Tools wear state recognition based on feature selection and fuzzy support vector machine

To improve the recognition accuracy of the tool wear state on unbalanced samples, a tool wear state recognition method based on feature selection and fuzzy support vector machine are proposed. The method selects features by discrete binary particle swarm optimization algorithm, eliminates redundant features and irrelevant features, and avoids the algorithm falling into the dimensional disaster. Then the hybrid fuzzy membership function is designed, and the fuzzy support vector machine classification model is constructed. The particle swarm optimization algorithm is used to optimize the key parameters of the fuzzy support vector machine to realize the tool wear state recognition. The experimental results show that in the case of unbalanced samples, the tool wear state recognition method based on feature selection and fuzzy support vector machine has good learning ability and high recognition accuracy.