摘要
抗压强度是高强混凝土的一项重要力学性能,但测试方法通常不经济且耗时。为此,基于324组样本,提出了一种长短期记忆网络模型来预测高强混凝土抗压强度,以5种成分的掺量作为输入特征,并将模型预测结果与传统支持向量回归模型进行了比较。结果表明,与支持向量回归模型的预测性能相比,长短期记忆网络模型的预测精度和可靠性更高,预测偏差较小,推荐用于实验室压缩试验前高强混凝土抗压强度的预估,以减少试验时间和成本。另外,参数的重要性分析也可以为混凝土配合比的设计提供更高效的方法。
Compressive strength is an important mechanical property of high strength concrete,but testing methods are often uneconomical and time-consuming.Based on 324 samples,a long and short term memory(LSTM)network model was proposed to predict the compressive strength of high-strength concrete.The content of five components is taken as the input feature,and the prediction results of the model were compared with the traditional support vector regression model.The results show that compared with the prediction performance of the support vector regression model,the prediction accuracy and reliability of the LSTM model are higher,and the prediction deviation is small.It is recommended to be used for the prediction of the compressive strength of high strength concrete before the laboratory compression test,so as to reduce the test time and cost.In addition,the importance analysis of parameters can also provide a more efficient method for the design of concrete mix ratio.
作者
陆孟杰
陈磊
李彪
邱人大
江山
LU Mengjie;CHEN Lei;LI Biao;QIU Renda;JIANG Shan(China Construction Fifth Engineering Division Co.,Ltd.,Hefei 230092,China)
出处
《建筑结构》
北大核心
2023年第S02期1371-1375,共5页
Building Structure
基金
中国建筑股份有限公司科技研发课题(CSCEC-2021-Z-30)。
关键词
高强度混凝土
LSTM
抗压强度
参数贡献度
high strength concrete
LSTM
compressive strength
parameter contribution
