A Wind Turbine Bearing Fault Detection Method Based on Improved CEEMDAN and AR-MEDA

Purpose This research tackles the complexities of detecting bearing faults in wind turbines, which involves non-Gaussian, non-stationary signals submerged in diverse noise sources. The study aims to present an effective algorithm to address these challenges. Methods The proposed algorithm integrates ICEEMDAN decomposition for signal analysis under varying conditions. AR filtering enhances fault feature extraction by eliminating noise. The method employs MEDA to refine detection accuracy by mitigating signal irregularities. Squared envelope analysis determines bearing fault characteristic frequencies. Results The algorithm’s performance is validated using experimental signals from Case Western Reserve University and real faulty wind turbine signals from Green Power Monitoring Systems (U.S). Conclusion The proposed method emerges as a robust solution for detecting bearing faults amidst challenging signal environments. Its capacity to accurately diagnose bearing faults, coupled with its proficiency across diverse scenarios, positions it as a potent diagnostic tool for wind turbine systems.