摘要
为了探究机制砂混凝土的抗压强度变化规律,进行了不同机制砂替代率(0、30%、50%、70%)、粉煤灰掺量(0、20%、30%、40%)和机制砂石粉含量(0、5.8%、11.6%)混凝土试件的抗压强度试验,并结合试验数据建立了BP神经网络模型预测抗压强度。结果表明:随着机制砂替代率的增加,试件的7 d、28 d抗压强度呈先增大后减小的趋势,且在机制砂替代率为50%时达到最大,机制砂替代率对试件的60 d抗压强度影响较小;掺入粉煤灰使试件的早期抗压强度降低,但30%掺量的粉煤灰有利于提高试件的60 d抗压强度;随着机制砂石粉含量的增加,试件的7 d抗压强度先增大后减小,28 d、60 d抗压强度则逐渐增大;建立的机制砂混凝土28 d抗压强度预测模型的精度较高。
In order to explore the change law of the compressive strength of manufactured sand concrete,the compressive strength tests of concrete specimens with different manufactured sand replacement rates(0,30%,50%,70%),fly ash contents(0,20%,30%,40%)and stone powder contents(0,5.8%,11.6%)in manufactured sand were carried out.Combined with the test datas,the BP neural network model was established to predict the compressive strength.The results show that the 7 d and 28 d compressive strength of the specimen increase first and then decrease with the increase of manufactured sand replacement rate,and reaches the maximum when the manufactured sand replacement rate is 50%.The manufactured sand replacement rate has little effect on the 60 d compressive strength of the specimen.Adding fly ash reduces the early compressive strength of the specimen,but 30%fly ash is beneficial to improve the 60 d compressive strength of the specimen.With the increase of stone powder content in manufactured sand,the 7 d compressive strength of the specimen first increases and then decreases,and the 28 d and 60 d compressive strength increase gradually.The established model for predicting the 28 d compressive strength of manufactured sand concrete has high accuracy.
作者
陶松涛
延永东
郑玉龙
刘甲琪
梁晓封
王鑫
TAO Song-tao;YAN Yong-dong;ZHENG Yu-long;LIU Jia-qi;LIANG Xiao-feng;WANG Xin(Faculty of Civil Engineering and Mechanics,Jiangsu University,Zhenjiang 212013,China;Shaoxing Traffic Construction Co.,Ltd.,Shaoxing 312099,China)
出处
《混凝土与水泥制品》
2022年第8期96-100,104,共6页
China Concrete and Cement Products
基金
国家自然科学基金项目(51878319、51608233)
江苏大学高级人才基金资助项目(20JDG19)
江苏省博士后科研资助计划项目(2020Z350)。
关键词
机制砂混凝土
抗压强度
石粉
粉煤灰
BP神经网络模型
Manufactured sand concrete
Compressive strength
Stone powder
Fly ash
BP neural network model
