基于BP神经网络的绿色混凝土抗压强度预测模型

英文篇名：Prediction model of green concrete compressive strength based on BP neural network
中文刊名：混凝土
英文刊名：Concrete
作者：徐国强 ; 苏幼坡 ; 韩佃利 ; 张静
英文作者：XU Guo-qiang 1 ; 2 ; SU You-po 1 ; 2 ; HAN Dian-li 1 ; 2 ; ZHANG Jing 1 ; 2(1.College of Civil and Architecture Engineering ; Hebei United University ; Tangshan ; 063009 China ; 2.Earthquake Engineering Research Center of Hebei ; Tangshan 063009 ; China)
中文关键词：BP神经网络 ; 绿色混凝土 ; 抗压强度 ; 预测模型
英文关键词：BP neural network ; green concrete ; compressive strength ; prediction model
出版日期：2013-02-27
机构：河北联合大学建筑工程学院;河北省地震工程研究中心;
年：2013
期：02
出版单位：混凝土

摘要

与普通混凝土相比,绿色混凝土具有成分复杂的特点,为了在多因素作用下更为准确地预测绿色混凝土的抗压强度,在分析三层BP神经网络原理的基础上,选择影响绿色混凝土抗压强度的7个指标,以66个抗压强度试验为示例,建立了三层BP神经网络抗压强度预测模型。验证样本的训练结果表明,该模型能够较准确地快速预测绿色混凝土的抗压强度,并通过对各指标的权重计算,确定了影响绿色混凝土抗压强度的主要因素。
Compared with ordinary concrete,green concrete was characterized by complicated composition.In order to more accurately predict the green concrete compressive strength under the influence of multiple factors,seven indexes that affect the compressive strength of green concrete were selected based on the analysis of three-layer BP neural network principle.With 66 compressive strength tests as an example,a prediction model of compressive strength on three-layer BP neural network was established.The training results of verification samples showed that the model could quickly and accurately predict the compressive strength of the green concrete.Through calculating the weight of various index,the main factors that affect green concrete compressive strength were determined.

引文

[1]吴中伟,廉慧珍.高性能混凝土[M].北京:铁道出版社,1999.
    [2]徐国强,刘娟红,乔兰,等.双掺石灰石粉和粉煤灰绿色高性能混凝土研究[J].武汉理工大学学报,2010,32(21):22-26.
    [3]李红,彭涛.基于BP、RBF神经网络混凝土抗压强度预测[J].武汉理工大学学报,2009,31(8):33-36
    [4]周双喜,赵碧华.人工神经网络在掺活化煤矸石粉混凝土强度预测中的应用[J].混凝土,2007(4):26-28.
    [5]王继宗,倪宏光.基于BP神经网络的水泥抗压强度预测研究[J].硅酸盐学报,1999,27(4):408-414.
    [6]李小雷,邓寅生,何小芳,等.应用人工神经网络预测高掺量粉煤灰混凝土的强度[J].混凝土,2008(5):20-22.
    [7]陈强,王新刚.人工神经网络在混凝土强度预测中的应用[J].工业建筑,2007,37(S1):1013-1016.
    [8]于山,王海霞,马亚杰.三层BP神经网络地震灾害人员伤亡预测模型[J].地震工程与工程振动,2005,25(6):113-117.