运用神经网络技术实现材料性能参数的实时识别是智能化拉深的重要研究课题。
The real-time identification via neural network is an important subject in intellectual deep drawing of sheet metal.
提出了一种神经网络参数的初始化方法——向量单位化方法。
The paper puts out a worthy popularized method of Parameter Initialization for neural network-vector unitization method.
轧机自动化以神经网络模型为基础进行道次表、弯辊和窜辊设定点、以及平直度动态控制参数的计算。
Mill automation is based on models with neural networks for pass schedule calculation and computation of set points for roll shifting and bending, and parameters for dynamic flatness control.
应用推荐