基于机器学习的混凝土抗压强度预测发展现状  

Development Status of Compressive Strength Prediction of Concrete Based on Machine learning

作　　者：何新初[1] 王建强 赵春涛 He Xinchu;Wang Jianqiang;Zhao Chuntao

机构地区：[1]水利部产品质量标准研究所 [2]杭州江河机电装备工程有限公司

出　　处：《工程机械》2024年第5期209-215,I0021,共8页Construction Machinery and Equipment

摘　　要：目前我国大部分工程建设都会用到混凝土建筑材料,混凝土的抗压强度对工程质量有着直接影响,因此混凝土抗压强度的试验工作一直受到重视,国内外学者也在混凝土抗压强度预测方面做了大量研究。为深入了解这方面的发展,对基于机器学习的混凝土抗压强度预测方法进行综述,通过常用的BP神经网络、支持向量机、随机森林3个模型介绍该领域的发展现状。At present,most of the engineering construction in China uses concrete building materials,and the compressive strength of concrete has a direct impact on the engineering quality.Therefore,the testing of compressive strength of concrete has always been valued,and scholars at home and abroad have done a lot of research on the compressive strength prediction of concrete.To gain a deep understanding of the development in this field,the methods for predicting compressive strength of concrete based on machine learning are reviewed,and the development status of this field is introduced through three commonly used models,the BP neural network,support vector machine and random forest.

关 键 词：抗压强度预测 BP神经网络 支持向量机 随机森林 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TU528[自动化与计算机技术—控制科学与工程]