This paper presents a new methodology to detect faults in synchronous generators. The proposed approach is based on principal component analysis. Principal component analysis is a multivariate statistical technique used for detecting fault transients and characterization of faults. The proposed fault detection scheme is able to distinguish internal and external faults. The proposed scheme will aid in development of an automatic protective relay for the synchronous generators.

Statistical method for fault detection in synchronous generators

This paper presents a new protection scheme for synchronous generator using an artificial neural network. The proposed scheme is able to discriminate internal and external faults of synchronous generator, consists of feature extraction using eigenvalues and fault classification using artificial neural networks. The performance of algorithm was tested using artificial neural networks and simulation results show the proposed scheme is able to identify and classify all types of faults of synchronous generator. The proposed approach has the ability to detect the generator winding faults which are close to neutral.

A new protection algorithm for synchronous generators using artificial neural networks

A novel technique for fault detection and classification in the synchronous generator is proposed. In this paper, a new statistical method based on independent component analysis is presented. The proposed fault detection scheme identifies external and internal faults of synchronous generator. This characterization of fault transients will aid in the development of a protection relay for synchronous generator and the proposed method is effective in detecting faults and has great potential in power engineering applications.

Fault Detection in Synchronous Generators Based on Independent Component Analysis

In this paper, a new method is proposed for 100% protection against the stator earth fault in synchronous generator. Conventional ground fault protection schemes can be applied to any generator but it covers at most 95% of generator stator length. For ensuring 100% protection of synchronous generator stator winding, conventional ground fault schemes are combined with our proposed third harmonic differential over current protection scheme. Moreover, an investigation into the differences between first harmonic fault current and third harmonic fault current is performed. By using proper simulation model, earth faults are simulated at various distant points from the generator neutral and using this simulations, first harmonic fault current and third harmonic fault current characteristics are properly distinguished. Finally, the threshold current of our proposed differential third harmonic over current relay is selected based on the results of the simulations.

Third harmonic differential over current relay based protection system for stator ground fault in synchronous generator

This paper deals with an algorithm, based on wavelet-Alienation coefficients for protection of wind farm connected distribution network. The proposed algorithm takes the differential current signal of grid node and wind farm coupling node. The Wavelet transform used to extract the approximation coefficients of all the three-phase current signals. Alienation coefficients of each differential phase current obtained over a half cycle is used to identify and categorize the various faults. A modified IEEE13 bus test feeder system used for simulation in MATLAB. Proposed technique tested for detection of all shunt faults at each bus of the distribution system.

Wind Farm Connected Distribution System Protection Using Wavelet-Alienation Coefficient Technique

This paper proposes a protection scheme for turbo generators to detect stator ground faults in particular closer to neutral. The scheme considers total generated voltage of the machine and makes use of Wavelet Multi Resolution Analysis. A Fault Index is defined in terms of peak and valley values of the highest-level wavelet decomposition, which is compared with a threshold value to discriminate from other transients like sudden unbalance in load. The results of digital simulation are presented for different fault impedances and fault locations.

P.V. Ramana Rao

Papers

A new Wavelet based ground fault protection scheme for turbo generators