Assessment of machining features for tool condition monitoring in face milling using an artificial neural network

Because of a wide scatter in the tool lives of face milling inserts and limitations of conventional methods for predicting the same, artificial neural systems have become advantageous for their ability to learn input-output mappings. Process parameters coupled with machining responses and experimental observations provide a basis for monitoring the tool wear in face milling. Chip characteristics such as shape and colour together with features of force and vibration are potential candidates for wear prediction in the field of tool condition monitoring.