应用人工神经网络预测高掺量粉煤灰混凝土的强度  

Strength prediction of HFCC by the method of Artificial Neural Network

作　　者：李小雷[1] 邓寅生[1] 何小芳[1] 曹新鑫[1] 

机构地区：[1]河南理工大学材料科学与工程学院,河南焦作454000

出　　处：《混凝土》2008年第5期20-22,共3页Concrete

基　　金：河南省教育厅自然科学基金项目(135035)

摘　　要：基于人工神经网络原理,建立了反映高掺量粉煤灰混凝土配方与强度之间映射关系的多因素智能分析模型。利用可视化CC++6.0开发了粉煤灰混凝土的强度预测应用软件,解决了高掺量粉煤灰混凝土的模式特征不明确、各组分对混凝土性能影响非线性、随机因素多等问题。该方法进行高掺量粉煤灰混凝土的配制具有优化设计及快速、定量、预测精度高、适应性强、成本低等特点。Based on the method of Artificial Neural Network, a strength prediction model for HFCC was built upon the experimental data and a software system for predicting mechanical property of HFCC has been developed by visual C＋＋ 6.0.The problem of modular ambiguity in HFCC, the nonlinear influence of every composition on concrete performance, the multiple random factors were solved.The experiment results show the method mentioned is effective and feasible.It will avail to the massive application and utilization of HFCC because the model for the prediction of HFCC strength is handy for operating,high precision in prediction and strong adaptability.

关 键 词：人工神经网络 高掺量粉煤灰混凝土 BP算法 性能预测 

分 类 号：TU528.01[建筑科学—建筑技术科学]