Author : Masoud Ahmadipour and Z. Moravej

This paper proposed a new classification method based on Slantlet Transform (ST) combined with an automated classification mechanism based on Artificial Neural Network (ANN) for power transformer protection to discriminate between internal faults and no fault conditions (normal, inrush condition, over excitation and external faults with current transformer saturation) in three phase power transformers. Slantlet Transform has been regarded as a contemporary development in the field of multi-resolution analysis, which is proposed as an improvement over the discrete wavelet transform (DWT). For the evaluation of the developed algorithm, transformer modeling and simulation of fault and no fault condition are carried out in power system computer–aided designing PSCAD/EMTDC. For each candidate internal fault or no fault conditions current waveform suitable features are extracted by employing ST. Then, a successfully trained Artificial Neural Network based classifier, developed utilizing inputs comprising the features extracted from a training set of waveforms, is implemented for a testing set of sample waveforms. The simulation results obtained show that the method is faster, more reliable and accurate when compared with some of published research works in the area. The proposed scheme could achieve nearly 100% classification accuracy in the testing phase.

Keywords: power transformer, differential protection, Slantlet transform, Artificial Neural network

Article published in International Journal of Current  Engineering  and Technology, Vol.3,No.1 (March- 2013)