DISCRIMINATION METHOD FOR SPINDLE VIBRATION ANALYSIS BASED ON EMPIRICAL MODE DECOMPOSITION AND INDEPENDENT COMPONENT ANALYSIS ALGORITHM

摘要

This paper describes a discrimination method for spindle vibration which can separate the additive vibration noises and fundamental vibration sources of signals to each part. The combination algorithm between ensemble empirical mode decomposition (EEMD) and independent component analysis (ICA) is used to identify the individual components of vibration signals of a spindle. EEMD offers a simple method to decompose adaptively spindle vibration signal into multiple empirical modes, and each mode represents a narrow band frequency-amplitude modulation that is usually related to a specific signal characteristic. After EEMD process, ICA is utilized to recognize the source signals from each mode. The experiment results reveal that the proposed algorithm can be struck out the spindle vibration noise to discriminate the clarity vibration of spindle.