基于BP神经网络的再生保温混凝土抗压强度预测  

Prediction of compressive strength of regenerated thermal insulation concrete based on BP neural network

作　　者：郭耀东[1] 刘元珍[1] 王文婧[1] 秦小超 GUO Yaodong;LIU Yuanzhen;WANG Wenjing;QIN Xiaochao(College of Civil Engineering,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原理工大学建筑与土木工程学院,山西太原030024

出　　处：《混凝土》2018年第10期33-35,39,共4页Concrete

基　　金：国家自然科学基金(51508370;51678384)

摘　　要：通过研究再生粗骨料取代率、水灰比对再生保温混凝土抗压强度的影响,建立了以再生粗骨料取代率、水灰比以及混凝土表观密度为因子的BP神经网络预测模型,旨在通过这三种因子的测量对再生保温混凝土28 d抗压强度进行预测。试验研究表明,当再生粗骨料取代率为50%时,再生保温混凝土抗压强度与混凝土拌合物表观密度近似成线性关系,抗压强度随着水灰比的增大而降低;当取代率为100%时,抗压强度与表观密度为非线性关系,抗压强度随表观密度的增大而增大,随水灰比的增加而增加。建立的三因子BP神经网络模型的预测值与实际值的误差在3%以内,可用于再生保温混凝土的抗压强度预测。BP neural network prediction model was established by studying the effect of recycled coarse aggregate substitution rate and water cement ratio on the compressive strength of regenerated concrete.The BP neural network prediction model was established based on the ratio of recycled coarse aggregate,water cement ratio and concrete apparent density.The aim of this study is to predict the 28-day compressive strength of regenerated thermal insulation concrete by the measurement of these three factors.The experimental results show that when the ratio of recycled coarse aggregate is 50%,the compressive strength of regenerated concrete is approximately linear with the apparent density of concrete mixture,and the compressive strength decreases with the increase of water-cement ratio.When the substitution rate is 100%,the compressive strength is nonlinear with the apparent density,and the compressive strength increases with the increase of apparent density,and increases with the increase of water-cement ratio.The three-factor BP neural network model established in this paper is less than 3%of the predicted value and the actual value,and can be used to predict the compressive strength of regenerated thermal insulation concrete.

关 键 词：再生粗骨料取代率 水灰比 表观密度 抗压强度 BP神经网络 

分 类 号：TU528.01[建筑科学—建筑技术科学]