Recognition of Fault Transients Using a Probabilistic Neural-Network Classifier

Perera, N.; Rajapakse, Athula D.

doi:10.1109/tpwrd.2010.2060214

Cited by 66 publications

(27 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the sum of squares is not reduced, then increase ex and go back to step 3, ael ael aXI aXn J( X) a �N a �N (6) aXI aXn where n = number of all weights in the network which are now collected together in a weight vector 5. The algorithm is assumed to converge when the norm of the gradient is less than some predetermined value, or when the mean squares error has been reduced to some error goal.…”

Section: Decision Algorithm and Resultsmentioning

confidence: 99%

“…In the literature for fault detection, several decision algorithms have been developed to be employed in the protective relay [1][2][3][4][5][6][7]. They (most of them) have different solutions and techniques [1][2][3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, based on the artifIcial intelligent techniques, artifIcial neural networks (ANNs) are often employed for fault classifIcation [5][6][7] due that these algorithms can give precise results. Back-propagation neural network (BPNN) is the most well-known and widely applied today because it can solve almost all types of problems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discriminati on between external short circuit and internal winding fault in power transformer using discrete wavelet transform and back-propagation neural network

Jettanasen

Klomjit

Bunjongjit

et al. 2012

2012 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

This paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and back-propagation neural network (BPNN) for detecting and identif y ing internal winding fault of three-phase two-winding transformer. The maximum ratio obtained from division algorithm between coefficient from DWT of differential current and zero sequence for post-fault differential current waveforms is emplo y ed as an input for the training pattern in order to discriminate between internal fault and external short circuit. Variouscases studies based on Thailand electricit y transmission and distribution s y stems have been investigated so that the algorithm can be implemented. Results show that the proposed technique has good accurac y to detect fault and to identif y its position in the considered s y stem.

show abstract

Section: Decision Algorithm and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminati on between external short circuit and internal winding fault in power transformer using discrete wavelet transform and back-propagation neural network

Jettanasen

Klomjit

Bunjongjit

et al. 2012

2012 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

show abstract

“…Similar energy has been used for fault and power-quality disturbance detection in real-time and/or offline analysis by using DWT or MODWT [34], [35], [36], [37]. However, this energy presents some drawbacks, such as time delay in realtime analysis with the choice of the mother wavelet, such as addressed in the remainder of this paper.…”

Section: A Energy Without Border Distortionsmentioning

confidence: 99%

Wavelet-Based Power System Stabilizer

Neto

Ribeiro

Barreto

et al. 2015

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

This paper proposes a wavelet-based power system stabilizer by using both the scaling coefficient energy and the wavelet coefficient energy with border distortions of a one-cycle sliding window. The boundary scaling coefficient energy is used for real-time extraction and compensation of electromechanical oscillations in the synchronous generator, whereas the boundary wavelet coefficient energy is used for the real-time detection of electrical oscillations and for tripping the wavelet-based power system stabilizer at the fault inception time. The performance of the proposed wavelet-based power system stabilizer was assessed in an experimental power system laboratory setup and compared with a conventional power system stabilizer.Index Terms-Wavelet transform, synchronous generator, power system stabilizer, electromechanical oscillations, electrical oscillations.

show abstract

“…It was first proposed by Specht in 1989 [11][12]. Based on the statistical theory it equals to the well-known Bayesian strategy in classification.…”

Section: B Probabilistic Neural Networkmentioning

confidence: 99%

The transformer fault diagnosis combing KPCA with PNN

Dai

Liu

Cui

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The probabilistic neural network (PNN) can detect the complex relationships and be used to develop its basis for the interpretation of dissolved gas-in-oil data that can identify the fault types. An efficient algorithm known as the kernel principle component analysis (KPCA) is applied to increase features in order to get higher detection accuracy. KPCA reflects the nonlinear or high order features that permit to represent and classify the varying states. More features can be obtained by the nonlinear transformation of KPCA, which can realize the biggest between-class margin of the classifiers. In this paper, we apply the method of combining KPCA with PNN in transformer fault diagnosis. The method has more superior performance than traditional PNN alone method. The property of the nonlinear extension of original data of KPCA can obtain the higher diagnosis accuracy, which can achieve better classification and diagnosis.

show abstract

Recognition of Fault Transients Using a Probabilistic Neural-Network Classifier

Cited by 66 publications

References 32 publications

Discriminati on between external short circuit and internal winding fault in power transformer using discrete wavelet transform and back-propagation neural network

Discriminati on between external short circuit and internal winding fault in power transformer using discrete wavelet transform and back-propagation neural network

Wavelet-Based Power System Stabilizer

The transformer fault diagnosis combing KPCA with PNN

Contact Info

Product

Resources

About