苏州混凝土水泥制品研究院有限公司

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
基于机器学习算法的混凝土28 d抗压强度预测
The Prediction of 28 d Compressive Strength of Concrete Based on Machine Learning Algorithms
2022年第9期
混凝土;28 d抗压强度;机器学习;强度预测
Concrete; 28 d compressive strength; Machine learning; Strength prediction
2022年第9期
10.19761/j.1000-4637.2022.09.020.05
刘德胜
安徽省交通控股集团有限公司,安徽 合肥 230000

刘德胜

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.

LIU D S.The Prediction of 28 d Compressive Strength of Concrete Based on Machine Learning Algorithms[J].China Concrete and Cement Products,2022(9):20-24.

浏览量:
1000
摘   要:为较准确预测混凝土28 d的抗压强度,以水泥、粉煤灰、砂、碎石和水5种原材料的单位用量作为输入,混凝土28 d抗压强度作为输出,构建了一个拥有249组样本的数据库。运用决策树、支持向量机、高斯过程回归、集成学习、神经网络5种机器学习算法进行超参数优化,构建了混凝土28 d抗压强度预测模型,并对其精度进行了评估。对比5种机器学习算法结果可知:高斯过程回归模型是预测混凝土28 d抗压强度的最优预测模型;基于构建的高斯过程回归模型对无岳高速WYTJ-07标段隧道工程自制的5种花岗岩混凝土28 d抗压强度进行了预测,预测值的最大相对误差为8.95%,证明该模型预测精度良好,可靠性高。 Abstract: In order to accurately predict the 28 d compressive strength of concrete, a database with 249 groups of samples was constructed with the unit dosage of cement, fly ash, sand, gravel and water as the input and the 28 d compressive strength of concrete as the output. 5 machine learning algorithms, namely decision tree, support vector machine, Gaussian process regression, ensemble learning and neural network were used to optimize the parameters. The prediction models of 28 d compressive strength of concrete were constructed and their accuracies were evaluated. Comparing the results of the 5 machine learning algorithms show that the Gaussian process regression model is the optimal model for predicting 28 d compressive strength of concrete. Based on the constructed Gaussian process regression model, the 28 d compressive strength of five kinds of granite concrete prepared by the project department of WYTJ-07 section of Wuyue Expressway tunnel project is predicted. The maximum relative error between the predicted and actual values is 8.95 %, proving that the constructed model has good prediction accuracy and high reliability.
英文名 : The Prediction of 28 d Compressive Strength of Concrete Based on Machine Learning Algorithms
刊期 : 2022年第9期
关键词 : 混凝土;28 d抗压强度;机器学习;强度预测
Key words : Concrete; 28 d compressive strength; Machine learning; Strength prediction
刊期 : 2022年第9期
DOI : 10.19761/j.1000-4637.2022.09.020.05
文章编号 :
基金项目 :
作者 : 刘德胜
单位 : 安徽省交通控股集团有限公司,安徽 合肥 230000

刘德胜

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.

LIU D S.The Prediction of 28 d Compressive Strength of Concrete Based on Machine Learning Algorithms[J].China Concrete and Cement Products,2022(9):20-24.

摘要
参数
结论
参考文献
引用本文

摘   要:为较准确预测混凝土28 d的抗压强度,以水泥、粉煤灰、砂、碎石和水5种原材料的单位用量作为输入,混凝土28 d抗压强度作为输出,构建了一个拥有249组样本的数据库。运用决策树、支持向量机、高斯过程回归、集成学习、神经网络5种机器学习算法进行超参数优化,构建了混凝土28 d抗压强度预测模型,并对其精度进行了评估。对比5种机器学习算法结果可知:高斯过程回归模型是预测混凝土28 d抗压强度的最优预测模型;基于构建的高斯过程回归模型对无岳高速WYTJ-07标段隧道工程自制的5种花岗岩混凝土28 d抗压强度进行了预测,预测值的最大相对误差为8.95%,证明该模型预测精度良好,可靠性高。

Abstract: In order to accurately predict the 28 d compressive strength of concrete, a database with 249 groups of samples was constructed with the unit dosage of cement, fly ash, sand, gravel and water as the input and the 28 d compressive strength of concrete as the output. 5 machine learning algorithms, namely decision tree, support vector machine, Gaussian process regression, ensemble learning and neural network were used to optimize the parameters. The prediction models of 28 d compressive strength of concrete were constructed and their accuracies were evaluated. Comparing the results of the 5 machine learning algorithms show that the Gaussian process regression model is the optimal model for predicting 28 d compressive strength of concrete. Based on the constructed Gaussian process regression model, the 28 d compressive strength of five kinds of granite concrete prepared by the project department of WYTJ-07 section of Wuyue Expressway tunnel project is predicted. The maximum relative error between the predicted and actual values is 8.95 %, proving that the constructed model has good prediction accuracy and high reliability.

扫二维码用手机看
未找到相应参数组,请于后台属性模板中添加

(1)通过5种机器学习模型预测了混凝土28 d抗压强度,高斯过程回归模型是预测混凝土28 d抗压强度的最优预测模型。
(2)基于所构建的高斯过程回归模型对无岳高速WYTJ-07标段隧道工程自制花岗岩混凝土28 d抗压强度进行预测,预测精度良好,可靠性高。

[1] 梁炯丰,严兰兰,胡鹏,等.BP神经网络在再生混凝土强度预测中的应用[J].混凝土,2017(6):9-12,16.
[2] SABAPATHY Y K,SABARISH S,NITHISH C N A,et al.Experimental Study on Strength Properties of Aluminium Fibre Reinforced Concrete[J].Journal of King Saud University-Engineering Sciences,2021,33(1):23-29.
[3] MILJAN K,SILVA L,KARLO N E,et al. Application of Artificial Intelligence Methods for Predicting the Compressive Strength of Self-compacting Concrete with Class F Fly Ash[J]. Materials,2022,15(12):4191-4191.
[4] 孙庆巍,高磊,赵华民.大掺量粉煤灰混凝土强度的LS-SVM预测[J].辽宁工程技术大学学报(自然科学版),2013,32(7):930-933.
[5] 云振军,姚占全,何梁,等.纳米SiO2粉煤灰混凝土抗压强度影响及灰熵分析[J].排灌机械工程学报,2022,40(5):467-474.
[6] RASMUSSEN C E,WILLIAMS C K I.Gaussian Processes for Machine Learning [M].Cambridge(MA): The MIT Press,2006.
[7] PORYA G,MASOUD K,ALIREZA Z N,et al. Application of Gaussian Process Regression to Forecast Multi-step Ahead SPEI Drought Index[J].Alexandria Engineering Journal,2021,60(6):5375-5392.
[8] CORTES C,VAPNIK V.Support-vector Networks.[J].Machine Learning,1995,20(3):273-297.
[9] CHAPELLE O,HAFFNER P,VAPNIK V.Support Vector Machines for Histogram-based Image Classification.[J].IEEE Trans.Neural Networks,1999,10(5):1055-1064.
[10] GAO Z,FANG S C,LUO J,et al.A Kernel-Free Double Well Potential Support Vector Machine with Applications[J].European Journal of Operational Research,2020,290(1):248-262.
[11] DING S F,ZHANG N,ZHANG X K,et al.Twin Support Vector Machine: Theory, Algorithm and Applications[J].Neural Computing and Applications,2017,28(11):3119-3130.
[12] 邓文其.机制砂自密实混凝土配合比设计及性能研究[D].重庆:重庆交通大学,2021.
[13] 马成功.泵送普通混凝土配合比优化研究[D].银川:宁夏大学,2014.
[14] 曹玉新.盾构管片钢纤维混凝土配合比的设计优化[J].工业建筑,2020,50(8):101-104,159.
[15] 杨黎明,孙玉杰,李凤霞.吉林省双河三级水电站工程混凝土配合比设计优化研究[J].吉林农业科技学院学报,2021,30(1):23-28.
[16] 方鹏程.高石粉机制砂自密实混凝土配合比优化及性能研究[D].重庆:重庆交通大学,2019.
[17] 邓重阳,王利,吴利静.机制砂自密实片石混凝土配合比设计及工程应用[J].现代盐化工,2020,47(4):43-44.
[18] 张戈,安明喆,王月,等.隧道湿喷高性能喷射混凝土配合比试验研究[J].混凝土与水泥制品,2021(12):12-15,28.
[19] 孙和平.矿粉和粉煤灰双掺用于配制混凝土的价值分析[J].中国设备工程,2022(5):252-253.
[20] 吕元师.矿粉和粉煤灰双掺用于配制混凝土的价值[J].福建建材,2019(5):10-11,84.
[21] 田帅,李翔,李世华.粉煤灰及含气量对混凝土抗冻性能影响的试验研究[J].山西建筑,2022,48(8):103-105,108.
[22] 温小非,吴庆,王波,等.粉煤灰替代细骨料的混凝土性能研究[J].混凝土与水泥制品,2016(9):19-23.
[23]李永庆.机制砂透水混凝土的制备及试验研究[D].西安建筑科技大学,2019.
[24] 高环宇.大掺量粉煤灰混凝土配合比设计及抗冻性能的研究[D].呼和浩特:内蒙古农业大学,2009.
[25] 艾红梅.大掺量粉煤灰混凝土配合比设计与性能研究[D].大连:大连理工大学,2005.
[26] 周林.高性能混凝土不同配合比下的性能研究[J].西部交通科技,2021(9):53-55,80.

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.

LIU D S.The Prediction of 28 d Compressive Strength of Concrete Based on Machine Learning Algorithms[J].China Concrete and Cement Products,2022(9):20-24.

相关文件

暂时没有内容信息显示
请先在网站后台添加数据记录。

关注《混凝土与水泥制品》

总访问量 468,401   网站统计

官方微信公众号关闭
苏州混凝土水泥制品研究院有限公司

关于我们    |    联系我们    |    订购杂志    |    回到顶部

版权所有:中国混凝土与水泥制品网  苏ICP备10086386号   网站建设:中企动力 苏州

版权所有:中国混凝土与水泥制品网

苏ICP备10086386号

网站建设:中企动力 苏州