基于多类超球支持向量机的铣削颤振预测方法

Milling chatter prediction method based on multiclass hypersphere support vector machine

为了预测薄壁件铣削过程颤振的发生,提出了一种应用小波系数特征和多类超球支持向量机进行铣削颤振预报的方法。首先基于连续小波变换分别提取高、低频段铣削振动信号的特征,然后利用多类超球支持向量机进行稳定铣削状态、铣削颤振孕育状态、铣削颤振状态识别。为了简化支持向量机进行多类分类时所带来的计算复杂性,该算法使每一类样本都获得一个超球支持向量机,在特征空间中以测试样本与超球中心距离、超球半径作为决策函数来进行识别。实验表明,在铣削颤振识别系统中多类双核超球支持向量机与连续小波系数特征向量相结合具有良好的识别效果,颤振孕育预报正确率达98.0%。

In order to predict the chatter of thin-walled workpiece in milling process, a cutting chatter prediction method based on wavelet coefficient feature and multiclass hypersphere support vector machine （SVM） is proposed in this paper. In this method, the continuous wavelet transform is used to extract the characteristics of the vibration signal in high and low frequency bands; and then multiclass hypersphere support vector machine is used to recognize the smooth cutting, chatter gestation and chatter outbreak states. In order to simplify the computational complexity when using binary classification support vector machines to do multiclass classification, the algorithm makes every kind of samples have a hypersphere support vector machine, in the feature space, the distance between test sample and hypersphere center, as well as hypersphere radius are used as the decision-making function to achieverecognition. Experimental results show that in the cutting vibration chatter recognition system, muhiclass dual-kernelhypersphere support vector machine combined with continuous wavelet coefficient feature vector has good recognition effect ; the accuracy of chatter gestation prediction can reach 98.0%.