基于BP神经网络的HPFL加固层与混凝土粘结强度预测  

Prediction of Bond Strength between HPFL Reinforced Layer and Concrete Based on BP Neural Networks

作　　者：黄华[1,2] 杨惠会 施明君[1] 刘伯权[1] 

机构地区：[1]长安大学建筑工程学院,西安710061 [2]长安大学公路学院,西安710064

出　　处：《硅酸盐通报》2014年第10期2565-2571,共7页Bulletin of the Chinese Ceramic Society

基　　金：国家自然科学基金(51308065);高等学校博士学科点专项科研基金项目优先发展计划(20130205130001);陕西省自然科学基础研究计划项目(2012JQ7024);中国博士后科学基金项目(2012M511956);中央高校基本科研业务费专项资金项目(2014G2280014)

摘　　要：根据HPFL加固层和加固混凝土构件之间的243个正拉粘结强度试验测试和24个剪切粘结强度试验测试,将影响二者粘结强度的主要因素,如抹灰龄期、加固界面粗糙度、混凝土和砂浆强度、修补方位等作为特征参数,建立了预测HPFL加固层与混凝土粘结强度的BP人工神经网络模型。采用训练好的BP神经网络对HPFL加固层与混凝土粘结强度进行了预测,并与实测值进行了对比。正拉粘结强度预测值与试验值之比的平均值为1.056,标准差为0.057;剪切粘结强度预测值与试验值之比的平均值为0.988,标准差为0.127。结果表明:预测值与试验值符合良好,利用BP神经网络对HPFL加固层与混凝土粘结强度进行预测是可行的。Based on the experiments about the tensile bond strength of 243 observation points and the shear bond strength of 24 observation points between HPFL reinforced layer and concrete, four influencing factors,such as curing age,interface roughness,the strength of concrete and mortar,position of the repaired interface were treated as characteristic parameters,and the BP neural network models were developed to predict the bond strength between HPFL reinforced layer and concrete. The bond strength values were predicted using the trained BP neural network and were compared with the measured values.The average ratio between the calculating values and test results of the tensile bond strength is 1. 056,and the standard error is 0. 057. The average ratio between the calculating values and test results of the shear bond strength is 0. 988,and the standard error is 0. 127. Results show that the calculating values are more secure,and using BP neural network to predict the bond strength between HPFL reinforced layer and concrete is feasible.

关 键 词：BP神经网络 HPFL加固层 正拉粘结强度 剪切粘结强度 

分 类 号：TQ178[化学工程—硅酸盐工业]