结合数学模型的模糊聚类BP网络预报板凸度  

Prediction of plate crown by BP neural network on fuzzy clustering integrating with mathematics model

作　　者：张延华[1] 刘相华[1] 王国栋[1] 

机构地区：[1]东北大学轧制技术及连轧自动化国家重点实验室

出　　处：《轧钢》2005年第3期8-11,共4页Steel Rolling

基　　金：国家重点基础研究发展规划项目(G2000067208-4)

摘　　要：分析了中厚板板凸度计算模型并给出了相应的在线数学模型。为了提高板凸度在线模型预测精度,提出了一种基于模糊聚类BP神经网络的板凸度模型影响系数的优化方法。并采用模糊聚类分析方法,科学选取学习样本,解决了由于样本多学习速度慢的问题。通过对大量在线数据分析得出,这种方法对中厚板板凸度的预报精度有很大改善,能适应不断变化的工艺过程和设备条件。This paper analyzes a simple plate crown model and gives an on-line model relevant to it. A new method is proposed to optimize plate crown model basis on BP neural networks to improve the control accuracy of crown predicted. The fuzzy cluster analysis was used as the preprocessing to select the sample set, which can solve the problem of study speed. It is shown that the prediction precision of BP neural networks can be improved greatly according to many on-line data and the optimization model can be adapted to varied techniques and equipment.

关 键 词：中厚板 凸度 BP神经网络 聚类 

分 类 号：TG335.52[金属学及工艺—金属压力加工]