Z.Q. Bo

A New Approach to Phase Selection Using Fault Generated High Frequency Noise and Neural Networks

Single-pole autoreclosure is quite extensively used in long-line applications and involves tripping only the faulted phase for single-phase earth faults. Reliable and fast phase selection is thus imperative in order to avoid potential problems of system insecurity and instability. Conventional phase selectors, primarily based on power frequency measurands, can suffer some impairment in performance because of their heavy dependency on varying system and fault conditions. However, the advent of artificial neural networks (ANNs), with their ability to map complex and highly nonlinear input/output patterns, provides an attractive potential solution to the long-standing problems of accurate and fast phase selection. This paper describes the design of a novel phase selector using ANNs. The technique is based on utilising fault generated high frequency noise (captured through the high voltage coupling capacitor of a conventional capacitor voltage transformer) to essentially recognise the various patterns generated within the frequency spectra of the fault generated noise signals on the three phases, for the purposes of accurately deducing the faulted phase. The paper demonstrates a new concept and methodology in phase selection which will facilitate single-pole autoreclosure applications in power systems.

Accurate fault location and protection scheme for power cable using fault generated high frequency voltage transients

A new technique for accurate fault location and protection of distribution cable is presented in the paper. A specially designed transient capturing unit is used to extract the fault generated high frequency voltage transient signals from the distribution cable system. The travelling time of the high frequency signal is used to determine the fault position. The scheme is insensitive to fault type, fault resistance, fault inception angle and system source configuration. Studies show that the proposed technique is able to offer a very high accuracy in both fault location and fault detection.

Distinguish between fault and switching operation generated transients using a fuzzy neural network

This paper proposes a technique for discriminating between faults and switching operations on a transmission system using a fuzzy logic controlled neural network (FCNN). In the technique, a specially designed transient detector is employed to capture the fault and switching operation induced transients. The detector outputs are used to train a fuzzy logic controlled neural network. The FCNN detects the different characteristics of switching from that of the fault. The digital modelling of typical 400 kV transmission system which includes a switching arc model is presented in the paper. The results show that the trained FCNN is able to discriminate between a fault and a switching operation under various system and fault conditions.

A novel measurement technique for power transformer faults using spectral comparison technique

The paper proposes a new measurement technique for detecting transformer faults. A specially designed transient current detection device is used to capture the fault generated high frequency current transients. The device tuned to a special band of high frequency is connected to the transformer through the CTs at both high and low voltage sides of the transformer. The captured transient signals at both ends of the transformer are then compared, with particular emphasis on the high frequency characteristics in the frequency domain; the internal faults are discriminated from the external fault by spectral comparison. The high frequency modelling of the transformer is incorporated into the simulation. The simulation also involves the modelling of the faults between any turn and the earth and between any two turns of the transformer windings.