A Novel Zone Division Approach for Power System Fault Detection Using ANN-Based Pattern Recognition Technique

This paper presents a waveform analysis-based approach for detection and classification of short-circuit faults in large power networks. To reduce the computational burden in dealing with a large volume of waveform data, a novel zone detection method has been used where a large power network is divided into optimal number of zones with manageable number of buses and lines. A first module of the artificial neural network-based classifier has been developed to perform an "exploratory global search" to find the faulty zone, which is then refined to a "local search" within a zone, by a second module of classifier for determination of exact fault location and fault type. The elementary waveform data are being captured by disturbance recorders placed at strategic buses, termed as "monitoring locations." Feature extraction, which is typically the underlying principle of any waveform analysis-based fault detection approach, is implemented by the extended Kalman filter. The proposed method has been successfully tested on the IEEE 57 bus network with encouraging results.