粉煤灰混凝土氯离子扩散系数的ANFIS预测模型比较研究  

Comparative Research on Chloride Ion Diffusion Coefficient ANFIS Prediction Models for Fly Ash Concrete

作　　者：黄露[1] 綦春明[1] 左江波[1] 

机构地区：[1]南华大学城市建设学院,湖南衡阳421001

出　　处：《粉煤灰》2012年第6期1-3,共3页Coal Ash China

摘　　要：采用网格法和减法聚类法划分网络,分别建立了基于ANFIS(Adaptive Neuron-Fuzzy Inference System)的两种粉煤灰混凝土氯离子扩散系数预测模型,并用NEL法试验中的数据作为样本来训练和测试两种模型,比较其预测精度。结果表明,采用减法聚类法建立的ANFIS模型预测精度更高,更能满足工程应用的要求。Grid method and subtractive clustering method are used to divide the network of ANFIS（Adaptive Neuron-Fuzzy Inference System）.Two kinds of chloride ion diffusion coefficient prediction models for fly ash concrete are respectively established.The data obtained from NEL test method are used as samples to train and test two models,and to compare their prediction accuracy.The results show that ANFIS model gets higher prediction accuracy by using subtractive clustering method and can be better to meet the requirements of engineering applications.

关 键 词：氯离子扩散系数 网格法 减法聚类法 粉煤灰混凝土 

分 类 号：TU528.2[建筑科学—建筑技术科学]