混凝土强度预测的混合神经网络模型  

The mix neutral network model for prediction of concrete strength

作　　者：丁声荣[1] 霍艳华[1] 姜新佩[2] 

机构地区：[1]南昌大学科学技术学院,江西南昌330029 [2]河北工程大学,河北邯郸056038

出　　处：《四川建筑科学研究》2010年第6期188-191,共4页Sichuan Building Science

基　　金：河北省建设厅建工新产品基金资助项目(2004-113)

摘　　要：针对由于混凝土配方的多样性,直接利用神经网络模型对其进行强度预测存在精度差和收敛差的缺点,采用多种神经网络模型相结合的方法,建立了混凝土强度预测的混合神经网络模型。模型的建立主要包括以下三个过程:(1)建立混凝土强度影响参数样本数据库;(2)利用自组织神经网络对样本数据分类;(3)以混凝土原材料和制作工艺为输入参数,混凝土最终性能为输出参数,训练双并联神经网络模型。通过实例验证了模型的可靠性。It has a low accuracy to forecast concrete strength utilizing neutral network prediction model directly,in order to overcome this shortcoming,the mix neutral network were built to forecast the concrete strength.The process of the system included three steps：first,established the database of the concrete strength influenced parameter;second,the sample data is grouped according to its distribution based on self-organizational neutral network model;third,in base of using raw material of concrete as model input parameter and the concrete strength as output parameter,the double parallel feed-forward neutral network model for prediction of concrete strength was established.The model was reliable,and the suitable software was programmed.

关 键 词：混凝土强度预测 自组织神经网络 双并联神经网路 

分 类 号：TU528[建筑科学—建筑技术科学]