摘要
在机械自动化加工中,为了防止刀具损坏,刀具磨损过程的监测是非常重要的。然而,由于加工过程的复杂性,对刀具磨损状态的监测十分困难。提出了一个基于小波包系数与隐马尔科夫模型的刀具磨损监测方法。将加工信号在不同频带上小波包系数的均方根值作为特征观测向量,即为隐马尔科夫模型的输入,并用隐马尔科夫模型模式识别方法识别刀具磨损状态。实验结果显示,提出的方法对刀具磨损状态具有很高的识别率。
In order to prevent tool failures during the automation machining process, the tool wear monitoring becomes very important. However, the state recognition of the tool wear is not an easy task. In this paper, an approach based on wavelet packet coefficient and hidden Markov model (HMM) for tool wear monitoring is proposed. The root mean square (RMS) of the wave- let packet coefficients at different scales are taken as the feature observations vector. The ap- proach of HMM pattern recognition is used to recognize the states of tool wear. The experimental results have shown that the proposed method has a good recognition performance.
出处
《机床与液压》
北大核心
2014年第12期40-44,共5页
Machine Tool & Hydraulics
基金
Project supported by Jiangxi Province Education Department Science Technology Project(GJJ14365)
Jiangxi Province Nature Science Foundation(20132BAB201047,20114BAB206003)
关键词
刀具磨损
小波包系数
隐马尔科夫模型
均方根
Tool wear, Wavelet packet coefficient, Hidden Markov model, Root mean square