Application of fuzzy support vector machine for determining the health index of the insulation system of in-service power transformers

Abstract

With the integration of data and information obtained from a variety of chemical and electrical tests on transformer insulating oil, it is possible to evaluate the health condition of the insulation system of an in-service power transformer. This paper develops an intelligent algorithm for automatically processing the data collected from oil tests and determining a health index for the transformer insulation system. This intelligent algorithm adopts a fuzzy support vector machine (FSVM) approach, which constructs a statistical model using a training database based on the historic data collected from 181 in-service power transformers. The procedure of constructing the training database, the formulation and implementation of FSVM and the data preprocessing methods for dealing with a class imbalanced training database is presented in this paper. Numerical experiments are also conducted to evaluate the performance of the algorithms developed in the paper.

Individual failure rates for transformers within a population based on diagnostic measures

“…These two methods were compared and the results match with 96.7%, according to [12]. Both methods classified transformers 4,[11][12][13][14][15]19, and 23 as bad and recommended an immediate replacement. The comparison of the computed IFRs to the health indices in [12] shows that the results are plausible.…”

“…However, to set a clear threshold of a diagnostic measure to determine the condition is difficult because in practice there are overlaps of scores. To address this challenge, fuzzy methods have been applied to the calculation of the health index as an alternative approach [12][13][14][15]. Other approaches are Bayesian networks [16] or artificial neural networks [17].…”

Estimation of Transformers Health Index Based on the Markov Chain

“…The conventional concept of HI formulation is based on a scoring method that is based on weighting and ranking techniques [29][30][31]. There were also a number of advanced methods that had been proposed to determine the HI [32,33]. These techniques are quite complex and require extensive information to compute the HI.…”

Índice de Salud para Transformadores de Potencia Inmersos en Aceite Mineral con Voltajes entre 69kV y 230kV usando Lógica Difusa

“…En la literatura se han realizado pocos estudios para obtener el índice de salud para los transformadores (Abu Elanien et al, 2012;Ashkezari et al, 2012;Ashkezari et al, 2013;Naderian et al, 2009;Young et al, 2010), sin embargo, las metodologías descritas en la literatura para calcular el índice de salud todavía sufren algunas limitaciones. Por ejemplo, los índices de salud calculados podrían no ser compatibles, esto se debe a que la importancia y asignación de un factor de ponderación apropiado para cada prueba en el cálculo del índice de salud son de carácter subjetivo, es decir, son basados en la experiencia de los expertos de transformadores, que difiere de un experto a otro, igualmente sucede con la normatividad asociada (Ashkezari et al, 2012).…”

“…Este equipo es muy costoso y puede alcanzar hasta el 60% del total de la inversión de una subestación, además es fundamental para la operación de las redes de transmisión y distribución de energía eléctrica (Naderian et al, 2009). Por tanto, es necesario desarrollar técnicas fiables y eficaces para evaluar la condición del transformador y que faciliten la toma de decisiones que inciden en la operación y el mantenimiento del transformador (Ashkezari et al, 2013;Romero et al, 2012). Existen métodos para determinar el índice de salud, los cuales han sido propuestos para la evaluación del estado del transformador de potencia.…”