Power Quality Disturbance Recognition Using S-Transform
Active In SP
Joined: Sep 2010
16-10-2010, 12:46 PM
Taking advantage of S-transform(ST), the paper proposes a new method of detecting and classifying power quality disturbances. The S-transform is unique in that it provides frequency-dependent resolution while maintaining a direct relationship with the Fourier spectrum. The features obtained from S-transform are distinct, understandable and immune to noise. According to a rule-based decision tree, eight types of single power disturbance and two types of complex power disturbance are well recognized, and there is no need to use other complicated classifiers. The comparison between the Wavelettransform- based method and the S-transform-based method for power quality disturbance recognition is also provided. The simulation results show that the proposed method is effective and immune against noise. The proposed method is feasible and promising for real applications.
With the common use of all kinds of electronic sensitive equipment, electric power quality, including voltage sag, voltage swell, voltage harmonics and oscillatory transients, has attracted great concerns. How to extract features of disturbances from large number of power signals and how to recognize them automatically are important for further understanding and improving of power quality. Many researchers have been engaging in this area and proposed automation systems. FFT, d-q transform, fractal dimensions or wavelet transform are widely used for feature extraction. Artificial neural networks(ANN), fuzzy logic(FL) and super vector machines(SVM) are also used for event classifications.
Although wavelet transform has the capability to extract information from the signal in both time and frequency domain simultaneously and has been applied in detection and classification of power quality, it also exhibits some disadvantages, such as its complicated computation, sensitivity to noise level and the dependency of its accuracy on the chosen basis wavelet.
The S-transform(ST), on the other hand, can be seen either as an extension of ideas of wavelet transform (WT) or a variable window short time Fourier transform(STFT), and it has characteristics superior to WT and STFT. In recent years, ST has been used to extract features and been combined with other pattern classifiers such as ANN, FL, or SVM to classify power quality events. All these systems need training, which may lead to poor classification accuracy rate when the training Samples are not adequate. In this paper, the features of each power disturbance are extracted from ST, and the disturbance patterns are well recognized using a rulebased decision tree.
for more details,please visit
|Possibly Related Threads...|
|ARL Comparisons Between Neural Network Models and ¯x-Control Charts for Quality||study tips||0||327||
28-05-2013, 12:58 PM
Last Post: study tips
|Discrete Fourier Transform pdf||study tips||0||331||
19-02-2013, 02:22 PM
Last Post: study tips
|Power Calculation – Milling||seminar tips||0||392||
14-02-2013, 12:49 PM
Last Post: seminar tips
|Application of Wavelet Transform and its Advantages Compared to Fourier Transform pdf||project girl||0||388||
30-11-2012, 03:09 PM
Last Post: project girl
|The Hilbert transform ppt||seminar flower||0||633||
03-09-2012, 11:18 AM
Last Post: seminar flower
|Optimally Sparse Image Representation by the Easy Path Wavelet Transform||seminar paper||0||521||
19-03-2012, 01:34 PM
Last Post: seminar paper
|Statistical Algorithm for Power Transmission Lines Distance Protection||seminar surveyer||0||992||
13-10-2010, 10:57 AM
Last Post: seminar surveyer