Effective feature selection with fuzzy entropy and similarity classifier for chatter vibration diagnosis

Feature selection represents the main challenge against the classification strategies for several applications of signal processing. Besides, the high computational speed and accuracy represent a critical requirement of chatter diagnosis. In this paper, a new fuzzy entropy measure with a similarity classifier is developed for feature selection vibration diagnosis in CNC machines. The measured signals are filtered using ensemble empirical mode decomposition and analyzed using Hilbert-Huang transform approach. The proposed feature selection technique can decrease noise and this strategy improves the classification accuracy. The proposed fuzzy entropy approach is compared with different feature selection and machine learning methods in the literature. The experimental results and comparative analyses confirm the superiority of the proposed fuzzy entropy method for chatter vibration identification with a low computational burden and a high accuracy of 98% that is significantly greater than other existing intelligent diagnosis techniques.

Automated summary

Feature selection is a major challenge for classification strategies in signal processing applications, with the need for high computational speed and accuracy in chatter diagnosis. This paper introduces a new fuzzy entropy measure paired with a similarity classifier for feature selection in vibration diagnosis on CNC machines. Experimental results show the proposed method has low computational burden and achieves a high accuracy of 98% in chatter vibration identification.