论文部分内容阅读
数控机床刀具磨损监测对于提高刀具利用率,减小因刀具磨损而造成的损失具有重要意义。基于对电流信号特点的分析和小波包分解技术对信号特征量提取的优势,提出一种通过监测机床主轴电机电流特征量变化来监测刀具磨损状态的方法。该方法利用db8小波基对电流信号进行4层小波包分解,将分解后各频带上的均值与方差作为特征量。建立从新刀到刀具磨损状态下特征量随刀具切削时间的变化关系,根据特征量的变化即可判别刀具磨损状态。试验结果验证了该方法在刀具磨损监测中的可行性。
CNC machine tool wear monitoring for improving tool utilization and reduce the loss caused by tool wear is of great significance. Based on the analysis of the characteristics of current signals and the advantages of wavelet packet decomposition in signal feature extraction, a method of monitoring tool wear status by monitoring the changes of machine tool spindle current characteristics is proposed. The method uses db8 wavelet base to carry out 4-layer wavelet packet decomposition on the current signal, and takes the mean and variance of each band after decomposition as the feature quantity. The relationship between the characteristic quantity and the tool cutting time is established from the new tool to the tool wear state, and the tool wear state can be judged according to the change of the characteristic amount. The test results verify the feasibility of this method in tool wear monitoring.