基于遗传算法优化SVM的刀具VB值预测的研究  

Research on Tool VB Value Prediction of Optimized SVM Based on Genetic Algorithm

作　　者：聂鹏[1] 何超[1] 许良[1] 李正强[1] 崔凯奇 

机构地区：[1]沈阳航空航天大学机电工程学院,辽宁沈阳110136

出　　处：《机床与液压》2015年第11期43-45,75,共4页Machine Tool & Hydraulics

基　　金：辽宁省重点实验室资助项目(LS2010117)

摘　　要：针对刀具磨损量的预测问题,建立了基于支持向量机回归理论的刀具VB值的在线预测模型。对声发射信号和电流信号分别进行EEMD分解和小波包分解得到的能量值,把它与主轴转速、进给量和背吃刀量一起组成初始特征向量。通过主成分分析进行数据处理,把得到主元作为遗传算法优化的支持向量回归机的输入向量。结果表明,该模型精度高,运行速度快。Aimed at the amount of tool wear prediction problems, tool wear model of online VB value prediction was established based on the theory of support vector regression （SVR） regression. The acoustic emission signals and current signals were respectively EEMD decomposed, and wavelet packet decomposed to get the energy values, which were combined with the spindle speed, feeding rate, and back engagement of the tool to form together the original feature vectors. By principal component analysis for data processing, the principal elements obtained were input to the machine of the Support Vector Regression （SVR） optimized by genetic algorithms. The results show that this model has high precision and fast operation.

关 键 词：支持向量回归机 遗传算法 主成分分析 VB值预测 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]