Chip Form Monitoring in Turning Based on Neural Network Processing of Cutting Force Sensor Data

Sensor monitoring of chip form during longitudinal turning of carbon steel Ck45 was carried out through the detection and analysis of cutting force sensor signals. Both single chip form classification and favourable/unfavourable chip form identification were considered. Signal processing for feature extraction was carried out through a parametric method of spectral estimation. Decision making on chip form typology was performed through a supervised neural network (NN) approach, using diverse back-propagation feed-forward NN configurations, in view of the development of an on-line and real time chip form control procedure.