Study of cutting parameter effect on spindle vibration for tool breakage monitoring in drilling

Abstract

The cutting parameter effect including tool diameter and feed rate on the spindle vibration signal for tool breakage monitoring was studied. The vibration signal obtained from the accelerometer installed on a fixture connected to the spindle housing was considered as the input signal for the monitoring system. The monitoring system was integrated by a signal transformation module, feature selection module for creating the features related to the breakage event, and a classifier module for classifying the tool breakage event based on the selected features. The linear discriminate function was adopted as the classifier in this chapter. To collect the vibration signals for analyzing the signals and system performance affected by cutting parameter, an experiment was implemented on a tapping machine along with 2 mm/3 mm diameter drill and aluminum alloy workpiece. In feature analysis, various wavelet coefficients for the collected signals were analyzed for system performance with various tool diameters and feed rates. The results show that the system developed by combined signals obtained from various cutting parameters is not reliable to detect tool breakage when implementing with any cutting parameters included in the model development. However, 100 % classification rate can be obtained for all case based on the model developed by type 3 signals and with properly choosing wavelet coefficient as features. © 2013 Springer Science+Business Media New York.