论文部分内容阅读
利用人工神经网络方法建立了挤压力系统模型,运用梯度下降法对BP神经网络进行训练,得到了15钢挤压时的挤压力与凹模锥角、凸模直径、断面缩减率的非线性映射关系。从而可预测在一定条件下挤压力的变化情况。结果表明:运用这种模型对挤压力进行预测是可行的。
The artificial neural network method was used to establish the squeezing force model and the gradient neural network was used to train the BP neural network. The squeezing force, die cone angle, punch diameter and reduction ratio of section Linear mapping. Which can predict the pressure changes under certain conditions. The results show that it is feasible to predict the squeezing pressure by this model.