摘要
针对切削加工过程颤振孕育的动态模式,提出基于KPCA-SVM模型的颤振预报新方法。首先提取切削加工振动信号,进行FFT变换,使KPCA-SVM模型对变换后的切削实验数据进行学习、训练,得到KPCA-SVM识别模型;提取切削加工过程的振动信号,经过FFT变换后,得到其幅频特征量,送给KPCA-SVM模型进行颤振情况分析与识别。
A new method of chatter prediction based on KPCA - SVM is proposed for dynamic pattems of chatter gestation in cutting process. At first, the typical vibration signal of cutting process are transformed and introduced to KPCA - SVM for machine learning and classification. Then the results of chatter gestation recognition and chatter prediction experiments are presented and show that the method proposed is effective.
出处
《煤矿机械》
北大核心
2009年第4期58-60,共3页
Coal Mine Machinery
基金
国家自然科学基金资助(No.50405023)
