Diagnosis and identification of transformer faults from frequency response data

Birlasekaran, S.; Xingzhou, Yu; Fetherstone, F.; Abell, R.; Middleton, Richard H.

doi:10.1109/pesw.2000.847706

Cited by 13 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The smart methods such as neural networks, genetic algorithm, and fuzzy logic are employed for this purpose [26][27][28][29]. Among these methods, artificial neural networks due to the simplicity of its application have been used widely in the literature [15,16,[27][28][29].…”

Section: Algorithms Based On Artificial Intelligence Methodsmentioning

confidence: 99%

“…Employing back‐propagation neural network training, the different types of transformer faults (such as inter‐turn faults and short circuiting the winding to ground at the top, middle, and bottom ends of it) have been classified in . With the use of probabilistic neural network (PNN) method through dissolved gas analysis, different types of electrical faults in transformer are classified .…”

Section: The Transformer Transfer Function Evaluation Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

A probabilistic neural network classifier-based method for transformer winding fault identification through its transfer function measurement

Bigdeli

Vakilian

Rahimpour³

2011

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

SUMMARY In this paper, a new method is introduced for identification of transformer winding fault through transfer function analysis. For this analysis, vector fitting and probabilistic neural network are used. The results of transfer functions estimation through vector fitting are employed for training of neural network, and consequently, probabilistic neural network is used for classification of faults. The required data for fault type identification are obtained by measurements on two groups of transformers (one is a classic 20 kV transformer, and the other is a model transformer) under intact condition and under different fault conditions (axial displacement, radial deformation, disc space variation, and short circuit of winding). Comparing the results of this new method with the well‐known published work in the literature, the superior capabilities of this proposed method are demonstrated. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

Section: Algorithms Based On Artificial Intelligence Methodsmentioning

confidence: 99%

Section: The Transformer Transfer Function Evaluation Algorithmsmentioning

confidence: 99%

A probabilistic neural network classifier-based method for transformer winding fault identification through its transfer function measurement

Bigdeli

Vakilian

Rahimpour³

2011

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

show abstract

“…En estas propuestas la respuesta en frecuencia medida se modela como una función racional con coeficientes reales. En [21] la función racional se resuelve a través de invfreqs. En [22] el problema de encontrar los coeficientes de los polinomios se resuelve a través de invfreqs y un algoritmo no iterativo de identificación basado en subespacios.…”

Section: B Comparación a Través De Modelos Equivalentesunclassified

“…Sin embargo, no se ha realizado un análisis de sensibilidad a las fallas de estos parámetros. [17], [21], [31]. Las ANN propuestas hasta ahora permiten la identificación del estado en falla o no falla, pero no identifican el tipo de falla.…”

Section: B Comparación a Través De Modelos Equivalentesunclassified

“…De manera similar, en [31] el CC se calcula para los mismos rangos de frecuencia y para el rango total de frecuencia. En [21] se entrenan varias redes usando como entradas la información de polos, ceros, y el factor de amortiguamiento. La salida de las redes es 0 indicando que no existe falla ó 1, indicando que existe falla.…”

Section: B Comparación a Través De Modelos Equivalentesunclassified

See 1 more Smart Citation

Review of Sweep Frequency Response Analysis -SFRA for Assessment Winding Displacements and Deformation in Power Transformers

Secue¹,

Mombello²

2007

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

Resumen-El análisis de la respuesta en frecuencia por el método de barrido frecuencial SFRA (Sweep Frequency Response Analysis) es una técnica de diagnóstico para detectar deformaciones y desplazamientos (entre otras fallas eléctricas y mecánicas) de devanados de transformadores de distribución y de potencia. El SFRA como técnica de diagnóstico debe integrar las mediciones off-line y la interpretación de los registros para dar una valoración adecuada de la condición de los devanados. Sin embargo, no existe una guía de medición SFRA y tampoco una metodología para la interpretación de los registros, la cual usualmente es realizada por expertos. En este trabajo se presenta una revisión de las variantes encontradas en cuanto a la metrología SFRA e interpretación de los registros.Palabras clave-Transformador, análisis de la respuesta en frecuencia, desplazamiento de devanados, deformación de devanados.

show abstract

Asset Management of Power Apparatus

Birlasekaran

Ledwich

Engineering Asset Management

View full text Add to dashboard Cite

Diagnosis and identification of transformer faults from frequency response data

Cited by 13 publications

References 4 publications

A probabilistic neural network classifier-based method for transformer winding fault identification through its transfer function measurement

A probabilistic neural network classifier-based method for transformer winding fault identification through its transfer function measurement

Review of Sweep Frequency Response Analysis -SFRA for Assessment Winding Displacements and Deformation in Power Transformers

Asset Management of Power Apparatus

Contact Info

Product

Resources

About