Journal of Software Engineering and Applications, 2013, 6, 526-532 Published Online October 2013 (
Intelligent System Design for Stator Windings Faults
Diagnosis: Suitable for Maintenance Work
Lane M. Rabelo Baccarini, Vinícius S. Avelar, Valceres Vieira R. E. Silva, Gleison F. V. Amaral
Department of Electrical Engineering, Federal University of São João del Rei, Praça Frei Orlando, Brasil.
Received June 3rd, 2013; revised July 4th, 2013; accepted July 12th, 2013
Copyright © 2013 Lane M. Rabelo Baccarini et al. This is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The short circuit is a severe fault that occurs in the stator windings. Therefore, it is very important to diagnose this type
of failure in its beginning before it causes unscheduled stop and the machine loss. In this context, the Support Vector
Machine (SVM) is a tool of considerable importance for standard classification. From some training data, it can diag-
nose whether or not there is a short circuit beginning, and which is important for predictive maintenance. This work
proposes a technique for early detection of a short circuit between the turns aiming at its implementation in a real plant.
The paper shows simulation and experimental results, and validates the proposed technique.
Keywords: Fault Diagnosis; Support Vector Machines; Maintenance Work; Software Tool; Winding Short-Circuit
1. Introduction
The induction machine is used in a wide variety of ap-
plications to convert electrical energy into mechanical
energy. There is no doubt that it is the most widely used
machine in industry due to its robustness and low cost.
However, the induction motors are very easy to be dam-
aged during their operations. In some industrial processes,
the induction motors are often installed in the hostile
environment that may easily lead to the deterioration [1].
The production technique evolution grows up as fast
as the productive capacity of industrial plants supported
by the equipment improvement. The equipment’s life
cycle requires high investments. Thus, the maintenance
and operation schedule need to be safe, efficient and en-
sure larger indexes of availability and security.
Recently, there are a lot of methods used to detect sta-
tor inter-turn short circuit in predictive maintenance.
Nevertheless, many of them are expensive, ineffective or
difficult to be implemented in real process. Another point
is the fact that many processes are in continuous activi-
ties or in aggressive environments; the motor requires
monitoring since it drives a non-stop machine. It depends
on a non-invasive way to detect faults, and no human is
exposed directly to the machine in working condition [2,
The induction machine stator windings are exposed to
stress by different causes: thermal effects; mechanical
vibrations; repetitive voltage pulses stresses under PWM
inverter drives. Research shows that stator faults are re-
sponsible for 36% of induction machine faults [4-6]. De-
terioration of the induction machine three-phase insula-
tion usually begins with short-circuit involving little
turns of one phase. Fault current is approximately twice
as high as the blocked rotor current. It causes local heat-
ing and quickly spreads to other winding sections [7-10].
A short circuit is recognized as one of the most diffi-
cult failures to be detected. Inter-turn short circuit faults
that occur on the stator, start with a few inter-turns until
reaching a more severe failure, such as phase-to-phase
faults and phase-to-ground faults. It is known that the
speed of the faults’ spread is fast, thereby justifying con-
tinuous motor monitoring to detect the short circuit [11].
Thomson and Fenger (2001) analyzed short circuit
between inter-turns of an induction machine in low volt-
age working conditions [12]. According to the authors,
even with a significant percentage of short-circuit (20%
of turns in short circuit), the engine worked for 20 min-
utes before complete breakdown. But researchers report
that the impact of failure on the characteristics of the
engine is small, which makes their detection difficult
A variety of sensors could be used to collect meas-
urement from the machine for the purpose of failure
monitoring. These sensors measure stator voltages and
currents, air-gap and external magnetic flux densities,
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work 527
rotor position and speed, output torque, internal and ex-
ternal temperature, vibrations [14]. Methods that use
voltage and current measurements offer several advan-
tages over test procedures that require machine to be
taken off line or techniques that require special sensors
coupled to the motor.
There are two main issues associated with the detec-
tion of induction machine faults. The first issue is the
induction motor modeling, due to the lack of comprehen-
sive field fault data-bases. The second issue is to develop
a completely faulty model in order to avoid the occur-
rence of false positives while diagnosing faults. Special
attention must be given to the net asymmetries and load
condition presence [13].
Some researchers have investigated the potentiality of
reading vibration signals to diagnose electrical faults
[15-17]. However, the techniques are invasive since they
depend on the signals measured and acquired by accel-
erometers, which placed at the equipment structures.
Moreover, the vibration analysis requires a specialist to
analyze the collected signals and provide the correct sys-
tem diagnosis and the techniques, which are ineffective
in diagnosing electrical faults.
The magnetic flux spectrum technique is also an inva-
sive method, once it studies the signals from sensors that
need to be installed inside the motor, thus increasing the
initial cost of the machine and making the system less ro-
bust [18]. The methods based on electrical current analy-
sis are not invasive and they do not require system inter-
ruption [2,3,7,19]. Measurement is made by common
sensors (Current Transformers) and often, they are al-
ready present in the application being monitored.
The fault causes impedance imbalance among the
three motor phases, resulting in the appearance of current
and impedance negative sequence components. However,
the unbalances of voltages supply are inherent sources
that have the same impact, i.e., it causes the appearance
of current and impedance negative sequence components,
which make it difficult to diagnose the failure.
In this context, the Support Vector Machine (SVMs)
has received great attention in the last years [2,20]. The
SVMs highlights are in its ability to generalize, and al-
low its use in diverse areas of knowledge. The technique
has not yet been well explored in the area of predictive
maintenance, thus, the detection and faults diagnosis in
induction machines still need more encouragement and
attention due to the lack of existing papers. The efforts to
find a new novel idea must be encouraged to give more
contributions to robust machine condition monitoring
and diagnosis [21].
This work aims to develop a diagnostic technique for
initial short-circuit between a few turns of the stator us-
ing SVMs features. The method requires only measure-
ment sensors normally presented in the application. First
we will present the simulations results for the technique
application and then it will be validated on a test bed.
The use of computational intelligence techniques re-
quires a set of significant data over faulty conditions for
system design, which precluded their use in a real plant.
It is therefore necessary to find alternatives to practical
systems implementation that requires real data especially
in the predictive maintenance area. The proposed tech-
nique has achieved this goal by making their practical
implementation possible. The following sections describe
the adopted procedures and their practical validation.
2. The SVM Design Using Computing
Simulation Data
This work first step was the design of support vector
machines using only the simulation data. The symmetric
and asymmetric machine model has been implemented
and current and voltage data were obtained from differ-
ent operating conditions. To make the model as close as
possible to the real plant the following conditions were
inserted: under or overload percentage, inherent unbal-
ance supply voltage, small percentage of short circuit
turns and noise in sensor’s measure.
2.1. Asymmetrical Induction Machine Model
The symmetrical machine model is well known in the
literature. The asymmetrical model that allows to analyze
the stator and power supply asymmetries was presented
in [5,13]. The shorted turn leakage inductance is as-
sumed to be ls
denotes the shorted turns
fraction. The voltage and flux linkage
of the stator and rotor windings are transformed to dq
axes, rotating at an arbitrary speed ddt
. The s
and r subscripts indicate the stator and rotor variables
respectively. The machine stator equations can be ex-
pressed in complex two-phase dq variables as follows:
qss qsdssf
vri ri
 
dss dsqssf
vri ri
  (2)
The parameters ,
and r
represent the fault re-
sistance, are the short circuit current and mechanical
speed. The equations for the rotor circuits are equal to
those corresponding to a healthy motor (Equations (3)
and (4)).
rqrr dr
  (3)
rdrr qr
  (4)
For the shorted turns (as2), the flux linkage equation is
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work
given by (5).
dcos sin
fs dsqsf
rir iii
 (5)
The differential equations derived above can be solved
by the fourth-order Runge-Kutta method. The stator and
rotor currents can be obtained from the following equa-
23 56
qs qsqrrmf
23 56
ds dsdrrmf
43 65
qrqr qss mf
43 65
drdr dss mf
27 87 8
cos sin
fasqsqr dsdr
56 78
1; ;;
aa aLa
 
 
The parameters
and are the stator and rotor
self inductances, ls and lr are the stator and rotor
leakage and m is the mutual inductance. The electro-
magnetic torque can be expressed in dq variables as:
3sin cos
22 2
mqsdrdsqrmf qrdr
TLiiiiLii i
 
The first member of this equation is equal to those
corresponding to a healthy motor and the second member
is the additional component introduced by the fault. The
Equations (1) to (11) computer implementations give the
fluxes, the speed and current of the motor in short-circuit
conditions. The components in dq axes (direct and quad-
rature) could be transformed to the abc phase axes. Noise
can be inserted in the current and voltage signals. The
current and voltage signals can be analyzed in time or
frequency domain using Fast Fourier Transform tool.
2.2. Induction Machine Model Simulations
Simulations of different squirrel cage induction machine
were carried out. The motor used here have the following
nominal parameters: 3 CV, 220 V, 60 Hz, 1710 rpm, 4
poles. It is the motor of the test bed. The equivalent cir-
cuit parameters were determined through a no-load test
and a blocked rotor test results. The machine equivalent
circuit parameters are: rs =1.81 , rr= 0.36 , Lls= 2.52
mH, Llr = 4 mH and Lm = 32.7 mH.
The machine symmetrical and the asymmetrical mod-
els were used to generate a database to train and validate
the SVM. For each condition, it was varied the load per-
centage, imbalance level inherent of the power condi-
tions and the percentage of the turns short-circuited. Ta-
ble 1 shows the simulations parameters variations, where
Tn and Vn are torque and voltage nominal values respec-
2.3. Simulations Results
The data were classified into two conditions:
Condition 1: Symmetrical operation, i.e., no short
circuit occurrence.
Condition 2: Inter-turn fault.
For the training process, the kernel parameter, the
Linear Function and the Radial Bases Function (RBF),
with variance within 0.001 to 1 were tested. The SVM
regularization parameters spanned from 1 to 100,000.
Possible combinations of these parameters were made
and the best results taken. The current and voltage fun-
damental and the third harmonic components were used.
The Support Vector Machines were trained in order to
get no failure condition to avoid the engine stop due to
false alarms.
Figure 1 shows the used methodology outline. The
decision making is responsible for diagnosing whether
the engine can continue to operate or if it is necessary to
interrupt service.
Figure 2 presents the current fundamental component
values in the R3 space. It can be noticed that the sampled
data are grouped and overlaid and thus, can not be line-
arly split.
Table 2 contains the number of simulated tests used
for network training and validation and Table 3 rein-
forces the SVM good performance for pattern classifica-
tion. The parameters used for SVM training and valida-
tion were the current fundamental and third harmonic
Table 1. Simulated system parameters variation database.
Parameter MinimumValue MaximumValue
Load 50% of Tn 100% of Tn
Source amplitude 95% of Vn 105% of Vn
Shorted turns percentageμ = 0 μ = 0.03
Figure 1. Decision making structure.
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work 529
Figure 2. Pattern distribution in R3 for the stator current
fundamental component—from Simulation.
Table 2. Number of simulations.
Training Validation
Condition 1 100 250
Condition 2 100 250
Table 3. Simulations results.
Training Validation
Condition 1 100 % 100 %
Condition 2 100 % 99.6 %
3. Implementation Using Experimental Data
The test rig, Figure 3, in the Electrical Engineering De-
partment Experimental Research Laboratory, was used to
validate the technique. The experimental systems is set
with: special induction machine to simulate the failure, a
DC machine, a measuring system, encoder, computer
with LabView software installed, a three phase varivolt,
resistances and the National Instruments board acquisi-
The mechanical load was provided by a separate DC
generator which feeds the variable resistor. In order to
allow tests to be performed at different load levels, the
DC excitation current and load resistor were both con-
trolled. The mechanical structure where the motors are
settled offers the possibility to move the two machines,
in a way the system can be either aligned or different
degrees of misalignment can be tested.
The motor was rewound to allow short circuit simula-
tion between different numbers of coil turns. The con-
figuration allows short-circuits between the minimum of
three turns to thirty three turns maximum. For data ac-
quisition, three to six turns were short circuited. To limit
the short circuit current, a resistance was inserted in se-
ries with the turns.
Shaft alignment in the setup was guaranteed by using a
laser alignment tool from the Ultraspec 8000 equipment.
The baseline measurements for this experiment were
recorded for the test case of minimum vibration magni-
tude. Table 4 shows the parameters deviation from the
engine nominal values.
Three types of mechanical faults: radial and angular
shaft misalignment, mechanical looseness and rotor im-
balances were performed. Each of these types was in-
duced mechanically to different degrees of intensity (or
fault level) and for different load conditions. This allows
analyze whether the mechanical failure misled the short
circuit diagnosis.
Radial misalignments were created by installing addi-
tional shims of specific thickness under the motor’s base
to lift it up slightly from the coupled load shaft. Angular
misalignments were created by rotating the machine at
specific angles away from the original position of the
coupled load shaft.
Mechanical imbalance was created by adding a steel
bolt and 21 grams nut of mass placed at different radial
distances from the rotor shaft on a balanced metal disk.
Mechanical looseness was caused by a structural loose-
ness at the induction motor base.
After each short circuit test, a symmetrical operation
test was performed. This procedure allowed the checking
if the short circuit tests had damaged the induction ma-
chine insulation system.
Figure 4 shows the current fundamental component
normalized in R3 space. The same way, for the model
simulation, Figure 2, we can see from this figure the two
classes splitting difficulty, i.e., no fault condition or short
circuit condition between turns.
Figure 3. The test bed for the exper i mental data acquisition.
Table 4. Real system’s measured parameters variation da-
Parameter Minimum Value Maximum Value
Load 20% of Tn 110% of Tn
Source amplitude 85% of Vn 105% of Vn
Shorted turns percentagenone 6 turns
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work
Figure 5 presents the 180 Hz stator current component
(3th harmonic) distributed in R3 space. This figure shows
that the short-circuit impact is not easily represented by
the current third harmonic component.
Table 5 presents the number of real tests used for the
network training and validation, and Table 6 shows the
classification results. For this condition the current and
voltage fundamental components were used since they
gave the best result. The current third harmonic compo-
nents were not used. It is important to notice that there
was no serious misleading to a short circuit diagnose in a
symmetrical operation causing unnecessary system stop-
Figure 4. Pattern distribution in R3 for the stator current
fundamental component: Experimental Re sults.
Figure 5. Pattern distribution in R3 for the stator current
third harmonic component: Experimental Result.
Table 5. Number of experimental tests.
Training Validation
Condition 1 45 55
Condition 2 25 55
Table 6. Each test condition hits.
Training Validation
Condition 1 100% 100%
Condition 2 100% 85%
Overall hit 100% 92%
4. Proposed Diagnostic Approach
We can concluded that the proposed technique can be
used to detect initial short-circuit fault. Notice that the
method uses only the plant actual sensor signals. The
proposed method disadvantage is the need of real faulty
condition data for the SVM design, what turns difficult
their use in a real plant. Thus, this work main motivation
is to answer the following question:
Do SVMs designed through simulation data be used
with real data? In different words, does the model pa-
rameters trained systems represent well the actual plant?
Dynamic symmetrical and asymmetrical model data to
train the SVM were obtained. After the network design
using simulation data we used real experimental data to
analyze the network performance. Table 7 gives the per-
formed tests number. For training we used simulated data,
and for validation real data. Tab l e 8 shows the individual
and overall hits using the normalized current and voltage
fundamental components real data.
The total hits rate for the SVM trained by simulated
data was 75%. The system performed significantly well,
since experiments in a short-circuit condition was con-
trolled by a resistance that limited the current dropping it
to less than the real faulty current. This was necessary
to prevent the machine to collapse due to the number of
tests performed. In practice, the faulty current is ap-
proximately 14 (fourteen) times the nominal motor cur-
rent. Thus, the hit rates could be even greater than that
5. Conclusions
Short-circuit is a severe fault and should be diagnosed in
an early stage to avoid major losses, such as unscheduled
production shutdown or even irreversible engine loss.
This study showed the SVM effectiveness for fault diag-
nosis in induction machines and furthermore, made it
possible to be implemented in real plant.
The method requires only sensors usually presented in
Table 7. Number of final tests.
Training Validation
Condition 1 100 100
Condition 2 100 80
Table 8. Experimental result hits.
Training Validation
Condition 1 100% 79%
Condition 2 100% 70%
Overall hit 100% 75%
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work 531
the application. The work proposed a non invasive fault
diagnosis method, and no human is exposed directly to
the machine in working condition.
It also showed that mechanical failures and unbalance
voltage supply do not compromise the system shortcir-
cuit fault diagnosis.
The proposed approach came up with very good re-
sults. Finally, from this work we also realized that the
current third harmonic component does not supply the
SVM with useful information for fault diagnosis purpose,
and reduce the cost of data processing.
6. Acknowledgements
The authors thank Fapemig (APQ-00589-11) for the sup-
port given to this work.
[1] D. A. Asfani, A. K. Muhammad, Syafaruddin, M. H.
Purnomo and T. Hiyama, “Temporary Short Circuit De-
tection in Induction Motor Winding Using Combination
of Wavelet Transform and Neural Network,” Expert Sys-
tems with Applications, Vol. 39, No. 5, 2012, pp. 5367-
[2] L. M. R. Baccarini, L. V. Silva, B. R. de Menezes and W.
M. Caminhas, “Svm Practical Industrial Application for
Mechanical Faults Diagnostic,” Expert Systems with Ap-
plications, Vol. 38, No. 6, 2011, pp. 6980-6984.
[3] M. F. S. V. D’Angelo, R. M. Palhares, R. H. C. Takaha-
shi, R., Loschi, L. M. R. Baccarini and W. Caminhas,
“Incipient Fault Detection in Induction Machine Stator-
Winding Using a Fuzzy-Bayesian Change Point Detec-
tion Approach,” Applied Soft Computing, Vol. 11, No. 1,
2011, pp. 179-192.
[4] P. Zhang, Y. Du, T. G. Habetler and B. Lu, “A Survey of
Condition Monitoring and Protection Methods for Me-
dium-Voltage Induction Motors,” IEEE Transactions on
Industry Applications, Vol. 47, No. 1, 2011, pp. 34-46.
[5] R. M. Tallam, S. B. Lee, G. C. Stone, G. B. Kliman, J.
Yoo and T. G. Habetler, “A Survey of Methods for De-
tection of Stator Related Faults in Induction Machines,”
IEEE Transaction on Industry Application, Vol. 43, No. 4,
2007, pp. 920-933.
[6] A. Siddique, G. S. Yadava and B. Singh, “A Review of
Stator Fault Monitoring Techniques of Induction Mo-
tors,” IEEE Transactions on Energy Conversion, Vol. 20,
No. 1, 2005, pp. 106-114.
[7] A. M. Somaya, H. S. Shehata, El-Goharey, M. I. Marei
and A. K. Ibrahim, “Detection of Induction Motors Ro-
tor/Stator Faults Using Electrical Signatures Analysis,”
Proceedings of International Conference on Renewable
Energies and Power Quality (ICREPQ’13), Bilbao, 20-22
March 2013, pp. 1-6.
[8] D. Zhen, T. Wang, F. S. Gu and A. Ball, “Fault Diagnosis
of Motor Drives Using Stator Current Signal Analysis
Based on Dynamic Time Warping,” Mechanical Systems
and Signal Processing, Vol. 34, No. 1-2, 2013, pp. 191-
[9] K. K. Pandey, P. H. Zope and S. R. Suralkar, “Review on
Fault Diagnosis in Three-Phase Induction Motor,” IJCA
Proceedings on National Conference MEDHA 2012, Vol.
1, 2012, pp. 53-58.
[10] O. Jasim, M. Sumner, C. Gerada and J. Arellano-Padilla,
“Development of a New Fault-Tolerant Induction Motor
Control Strategy Using an Enhanced Equivalent Circuit
Model,” IET Electric Power Applications, Vol. 5, 2011,
pp. 618-627.
[11] J. Sottilee, F. C. Trutt and J. L. Kohler, “Condition
Monitoring of Stator Windings in Induction Motors. II.
Experimental Investigation of Voltage Mismatch Detec-
tors,” IEEE Transactions on Industry Applications, Vol.
38, No. 5, 2002, pp. 1454-1459.
[12] W. T. Thomson and M. Fenger, “Current Signature Ana-
lysis to Detect Induction Motor Faults,” IEEE Industry
Application Magazine, Vol. 7, No. 4, 2001, pp. 26-34.
[13] L. M. R. Baccarini, B. R. de Menezes and W. M. Camin-
has, “Fault Induction Dynamic Model, Suitable for Com-
puter Simulation: Simulation Results and Experimental
Validation,” Mechanical Systems and Signal Processing,
Vol. 24, No. 1, 2010, pp. 300-311.
[14] O. A. Mohamed, N. Y. Abed and S. Garni, “Modeling
and Characterization of Induction Motor Internal Faults
Using Finite Element and Discrete Wavelet Transforms,”
IEEE Transactions on Magnetics, Vol. 42, No. 10, 2006,
pp. 3434-3436.
[15] Md. R. Shahriar, T. Ahsan and U. Chong, “Fault Diagno-
sis of Induction Motors Utilizing Local Binary Pattern
Based Texture Analysis,” EURASIP Journal on Image
and Video Processing, Vol. 2013, 2013, pp. 1-13.
[16] H. A. Khwaja, S. P. Gupta and V. Kumar, “A Statistical
Approach for Fault Diagnosis in Electrical Machines,”
IETE Journal of Research, Vol. 56, No. 3, 2010, pp 146-
[17] G. S. Maruthi and P. S. Vittal, “Electrical Fault Detection
in Three Phase Squirrel Cage Induction Motor by Vibra-
tion Analysis Using MEMS Accelerometer,” Proceeding
of International Conference on Power Electronics and
Drives Systems, Vol. 2, 28 October-1 November 2005, pp.
[18] Y.-W. Youn, S.-H. Yi, D.-H. Hwang, J.-H. Sun, D.-S.
Kang and Y.-H. Kim, “MUSIC-Based Diagnosis Algo-
rithm for Identifying Broken Rotor Bar Faults in Induc-
tion Motors Using Flux Signal,” Journal of Electrical
Engineering & Technology, Vol. 8, No. 2, 2013, pp. 288-
[19] S. Chen and R. Živanović, “Modelling and Simulation of
Copyright © 2013 SciRes. JSEA
Intelligent System Design for Stator Windings Faults Diagnosis: Suitable for Maintenance Work
Copyright © 2013 SciRes. JSEA
Stator and Rotor Fault Conditions in Induction Machines
for Testing Fault Diagnostic Techniques,” European
Transactions on Electrical Power, Vol. 20, No. 5, 2010,
pp. 611-629.
[20] A. Widodo, B. S. Yang and T. Han, “Combination of
Independent Component Analysis and Support Vector
Machines for Intelligent Faults Diagnosis of Induction
motors,” Expert Systems with Application, Vol. 32, No. 2,
2007, pp. 299-312.
[21] A. Widodo and B. S. Yang. “Wavelet Support Vector
Machine for Induction Machine Fault Diagnosis Based on
Transient Current Signal,” Expert System with Applica-
tion, Vol. 35, No. 1-2, 2008, pp. 307-316.