Deep learning fan fault diagnosis method based on double-wavelet fusion and CEEMDAN decomposition
Through the deep learning method of dual wavelet fusion and CEEMDAN decomposition, independent modeling is performed for the key measurement points of the fan, which solves the non-stationary and noise interference problems of the fan fault signal and achieves high-precision fault diagnosis.
Patent Information
- Application Number
- CN202510719120.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-30
- Publication Date
- 2025-09-26
AI Technical Summary
When a wind turbine operates in an underground space, the fault signal exhibits non-stationarity and nonlinearity. Traditional methods are difficult to effectively extract fault features, and deep learning methods are limited in their feature learning capabilities under noise interference. CEEMDAN is sensitive to noise, and single wavelet packet decomposition has the problem of insufficient matching.
The method of dual wavelet fusion and CEEMDAN decomposition is adopted. By improving the wavelet packet denoising algorithm and CEEMDAN decomposition, combined with time-frequency domain feature extraction, independent modeling is performed on the key measurement points of the wind turbine. 1D-CNN and LSTM are used to extract time domain features, and CNN is used to extract frequency domain features to achieve fault diagnosis.
It significantly improves the signal reconstruction quality and fault identification accuracy, avoids interference between measurement points, and enhances the sensitivity and accuracy of fault diagnosis. It is suitable for fan fault identification under complex working conditions.