基于BP神经网络的机器人砂带磨削表面粗糙度研究
2018-09-21
作者：田凤杰，吕冲
单位：沈阳理工大学
摘要：为提高机器人砂带磨削工件表面粗糙度的预测精度，采用基于BP神经网络方法进行研究，进行机器人砂带磨削铝合金板材试验，基于试验结果采用BP神经网络建立各工艺参数与工件表面粗糙度之间的预测模型。对该模型进行仿真预测，并通过试验验证该模型的预测精度。结果表明该模型预测精度高，可以预测不同工艺参数磨削后的工件表面粗糙度，实现了机器人砂带磨削铝合金板材工艺参数的优化。
关键词：机器人砂带磨削；表面粗糙度；BP神经网络；预测模型
中图分类号：TG84；TG580.61+9.2；TH162文献标志码：A
Research on Surface Roughness of Robotic Abrasive Belt Grinding
Based on BP Neural Network
Tian Fengjie，Lv Chong
Abstract:In order to improve the prediction accuracy of the surface roughness of robot abrasive belt grinding，the research method based on BP neural network is selected to study.The experiment of grinding aluminum alloy plate with robot abrasive belt is carried out.BP neural network is used to establish the prediction model between process parameters and the workpiece surface roughness based on test results.The prediction model is simulated，and the prediction accuracy of this model is verified by the experiment.The results show that the prediction accuracy of this model is high.It can predict the surface roughness based on different process parameters，and optimize the process parameters of aluminum alloy plate grinding with robot abrasive belt.
Keywords:robotic abrasive belt grinding；surface quality；BP neural network；prediction model