A two-step feature selection method for monitoring tool wear and its application to the coroning process

Coroning is a complex and multi-directional gear finishing process involving metal removal of gear teeth surface, and condition monitoring has not been applied to this process. In order to capture the progress of wear, an acoustic emission (AE) sensor is used, but the large data size of AE requires extensive dimension reduction and feature selection. The conventional method of averaging to reduce the data size may have the risk of losing information as higher frequencies are filtered off. A two-step feature selection method is implemented using class mean scatter criterion and modified relevance/redundancy analysis. This method results in feature dimension reduction and enhances classification performance. It involves first ranking candidate features by calculating their separability. Features which are correlated are then combined to reduce dimensions without averaging. Application of this two-step feature selection technique enables coroning tool wear to be monitored with a classification rate of 98.3 % compared to 94.1 % using conventional feature selection.