An approach to classify transient disturbances with incomplete S-transform and Morlet wavelet spectral kurtosis

To classify and recognize the transient power quality disturbances (PQDs), an algorithm based on incomplete S-transform (IST) and Morlet wavelet spectral kurtosis (SK) is proposed. Firstly, Morlet wavelet SK and IST are used to obtain characteristics of different transient PQDs. Characteristics extracted from the IST and the Morlet wavelet SK are respectively used to classify amplitude disturbances and disturbances of oscillation and impulsive transient. Then the K-means algorithm is used to give a clustering center of the classification, and different disturbances are distinguished from each other by different clustering center. Simulation results show that the transient disturbance characteristics can be effectively extracted with the presented algorithm.

[1]  Azah Mohamed,et al.  Support Vector Regression Based S-transform for Prediction of Single and Multiple Power Quality Disturbances , 2009 .

[2]  Ming Zhang,et al.  A New Transient Power Quality Disturbances Detection Using Strong Trace Filter , 2014, IEEE Transactions on Instrumentation and Measurement.

[3]  Weiguo Huang,et al.  Adaptive spectral kurtosis filtering based on Morlet wavelet and its application for signal transients detection , 2014, Signal Process..

[4]  Xu Jia.  Comparative study of STFT and S transform on detecting voltage sag , 2014 .

[5]  A. Cruz Serra,et al.  PQ Monitoring System for Real-Time Detection and Classification of Disturbances in a Single-Phase Power System , 2008, IEEE Transactions on Instrumentation and Measurement.

[6]  P. Laguna,et al.  Signal Processing , 2002, Yearbook of Medical Informatics.

[7]  Zhang Tai-qin.  Study on application of Morlet complex wavelet on adaptive current protection , 2009 .

[8]  Shi Lin-suo.  Rolling Bearing Fault Detection Using Improved Envelope Analysis , 2006 .

[9]  Li Sheng-qing.  Tracking capacitor switching disturbance source using cross incomplete S-transform , 2012 .

[10]  Rengang Yang,et al.  Power-Quality Disturbance Recognition Using S-Transform , 2007, IEEE Transactions on Power Delivery.

[11]  Zhigang Liu,et al.  An Approach to Recognize the Transient Disturbances With Spectral Kurtosis , 2014, IEEE Transactions on Instrumentation and Measurement.

[12]  Ricardo García-Ródenas,et al.  K-means algorithms for functional data , 2015, Neurocomputing.

[13]  Liu Zhigang.  A New Method for Power Quality Mixed Disturbance Classification Based on Time-frequency Domain Multiple Features , 2012 .

[14]  Zhigang Liu,et al.  A new detection approach of transient disturbances combining wavelet packet and Tsallis entropy , 2014, Neurocomputing.

[15]  J. Antoni.  The spectral kurtosis: a useful tool for characterising non-stationary signals , 2006 .