基于支持向量机的复杂曲面磨削去除量预测  

Prediction of Complex Surface Grinding Removal Based on Support Vector Machine

作　　者：赵敬川 赵吉宾[1,2,3] 李论 张洪瑶[1,2,3] ZHAO Jing-chuan;ZHAO Ji-bin;LI Lun;ZHANG Hong-yao(State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institute for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;不详)

机构地区：[1]中国科学院沈阳自动化研究所机器人国家重点实验室,沈阳110016 [2]中国科学院机器人与智能制造研究所,沈阳110169 [3]中国科学院大学,北京100049

出　　处：《组合机床与自动化加工技术》2021年第11期58-61,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金项目(51775542);国家自然科学基金-辽宁省联合基金(U1908230)。

摘　　要：为了提高工业机器人对复杂曲面磨削去除量的磨削精度,提出了一种基于支持向量机的复杂曲面磨削去除量预测方法,通过分析磨削去除量与磨削去除量的影响因素—工件材料、工件进给速度、磨削力、工件表面曲率、砂带线速度、砂带型号、砂带磨损程度等之间的相关性,利用支持向量回归机方法建立预测模型,对磨削去除量进行预测。该方法可以充分考虑到磨削去除量影响因素之间的耦合关系。实验数据表明,该预测模型的预测精度达到99.963%。In order to improve the grinding accuracy of robot for complex surface grinding removal,a prediction method of complex surface removal amount based on support vector regression(SVR)machine is proposed.By analyzing the correlation between the grinding removal amount and the factors affecting the grinding removal amount,such as workpiece feed speed,grinding force,workpiece surface curvature,abrasive belt linear speed,abrasive belt type,abrasive belt wear degree,etc.The prediction model is established by using support vector regression(SVR)machine to predict the grinding removal.This method can fully consider the coupling relationship between the influencing factors of grinding removal.The experimental data show that the prediction accuracy of the model is up to 99.963%.

关 键 词：支持向量回归机 复杂曲面 磨削加工 去除量预测 工业机器人 

分 类 号：TH16[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]