Tool condition monitoring in micro-drilling using vibration signals and artificial neural network: Subtitle: TCM in micro-drilling using vibration signals

Tool condition monitoring is one of the key issues in mechanical micromachining for efficient manufacturing of the micro-parts in several industries. In the present study, a tool condition monitoring system for micro-drilling is developed using a tri-axial accelerometer, a data acquisition and signal processing module and an artificial neural network. Micro-drilling experiments were carried out on an austenitic stainless steel ((X5CrNi 18-10) workpiece with the 500 μm diameter micro-drill. A three-axis accelerometer was installed on a sensor plate attached to the workpiece to collect vibration signals in three directions during drilling. The time domain “root mean square” feature representing changes in tool wear was estimated for vibration signals of all three directions. The variations of the rms micro-drilling vibrations were investigated with the increasing number of holes under different cutting conditions. An artificial neural network (ANN) model was developed to fuse the rms values of all three directional vibration signals, the spindle speed and feed parameters to predict the drilled hole number. The predicted drilled hole number obtained with the ANN model is in good agreement with the experimentally obtained drilled hole number. It has been also shown that the error of hole number prediction obtained by the neural network model is less than that obtained by using the regression model.