A wind power converter open circuit and current sensor fault diagnosis method
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HOHAI UNIV
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies struggle to accurately identify IGBT open-circuit faults and current sensor faults in wind power converters, especially under wind speed fluctuations and noise interference, leading to overlapping fault characteristics, misdiagnosis, or missed diagnosis. Furthermore, existing methods increase hardware costs or rely on precise system parameters, resulting in insufficient robustness.
Adaptive Noise Complete Ensemble Empirical Mode Decomposition (CEEMDAN) is used to decompose the three-phase current signal at multiple scales, select discriminative Intrinsic Mode Functions (IMFs), construct an adaptive hybrid topology graph structure, and achieve joint fault diagnosis through a spatiotemporal feature graph convolutional network to extract composite features that fuse time and frequency information.
Under conditions of wind speed fluctuations and noise interference, it can accurately distinguish between IGBT open circuit faults and current sensor faults, reduce false alarm rates, improve the stability and reliability of diagnosis, meet the needs of online monitoring and fault early warning, and enhance the operational safety of wind turbine units.
Smart Images

Figure CN121831518B_ABST