A fan fault detection method, system, device and medium
By combining the CRITIC objective weighting method and the ICEEMDAN decomposition algorithm with ant colony optimization, we achieved adaptive decomposition and accurate identification of early fault characteristics of wind turbines, solving the problems of low signal-to-noise ratio and strong non-stationarity, and improving the reliability of fault detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHANGJIAKOU WIND & SOLAR POWER ENERGY DEMONSTRATION STATION CO LTD
- Filing Date
- 2026-06-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing wind turbine fault diagnosis methods are difficult to effectively identify early fault characteristics under complex operating conditions. They have low signal-to-noise ratios and strong non-stationarity, leading to signal decomposition and aliasing, and missed detection of early faults.
By employing the CRITIC objective weighting method combined with the ICEEMDAN decomposition algorithm, optimizing the decomposition parameters through the ant colony optimization algorithm, and selecting components using the maximum inter-class variance method, the noise reduction threshold is adaptively adjusted to achieve accurate identification of early fault characteristics.
It significantly improves the sensitivity of early fault feature identification, effectively suppresses mode aliasing and endpoint effects in the decomposition process, preserves weak early fault information, and adapts to component distribution under different signal-to-noise ratios and operating conditions.
Smart Images
Figure CN122407480A_ABST