In-process monitoring of drilling burr formation using acoustic emission and a wavelet-based artificial neural network

Abstract

Prediction/detection of exit burrs is critical in manufacturing automation. In this research, an intelligent burr sensing/monitoring scheme is proposed. Acoustic emission (AE) was selected to detect burr formation during drilling. For effective extraction of information contained in the collected AE signals, wavelet transform (WT) was adopted and the selected features through WT were fed into a back-propagation artificial neural net (ANN) as input vectors. To validate the in-process AE monitoring system, both WT-based ANN and cutting condition-based ANN outputs (cutting speed, feed, drill diameter, etc.) were compared with experimental data. The results show that the proposed scheme is not only efficient with fewer inputs, but more reliable in predicting drilling burr types over cutting condition-based ANN.