基于高阶累积量的特征提取方法研究  

Research on a new feature extraction algorithm based on high-order cumulants and bispectrum on milling

作　　者：马建峰[1] 王信义[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：《机械》2002年第1期30-31,共2页Machinery

摘　　要：提出一种基于高阶累积量和双谱估计的声发射信号特征生成方法 ,为铣刀的磨损提供新的征兆。实验表明 ,高阶累积量对铣刀的磨损非常敏感 ,可以有效地用于铣刀的磨损监测中。This paper develops a new feature extraction algorthim based on high-order cumulants Experiments show that the 3 rd -order cumulant and 4 th -order cumulant are very sensitive to the flank wear These two cumulants of the AE signals can be employed in pattern recognition for tool wear monitoring effectively Bispectrum analysis can also be employed to monitor the tool state

关 键 词：铣刀 高阶累积量 磨损 实时线性监控 声发射 特征提取 

分 类 号：TG714[金属学及工艺—刀具与模具]