室开放基金项目（BHSKL21-08-KF）；中国中铁股份有限公司科技研究开发计划课题项目（2022-专项-02）；中国中铁股份有限公司科技研究开发计划课题项目（2021-专项-02）；中铁大桥局集团有限公司科学技术研究与开发课题项目（2022-25-重点）。

鄢亦斌1，2，刘开志1，2，*，高立强1，2，龙勇1，2，李晨2，费顺鑫3

1.桥梁智能与绿色建造全国重点实验室，湖北武汉 430034；2.中铁大桥科学研究院有限公司，湖北武汉 430034；3.安徽工业大学材料科学与工程学院，安徽马鞍山 243002

鄢亦斌1，2，刘开志1，2，*，高立强1，2，龙勇1，2，李晨2，费顺鑫3

鄢亦斌,刘开志,高立强,等.基于机器学习的超高性能混凝土性能预测[J].混凝土与水泥制品,2024(11):49-53,59.

YAN Y B,LIU K Z,GAO L Q,et al.Performance prediction of ultra-high performance concrete based on machine learning[J].China Concrete and Cement Products,2024(11):49-53,59.

浏览量:

1000

摘要：基于改进的Andreasen-Andersen（MAA）颗粒堆积模型设计了93组UHPC配合比，根据93组样本的抗压强度与流动度建立了数据库，采用线性回归模型、二次项回归模型、人工神经网络（ANN）模型预测了UHPC的流动度和28 d抗压强度，并使用遗传算法（GA）对ANN模型进行优化得到了GA-ANN模型，最后对比了四种模型的预测精度和稳定性。结果表明：四种模型对UHPC流动度和28 d抗压强度预测精度的高低顺序为GA-ANN模型＞ANN模型＞二次项回归模型＞线性回归模型，其中，GA-ANN模型的R2分别达到了0.979和0.982。 Abstract：Based on the modified Andreasen-Andersen(MAA) particle accumulation model, 93 groups of UHPC proportions were designed, and a database was established based on the compressive strength and fluidity of the 93 groups of samples. Then the linear regression model, quadratic term regression model, and artificial neural network(ANN) model were used to predict the fluidity and the 28 d compressive strength of UHPC. And the genetic algorithm(GA) was used to optimize the ANN model to obtain the GA-ANN model. Finally, the prediction accuracy and stability of the four models were compared. The results show that, the order of accuracy of the four models in predicting the fluidity and 28 d compressive strength of UHPC is as follows: GA-ANN model ＞ ANN model ＞ quadratic term regression model ＞ linear regression model, in which the R2 of the GA-ANN model reaches 0.979 and 0.982, respectively.

英文名 : Performance prediction of ultra-high performance concrete based on machine learning

刊期 : 2024年第11期

关键词 : 超高性能混凝土（UHPC）；人工神经网络（ANN）；遗传算法（GA）；性能预测；抗压强度；流动度

Key words : Ultra-high performance concrete(UHPC); Artificial neural network(ANN); Genetic algorithm(GA); Performance prediction; Compressive strength; Fluidity

刊期 : 2024年第11期

DOI : 10.19761/j.1000-4637.2024.11.049.06

文章编号 :

基金项目 : 桥梁智能与绿色建造全国重点实验室开放基金项目（BHSKL21-08-KF）；中国中铁股份有限公司科技研究开发计划课题项目（2022-专项-02）；中国中铁股份有限公司科技研究开发计划课题项目（2021-专项-02）；中铁大桥局集团有限公司科学技术研究与开发课题项目（2022-25-重点）。

作者 : 鄢亦斌1，2，刘开志1，2，*，高立强1，2，龙勇1，2，李晨2，费顺鑫3

单位 : 1.桥梁智能与绿色建造全国重点实验室，湖北武汉 430034；2.中铁大桥科学研究院有限公司，湖北武汉 430034；3.安徽工业大学材料科学与工程学院，安徽马鞍山 243002

鄢亦斌1，2，刘开志1，2，*，高立强1，2，龙勇1，2，李晨2，费顺鑫3

鄢亦斌,刘开志,高立强,等.基于机器学习的超高性能混凝土性能预测[J].混凝土与水泥制品,2024(11):49-53,59.

YAN Y B,LIU K Z,GAO L Q,et al.Performance prediction of ultra-high performance concrete based on machine learning[J].China Concrete and Cement Products,2024(11):49-53,59.





摘要

参数

结论

参考文献

引用本文

Abstract：Based on the modified Andreasen-Andersen(MAA) particle accumulation model, 93 groups of UHPC proportions were designed, and a database was established based on the compressive strength and fluidity of the 93 groups of samples. Then the linear regression model, quadratic term regression model, and artificial neural network(ANN) model were used to predict the fluidity and the 28 d compressive strength of UHPC. And the genetic algorithm(GA) was used to optimize the ANN model to obtain the GA-ANN model. Finally, the prediction accuracy and stability of the four models were compared. The results show that, the order of accuracy of the four models in predicting the fluidity and 28 d compressive strength of UHPC is as follows: GA-ANN model ＞ ANN model ＞ quadratic term regression model ＞ linear regression model, in which the R2 of the GA-ANN model reaches 0.979 and 0.982, respectively.

扫二维码用手机看

[1] 陈宝春,季韬,黄卿维,等.超高性能混凝土研究综述[J].建筑科学与工程学报,2014,31(3):1-24.
[2] 黄政宇,阳东翱.超高性能混凝土基体的组成与微结构关系研究[J].硅酸盐通报,2017,36(12):4104-4111.
[3] 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.
[4] YIN T,LIU K,FAN D,et al.Derivation and verification of multilevel particle packing model for ultra-high performance concrete(UHPC):Modelling and experiments[J].Cement and Concrete Composites,2023,136:104889.
[5] 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,2021,122:104171.
[6] JOAQUIN A G,JAIME F G,KHAN M I,et al.ANN approach to evaluate the effects of supplementary cementitious materials on the compressive strength of recycled aggregate concrete[J].Construction and Building Materials,2023,402:132992.

[7] KHADEEJA R S,RIJADH A A.Structural assessment of basalt FRP reinforced self-compacting geopolymer concrete using artificial neural network(ANN) modelling[J].Construction and Building Materials,2023,397:132464.
[8] 苏青松.绿色高性能混凝土的试验研究及其预测的神经网络方法[D].西安:西北工业大学,2005.
[9] 尚莉.基于人工神经网络技术的机制砂自密实混凝土配合比设计研究[D].深圳:深圳大学,2020.
[10] AKKUURT S,OZDEMIR S,TAYFUR G,et al.The use of GA-ANNs in the modelling of compressive strength of cement mortar[J].Cement and Concrete Research,2003,33(7):973-979.
[11] WANG J N,YU R,JI D D,et al.Effect of distribution modulus(q) on the properties and microstructure development of a sustainable ultra-high performance concrete(UHPC)[J].Cement and Concrete Composites,2022,125:104335.
[12] YU R,SPIESZ P,BROUWERS H J H.Mix design and properties assessment of ultra-high performance fibre reinforced concrete(UHPFRC)[J].Cement and Concrete Research,2014,56:29-39.
[13] YU R,LIU K N,YIN T Y,et al.Comparative study on the effect of steel and polyoxymethylene fibers on the characteristics of ultra-high performance concrete(UHPC)[J].Cement and Concrete Composites,2022,127:104418.
[14] SHI C J,WU Z M,XIAO J F,et al.A review on ultra high performance concrete:Part Ⅰ.Raw materials and mixture design[J].Construction and Building Materials,2015,101:741-751.
[15] ZHOU M,WU Z,OUYANG X,et al.Mixture design methods for ultra-high-performance concrete—A review[J].Cement and Concrete Composites,2021,124:104242.
[16] NITHURSHAN M,ELAKNESWARAN Y.A systematic review and assessment of concrete strength prediction models[J].Case Studies in Construction Materials,2023,18:e1830.
[17] SARYAZDI S M E,ETEMAD A,SHAFAAT A,et al.Data-driven performance analysis of a residential building applying artificial neural network(ANN) and multi-objective genetic algorithm(GA)[J].Building and Environment,2022,225:109633.
[18] DAS R,KARTHIKA S,BHASARKAR J,et al.GA-coupled ANN model for predicting porosity in alginate gel scaffolds[J].Journal of the Mechanical Behavior of Biomedical Materials,2023,148:106204.
[19] ZHENG J,LIU C,HUANG S,et al.A novel adaptive dynamic GA combined with AM to optimize ANN for multi-output prediction: Small samples enhanced in industrial processing[J].Information Sciences,2023,644:119285.

上一个

纤维素醚对石膏基自流平砂浆性能的影响研究

下一个

环境温度对超高韧性地聚合物复合材料抗冲击性能的影响

头部文案

基于机器学习的超高性能混凝土性能预测

相关文件