The Recognition Study of Impulse and Oscillation Transient Based on Spectral Kurtosis and Neural Network
To improve the precision of classification and recognition of transient power quality disturbances, a new algorithm based on spectral kurtosis (SK) and neural network is proposed. In the proposed algorithm, Morlet complex wavelet is used to obtain the WT-based SK of two kinds of disturbances, such as the impulse transient and oscillation transient. Two characteristic quantities, i.e., the maximum value of SK and the frequencies of the signals, are chosen as the input of neural network for the classification and recognition of transient power quality disturbances. Simulation results show that the transient disturbance characteristics can be effectively extracted by WT-based SK. With RBF neural network, the two kinds of transient disturbances can be effectively classified and recognized with the method in the paper.
KeywordsImpulse and Oscillation Transient Classification and Recognition Spectral Kurtosis Neural Network
Unable to display preview. Download preview PDF.
- 1.Zhao, J., He, Z., Jia, Y.: Classification of transient power quality disturbances based on high-order cumulants. Power System Technology 35(5), 103–110 (2011)Google Scholar
- 2.Wang, J., Xia, L., Wu, G., et al.: Analysis of power system transient signal using genetic algorithm and network. High Voltage Engineering 37(1), 170–176 (2011)Google Scholar
- 3.Lin, S., He, Z., Luo, G.: A wavelet energy moment based classification and recognition method of transient signals in power transmission lines. Power System Technology 32(20), 30–34 (2008)Google Scholar
- 5.Wang, X., He, Z., Zi, Y.: Spectral kurtosis of multiwavelet for fault diagnosis of rolling bearing. Journal of Xi An Jiaotong University 44(3), 77–81 (2010)Google Scholar
- 6.Shi, L., Zhang, Y., Mi, W.: Application of Wigner-Ville-distribution-based spectral kurtosis algorithm to fault diagnosis of rolling bearing. Journal of Vibration, Measurement & Diagnosis 31(1), 27–33 (2011)Google Scholar
- 8.Ding, S., Xu, L., Su, C.: An optimizing method of RBF neural network based. Neural Comput & Applic. (2011)Google Scholar
- 10.Dwyer, R.: Detection of non-Gaussian signals by frequency domain kurtosis estimation. In: Proceedings of IEEE ICASSP, vol. 8, pp. 607–610 (1983)Google Scholar
- 12.Shi, L.: Rolling bearing fault detection using improved envelope analysis. Bearing (2), 36–39 (2006)Google Scholar
- 14.Juan, J.G., Antonio, M.M., Luque, A., et al.: Characterization and classification of electrical transients using higher-order statistics and neural networks. In: CIMSA 2007-IEEE (2007)Google Scholar