神经网络在无机保温砂浆收缩预测中的应用

英文篇名：Application of Neural Networks on Shrinkage Prediction of Inorganic Thermal Insulation Mortar
中文刊名：武汉理工大学学报
英文刊名：Journal of Wuhan University of Technology
作者：邓义群 ; 王培铭
英文作者：DENG Yi-qun ; WANG Pei-ming(Key Laboratory of Advanced Civil Engineering Materials of Education Ministry ; Tongji University ; Shanghai 200092 ; China)
中文关键词：径向基概率神经网络 ; 多项式回归模型 ; 保温砂浆 ; 收缩
英文关键词：radial basis probabilistic neural networks ; polynomial regression model ; thermal insulation mortar ; shrinkage
出版日期：2010-08-15
机构：同济大学先进土木工程材料教育部重点实验室;
年：2010
期：15
出版单位：武汉理工大学学报

摘要

以水灰比、相对湿度、水泥、粉煤灰以及玻化微珠含量为输入变量,基于径向基概率神经网络对无机保温砂浆的收缩进行预测。与多项式回归模型相比,RBPNN模型的预测精度、平衡性以及泛化性都显著优于前者。此外,通过反演的方法该模型还可以用于无机保温砂浆配比的优化。
In this work,shrinkage of inorganic thermal insulation mortar were predicted by RBPNN with five input variables covering water-cement ratio,relative humidity,content of cement,fly ash and aggregate.The simulation results showed that the RBPNN model exhibited promising precision,equilibrium and generalization ability for predicting shrinkage of mortar compared with polynomial regression model.Furthermore,the RBPNN model was employed for optimizing mixtures of mortar with satisfactory shrinkage by means of refutations.

引文

[1]曾国海,周玉生,杨林.无机保温砂浆技术研究与开发[J].建筑节能,2009(8):34-36.
    [2]黄新.无机保温砂浆在外墙保温中的应用[J].山西建筑,2010(10):232-233.
    [3]Huang De-shuang,Ma Song-de.A New Radial Basis Probabilistic Neural Network Model[C]//3rd International Conference onSignal Processing.Beijing:[s.n.],1996:1449-1452.
    [4]Guo Lin,Huang De-shuang.Human Face Recognition Based on Radial Basis Probabilistic Neural Network[C]//Proceedings ofthe International Joint Conference on Neural Networks.Portland:[s.n.],2003:2208-2211.
    [5]陈晓利,赵健,叶洪.应用径向基概率神经网络研究地震滑坡[J].地震地质,2006,28(3):430-440.
    [6]黄德双.神经网络模式识别系统理论[M].北京:电子工业出版社,1996.
    [7]李洪升.K-Medoids算法在人脸识别系统中的应用[J].现代计算机:专业版,2009(4):59-62.
    [8]Akthem Al-Manaseer,Lam Jian-Ping.Statistical Evaluation of Shrinkage and Creep Models[J].ACI Materials Journal,2005,102(3):170-176.