Fault Diagnosis for Key Components of Metro Vehicles based on Wavelet Threshold Denoising and EEMD

With the increasing adoption of intelligent operation and maintenance technologies in urban rail transit, most maintenance systems have been equipped with fault diagnosis modules targeting key components of metro vehicles. However, the integration between engineering-level diagnostic algorithms and advanced academic research remains limited. Two major challenges hinder vibration-based fault diagnosis under real-world operating conditions: the complex noise and interference caused by wheel–rail coupling and the typically weak expression of fault features. Considering the widespread application of wavelet transform in noise reduction and the maturity of ensemble empirical mode decomposition (EEMD) in handling nonlinear and non-stationary signals without parameter tuning, this study proposes a diagnostic method that combines wavelet threshold denoising with EEMD. The method was applied to bearing vibration signals collected from an operational subway line. The diagnostic results were consistent with actual disassembly findings, demonstrating the effectiveness and practical value of the proposed approach.