Fault identification of rolling bearing based on time-frequency analysis

Rolling bearing is the core component of mechanical equipment and rail transit, which bear complex loads while running rapidly, thus causing bearing failures such as fatigue wear, peeling and scratching, affecting the safe operation of mechanical equipment and rail transit. Therefore, the condition monitoring and fault diagnosis of rolling bearing is a research hotspot in recent years. The modern signal processing technology is applied to fault diagnosis of rolling bearing. Aiming at the nonlinear and non-stationary characteristics of bearing vibration signal, the vibration signal is firstly decomposed by Ensemble empirical mode decomposition (EEMD). The Intrinsic Mode Function (IMF) without mode aliasing is obtained, and then all IMF are evaluated by sensitivity evaluation algorithm, and the IMF that sensitive to fault characteristics is selected. Finally, the sensitive IMF is transformed by Hilbert transform, and the fault characteristics related to the fault of rolling bearing are extracted, so as to realize the fault identification and diagnosis of rolling bearing.