Page 1 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 04
April 2019
Available online: https://ejbss.org/ P a g e | 1998
A Fuzzy C- Means Clustering Algorithm for
Discrimination of Fault & Inrush Current in Power
Transformer
SAMANIDEESWARI.P
M.Tech – Power System Engineering,
PRIST Deemed University, Madurai, Tamilnadu
Abstract - However, the identification of the faulted location by
the traditional method is not always an easy task due to the
variability of gas data and operational natures. Incipient fault
detection in transformers can provide early warning of electrical
failure and could prevent catastrophic losses. To develop
transformer incipient fault detection technique, a transformer
model to simulate internal incipient faults is required. By
Improving high Performance the proposed new Algorithm is
Fuzzy C-Means Clustering for Identification of Inrush & Fault
current in the Power Transformer. This approach has the
advantages of high accuracy. The other advantage is that the
model is practically applicable and may be utilized for an
automated power transformer diagnosis. The test results indicate
that the developed preprocessing approach can significantly
improve the diagnosis accuracies for power transformer fault
classification. The algorithm is evaluated using simulation
performed with MATLAB.
Key Words: Fault Current , Inrush current, C- Means Clustering
I.INTRODUCTION
Large power transformers are probably the most
important equipment in an electrical system. Correct diagnosis
of their incipient faults is vital for safety and reliability of an
electrical network. An in-service transformer is subject to
electrical and thermal stresses, which can break down the
insulating materials and release gaseous decomposition products.
Overheating ,partial discharge and arcing are three primary
causes of fault related gases. There are many interpretative
methods based on DGA to diagnose the nature of transformer
deterioration. Stability and reliability of a power system in
depend upon the condition of power transformers. Essential
devices as power transformers are in a transmission and
distribution system. The wide varieties of electrical and thermal
stresses often age the transformers and subject them to incipient
faults. Being one of the most expensive and important elements,
a power transformers a highly essential element, whose failures
and damage may cause the outage of a power system. If an
incipient failure of a transformer is detected before it leads to a
catastrophic failure, predictive maintenance can be deployed to
minimize the risk of failures and further prevent loss of services.
To monitor the serviceability of power transformers, many
devices have evolved, such as Buchholz relays or differential
relays. But the main short coming of these devices is that they
only respond to the sever e power failures which require removal
of equipment from the service. Thus, techniques for early
detection of the faults would be very valuable to avoid outages
.In industrial practice, dissolved gas analysis (DGA) is a very
efficient tool for such purposes since it can warn about an
impending problem, provide an early diagnosis, and ensure
transformers maximum up time. To find out the incipient faults,
DGA is a prevailing method with periodically samples which
test the insulation oil of transformers to obtain the composition
of the gases dissolved in the oil due to the breakdown of the
insulating materials inside. Diverse diagnostic criteria were
developed for identification of the possible fault types by Rogers
ratios method and Doernenburg ratios method
This may improve and computerize transformer fault diagnosis.
By Improving high Performance the proposed new
Algorithm is Fuzzy C-Means Clustering for Identification of
Inrush & Fault current in the Power Transformer. This approach
Page 2 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 04
April 2019
Available online: https://ejbss.org/ P a g e | 1999
has the advantages of high accuracy. The other advantage is that
the model is practically applicable and may be utilized for an
automated power transformer diagnosis. The test results indicate
that the developed preprocessing approach can significantly
improve the diagnosis accuracies for power transformer fault
classification. The algorithm is evaluated using simulation
performed with MATLAB
II.POWER TRANSFORMER FAILURES
Damages to the power transformer can be caused by
different stresses, which are due to overheating, open circuits
and short circuits. The major focus of power transformer
protection is short circuits because open circuits do not present a
particular hazard. Short circuit protection includes internal and
external faults.
External faults occur outside the protection zone of the
transformer and include:
over voltage
Overloads
under frequency
Internal faults occur within the transformer protection zone. The
internal faults can be divided into two groups:
1. Incipient faults develop slowly and may develop into major
faults such as phase-to-ground faults or three phase faults if the
cause is not detected and corrected. Incipient faults can be
divided into three groups:
Overheating
Over fluxing
Overpressure
2. Active faults – caused by the breakdown in insulation which
creates a sudden stress. The active fault occurs when the current
flows from one phase conductor to another such as phase-to- phase and phase-to-ground. These faults may occur suddenly
and they require fast action by protective relays. Active faults:
Turn-to-turn short circuits.
Phase-to-phase short circuits.
Phase-to-ground short circuits.
Tank faults.
Core faults.
III.MAGNETIC INRUSH CONDITION
For the purposes of the discussion, inrush current is
described as the magnitude of instantaneous current drawn by a
line-frequency power transformer at the time the core is
energized; it’s of short duration, often milliseconds .Under a
combination of certain conditions, inrush current can be
measured at many times the rated load current. High inrush
current is a time-dependent phenomenon caused by a
coincidental set of circumstances that must occur simultaneously
at the moment of switch ON. Inrush current is a problem,
because it interferes with the operation of circuits as they have
been designed to function. In a digital world, there is a zero
tolerance for power interruptions. Some effects of high inrush
include nuisance fuse or breaker interruptions, as well as arcing
and failure of primary circuit components, such as switches.
High inrush currents also necessitate over sizing of fuses or
breakers, which complicates other aspects of approvals testing
and may compromise protection on other vital components.
Another side effect of high inrush is the injection of noise and
distortion back into the mains.
Fig-1 Graphical description of the inrush current phenomena
IV.PHYSICAL PROPERTIES OF INRUSH
Transformer inrush currents are drawn by the high
saturation of the iron core during the switching-in of the
transformer. Fig-1 illustrates a graphical description of the
inrush current phenomenon, while Fig.- 2shows that remanence
flux in the core at the moment of switch on increases inrush
current. Flux is generated as the results of applied voltage; it is
then cross-plotted with Φ-I characteristics to show the inrush
current magnitude. This practice is shown for two cases: with
Page 3 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 04
April 2019
Available online: https://ejbss.org/ P a g e | 2000
and without resistance. The driving force of the inrush currents
is the voltage applied to the primary of the transformer. This
voltage forces the flux to build up to a maximum theoretical
value of double the steady-state flux plus remanence. Therefore,
the transformer is saturated and draws a large amount of current.
Since the current is of short duration, no adverse effects occur to
the transformer. However, the protective devices for overloads
may falsely operate and disconnect the transformer.
Fig- 2 Graphical description of inrush current phenomenon
including permanence.
V.DIAGNOSIS OF INCIPIENT FAULT
Importance of power transformer incipient fault diagnosis
Power transformers are major power system
equipment. Their reliability not only affects the electric energy
availability of the supplied area, but also affects the economical
operation of a utility. For example, the fault of a distribution
transformer may leave thousands of homes without heat and
light, and the fault of a step-up transformer in a power
generation plant may cause the shutdown of the attached
generation unit. Under the deregulation policy of electric
systems, each utility is trying to cut its cost, and the prevention
of accidental loss is much more important than before. The
capital loss of an accidental power transformer outage is often
counted in million dollars for output loss only, not to say the
costs associated with equipment repair or replacement. Because
of this economic incentive, preventive tests and on-line
monitoring are of benefit to predict incipient fault conditions,
and to schedule outage, maintenance and retirement of the
transformers.
Methodology of incipient fault diagnosis
The major concern of power transformer incipient
faults is that they may decrease the electrical and mechanical
integrity of the insulation system. This may progress to a point
that the insulation cannot withstand transient overstresses caused
by through-fault current (mechanical forces on windings) and
electrical over voltages (temporary, switching or lightning).
Incipient fault diagnosis is therefore closely related to insulation
condition assessment.
Insulation condition assessment test
Insulation condition assessment test refers mainly to
off-line routine tests, including measurement of insulation
resistance (IR), dielectric loss factor (DLF), interfacial
polarization(IP) using anomalous IR and frequency dispersion of
capacitance, turns ratio (TR), winding resistance (WR), core
ground resistance (CGR), and some excitation tests. These tests
are applied to the whole transformer and thus are bulk
measurements of the insulation condition. They can reveal some
severe problems but may not find the incipient ones. Other tests
examine paper or pressboard samples taken from transformers
(and which must be replaced if the transformer is to be returned
to service). These tests include measurement of the degree of
polymerization (DP) and tensile strength (TS). Some relatively
new methods, such as high performance liquid chromatography
(HPLC) furan analysis, interfacial polarization spectra (IPS)
using return voltage (RV) measurement, and analytical chemical
techniques , are also used for the same purpose. These intrusive
techniques are usually not favorable because the sampling
process may damage the integrity of the insulation system, but
may be necessary for very old transformers. The most favorable
tests for power transformer insulation assessment are on-line
types, including partial discharge (PD) monitoring and dissolved
gas-in-oil analysis (DGA). These online tests are also the major
incipient fault diagnosis methods.
Dissolved gas-in-oil analysis (DGA)
A more successful technique for on-line incipient fault
diagnosis is dissolved gas-in-oil analysis (DGA). By “on-line”
we mean the transformer does not need to be de-energized. This
type of analysis includes the conventional DGA, which is based
on routine oil sampling, and the modern technology of on-line
gas monitors. Conventional DGA has been in practice for about
thirty years, and has gained tremendous success compared to
other techniques. The main reason for this success is that the
sampling and analyzing procedures are simple and inexpensive,
and easy to be standardized. Many experiences have been gained
from the process and several DGA standards have been set up.
