Indentification Methods Of Power Quality Disturbances

Nowadays, power characteristics, power grid and load structure is undergoing profound changes, various nonlinear,impactive and unbalanced load is put into use, which resulting in a series of power quality problems. But electrical equipments are more sensitive to power quality problems. The effective recognition of power quality disturbance types can give decisition support for power quality management, thus improve power quality and bring huge economic benefits.S-transform and wavelet transform are used to study on single power quality disturbances identification in this paper.About single power quality disturbances recognition using wavelet transform, wavelet transform is used to extract energy difference distribution features and support vector machine (SVM) is employed as classifier. In the process of power quality disturbances identification, the wavelet decomposition level usually lack theoretical basis when using wavelet transform to extract energy difference distribution features and training signal samples for SVM are usually in one condition of signal-noise ratio (SNR). For the above two problems, the wavelet decomposion level is decided by signal sampling rate when using wavelet doing multi-resolution analysis, which reduces the calculation time and the number of characteristic dimension, then the extracted energy distribution features are used as the input vector of SVM to train a SVM based classifier; Training signal samples in different SNR conditions are employed to train SVM and the classification ability of SVM is enforced. The simulation results indicate that this improved method can accurately classify6types of power quality disturbances and the accuracy can still reach95.20%even the SNR is20dB.About single power quality disturbances recognition using S-transform, A new approach to recognize power quality disturbances is proposed. Based on fast Fourier transform (FFT) combined with dynamic measure method three kinds of features in power quality disturbance signals are extracted and using S-transform four features in power quality disturbance signals are extracted, and by use of decision tree and SVM a combination classifier is designed. Firstly, for disturbance types with evident harmonic frequencies in FFT spectrum the features of main frequency points in FFT spectrum are extracted by the extreme point-enveloped dynamic measure method, and combining with the features extracted by S-transform, the disturbance types are preliminarily classified into several categories, and then by use of the two features extracted by S-transform the follow-up classification can be implemented. During the classification of decision tree the SVM is used to distinguish voltage sag from voltage interruption, thus the trouble that the feature thresholds, which vary with signal-to-noise ratio (SNR), are hard to be determined can be overcome. Simulation experiments show that using the proposed method eleven power quality disturbance signals, including two kinds of compound disturbances, can be accurately recognized, and when SNR is lowered to20dB the recognition accuracy can still reach to96.50%. Comparison of the obtained results with reported classification results shows that the proposed method is accurate, stable and can be utilized in environment of low SNR.About study on multiple disturbance types. A new approach to recognize multiple power quality disturbances is proposed. Firstly, based on S-transform five kinds of features in power quality disturbance signals are extracted and using FFT combined with dynamic measure method six features in power quality disturbance signals are extracted. Disturbance signals are characterized by these features from the baseband, intermediate frequency, high-frequency, standard deviation of the fundamental frequency, extreme point symmetry and variations of spectrum. Characteristics aliasing or failures because of interferences between the single disturbance were fully considered in this method. Then a classifier is designed with eight rules in the form of "IF-THEN", finally features were input into the rule-based classifier for the disturbance identification. Simulation results show that this method can effectively recognize the compound power quality disturbances with the noise including eight single disturbances and eighteen double disturbances.