Sürdürülebilir Kalkınma Amaçları

• 1

• MakaleYalnız künye2018Scopus SJRQ1/r/munzur/3373
  Transmission line fault location using traveling wave frequencies and extreme learning machine

  Akmaz, Düzgün; Mamiş, Mehmet Salih; Arkan, Müslüm; Tağluk, Mehmet Emin

  In this research, a new approach was proposed for determining the fault location in transmission lines. Traveling wave frequencies and an extreme learning machine (ELM) were used to determine fault location. Transient signals in the time domain were transformed to the frequency domain using the fast Fourier transform (FFT) and the traveling wave frequencies were detected from the transient frequency spectrum. In order to detect the location of fault, traveling wave frequency was used initially to predict the fault location. The prediction of this fault location was tested for many different fault conditions and was found to be adversely affected by only the source inductance value. This is due to the negative effect of source inductance on wave velocity. Regression feature of ELM was used in order to improve the prediction of fault location and to minimize the negative effect of source inductance. For ELM regression training, values of the fault distance estimated from the traveling-wave frequencies and the source inductance values were used as ELM input data, and the actual distance values were used as ELM output data. After ELM regression training, ELM predicted a new fault location using the input data. The Alternative Transients Program (ATP/EMTP) was used to model J. Marti frequency dependent line model, and the MATLAB program was used to perform fault-detection algorithms. Simulation results show that the proposed method is very successful against many variables such as different fault resistances, source inductances, transmission line characteristics, transmission line lengths.

  • 
  AtıfScopus104·WoS74·OpenAlex101

  İncele
• MakaleAçık Erişim2010Scopus SJRQ1/r/munzur/4054
  Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines

  Eristi, Hueseyin; Uçar, Ayseguel; Demir, Yakup

  This paper presents a new approach for the classification of the power system disturbances using support vector machines (SVMs). The proposed approach is carried out at three serial stages. Firstly, the features to be form the SVM classifier are obtained by using the wavelet transform and a few different feature extraction techniques. Secondly, the features exposing the best classification accuracy of these features are selected by a feature selection technique called as sequential forward selection. Thirdly, the best appropriate input vector for SVM classifier is rummaged. The input vector is started with the first best feature and incrementally added the chosen features. After the addition of each feature, the performance of the SVM is evaluated. The kernel and penalty parameters of the SVM are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. Finally, both the noisy and noiseless signals are applied to the classifier given above stages. Experimental results indicate that the proposed classifier is robust and has more high classification accuracy with regard to the other approaches in the literature for this problem. (C) 2010 Elsevier B.V. All rights reserved.

  AtıfWoS119·OpenAlex163

  İncele