Busbar Protection Using a Wavelet Based ANN

This paper presents a new application of wavelet based artificial neural networks to the field of high voltage busbar protection. Any transient event type - whether fault or not-causes high frequency components to be generated and imposed on the fundamental frequency current. Those components propagate from the line causing them passing through the protected bus bar to the other lines connected to the same bus. In this paper, it is shown that those components captured at any line connected to the bus can be used not only to detect internal and external bus faults but also to identify the faulted line in case of external faults. A scheme will be presented that uses the current from any of the lines connected to the bus to detect internal and external bus faults, classify transients on adjacent lines and identify the line that is causing the transient disturbance. Modal transformation is used to transform phase quantities to modal quantities. Discrete Wavelet Transform (DWT) is used to extract high frequency components of the two aerial modes of the current measured. A feature vector consisting of level 3 details coefficients of the two aerial mode currents is used to train a feedforward neural network with one hidden layer. Results show that very accurate classification can be made using one eighth of a cycle of post event data.