一种带钢力学性能预测的神经网络方法

Mechanical properties forecasting of strip steel based on neural networks

采用神经网络进行建模,应用递推预报误差(RPE-recursive predict error)算法进行网络训练,实现了带钢力学性能预测,仿真结果表明算法的有效性,该方法可应用于轧钢流程的参数控制,提高生产的自动化水平。

The artificial neural networks with RPE algorithm was adopted in mechanical properties forecasting of strip steel,the simulation shows the method is effective and can applied into parameters control of rolling industrial with the automation enhanced.