The Prediction of Rolling Force Forming Shafts with Multi-wedge Cross Wedge Rolling Based on Neural Network

摘要：

The rolling force of multi-wedge rolling force is forecasted by the combination of finite element simulation and neural network prediction in order to overcome the shortage of finite element method predicting the rolling force of multi-wedge cross wedge rolling. The average error is 4.95％ in the prediction of rolling force between neural network and the finite element simulation. The results show that the accuracy and speed of forecasting rolling force system can meet the requirements of the online prediction.

关键词： multi-wedge cross wedge rolling rolling finite element simulation neural network forecasting system

作者: LU Liqun

作者单位: School of Transportation and vehicle Engineering, ShanDong University of Technology, Zibo, 255049,China

会议类型: 国际会议

会议名称: The Third International Conference on Modelling and Simulation(第三届国际建模、计算、仿真、优化及其应用学术会议 ICMS 2010)

会议地点: 无锡

会议语种:英文

页码: 232-235

在线出版日期: 2010-06-04（万方平台首次上网日期，不代表论文的发表时间）