论文部分内容阅读
针对中厚板轧机控制模型中的轧制温度精度的提高问题,以4200轧机轧制的大量实测数据为基础,利用Matlab人工神经网络工具箱,建立了中厚板轧制温度的GRNN神经网络预测模型。通过分析影响钢板温度变化的各种因素,调整神经网络的光滑因子,确定了最佳的网络结构形式,提高了模型的预测精度,并与传统的BP神经网络模型相比较。结果表明,GRNN网络具有更高的精度和更好的泛化能力。该神经网络模型可应用于中厚板轧制温度的预测,也可为人工神经网络在其它自动控制方面的应用提供参考。
Aimed at the problem of raising the rolling temperature accuracy in the control model of plate mill, based on a large number of measured data of 4200 rolling mill, a neural network toolbox of Matlab was used to predict the GRNN neural network of plate rolling temperature model. By analyzing various factors that affect the temperature change of the steel plate, the smoothing factor of the neural network is adjusted, the optimal network structure is determined, the prediction accuracy of the model is improved, and compared with the traditional BP neural network model. The results show that GRNN network has higher accuracy and better generalization ability. The neural network model can be applied to the prediction of plate rolling temperature, but also can provide reference for the application of artificial neural network in other automatic control.