Fault Section Identification Research Articles

Artificial neural network based fault diagnostic system for electric power distribution feeders

Abstract This paper describes the development of a fast, efficient, artificial neural network (ANN) based fault diagnostic system (FDS) for distribution feeders. The principal functions of this diagnostic system are: (i) detection of fault occurrence, (ii) identification of faulted sections, and (iii) classification of faults into types, e.g. HIFs (high impedance faults) or LIFs (low impedance faults). This has been achieved through a cascaded, multilayer ANN structure using the back-propagation (BP) learning algorithm. This paper shows that the FDS accurately identifies HIFs, which are relatively difficult to identify with other methods. Test results are generated using the Manitoba Hydro 24 kV distribution feeder. These results amply demonstrate the capacibility of the FDS in terms of accuracy and speed with respect to detection, localization, and classification of distribution feeder faults.

A hybrid expert system for faulted section identification, fault type classification and selection of fault location algorithms

The authors present an expert system developed in Turbo PROLOG to identify faulted sections and interpret protective apparatus operation in large interconnected power systems. This expert system is capable of identifying bus faults, line fault sections, and fault sections in the common area of a specific bus and line. Also, the expert system identifies relays or breaker malfunctions. The expert system is expanded to include real-time measurements of current and voltage phasors to classify the type of fault that the faulted section has experienced. When the faulted section is a transmission line, the expert system then selects an appropriate fault location algorithm to compute the fault location in miles. The importance of using a combination of numeric and database algorithms is emphasized.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A Hybrid Expert System for Faulted Section Identification, Fault Type Classification and Selection of Fault Location Algorithms

This paper presents an expert system developed in turbo prolog to identify faulted sections and interpret protective apparatus operation in large interconnected power systems. The expert system presented here is capable of identifying bus faults, line fault sections, and fault sections in the common area of a specific bus and line. Also, the expert system identifies relays or breakers malfunctions. The expert system is then expanded to include real-time measurements of current and voltage phasors to classify the type of fault that the faulted section has experienced. Furthermore, when the faulted section is a transmission line, the expert system selects an appropriate fault location algorithm to compute the fault location in miles. This paper shows that the combination of numeric and data base algorithm is essential to many developments in expert system application in power systems. Evaluating the expert systems reported so far for fault diagnosis reveals that all of these schemes utilize only the data received from breaker and relay status. Consider the recent trend in digital protection, real-time phasor measurements would be available. To combine real-time phasor measurements with relay and breaker status, a hybrid expert system is required. A hybrid expert system combines numeric algorithms with data base algorithms in one scheme. This paper recognizes this feature in the expert system developed here. The expert system reported in this paper includes four stages. The first stage determines the faulted section of the power system and reports correct and incorrect breaker and relay operation.