摘要
针对切削力旧有时域特征易受切削参数变动影响而不适用于变参数铣削刀具磨损状态监测的缺陷,采用了一组新的无量纲切削力时域特征(归一化切削力指标NCF、变异系数Cv和峰值力比MFR)。并以难加工材料TC4钛合金变参数铣削实验来验证新特征在变参数铣削刀具磨损状态监测上的有效性,分别以新旧特征作为SVM分类器的输入,分析和比较结果表明本文提出的无量纲切削力时域特征对切削参数变化不敏感,而仅对刀具磨损状态变化敏感,因此能够实现变参数铣削刀具磨损状态监测。
The old time domain features from the cutting force are vulnerable to changes of cutting parameters. So it is not suitable for tool wear monitoring under variable parameters. In order to solve the above mentioned problem, a new set of dimensionless time domain feature including normalized cutting force indicator NCF, variation coefficient Cv and peak force ratio MFR are adopted. To verify the effectiveness of the present feature for tool wear monitoring under variable parameters, the end milling experiment of TC4 titanium alloy was designed. Then, the present features and the old features are input Support Vector Machines （SVM） to monitor the tool wear state respectively. The analysis and comparison results show that the dimensionless time domain feature presented in the paper is not sensitive to the cutting parameters, but only sensitive to the tool wear state. Hence, the tool wear state monitoring under variable parameters can be implemented.
出处
《机械科学与技术》
CSCD
北大核心
2016年第12期1842-1847,共6页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(51175371)
国家重大专项(2014ZX04012014)
天津市科技支撑计划项目(14ZCZDGX00021)资助
关键词
刀具磨损
变参数
监测
tool wear state
variable parameters
monitoring
milling
surpport vector mochines
design of experiments
