首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络的中厚板凸度预报
引用本文:王冬菊,姚晓兰.基于神经网络的中厚板凸度预报[J].有色金属,2007,59(2):41-42,49.
作者姓名:王冬菊  姚晓兰
作者单位:1. 安徽师范大学,电子系,安徽芜湖,241000
2. 北京理工大学,信息科学技术学院,北京,100081
摘    要:应用改进BP神经网络建立中厚板凸度预报的三层神经网络预报模型,用自适应学习速率法和附加动量法两种改进BP算法结合起来训练神经网络模型。试验仿真结果表明,该模型对测试数据预报结果均在3%之内,精度高,训练速度较快,具有很好的实用性。

关 键 词:金属材料  中厚板凸度预报  BP改进算法  神经网络
文章编号:1001-0211(2007)02-0041-03
收稿时间:2005-12-29
修稿时间:2005-12-29

Crown Prediction of Media and Heavy Plate Based on Neural Network
WANG Dong-ju,YAO Xiao-lan.Crown Prediction of Media and Heavy Plate Based on Neural Network[J].Nonferrous Metals,2007,59(2):41-42,49.
Authors:WANG Dong-ju  YAO Xiao-lan
Affiliation:1. Electronic Department, Anhui Normal University, Wuhu 241000 ,Anhui, China ; 2. School of Information Science and Technology, Beijing Institute of Technology, Beijing 100081, China
Abstract:A three-layered neural network predictive model for crown prediction of media and heavy plate is established by improved neural network. The model is trained with BP algorithm modified with adaptive learn-rate algorithm and additional momentum algorithm. It is indicated by the simulation results that the predictive model is of good utility with high precision and train-speed, the error of the predictive results for the test data is all within 3%.
Keywords:metal material  crown prediction of media and heavy plate  improved BP method  neural network
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号