摘要
以4200轧机大规模测试得到的实验数据为基础,利用Matlab人工神经网络工具箱,建立了该轧机的应力状态系数模型.通过对该网络隐层神经元个数的调整,提高了收敛速度,使应力状态系数的预测精度大为提高.
Based on the data obtained from large scale experiments on 4200 rolling mill,the prediction model of this mill is established using Matlab neural network toolbox.The number of hidden-layer neurons in the network is adjusted to increase the convergence speed and then to improve the prediction accuracy of the stress state modulus.
出处
《郑州大学学报（理学版）》
CAS
2007年第3期127-130,共4页
Journal of Zhengzhou University:Natural Science Edition
关键词
BP神经网络
应力状态系数
预测
BP neural network
stress state modulus
prediction
