An Improved Variational Mode Decomposition and Its Application on Fault Feature Extraction of Rolling Element Bearing

The fault diagnosis of rolling element bearing is great significance to avoid serious accidents and huge economic losses. However, the characteristics nonlinear, non-stationary vibration signals make feature extraction signal become a challenging work. This paper proposes an improved variational mode decomposition (IVMD) algorithm for bearing, which has advantages extracting optimal from decomposed overcoming noise interference. Shuffled Frog Leap Algorithm (SFLA) employed in adaptive selection number K bandwidth control parameter α. A multi-objective evaluation function, based on envelope entropy, kurtosis correlation coefficients, constructed select component. efficiency coefficient method (ECM) utilized transform optimization problem into single-objective problem. spectrum technique used analyze reconstructed by components. proposed IVMD evaluated simulation practical under different conditions. results show that can improve accuracy adaptability influence parameters realize effective signal.