2. Content
a) What is Condition Monitoring??
b) Faults in Induction Motor
c) Fault Detection Techniques
d) Motor Current Signature Analysis
e) Process of detection of fault
f) Artificial Neural Network
3. What is Condition Monitoring??
Condition monitoring is a technique or process of
observing the operating characteristics of machine in
such a way that any change in the trend of target
parameters could be used to predict the need for
maintenance before any serious deterioration occurs.
Condition monitoring implies the continuous
evaluation of the health of equipments.
4. Condition monitoring plays a vital role for fault
detection in induction motor.
The induction motors are most widely used motors in
industrial, commercial and residential sectors because
of enormous merits of these over other types of
available electrical motors.
These motors work under various operating stresses,
which deteriorate their motor conditions giving rise to
faults.
5. FAULTS IN INDUCTION MOTOR
Bearing Fault
40%
Stator Fault
30%
Broken Rotor
Bar
10%
Other
Fault
20%
6. Cause of Fault in Induction Motor
Mechanical stress
Frequent starts of the motor at rated voltage
Misalignment of bearings
Due to failure of insulation of the stator winding.
Over Voltage, Under Voltage, Overload
7. NECESSITY OF FAULT DIAGNOSTIC
To increase reliability
to decrease the possibility of production loss due to
machine breakdown.
To extend the motor life time.
9. MOTOR CURRENT
SIGNATURE ANLYSIS
MCSA tests are performed online without interrupting
production with motor running under the load at
normal operating conditions.
MCSA is monitoring stator current of the motor.
Motor stator windings are used as transducer in
MCSA, picking the signals (induced currents) from the
rotor (but also revealing information about the state of
the stator).
10. Process of detection of fault
Whenever a fault occurs in a three-phase induction
motor, it is mostly due to broken rotor bars, air-gap
eccentricity and stator windings short circuits. As a
result of these faults, various magnetic flux
components are produced in the magnetic circuit of
the induction motor. This gives rise to harmonic
components in the line current of the stator, which is
detectable by current transducers and spectrum
analysers.
13. Process of detection of fault
When a fault is present, the frequency spectrum of the
line current becomes different from healthy motor.
By comparing the faulty spectrum with the healthy
spectrum the detection of various faults can be
identified.
15. ARTIFICIAL NEURAL NETWORK
The ANN represents information-processing systems
formed by interconnecting simple-processing units
called neurons.
16. This system consists of detection and the location of a
fault on the stator windings of a three phase induction
motor by using the Neural Networks .
The number of input nodes and the number of output
nodes are determined by the number of patterns to be
identified.
17. Prediction With Neural Network
It involves two steps:-Training and Learning
Different faults have different characteristics in their
fault patterns, which gives rise to unique current
signature patterns.
19. Future Objective
Determination of stator fault , broken rotor bar of
induction motor using motor current signature
analysis and ANN.
20. Reference
N Mehala and R. Dahiya, Motor Current Signature
Analysis and its Applications in Induction Motor Fault
Diagnosis, International Journal of Systems
Applications, Engineering & Development Volume 2
W T Thomson: “On-Line MCSA to Diagnose Shorted
Turns in Low Voltage Stator Windings of 3-Phase
Induction Motors Prior to Failure”, IEEE, PES&IAS
IEMDC, MIT,Boston.
S. Rajakarunakaran, et al., “Artificial Neural Network
for Fault Detection in Rotary System “.