Application of Continuous Wavelet Features and Multi-Class Sphere SVM to Chatter Prediction
A cutting chatter forecast method based on continuous wavelet feature and multi-class spherical Support Vector Machines is studied in this paper. The method based on continuous wavelet transform extracts the cutting vibration signal feature and uses multi-class spherical Support Vector Machines to discern the chatter. In order to simplify computational complexity when binary classification SVM turn to multi-class classification, the algorithm makes every kind of samples have a spherical SVM. In the feature space identified the test sample and spherical SVM centre distance as a decision-making function. Experiments show that using combine spherical SVM with continuous wavelet feature Vector has good recognition effect in the milling chatter recognition system. Chatter inoculation forecast accuracy reaches 95%, and chatter outbreak forecast accuracy reaches 97.5%.
Chengyong Wang, Ning He, Ming Chen and Chuanzhen Huang
S. Wu et al., "Application of Continuous Wavelet Features and Multi-Class Sphere SVM to Chatter Prediction", Advanced Materials Research, Vol. 188, pp. 675-680, 2011