![](bg1.png)
NEURAL NETWORKS APPLICATION TO FAULT DETECTION
IN ELECTRICAL SUBSTATIONS
Luiz Biondi Neto, Pedro Henrique Gouvêa Coelho
Electronics and Telecommunications Department, State University of Rio de Janeiro - UERJ
Rua São Francisco Xavier, nº 524, Bl. A, Sala 5036, Maracanã, 20550-013, Rio de Janeiro, RJ, Brazil
Alexandre Mendonça Lopes, Marcelo Nestor da Silva
AMPLA Energia e Serviços S.A., Praça Leoni Ramos, nº 1, São Domingos, Niterói, RJ, Brazil
David Targueta
Pro-Energy Engenharia LTDA, Rua cinco de Julho nº322, sala 902, Icaraí, Niterói, RJ, Brazil
Keywords: Fault detection in substations, Alarm Processing, Neural Networks, Decision Making Support.
Abstract: This paper proposes an application of neural networks to fault detection in electrical substations, particularly
to the Parada Angélica Electrical Substation, part of the AMPLA Energy System provider in Rio de Janeiro,
Brazil. For research purposes, that substation was modeled in a bay oriented fashion instead of component
oriented. Moreover, the modeling process assumed a substation division in five sectors or set of bays
comprising components and protection equipments. These five sectors are: 11 feed bays, 2 capacitor bank
bays, 2 general/secundary bays, 2 line bays and 2 backward bays. Electrical power engineer experts mapped
291 faults into 134 alarms. The employed neural networks, also bay oriented, were trained using the
Levenberg-Marquardt method, and the AMPLA experts validated training patterns, for each bay. The test
patterns were directly obtained from the SCADA (Supervisory Control And Data Acquisition) digital
system signal, suitably decoded were supplied by AMPLA engineers. The resulting maximum percentage
error obtained by the fault detection neural networks was within 1.5 % which indicates the success of the
used neural networks to the fault detection problem. It should be stressed that the human experts should be
the only ones responsible for the decision task and for returning the substation safely into normal operation
after a fault occurrence. The role of the neural networks fault detectors are to support the decision making
task done by the experts.
1 INTRODUCTION
Electrical substations evolved rapidly in time not
only in their conception but also in their protection
equipment that are now fully electronic instead of
electromechanical, in the digital substation age. The
Standard IEC (International Electromechanical
Commission) 61850 and the possibility of using high
speed and reliable Ethernet LAN networks brought
new developments to the area. Such developments
include sharing information among several IEDs
(Intelligent Electronic Devices) as well as the
capability of providing these information to several
Electrical Energy Companies users or industrial
heavy consumers (Cascaes et alli., 2007) As a
natural consequence, the current supervision,
automation, and control systems are gradually being
adapted to that new reality that is present in the
Brazilian electrical sector. Nowadays, the main
facility to aid the operator in the supervision system
system comprised by multiple alarms having the
purpose of making the operator aware of the
problems that is afflicting the electrical sector
(Chan, 1990). The operator must detect the fault
based on the set of fired alarms and proceed to the
corrective action towards a quick recover of the
system and to normal operation conditions. So all
the responsibility to return the system to normal
operation lies on the shoulders of the operator which
can suffer a lot of stress and pressure. Due to
484
Biondi Neto L., Henrique Gouvêa Coelho P., Mendonça Lopes A., Nestor da Silva M. and Targueta D. (2008).
NEURAL NETWORKS APPLICATION TO FAULT DETECTION IN ELECTRICAL SUBSTATIONS.
In Proceedings of the Tenth International Conference on Enterprise Information Systems - AIDSS, pages 484-487
DOI: 10.5220/0001697204840487
Copyright
c
SciTePress