Seminar by Xiaowen Zhu

Tool health monitoring based on SVD analysis

In this seminar, a SVD (Singular Value Decomposition) method to supervise the machining tool health monitoring is introduced. It is based on angular domain in which the rotation angle of the tool itself and the angular change of the cutting path are unified. Based on this, the separate parts corresponding to the decomposition by SVD will be exploited their physique meaning. And the order separability index is proposed to assess the current operating state of the tool.

Under normal operating conditions, the first-order main component can already express more than 95% of the information. In the event of abnormal wear, the signal will deviate from the typical waveform, and the first order will no longer be sufficient to describe the signal, while the second or third order contribution of SVD will increase rapidly. Therefore, analysis of the separability index can detect abnormal cutting conditions. The goal of this research is to understand the ability of the SVD to analyze milling under cyclo-stationary and cyclo-non-stationary conditions (complex trajectories) under the reference of the angular domain.

This seminar will be held online. Click here to join the Zoom event.