Chip Form Classification in Carbon Steel Turning through Cutting Force Measurement and Principal Component Analysis

摘要

Sensor monitoring of chip form in turning Of C45 carbon steel was performed through sensor fusion based signal feature extraction and pattern recognition aimed at single chip form classification and favourable/unfavourable chip type identification. Features from signals provided by a cutting force based sensor monitoring system were extracted through the Principal Component Analysis algorithm. Pattern recognition of chip form typology was performed by inputting the extracted features into feed-forward back-propagation neural networks.