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.
参考文献
相似文献
引证文献
引用本文
聂鹏,何超,许良,李正强,崔凯奇.基于遗传算法优化SVM的刀具VB值预测的研究[J].机床与液压,2015,43(11):43-45. . Research on Tool VB Value Prediction of Optimized SVM Based on Genetic Algorithm[J]. Machine Tool & Hydraulics,2015,43(11):43-45