A micro tool wear monitoring system based on the audible sound signal was developed and studied in this report. Three modules featuring the signal transformation, feature selection and classification, respectively, were included in this system. A micro milling experiment was conducted on a research platform and the audible sound signals collected by the microphone during the cutting processes were obtained for system development and verification. In the system development, the audible sound was first transformed to the frequency domain and the best features for condition classification was selected based on the class scatter criteria. In classifier design, the Fisher Linear Discriminant (FLD) was used to identify the tool wear condition from the selected features. This study shows that the performance of system was affected by the bandwidth of the feature, as well as the number of features selected for classification. With carefully selecting the parameters, higher than 90% classification rate can be obtained by this system for micro tool condition monitoring.

This content is only available via PDF.
You do not currently have access to this content.