基于RBF神经网络的热轧碳钢变形抗力预测

以凸轮式高速形变试验机得到的实验数据为基础,利用Matlab人工神经网络工具箱,建立了碳钢的变形抗力与其化学成分、变形温度、变形程度及变形速度对应关系的RBF神经网络预测模型.通过对函数newrb()中宽度系数的调整,确定了最佳的网络结构形式,提高了模型的预测精度以及网络的泛化能力.结果表明,与传统的BP网络模型相比较,RBF网络模型具有更高的精度和较强的泛化能力.

Prediction of Metal Flow Stress Based on RBF Neural Network

On the basis of the data obtained from Cam Plastometer,an RBF neural network prediction model is established by Matlab neural network toolbox,which corresponds with the relationship between flow stress and chemistry elements,temperature,deformation strain and strain rate of carbon steel.By selecting suitable spread in function newrb(),the best form of the network is affirmed.As a result,the prediction accuracy and the adaptability of the network are increased.And compared with traditional BP network,the results indicate that RBF network has better accuracy and adaptability.