Monitoring Tool Wear States in Turning Based on Wavelet Analysis  

基于小波分析的刀具磨损状态监测方法(英文)

作　　者：王忠民[1] 王信义[1] 陈爱第 贾玉平[1] 

机构地区：[1]北京理工大学机械工程与自动化学院,北京100081

出　　处：《Journal of Beijing Institute of Technology》2001年第1期101-107,共7页北京理工大学学报（英文版）

基　　金：MinisterialLevelFoundation

摘　　要：To monitor the tool wear states in turning, a new way based on the wavelet transformation to get the signal characters, which can reflect the tool wear states, was proposed. Using discrete dyadic wavelet transform, the acoustic emission(AE) signal of cutting process was decomposed; the root mean square(RMS) values of the decomposed signals at different scales were taken as the feature vector; the technique of fuzzy pattern identification was used to real time monitor the tool wear states. Based on choosing the suitable standard samples, this method can correctly identify the tool wear states. Experiments showed that the technique based on wavelet analysis is suitable for real time implementation in manufacturing application.为了实现车削过程刀具磨损状态的实时在线监测 ,使用离散二阶小波变换对切削过程声发射信号进行分解 ,以不同尺度下信号分量的均方根值组成的特征向量为样本 ,利用模糊模式识别技术实现对刀具磨损状态的在线识别 .实验表明 ,在选择适当的标准样本基础上 ,所提出的基于声发射信号小波分解的模糊模式识别方法能准确实现刀具磨损状态的正确识别 ,具有较高的可靠性和准确性 .

关 键 词：wavelet transform fuzzy pattern identification acoustic emission(AE) tool wear 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]