De-Noising Method for Gyroscope Signal Based on Improved Ensemble Empirical Mode Decomposition

In order to suppress the nonlinear and nonstationary noise of a gyroscope, this paper proposes an improved dc-noising method called EEMD-M based on ensemble empirical mode decomposition (EEMD). First, the information and noise dominated intrinsic mode function (IMF) components arc obtained by EEMD threshold filtering. Then, EEMD is applied to the discarded IMF components in the first threshold filtering to extract the signal detail. The scaling index of each IMF component is defined by the detrended fluctuation analysis (DFA) method, and the useful components in the secondary decomposition arc further extracted. Finally, the useful IMF components obtained after the two decompositions are reconstructed to obtain a dc-noised signal. In order to verify the effectiveness of the proposed EEMD-M, the noise reduction experiments for the measured data arc carried out. The results show that the proposed algorithm is superior to the empirical mode decomposition (EMD) de-noising method, DFA-EMD de-noising method, EEMD dc-noising method, and wavelet analysis method. The mean square error of the measured data decreases by 82.9%, and the random drift is significantly suppressed, which verifies the feasibility and superiority of the proposed EEMD-M and improves the stability and reliability of the micro electromechanical system gyroscope in optical image processing.