基于小波包分解的刀具磨损特征分析

为了高效准确地在线监测加工高温合金过程中的刀具磨损,有效地提取刀具磨损相关特征显得尤为重要。文章提出了基于小波包分解的刀具磨损特征提取方法,将刀具切削过程中的切削力信号在时频域下分解重构,分析了各频段重构信号能量值与刀具磨损的相关性,提取了信号分解重构后小波包系数能量值中与刀具磨损相关的两个频段信号作为刀具磨损监测的特征参数,最后通过试验结果表明,采用小波包分解方法在切削力信号中提取的切削力特征和切削振动特征可作为刀具磨损特征,从而为后续研究刀具磨损在线监测提供有效输入。

Analysis of Tool Wear Characteristics Based on Wavelet Packet Decomposition

In order to efficiently and accurately monitor the tool wear during the processing of superalloys, it is particularly important to effectively extract the relevant features of tool wear. Therefore, this paper proposes a tool wear feature extraction method based on wavelet packet decomposition. The cutting force signal in the cutting process is subdivided and reconstructed in the time-frequency domain, and the correlation between the energy value of the reconstructed signal and the tool wear in each frequency band is analyzed. The two frequency bands related to tool wear in the energy value of wavelet packet coefficients after signal decomposition reconstruction are used as the characteristic parameters of tool wear monitoring. Finally, the experimental results show that the cutting force characteristics and cutting vibration characteristics extracted by wavelet packet decomposition can be used as tool wear characteristics, which in turn provide input for subsequent online monitoring of tool wear.