DIAGNOSIS OF INTER TURNS FAULT OF INDUCTION MOTOR?

docx
1 | P a g e
A
Seminar Report
On
DIAGNOSIS OF INTER TURNS FAULT OF INDUCTION
MOTOR

Submitted in partial fulfillment of
The requirements for the degree of
Bachelor of Engineering
In Electrical (Electronics &Power)

of
Submitted by
[Electrical Engineering Department]
2 | P a g e
Acknowledgement
The real spirit of achieving a goal is through the way of excellence and lustrous discipline
. I would have never succeeded in completing my task without the cooperation, encouragement a
nd help provided to me by various personalities.
I would like to take this opportunity to express my heartfelt thanks to my guide, Mr.P. R.
Bharambe sir for his esteemed guidance and encouragement, especially through difficult times.
His suggestions
oaden my vision and guided me to succeed in this work. I am also very gratefu
l for his guidance and comments while studying part of my seminar and learnt many things unde
his leadership.
I extend my thanks to Prof. R. S. Pote, Head of Electrical Engineerimg. Department, Shri
Sant Gajanan Maharaj College of Engineering, Shegaon for their valuable support that made me
consistent performer.
I also extend my thanks to Dr. S. B. Somani, Principal, Shri Sant Gajanan Maharaj Colleg
e of Engineering, Shegaon for their valuable support.
Also I would like to thanks to all teaching and non-teaching staff of the department for th
eir encouragement, cooperation and help. My greatest thanks are to all who wished me success e
specially my parents, my friends whose support and care makes me stay on earth.
Place: SSGMCE, Shegaon Mr. Shivcharan S. Aware

3 | P a g e
Contents

1. Abstract
2. Introduction
3. Causes
4. Various Methods Of Diagnosis
A) Negative sequence cu
ent method
B) Signal Processing Techniques
i. Frequency Analysis
ii. Park's Transformation
iii. Wavelet Transformation
C) Artificial Neural Techniques
5. Conclusion
6. References.


4 | P a g e
1. Abstract:
Induction motor plays a pivotal role in industry and there is a strong demand for their reliable
and safe operation. They are generally reliable but eventually do wear out. failures of Induction
motor can lead to excessive downtimes, hence it is important to detect fault in induction moto
.This seminar surveys the cu
ent trends in on-line fault detection and diagnosis of induction m
otor.
Motor line cu
ent has been analyzed using modern signal processing and data re
duction tool combing Park’s Transformation and Discrete Wavelet Transform (DWT). Feed Fo
ward Artificial Neural (FFANN) based data classification tool is used for fault characterization
ased on DWT features extracted from Park’s Cu
ent Vector Pattern
.
2. Introduction:

Electric motors are the critical components of many industrial processes and are frequently integrate
d in commercially available equipment and industrial processes. Squi
el cage induction motors have
a dominant over the other motors due to their low cost, ruggedness, low maintenance and operation
with easily available power supply. Motor faces various stresses during operating conditions and thes
e stresses may lead to several failures. Stator inter turn fault is the most common type of fault in elect
ic motor. If these faults are undetected, it may lead to motor failure. Hence it becomes necessary for
induction motor to detect any fault in early stage in order to avoid disastrous failures.
Several schemes for detecting inter turn faults are proposed. Some of the reported te
chniques necessitates mathematical model of the system. the models have been successfully used to s
tudy the transient and steady state behaviour of induction motor with short circuited turns. Number of
techniques uses frequency spectrum of line cu
ents to detect inter turn faults . Fourier transform is n
ot appropriate to analyze a signal that has transient characteristics such as drift, a
upt changes and f
equency trends. An induction motor fault diagnosis using stator cu
ent envelopes for
oken rotor ba
s and inter turn short circuit in stator winding have been proposed . A wavelet packet for extracting
useful information from vi
ation signals has been employed. Inter turn fault detection based on mea
suring the neutral voltage is proposed , but it is limited to star connected machines with an accessible
neutral.
Wavelet techniques for fault monitoring and diagnosis of induction motor are incre
asing because these techniques allow performing stator cu
ent signal analysis during transients. Wav
elet transform can be used for a localized analysis in time-frequency or time- scale domain. It is thus
a powerful tool for fault diagnosis.
In this ANN based approach is been proposed and found to be an effective alte
native for detecting inter turn fault in induction motor. Artificial Immune system has abilities of learn
ing memory and self adaptive control. In addition ANN can perform continuous nonlinear functions
online through the use of inexpensive monitoring devices. Main problems facing the use of ANN are
the selection of best inputs and choice of ANN parameters so as to make the structure compact to cre
ate highly accurate networks. Many input features require a...