【摘要】 针对切削加工过程中颤振孕育的动态模式,提出一种基于PCA—SVM模型的颤振预报新方法。建立切削加工振动信号的识别模型,进行FFT变换,再归一化处理,把数据送入PCA—SVM模型,对变换后的切削实验数据进行学习、训练,得到PCA—SVM识别模型;提取切削加工过程的振动信号,送给PCA—SVM模型进行颤振情况分析与识别。试验结果表明,具有较好的颤振预测性,颤振预报正确率达到95.5%以上,提高了运算速度,为颤振预报提供了充足的时间。更多还原

【Abstract】 A new method of chatter prediction based on PCA—SVM is proposed for dynamic patterns of chatter gestation in cutting process.At first,the recognition pattern for cutting process vibrational signal is established,then FFT transformation and normalization are carried out.Introduce the data to PCA-SVM for machine learning and classification to obtain PCA-SVM recognition pattern;extract the vibrational signal from the cutting process and send PCA-SVM pattern to carry out the chatter analysis and recognition.Experimental results show that the method proposed is effective,and the rate of chatter gestation recognition can reach up to 95.5%,the calculation speed is enhanced and enough time is provided for chatter prevention.更多还原