In view of the non-stationary and time-varying characteristics of the pressure fluctuation signal in the draft tube of hydraulic turbine, a method combining noise reduction based on Singular Value Decomposition (SVD) with Cascade Correlation (CC) neural network to analyze the pressure fluctuation signal is developed. Firstly, the singular value decomposition based on an improved threshold is used to reduce the noise, and then the signal component of different frequency band is extracted, finally the feature vector is applied to the CC neural network for pattern recognition, obtaining the different patterns of pressure fluctuation in the draft tube. The results show that this method is effective in identifying states of pressure fluctuation in the draft tube.
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|