Unsupervised Planetary Gearbox Fault Detection for Nuclear Circulating Water Pump Based on Generalized Features

Ensuring reliable machine operation is dependent on effective fault detection. Feature indicator construction is considered the foundation for operational condition assessment among various detection methods. However, the nuclear circulating water pump (NCWP) experiences severe disturbances due to noise and changes in operating conditions. In addition, the complex movement of the gears causes signal interference, which may result in the feature indicators failing. To address the above issues, this article proposes a generalized features construction (GFC) method to realize unsupervised planetary gearbox fault detection. First, a feature relevance evaluation method is presented to filter intrinsic mode functions (IMFs) obtained through ensemble empirical mode decomposition (EEMD) for noise reduction. Second, feature indicators are constructed based on interpretable frequency information. Then, global and local features are evaluated, respectively, to realize fault detection and further detection of faults from the sun or planetary gears. Finally, the effectiveness of the proposed method is demonstrated through data obtained from the NCWP test bench.