Jixie chuandong (Nov 2022)
Gear Fault Diagnosis Based on APIT-SA-MEMD and FLLE
Abstract
Gears are often in a harsh working environment, and their vibration signals have the characteristics of non-linearity and non-stationarity. Therefore, it is of great significance to develop a fault diagnosis method suitable for gears. To solve this problem, an intelligent fault diagnosis method based on adaptive projection intrinsically transformation sine-assisted multivariate empirical mode decomposition (APIT-SA-MEMD) and Floyd local linear embedding (FLLE) algorithm is proposed. Multivariate empirical mode decomposition of adaptive projection intrinsically transformation has modal aliasing phenomenon, so APIT-SA-MEMD is proposed to reduce the modal aliasing phenomenon existing in traditional empirical mode decomposition. First, the APIT-SA-MEMD method is used to decompose the gear vibration signal, and the IMF component that can characterize the gear vibration signal is obtained. On this basis, the time domain and frequency domain features of the selected IMF components are extracted to obtain a high-dimensional feature matrix. Finally, FLLE is used to perform dimensionality reduction and clustering analysis on the high-dimensional feature matrix to realize the identification of gear fault modes. Experimental results show that the proposed method can accurately identify different types of gear faults.
