Vol.:(0123456789) 1 3
Journal of Control, Automation and Electrical Systems
https://doi.org/10.1007/s40313-019-00487-6
A General Methodology for Evaluation and Classifcation
of Oil‑Immersed Power Transformers: Application to Electrical
and Physicochemical Parameters
Leonardo da Cunha Brito
1
· André Pereira Marques
2,3
· Cacilda de Jesus Ribeiro
1
· Nicolas Kemerich de Moura
1
·
Yuri Andrade Dias
1
· Cláudio Henrique Bezerra Azevedo
2
· José Augusto Lopes dos Santos
2
·
Pedro Henrique da Silva Palhares
1
Received: 16 April 2018 / Revised: 6 April 2019 / Accepted: 8 June 2019
© Brazilian Society for Automatics--SBA 2019
Abstract
Condition monitoring of power transformers is of vital importance to prevent electricity supply stoppages and reduce power
plant maintenance costs. To that end, the use of techniques to evaluate and classify the condition of these devices is highly
recommended in order to obtain good quality information for their proper maintenance planning. This article presents and
details a general methodology for the creation of methods to evaluate and classify these devices, by means of computational
modeling and optimization. The results indicate a higher than 93% accuracy rate compared to that of numerical evaluations
and symbolic classifcations expected by experts, thus demonstrating the applicability of the proposed methodology, which
is found to be superior in comparisons against Computational Intelligence and Statistical Learning methods.
Keywords Classifcation · Evaluation · Methodology · Diagnostic · Power transformers
1 Introduction
The development and use of predictive techniques aimed
at increasing the efciency of preventive maintenance pro-
cesses are essential to preserve the service life of power
transformers, which are vital and high-cost devices in the
power transmission and distribution system (Marques et al.
2014; Jahromi et al. 2009). Obviously, the same concept
applies to the other elements that make up electric power
supply systems.
Typically, a wide range of methods can be applied to eval-
uate the condition of power transformers. These methods
usually include, among others:
• Dissolved gas analysis of transformer insulating oil,
which reveals the existence of incipient thermal or elec-
trical faults in the transformer (Duval and Lamarre 2014;
IEC 2007; Singh and Bandyopadhyay 2010);
• Physicochemical analysis, which allows one to identify
the degradation level of transformer insulating oil and
infers that of electrical insulation paper (Barbosa et al.
2012; Moulai et al. 2010);
• Detection of partial discharges in power transformers
by means of acoustic emission, which can indicate the
* Nicolas Kemerich de Moura
nicolas.nk@gmail.com
Leonardo da Cunha Brito
leonardo_brito@ufg.br
André Pereira Marques
andre.marques@enel.com.br
Cacilda de Jesus Ribeiro
cacildaribeiro@gmail.com
Yuri Andrade Dias
yuriadias@gmail.com
Cláudio Henrique Bezerra Azevedo
claudio.hb@celg.com.br
José Augusto Lopes dos Santos
jose.augusto@celg.com.br
Pedro Henrique da Silva Palhares
phpalhares@gmail.com
1
School of Electrical, Mechanical and Computer Engineering,
Federal University of Goiás, Goiânia, GO, Brazil
2
Enel Distribuição Goiás, Goiânia, GO, Brazil
3
Federal Institute of Education, Science and Technology
of Goiás, Goiânia, GO, Brazil