CLASSIFICATION of TRANSMISSION LINE FAULTS by USING WAVELET TRANSFORM and PROBABILISTIC NEURAL NETWORKS

Sami EKİCİ ¹

In this paper, an alternative method which uses discrete wavelet transform (DWT) and probabilistic neural networks (PNN) is presented for classification of transmission line faults. DWT is used to extract distinctive features of fault transients. Detail coefficients of DWT feed the PNN. A comparison study with other classification methods such as Back Propagation Algorithm (BPA) and Bayes classifiers is also performed to confirm the feasibility of the proposed method. It has been shown that the proposed method classify all fault types with %99 accuracy rate.

Keywords
Transmission Line Faults, Discrete Wavelet Transfo,