Evaluation of statistical interpretation methods for frequency response analysis based winding fault detection of transformers

Wesley, Neoh-Khoo; Bhandari, Saurabh; Subramaniam, Aravinth; Bagheri, Mehdi; Panda, Sanjib Kumar

doi:10.1109/icset.2016.7811753

Cited by 11 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Step3. Iterative update: generate the initial solution randomly, and update the next position of best seagull according to (12).…”

Section: B Attackingmentioning

confidence: 99%

“…The FRA is a comparative method that relies on the accurate interpretation of the deviation of FRA traces caused by faults. To interpret the FRA results, various methods, such as the numerical index method [12], [13], electrical circuit model method [13], [14], and digital image processing method [15] have been proposed. However, since the structure of the transformer and the FRA results are completely complex, it is very hard to use these methods to recognize the fault degrees and types of the winding.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosing Fault Types and Degrees of Transformer Winding Combining FRA Method With SOA-KELM

Wang,

Qiu,

Xie

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Power transformers are the vital and expensive components of the power system. Timely identifying and diagnosing the transformer faults is critical to maintaining the stability of the power grid. As a sensitive and economical tool, the frequency response analysis (FRA) method has been widely employed to detect winding faults. However, it is still a challenge to accurately identify the fault types and degrees only by the FRA method. In this article, a new diagnosis method that combines the FRA method with a kernelbased extreme learning machine (KELM) optimized by a seagull optimization algorithm (SOA), is proposed to diagnose the fault types and degrees of the winding. First, a series of FRA tests are performed on a laboratory winding model under three different faults to obtain the FRA dataset. Furthermore, various numerical indices are applied to extract the characteristics of FRA signatures to train the SOA-KELM model. Then, the trained SOA-KELM model is utilized to classify fault types and degrees of the winding. Finally, the feasibility and superiority of SOA-KELM are verified by comparing with SOA optimized support vector machine (SOA-SVM) and random forest (SOA-RF), particle swarm optimization (PSO) algorithm optimized KELM (PSO-KELM), PSO-SVM, PSO-RF, SVM, RF, and KELM from the aspects of diagnosis accuracy and running time. The comprehensive comparison results show that SOA-KELM has the best diagnosis performance.

show abstract

“…Step3. Iterative update: generate the initial solution randomly, and update the next position of best seagull according to (12).…”

Section: B Attackingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Diagnosing Fault Types and Degrees of Transformer Winding Combining FRA Method With SOA-KELM

Wang,

Qiu,

Xie

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Several studies like [24][25][26][27][28] have been conducted to interpret the frequency response analysis (FRA) results of transformers using statistical and numerical indices. Under normal and healthy conditions, the FRA characteristic, called a transformer's fingerprint, is needed to use this method.…”

Section: Statistical Indicesmentioning

confidence: 99%

Diagnosis of Moisture Content in Oil-Paper Bushings Using Statistical Indicators Based on Frequency Domain Spectroscopy

Ansari

Vahedi

Khlyupin

et al. 2021

Electromechanics and Robotics

View full text Add to dashboard Cite

Condenser bushings are considered the Achilles' heel of power transformers because most of the explosions of transformers relate to their bushings' failure. Typical bushings monitoring methods measure the tan delta, power factor, and bushings' capacitance in line frequency. In contrast, the dielectric frequency response (DFR) or the frequency domain spectroscopy (FDS) measures these parameters over a wide frequency range. Some studies have revealed that the FDS curves have distinguished data that help detect bushing failures in their onset. However, there has not been a standard FDS interpretation method. Human experts' opinions play a considerable role in the interpretation process. In this paper, a finite element method model of a 96 kV oil-impregnated paper bushing is built with different OIP moisture content. The FDS test is simulated under these moisture levels. Seven twoarray and six one-array statistical indices are introduced to interpret the FDS results. The results have shown that all six one-array statistical indices, apart from average deviation (AVEDEV) and standard deviation (SD), can be perfect indicators of moisture levels of the OIP. Moreover, they can be used to assess the moisture content of the OIP bushings, and human errors are eliminated using this method.

show abstract

“…La medición puede ser realizada con 3 métodos diferentes: IFRA (Impulse Frequency Response Analysis) se inyecta un impulso de tensión a los devanados [20] [30]. Además se destacan otros artículos que siguen contribuyendo en la evolución del método [31][32][33][34][35][36][37]. En Colombia también se han realizado publicaciones relacionadas con esta temática [38][39][40][41].…”

Section: Análisis De Respuesta En Frecuencia (Fra)unclassified

Técnicas para el diagnóstico de transformadores de potencia: Una revisión crítica

Henao

Fernández

Gómez

2020

Ingeniare. Rev. chil. ing.

View full text Add to dashboard Cite

Los sistemas de transmisión de energía eléctrica comprenden un enlace fundamental en el sector productivo y social de un país. Uno de los principales componentes de estos sistemas son los transformadores de potencia que permiten la exportación de energía en alta tensión a grandes distancias. La falla de un transformador de potencia puede conllevar el colapso parcial o total de un sistema eléctrico. Existen diversas técnicas para el mantenimiento y diagnóstico de dichos equipos. En este trabajo se realiza una revisión crítica de ocho de las principales técnicas de diagnóstico de transformadores de potencia incluyendo una descripción básica y evolución histórica, teniendo en cuenta que actualmente son aplicadas en línea o que tienen un alto potencial para llegar a serlo. Palabras clave: Técnicas de diagnóstico en línea, monitoreo, transformadores de potencia, revisión crítica.

show abstract

Evaluation of statistical interpretation methods for frequency response analysis based winding fault detection of transformers

Cited by 11 publications

References 19 publications

Diagnosing Fault Types and Degrees of Transformer Winding Combining FRA Method With SOA-KELM

Diagnosing Fault Types and Degrees of Transformer Winding Combining FRA Method With SOA-KELM

Diagnosis of Moisture Content in Oil-Paper Bushings Using Statistical Indicators Based on Frequency Domain Spectroscopy

Técnicas para el diagnóstico de transformadores de potencia: Una revisión crítica

Contact Info

Product

Resources

About