Feature Selection for Tool Wear Diagnosis Using Soft Computing Techniques
Kai Goebel, Weizhong Yan · Manufacturing engineering · 2000
Abstract This paper examines feature selection methods in the context of milling machine tool wear diagnosis. Given raw sensor signals acquired during experiments, a pool of features was created through calculation by several feature extraction methods. Five techniques for selecting the most discriminating features were employed. These techniques included decision trees, neural-fuzzy methods, scatter matrix, and a cross-correlation method. We used a diagnostic neural network to evaluate the five different feature selection schemes by comparing their classification rate and test errors.