Neural Network Based Dynamic

Performance of Induction Motor Drives
P. M. Menghal and A. Jaya Laxmi
Abstract In industries, more than 85 % of the motors are Induction Motors,
because of the low maintenance and robustness. Maximum torque and efficiency is
obtained by the speed control of induction motor. Using Artificial Intelligence (AI)
techniques, particularly the neural networks, performance and operation of
induction motor drives is improved. This paper presents dynamic simulation of
induction motor drive using neuro controller. The integrated environment allows
users to compare simulation results between conventional, Fuzzy and Neural
Network controller (NNW). The performance of fuzzy logic and artificial neural
network based controller’s are compared with that of the conventional proportional
integral controller. The dynamic modeling and simulation of Induction motor is
done using MATLAB/SIMULINK and the dynamic performance of induction
motor drive has been analyzed for artificial intelligent controller.
Keywords Neuro network (NNW)
Á
PI controller
Á
Fuzzy logic controller
(FLC)
Á
Sugeno fuzzy controller
Á
Hebbian learning algorithm
P. M. Menghal (&)
Faculty of Degree Engineering, Military College of Electronics and Mechanical
Engineering, Secunderabad 500015, India
e-mail: prashant_menghal@yahoo.co.in
Department of EEE, Jawaharlal Nehru Technological University, Anantapur 515002,
Andhra Pradesh, India
A. Jaya Laxmi
Department of EEE, Jawaharlal Nehru Technological University, College of Engineering,
Kukatpally, Hyderabad 500085, Andhra Pradesh, India
e-mail: ajl1994@yahoo.co.in
M. Pant et al. (eds.), Proceedings of the Third International Conference on Soft
Computing for Problem Solving, Advances in Intelligent Systems and Computing 259,
DOI: 10.1007/978-81-322-1768-8_48, Ó Springer India 2014
539
1 Introduction
Three phase Induction Motor have wide applications as electrical machines. About
half of the electrical energy generated in a developed country is ultimately con-
sumed by electric motors, of which over 90 % are induction motors. For a rela-
tively long period, induction motors have mainly been deployed in constant-speed
motor drives for general purpose applications. The rapid development of power
electronic devices and converter technologies in the past few decades, however,
has made possible efficient speed control by varying the supply frequency, giving
rise to various forms of adjustable-speed induction motor drives. In about the same
period, there were also advances in control methods and Artificial Intelligence (AI)
techniques. Artificial Intelligent techniques mean use of expert system, fuzzy
logic, neural networks and genetic algorithm. Researchers soon realized that the
performance of induction motor drives can be enhanced by adopting artificial-
intelligence-based methods. The Artificial Intelligence (AI) techniques, such as
Expert System (ES), Fuzzy Logic (FL), Artificial Neural Network (ANN), and
Genetic Algorithm (GA) have recently been applied widely in control of induction
motor drives. Among all the branches of AI, the NNW seems to have greater
impact on power electronics and motor drives area that is evident by the publi-
cations in the literature. Since the 1990s, AI-based induction motor drives have
received greater attention. Apart from the control techniques that exist, intelligent
control methods, such as fuzzy logic control, neural network control, genetic
algorithm, and expert system, proved to be superior. Artificial Intelligent Con-
troller (AIC) could be the best controller for Induction Motor control [1–6]. Fuzzy
controller conventionally is totally dependent to memberships and rules, which are
based broadly on the intuition of the designer. This paper tends to show Neuro
Controller has edge over fuzzy controller. Sugeno fuzzy controller is used to train
the fuzzy system with two inputs and one output [7–11]. The performance of fuzzy
logic and artificial neural network based controllers is compared with that of the
conventional proportional integral controller.
2 Dynamic Modeling and Simulation of Induction Motor
Drive
The induction motors dynamic behavior can be expressed by voltage and torque
which are time varying. The differential equations that belong to dynamic analysis
of induction motor are so sophisticated. Then with the change of variables the
complexity of these equations decrease through movement from poly phase
winding to two phase winding (q-d). In other words, the stator and rotor variables
like voltage, current and flux linkages of an induction machine are transferred to
another reference model which remains stationary [1–6].
540 P. M. Menghal and A. Jaya Laxmi
In Fig. 1 stator inductance is the sum of the stator leakage inductance and
magnetizing inductance (L
ls
= L
s
? L
m
), and the rotor inductance is the sum of
the rotor leakage inductance and magnetizing inductance (L
lr
= L
r
? L
m
). From
the equivalent circuit of the induction motor in d-q frame, the model equations are
derived. The flux linkages can be achieved as:
1
x
b
dw
qs
dt
¼ v
qs
À
x
e
x
b
w
ds
ÀR
s
i
qs
ð1Þ
1
x
b
dw
ds
dt
¼ v
ds
À
x
e
x
b
w
qs
ÀR
s
i
ds
ð2Þ
1
x
b
dw
qr
dt
¼ v
qr
À
ðx
e
Àx
r
Þ
x
b
w
dr
ÀR
s
i
qr
ð3Þ
1
x
b
dw
dr
dt
¼ v
dr
þ
ðx
e
Àx
r
Þ
x
b
w
qr
ÀR
s
i
dr
ð4Þ
By substituting the values of flux linkages in the above equations, the following
current equations are obtained as:
i
qs
¼
w
qs
Àw
mq
À Á
X
ls
ð5Þ
i
ds
¼
w
ds
Àw
md
ð Þ
X
ls
ð6Þ
i
qr
¼
w
qr
Àw
mq
À Á
X
ls
ð7Þ
Fig. 1 d q model of induction motor
Neural Network Based Dynamic Performance 541
i
dr
¼
w
dr
Àw
md
ð Þ
X
ls
ð8Þ
where w
mq
and w
md
are the flux linkages over L
m
in the q and d axes. The flux
equations are written as follows:
w
mq
¼ X
ml
w
qs
X
ls
þ
w
qr
X
lr

ð9Þ
w
md
¼ X
ml
w
ds
X
ls
þ
w
dr
X
lr

ð10Þ
X
ml
¼
1
1
X
m
þ
1
X
ls
þ
1
X
lr
ð11Þ
In the above equations, the speed x
r
is related to the torque by the following
mechanical dynamic equation as:
T
e
¼ T
load
þJ
dx
m
dt
¼ T
load
þ
J2
p
dx
r
dt
ð12Þ
then x
r
is achievable from above equation, where:
p: number of poles.
J: moment of inertia (kg/m
2
).
In the previous section, dynamic model of an induction motor is expressed. The
model constructed according to the equations has been simulated by using
MATLAB/SIMULINK as shown in Fig. 2 in conventional mode of operation of
induction motor. A 3 phase source is applied to conventional model of an
induction motor and the equations are given by:
V
a
¼
ffiffiffi
2
p
V
rms
sin xt ð Þ ð13Þ
V
b
¼
ffiffiffi
2
p
V
rms
sin xt À
2p
3

ð14Þ
V
c
¼
ffiffiffi
2
p
V
rms
sin xt þ
2p
3

ð15Þ
By using Parks Transformation, voltages are transformed to two phase in the
d-q axes, and are applied to induction motor. In order to obtain the stator and rotor
currents of induction motor in two phase, Inverse park transformation is applied in
the last stage [4].
542 P. M. Menghal and A. Jaya Laxmi
3 Fuzzy Logic Controller
The speed of induction motor is adjusted by the fuzzy controller. The membership
function of D
e
, e and three scalar values of each triangle are applied into this
controller. In Table 1, the fuzzy rules decision implemented into the controller are
given. The conventional simulated induction motor model as shown in Fig. 2 is
modified by adding Fuzzy controller and is shown in Fig. 3. Speed output terminal
of induction motor is applied as an input to fuzzy controller, and in the initial start
of induction motor the error is maximum, so according to fuzzy rules fuzzy
controller produces a crisp value. Then this value will change the frequency of sine
wave in the speed controller. The sine wave is then compared with triangular
waveform to generate the firing signals of IGBTs in the PWM inverters. The
frequency of these firing signals also gradually changes, thus increasing the fre-
quency of applied voltage to Induction Motor [9].
As discussed earlier, the crisp value obtained from Fuzzy Logic Controller is
used to change the frequency of gating signals of PWM inverter. Thus the output
AC signals obtained will be variable frequency sine waves. The sine wave is
generated with amplitude, phase and frequency which are supplied through a GUI.
Then the clock signal which is sampling time of simulation is divided by crisp
value which is obtained from Fuzzy Logic Controller (FLC). So by placing three
sine waves with different phases, one can compare them with triangular waveform
and generate necessary gating signals of PWM inverter. So at the first sampling
point the speed is zero and error is maximum. Then whatever the speed rises, the
error will decrease, and the crisp value obtained from FLC will increase. So, the
frequency of sine wave will decrease which will cause IGBTs switched ON and
OFF faster. It will increase the AC supply frequency, and the motor will speed up.
Figure 3 shows the Fuzzy logic induction motor model.
Torque
Speed
iqs
ids
iqr
idr
teta
Iabc
Ir-abc
Vqs
Vds
TL
iqs
ids
iqr
idr
Te
Wr
induction motor d-q model
Va
Vb
Vc
teta
Vqs
Vds
abc to d-q
Park transformation
XY Graph
ICONR
To Workspace 2
ICONS
To Workspace 1
SCON
To Workspace
Scope1
Scope
1/s
Integrator
Final speed value
0
Constant 1
Va
Vb
Vc
AC Source
Fig. 2 Simulated induction motor model with conventional controller
Neural Network Based Dynamic Performance 543
4 Adaptive Neuro Fuzzy Controller
In the designing of a controller, the main criterion is the controllability of torque in
an induction motor with good transient and steady state responses. With certain
drawbacks, PI controller is able to achieve these characteristics. The main draw-
backs are (1) The gains cannot be increased beyond certain limit. (2) Non linearity
is introduced, making the system more complex for analysis. The shortcomings of
PI controller are overcome by artificial intelligent techniques. One such technique
is the use of Fuzzy Logic in the design of controller either independently or in
hybrid with PI controller. The draw-backs of Fuzzy Logic Control and Artificial
Neural Network are replaced by Adaptive Neuro-Fuzzy Inference System
(ANFIS). Adaptive neuro fuzzy combines the learning power of neural network
with knowledge representation of fuzzy logic. A neuro fuzzy system is based on a
fuzzy system which is trained by a learning algorithm derived from neural network
theory. Depending on the applications, one can use either ANN or FIS, or com-
bination of both. In this paper, the inputs will be e(k) and D
e
(k) [9, 12, 17]. A first-
order Sugeno fuzzy model has rules which are as follows:
Table 1 Modified fuzzy rule decision
D
e
NB NS ZZ PS PB
e PB ZZ NS NS NB NB
PS PS ZZ NS NS NB
ZZ PS PS ZZ NS NS
NS PB PS PS ZZ NS
NB PB PB PS PS ZZ
Speed contrller
d-q to abc
Park transformation
stator current Scope
rotor current Scope
Continuous
powergui
iqs
ids
iqr
idr
teta
Iabc
Ir-abc
Vqs
Vds
TL
iqs
ids
iqr
idr
Te
Wr
induction motor d-q model
Va
Vb
Vc
teta
Vqs
Vds
abc to d-q
Park transformation
Torque Scope
I
n
1
143652
Speed Scope
IGBT1
IGBT4
IGBT3
IGBT6
IGBT5
IGBT2
Va
Vb
Vc
PWM ac source
0
Load Torque
1/s
Integrator
Feedback
Reference
U(k)
Fuzzy controller
Divide
1710
1
Fig. 3 Fuzzy control induction motor model
544 P. M. Menghal and A. Jaya Laxmi
• Rule1: If x is A
1
and y is B
1
, then f
1
= p
1
x ? q
1
y ? r
1
• Rule2: If x is A
2
and y is B
2
, then f
2
= p
2
x ? q
2
y ? r
2
.
In the Sugeno model if–then rules are used, and output of each rule is linear
combination of inputs plus a constant value. The learning algorithm applied to this
model is Hebbian. This method is feed forward and unsupervised and the weights
will be adjusted by the following formula:
w
i
new ð Þ ¼ w
i
old ð Þ þx
i
y ð16Þ
The ANFIS layout is shown in Fig. 4. It states that if the cross product of output
and input is positive, then it results in increase of weight, otherwise decrease of
weight.
In layer 2 of ANFIS layout, the triangular membership function is same as that
of the fuzzy controller model. The output of layer 2 is given by:
O
2
¼ l
1
; l
2
; l
3
ð17Þ
Layer 3 indicates the pro (product) layer and its output is product of inputs,
which is given by:
O
3
¼ l
i
e ð Þ Á l
j
De ð Þ ð18Þ
Layer 4 represent Norm and it calculates the ratio of ith firing strength to sum of
all firing strengths. The obtained output is normalized firing strength, which is
given by:
Fig. 4 ANFIS layout
Neural Network Based Dynamic Performance 545
O
4
¼
w
i
P
w
ð19Þ
Layer 5 is an adaptive node with functionality as follows:
O
5
¼ w
i
f
i
¼ w
i
p
i
e ð Þ þq
i
De ð Þ þr
i
ð Þ ð20Þ
where p
i
, q
i
, r
i
are consequent parameters, which are initially are set to 0.48, 0.25
and 1 respectively. Then they are adaptively adjusted with Hebbian learning
algorithm. Layer 6 calculates the output which is given by:
O
6
¼
P
w
i
f
i
P
w
i
ð21Þ
Figure 5 shows the overall structure of Adaptive Neuro-Fuzzy controller.
5 Neuro Controller
The most important feature of Artificial Neural Networks (ANN) is its ability to
learn and improve its operation using neural network training [13, 14]. The
objective of Neural Network Controller (NNC) is to develop a back propagation
algorithm such that the output of the neural network speed observer can track the
target one. The network structure of the NNC, indicates that the neural network has
three layered network structure. The first is formed with five neuron inputs
D(x
ANN
(K ? 1)), D(x
ANN
(K)), x
ANN
, x
S
(K - 1), D(x
S
(K - 2)). The second
layer consists of five neurons. The last one contains one neuron to give the
command variation D(x
S
(K)). The aim of the proposed NNC is to compute the
Speed contrller
d-q to abc
Park transformation
stator current Scope
rotor current Scope
Continuous
powergui
iqs
ids
iqr
idr
teta
Iabc
Ir-abc
Vqs
Vds
TL
iqs
ids
iqr
idr
Te
Wr
induction motor d-q model
Va
Vb
Vc
teta
Vqs
Vds
abc to d-q
Park transformation
Torque Scope
I
n
1
143652
Speed Scope
IGBT1
IGBT4
IGBT3
IGBT6
IGBT5
IGBT2
Va
Vb
Vc
PWM ac source
0
Load Torque
1/s
Integrator
Feedback
Reference
U(k)
Fuzzy controller
Divide
1710
1
Fig. 5 Adaptive neuro-fuzzy controller simulation model
546 P. M. Menghal and A. Jaya Laxmi
command variation based on the future output variation D(x
ANN
(K ? 1)). Hence,
with this structure, a predictive control with integrator has been realised. At time k,
the neural network computes the command variation based on the output at time
(k ? 1), while the later isn’t defined at this time. In this case, it is assumed that
x
ANN
(K ? 1) : x
ANN
(K). The control law is deduced using the recurrent
equation given by,
x
S
K ð Þ ¼ x
S
K À1 ð Þ þGD x
S
K ð Þ ð Þ:
It can be seen that the d axis and q axis voltage equations are coupled by the
terms d
E
and q
E
. These terms are considered as disturbances and are cancelled by
using the proposed decoupling method. If the decoupling method is implemented,
the flux component equations become
U
dr
¼ G s ð Þv
ds
U
qr
¼ G s ð Þv
qs
Large values of g may accelerate the ANN learning and consequently fast
convergence but may cause oscillations in the network output, whereas low values
will cause slow convergence. Therefore, the value of g has to be chosen carefully
to avoid instability. The proposed neural network controller is shown in Fig. 6.
6 Simulation Results and Discussion
Modeling and simulation of Induction motor in conventional, fuzzy and adaptive
neuro fuzzy are done on MATLAB/SIMULINK. A complete simulation model
and dynamic performance for inverter fed induction motor drive incorporating the
proposed FLC, adaptive neuro fuzzy controller and Neuro controller has been
2
is
1
wo
Wo
idq
Vdq
X1
X2
X3
X4
X5
X6
X7
Y1
Y2
Y3
Y4
Y5
Y6
Y7
Sub system 1
Pure linear
Neuron2
Pure linear
Neuron1
Ia
Ib
Va1
Vb1
TL
W
Mech_ANN
1
s
Integrator6
1
s
Integrator1
mu
2
TL
1
V
Fig. 6 Neural network controller
Neural Network Based Dynamic Performance 547
developed. The proposed neuro controller is proved to be more superior as com-
pared to adaptive by comparing the response of conventional PI, with FLC,
Adaptive neuro fuzzy speed controller based IM drive. The results of simulation
for induction motor with its characteristics are listed in Appendix ‘A’. Figures 7, 8
and 9 shows the torque–speed characteristics, torque and speed responses of
conventional, FLC, adaptive neuro fuzzy controller and neuro controller respec-
tively. It appears the rise time drastically decreases when neuro controller is added
to simulation model and both the results are taken in same period of time. In neural
network based simulation, it is apparent from the simulation results shown in
Fig. 7c and d, torque-speed characteristic converges to zero in less duration of time
when compared with conventional Controller and FLC, which is shown in Fig. 7a
and b. Neuro controller has no overshoot and settles faster in comparison with FLC
and adaptive neuro fuzzy controller. It is also noted that there is no steady-state
error in the speed response during the operation when neuro controller is activated.
In conventional controller, oscillations occur, whereas in neuro controller, adap-
tive neuro fuzzy and FLC, no oscillations occur in the torque response before it
finally settles down as shown in Fig. 8 good torque response is obtained with
Neuro controller as compared to conventional, FLC and adaptive neuro fuzzy
controller at all time instants and speed response is better than conventional
controllers, FLC and adaptive neuro fuzzy controller. There is a negligible ripple
in speed response with neuro fuzzy controller in comparison with conventional
0 200 400 600 800 1000 1200 1400 1600 1800
-5
0
5
10
15
20
Speed
T
o
r
q
u
e
-200 0 200 400 600 800 1000 1200 1400 1600 1800
-60
-40
-20
0
20
40
60
80
100
120
Speed
T
o
r
q
u
e
-200 0 200 400 600 800 1000 1200 1400 1600 1800
-60
-40
-20
0
20
40
60
80
100
120
140
Speed
T
o
r
q
u
e
-200 0 200 400 600 800 1000 1200 1400 1600 1800
-60
-40
-20
0
20
40
60
80
100
120
Speed
T
o
r
q
u
e
(a)
(b)
(c)
(d)
Fig. 7 Torque-speed characteristics. a Torque-speed characteristics with conventional control-
ler. b Torque-speed characteristics withfuzzy controller. c Torque-speed adaptive neuro fuzzy
controller. d Torque speed characteristics with neuro controller
548 P. M. Menghal and A. Jaya Laxmi
0 500 1000 1500
-5
0
5
10
15
20
Time
T
o
r
q
u
e
0 0.5 1 1.5 2 2.5 3
x 10
5
-60
-40
-20
0
20
40
60
80
100
120
Time
T
o
r
q
u
e
0 0.5 1 1.5 2 2.5 3
x 10
5
-60
-40
-20
0
20
40
60
80
100
120
140
Time
T
o
r
q
u
e
0 2 4 6 8 10 12 14
x 10
4
-60
-40
-20
0
20
40
60
80
100
120
Time
T
o
r
q
u
e
(a)
(b)
(c)
(d)
Fig. 8 Torque characteristics. a Conventional controller. b Fuzzy controller. c Adaptive neuro
fuzzy controller. d Neuro controller
0 0.5 1 1.5 2 2.5
x 10
6
0
200
400
600
800
1000
1200
1400
1600
1800
Time
S
P
E
E
D
0 0.5 1 1.5 2 2.5 3
x 10
5
-200
0
200
400
600
800
1000
1200
1400
1600
1800
Time
S
p
e
e
d
0 0.5 1 1.5 2 2.5 3
x 10
5
-200
0
200
400
600
800
1000
1200
1400
1600
1800
Time
p
0 0.5 1 1.5 2 2.5 3
x 10
5
-200
0
200
400
600
800
1000
1200
1400
1600
1800
Time
S
p
e
e
d
(a)
(b)
(c)
(d)
Fig. 9 Speed characteristics. a Conventional controller. b Fuzzy controller. c Adaptive neuro
fuzzy controller. d Neuro controller
Neural Network Based Dynamic Performance 549
controller, FLC and adaptive neuro controller under dynamic conditions which are
shown in Fig. 8. With the neuro controller, speed reaches its steady state value
faster as compared to Conventional, FLC and adaptive neuro fuzzy controller.
7 Conclusion
In this paper, comparison of simulation results of the induction motor are pre-
sented with different types of controller such as conventional, fuzzy control,
Adaptive neuro fuzzy and neuro controller. From the speed waveforms, it is
observed that with adaptive fuzzy and neuro controller the rise time decreases
drastically, in the manner which the frequency of sine waves are changing
according to the percentage of error from favourite speed. According to the direct
relation of induction motor speed and frequency of supplied voltage, the speed will
also increase. Fuzzy controller has better performance than the conventional
controller. By comparing neuro controller, Adaptive neuro fuzzy model with FLC
model, it is apparent that by adding learning algorithm to the control system will
decrease the rising time more than expectation and it proves neuro controller has
better dynamic performance as compared to FLC and Adaptive neuro fuzzy
controller.
Appendix A
The following parameters of the induction motor are chosen for the simulation
studies:
V = 220 f = 60 HP = 3 R
s
= 0.435 R
r
= 0.816 X
ls
= 0.754
X
lr
= 0.754 X
m
= 26.13 p = 4 J = 0.089 rpm = 1,710
References
1. Chan, T.F., Shi, K.: Applied Intelligent Control of Induction Motor Drives. IEEE Willey
Press (2011)
2. Krause, P.C.: Analysis of Electrical Machinery and Drives System. IEEE Willey Press (2000)
3. Mohan, N.: Advanced Electric Drives: Analysis, Control Modeling using Simulink.
MNPERE Publication (2001)
4. Menghal, P.M., Laxmi, A.J.: Adaptive neuro fuzzy based dynamic simulation of induction
motor drives. IEEE International Conference on Fuzzy Systems, pp. 1–8 (2013)
5. Menghal, P.M., Laxmi, A.J.: Neural network based dynamic simulation of induction motor
drives. IEEE International Conference on Power, Energy and Control (2013). doi:10.1109/
ICPEC.2013.6527722
550 P. M. Menghal and A. Jaya Laxmi
6. Menghal, P.M., Laxmi, A.J.: Adaptive neuro fuzzy interference (ANFIS) based simulation of
Induction motor drive. Int. Rev. Model. Simul. (IRMOS) 5(5), 2007–2016 (2012)
7. Shi, K.L., Chan, T.F., Wong, Y.K., Ho, S.L.: Modeling and simulation of the three phase
induction motor using SIMULINK. Int. J. Elect. Eng. Educ. 36, 163–172 (1999)
8. Dandil, B., Gokbulut, M., Ata, F.: A PI type fuzzy—neural controller for induction motor
drives. J. Appl. Sci. (2005). doi:10.3923/jas.2005.1286.1291
9. Kumar, R., Gupta, R.A., Surjuse, R.S.: Adaptive neuro-fuzzy speed controller for vector
controlled induction motor drive. APEJ (2009). doi:14.79e41505757a2a8cab
10. Denai, M.A., Attia, S.A.: Fuzzy and neural control of an induction motor. Int. J. Appl. Math.
Comput. Sci. (2002). doi:10.1.1.135.303
11. Subudhi, B., Anish Kumar, A.K., Jena, D.: dSPACE implementation of fuzzy logic based
vector control of induction motor. IEEE TENCON (2008). doi:10.1109/TENCON.2008.
4766502
12. Bose, B.K.: Neural network applications in power electronics and motor drives—an
introduction and perspective. IEEE Trans. Ind. Electron. (2007). doi:10.1109/TIE.2006.
888683
13. Uddin, M.N., Hafeez, M.: FLC-based DTC scheme to improve the dynamic performance of
an IM drive. IEEE Trans. Ind. Appl. (2012). doi:10.1109/TIA.2011.2181287
14. Uddin, M.N., Wen, H.: Development of a self-tuned neuro-fuzzy controller for induction
motor drives. IEEE Trans. Ind. Appl. (2007). doi:10.1109/TIA.2007.900472
15. Uddin, M.N., Radwan, T.S., Rahman, A.: Performance of fuzzy logic based indirect vector
control for induction motor drive. IEEE Trans. Ind. Appl. (2002). doi:10.1109/TIA.2002.
802990
16. Uddin, M.N., Huang, Z.R., Chy, M.M.I.: A simplified self-tuned neuro-fuzzy controller based
speed control of an induction motor drive. IEEE Power Engineering Society General Meeting
(2007). doi:10.1109/PES.2007.385720
Neural Network Based Dynamic Performance 551

Sign up to vote on this title
UsefulNot useful