Journal of ELECTRICAL ENGINEERING, VOL. 59, NO.

4, 2008, 210–215

DIRECT TORQUE NEURO FUZZY SPEED CONTROL

OF AN INDUCTION MACHINE DRIVE BASED
ON A NEW VARIABLE GAIN PI CONTROLLER
∗
Eid Al-radadi

This paper presents an original variable gain PI (VGPI) controller for speed control of a simplified direct torque neuro
fuzzy controlled (DTNFC) induction motor drive. First, a simplified direct torque neuro fuzzy control (DTNFC) for a voltage
source PWM inverter fed induction motor drive is presented. This control scheme uses the stator flux amplitude and the
electromagnetic torque errors through a four rules adaptive NF inference system (ANFIS) to generate a voltage space vector
(reference voltage). This voltage is used by a space vector modulator to generate the inverter switching states. Then a VGPI
controller is designed in order to be used as the speed controller in the simplified DTNFC induction motor drive. Simulation
of the simplified DTNFC induction motor drive using VGPI for speed control shows promising results. The motor reaches
the reference speed rapidly and without overshoot, load disturbances are rapidly rejected and the detuning problem caused
by the stator resistance variation is fairly well dealt with.
K e y w o r d s: induction motor, direct torque control, direct torque neuro fuzzy control, adaptive NF inference system,
variable gain PI controller, space vector modulation

1 INTRODUCTION The ANFIS controller combines fuzzy logic and arti-

The apparition of the field oriented control (FOC)
made induction machine drives a major candidate in high
performance motion control applications. However, the
complexity of field oriented algorithms led to the devel-
opment in recent years of many studies to find out differ-
ent solutions for the induction motor control having the
features of precise and quick torque response. The direct
torque control technique (DTC) proposed by I. Takahashi
[1] and M. Depenbrock [2] in the mid eighties has been
recognised to be a viable solution to achieve these require-
ments [1–3], [7–9], [11–17].
In the DTC scheme [1] (Fig. 1), the electromagnetic
torque and flux signals are delivered to two hysteresis
comparators. The corresponding output variables and the
stator flux position sector are used to select the appropri-
ate voltage vector from a switching table which generates
pulses to control the power switches in the inverter. This
scheme presents many disadvantages (variable switching
frequency - violence of polarity consistency rules - cur-
rent and torque distortion caused by sector changes -
start and low-speed operation problems - high sampling
frequency needed for digital implementation of hystere-
sis comparators) [8], [11], [13–15], [17]. To eliminate the
above difficulties, a Direct Torque Neuro Fuzzy Control
scheme (DTNFC) has been proposed [17]. This scheme
uses a controller based on an adaptive NF inference sys-
tem (ANFIS) [5], [6], [10] together with a space voltage
modulator to replace both the hysteresis comparators and
the switching table.
ficial neural networks to evaluate the reference voltage
required to drive the flux and torque to the demanded
values within a fixed time period. This evaluation is per-
formed using the electromagnetic torque and stator flux
magnitude errors together with the stator flux angle. This
calculated voltage is then synthesised using Space Vec-
tor Modulation (SVM). To generate the desired reference
voltage using this scheme, the ANFIS controller acts only
on the amplitude of the reference voltage components
whereas the angle is chosen from a table. A proposed
modification of this scheme is to design an ANFIS con-
troller in order to act on both the amplitude and the angle
of the reference voltage components. All the schemes cited
above use a PI controller for speed control. The use of PI
controllers to command a high performance direct torque
controlled induction motor drive is often characterised by
an overshoot during start up. This is mainly caused by
the fact that the high value of the PI gains needed for
rapid load disturbance rejection generates a positive high
torque error. This will let the DTC scheme take control
of the motor speed driving it to a value corresponding to
the reference stator flux.
At start up, the PI controller acts only on the error
torque value by driving it to the zero border. When this
border is crossed, the PI controller takes control of the
motor speed and drives it to the reference value. To over-
come this problem, we propose the use of a variable gains
PI controller (VGPI) [18]. A VGPI controller is a general-
ization of a classical PI controller where the proportional
and integrator gains vary along a tuning curve. In this

∗ Department of Industrial Electronics and Control, Madina College of Technology, P.O.Box 15389, Madinah, Saudi Arabia; al-
radadi2000@yahoo.com

c 2008 FEI STU

ISSN 1335-3632 °
 Journal of ELECTRICAL ENGINEERING 59, NO. 4, 2008 211

Fig. 1. Two-input NF controller structure

Fig. 2. Direct Torque Neuro Fuzzy Controller scheme

paper, a variable gain PI controller is used to replace the
classical PI controller in the speed control of a modified
direct torque neuro fuzzy controlled induction machine
drive where the ANFIS of the DTNFC acts on both the
amplitude and the angle of space vector components.
2 SIMPLIFIED DIRECT TORQUE
NEURO FUZZY CONTROLLER
Fuzzy logic and artificial neural networks can be com-
bined to design a direct torque neuro fuzzy controller.
Human expert knowledge can be used to build an ini-
tial artificial neural network structure whose parameters
could be obtained using online or offline learning pro-
cesses.
The adaptive NF inference system (ANFIS) [5], [6],
[10] is one of the proposed methods to combine fuzzy
logic and artificial neural networks. Figure 1 shows the
adaptive NF inference system structure proposed in [5],
[6], [10]. It is composed of five functional blocks (rule base,
database, a decision making unit, a fuzzyfication interface
and a defuzzyfication interface) which are generated using
five network layers :
212 E. Al-radadi: DIRECT TORQUE NEURO FUZZY SPEED CONTROL OF AN INDUCTION MACHINE DRIVE BASED ON A NEW . . .
Fig. 3. Proposed Neuro Fuzzy Controller Structure
Fig. 4. Triangular membership function sets.
Table 1. Reference Voltage Increment Angle Table.
εψ P N
εT P N P N
∆γi + π3 − π3 + 2π − 2π
3 3
Layer 1. This layer is composed of a number of com-
puting nodes whose activation functions are fuzzy logic
membership functions (usually, triangular or bell- shaped
functions).
Layer 2. This layer chooses the minimum value of the
inputs.
Layer 3. This layer normalises each input with respect
to the others (The ith node output is the ith input di-
vided the sum of all the other inputs).
Layer 4. This layer’s ith node output is a linear func-
tion of the third layer’s ith node output and the ANFIS
input signals.
Layer 5. This layer sums all the incoming signals.
The ANFIS structure can be tuned automatically by
a least-square estimation (for output membership func-
tions) and a back propagation algorithm (for output and
input membership functions).
The block of the proposed self-tuned direct torque
neuro-fuzzy controller (DTNFC) for a voltage source
PWM inverter fed induction motor is presented in Fig. 2.
The internal structure of the NFC is shown in Fig. 3.
In the first layer of the proposed NF structure, sampled
flux error εψ and torque error εT , multiplied by respec-
tive weights wψ and wT , are each mapped through two
fuzzy logic membership functions which are chosen to be
triangular shaped as shown in Fig. 4.
The second layer calculates the minimum of the input
signals. The output values are normalised in the third
layer, to satisfy the following relation :
wi
σi = P (1)
k wk
where wi and σi ( i = 1, . . . , 4 ) are the ith output signal
of the second and third layer respectively. σi is considered
to be the weight of the ith component amplitude of the
desired reference voltage , so that:
VSi = σi Udc (2)
ϕVSi = γS + ∆γi (3)
where VSi is the ith component amplitude of the desired
reference voltage, ϕVSi is the ith component angle of the
desired reference voltage, γS is the actual angle of the
stator flux vector and ∆γi is the increment angle (from
Table 1).
The components of the desired reference voltage vec-
tor are added to each other and the result, is delivered to
the space vector modulator which calculates the switch-
ing states Sa , Sb and Sc according to the well known
algorithm [4], [8], [15].
The proposed NF structure is a simplification of the
structure used in [17] and [19] where the first layer is
composed of three membership functions (NEGATIVE,
ZERO and POSITIVE) and was then governed by nine
fuzzy rules. To decrease the number of rules used by the
NF structure, we had the idea of merging the zero mem-
bership function into both the positive and negative mem-
bership functions. This will result in only two membership
functions as shown in Fig. 4.
The proposed NF structure is then governed by only
four fuzzy rules. This will result in decreasing the calcu-
lation time by more than a half.
3 VGPI CONTROLLER IN SPEED CONTROL
OF THE SIMPLIFIED DTNFC MOTOR DRIVE
The use of PI controllers to command an induction
motor speed is often characterised by an overshoot in
tracking mode and a poor load disturbance rejection.
This is mainly caused by the fact that the gains of the
 Journal of ELECTRICAL ENGINEERING 59, NO. 4, 2008
controller cannot be set to solve the overshoot and load
disturbance rejection problems simultaneously.
Overshoot elimination setting will cause a poor load
disturbance rejection, and rapid load disturbance rejec-
tion setting will cause important overshoot.
Table 2. Induction Machine Parameters.
Number of pairs of poles p=2
Rated power 2 hp
Rated frequency 50 Hz
Rated speed 1420 rpm
Rated voltage 220/380 V
Rated current 6.4/3.7 A
Stator resistance Rs = 4.85 W
Rotor resistance Rr = 3.805 W
Stator inductance Ls = 274 mH
Rotor inductance Lr = 274 mH
Mutual inductance Lm = 258 mH
Moment of inertia J = 0.031 kg.m2
Viscous friction coefficient f = 0.0114 kg.m2 /s
To overcome this problem, we propose the use of vari-
able gains PI controllers.
A variable gain PI (VGPI) controller is a generalisa-
tion of a classical PI controller where the proportional
and integrator gains are not fixed values but increases
gradually from an initial value to a terminal value along
a polynomial curve [18].
The initial value of the gains can be chosen to attenu-
ate the step response in the transient region [18]. A VGPI
controller could then be used to eliminate start up over-
shoot of the high performance DTNFC induction motor
drive.
In this section a simulation study of the performances
of the simplified direct torque neuro fuzzy controlled in-
duction motor drive is performed by using a VGPI con-
troller.
Tuning the modified DTNFC system comes to tuning
the weights ωΨ and ωT so as to minimize the flux and
torque errors. These weights are the scaling factors of the
flux and torque errors and their tuning corresponds to
the two ANFIS structure membership functions width.
Since the proposed DTNFC is a high order non linear
system, a simple way of tuning it is the successive trials
method. It has been shown in [17] that for nonzero syn-
chronous angular speed, the changes of the flux influences
the output torque, while the changes in the torque does
not influence the flux. That is why the proposed method
searches first the flux error minimum, before searching
the torque error minimum. The tuning method proposed
searches by successive trials method in a grid of values of
ωψ the value that gives the minimum stator flux error,
then by using this value, searches in a grid of values of
ωT the value that gives the minimum torque error. Using
this method the tuning values of the DTNFC are given
by ωψ = 100 and ωT = 10 .
213
Figure 5 shows a simulation of the settling perfor-
mance and the disturbance rejection capability of the
simplified DTNFC motor drive with the VGPI speed con-
troller gains given by equations 4 and 5. The VGPI con-
troller is tuned using the method given in [18]. The pa-
rameters of the motor used in the simulation are given in
Table 2.
½
0.5 + 49.5t3 if t < 1 ,
Kp = (4)
50 if t ≥ 1 ,
½
500t3 if t < 1 ,
Ki = (5)
500 if t ≥ 1 .
Initially the machine is started up with a load of
10 Nm. At 1 s, a 2 Nm load disturbance is applied dur-
ing a period of 1 s. The sampling time used is 50 µs.
The space vector modulator switching frequency used is
20 kHz, that is the space vector modulator generates the
desired reference vector after one sampling time.
The speed of the motor reaches the 1000 rpm refer-
ence speed at 0.53 s without overshoot. The VGPI con-
troller compensates the 2 Nm disturbance by increasing
the mean value of the torque command from 10.8 Nm
to 12.8 Nm. The controller rejects the 2 Nm load distur-
bance in less than 0.25 s with a maximum speed dip of
0.6 rpm (0.06 %). One can note that the current wave-
form is almost a sinusoidal waveform as expected us-
ing space vector modulator with a 20 KHz switching fre-
quency.
Figure 6 shows the speed tracking performance of the
system under no load. The slope of the trapezoidal com-
mand speed is 2000 rpm/s. The motor speed tracks the
trapezoidal commands with zero steady state error and
no overshoot
Figure 7 shows the reaction of the proposed VGPI
controller to stator resistance variation. The motor is
started up with a load of 10 Nm. The rotor resistance
is supposed to double at 1 sec.
Stator resistance variation is shown to affect the mean
value of the estimated electromagnetic torque which
changes from 10.15 Nm to 12.35 Nm.
The VGPI controller compensates the torque estima-
tor detuning problem by increasing the mean value of the
torque command to about 30 % of its rated value.
The VGPI controller rejects the stator resistance dis-
turbance in less than 0.25 s with a maximum speed dip
of 0.6 rpm ( 0.06 %).
4 CONCLUSION
In this paper a simplified direct torque neuro fuzzy
controlled induction motor drive is presented. This con-
trol scheme uses the stator flux amplitude and the elec-
tromagnetic torque errors through a four rules adaptive
NF inference system (ANFIS) to generate the desired ref-
erence voltage. This vector is used by a space vector mod-
ulator to generate the inverter switching states.
214 E. Al-radadi: DIRECT TORQUE NEURO FUZZY SPEED CONTROL OF AN INDUCTION MACHINE DRIVE BASED ON A NEW . . .

Fig. 5. Settling performance of the proposed DTNFC motor drive using a VGPI speed controller

Fig. 6. Speed tracking performance of the proposed DTNFC motor drive using a VGPI speed controller

Fig. 7. Variation of the stator resistance.

 Journal of ELECTRICAL ENGINEERING 59, NO. 4, 2008 215

A VGPI controller has been designed and used as a [11] KAZMIERKOWSKI, M. P.—KASPROWICZ, A. : Improved
speed controller in the DTNFC control scheme. Direct Torque and Flux Vector Control of PWM Inverter-Fed
Induction Motor Drives, IEEE Trans. Ind. Electron. 45 (Aug
Simulation of the simplified DTNFC induction motor
1995), 344-350.
drive using VGPI for speed control shows promising re-
[12] NASH, J. N. : Direct Torque Control, Induction Motor Vector
sults. The motor reaches the reference speed rapidly and Control without an Encoder, IEEE Trans. Ind. Applicat. 33
without overshoot, trapezoidal commands under no load (Mar/Apr 1997), 333-341.
are tracked with zero steady state error and no overshoot, [13] DAMIANO, A.—VAS, P. et al : Comparison of Speed-Sensor-
load disturbances are rapidly rejected and the detuning less DTC Induction Motor Drives, in Proc. PCIM, Nuremberg,
problem caused by the stator resistance variation is fairly Germany, 1997, pp. 1-11.
well dealt with. [14] BUJA, G. : A new Control Strategy of the Induction Motor
Drives: The Direct Flux and Torque Control, IEEE Ind. Elec-
Acknowledgement tron. Soc. Newslett. 45 (Dec 1998), 14-16.
[15] VAS, P. : Sensorless Vector and Direct Torque Control, Oxford
The author wishes to thank sincerely Mr. A. Draou Univ. Press, Oxford, U.K., 1998.
and Mr. A. Miloudi for the help in preparing this manu-
[16] CASADEI, D.—SERRA, G.—TANI, A. : Implementation of a
script as well as for fructuous discussions. Direct Torque Control Algorithm for Induction Motors based on
Discrete Space Vector Modulation, IEEE Trans. Power Electron.
15 No. 4 (July 2000), 769–777.
References [17] GRABOWSKI, P. Z.—BOSE, B. K.—BLAABJERG, F. : A
Simple Direct Torque Neuro Fuzzy Control of PWM Inverter
[1] TAKAHASHI—NOGUCHI, T. : A New Quick Response and Fed Induction Motor Drive, IEEE Trans. Ind. Electron. 47 No.
High Efficiency Control Strategy of an Induction Motor, IEEE 4 (Aug 2000), 863–870.
Trans. Ind. Applicat. IA-22 (Sept/Oct 1986), 820-827.
[18] MILOUDI, A.—DRAOU, A. : Variable Gain PI Controller De-
[2] DEPENBROK, M. : Direct Self-Control (DSC) of Inverter Fed
sign For Speed Control and Rotor Resistance Estimation of an
Induction Machine, IEEE Trans. Power Electron. PE-3 (Oct
Indirect Vector Controlled Induction Machine Drive, in Proc.
1988), 420-429.
IECON’02, Sevilla, Spain, Nov.58, 2002, pp. 323–328.
[3] BOLDEA, I.—NASAR, S. A. : Torque Vector Control (TVC) —
A Class of Fast and Robust Torque Speed and Position Digital [19] MILOUDI, A.—Al RADADI, E. A.—DRAOU, A.—MILOUD,
Controller for Electric Drives, Proc. EMPS 15 (1988), 135-148. Y. : Simulation and Modelling of a Variable Gain PI Controller
For Speed Control of a Direct Torque Neuro Fuzzy Controlled
[4] HABLETER, T. G.—PROFUMO, F.—PASTORELLI, M.—
TOLBERT, L. M. : Direct Torque Control of Induction Ma- Induction Machine Drive, in Proc. PESC’04, Aachen, Germany,
chines using Space Vector Modulation, IEEE Trans. Ind. Appli- June. 20-25, 2004, pp. 3493–3498.
cat. 28 (Sept/Oct 1992), 1045-1053. [20] MILOUDI, A.—Al RADADI, E. A.—DRAOU, A. : A Variable
[5] JANG, J.-S. R. : Self-Learning Fuzzy Controllers Based on Tem- Gain PI Controller Used for Speed Control of a Direct Torque
poral Back Propagation, IEEE Trans. Neural Networks 3 (Sept Neuro Fuzzy Controlled Induction Machine Drive, Turkish Jour-
1992), 714-723. nal of Electrical Engineering 15 No. 1 (2007).
[6] JANG, J.-S. R. : ”ANFIS: Adaptive-Network-Based Fuzzy In-
ference System, IEEE Trans. Syst., Man, Cybern. 23 (May/June Received 20 March 2007
1993), 665-684.
[7] CASADEI, D.—GRANDI, G.—SERRA, G. : Study and Im- Eid Al-radadi was born in Madinah, Saudi Arabia in
plementation of a Simplified and Efficient Digital Vector Con-
1967. He received the BEng degree from Detroit Mercy Uni-
troller for Induction Motors, in Proc. EMD’93, Oxford, U.K.,
Sept. 8-10, 1993, pp. 196-201. versity, USA in 1994, the MSc and PhD degrees from Wayne
[8] KAZMIERKOWSKI, M. P.—TUNIA, H. : Automatic Control State University, USA in 2002 all in Electrical Engineering. He
of Converter-Fed Drives, Elsevier, Amsterdam, 1994. was the vice dean for education and training affairs, Medina
[9] TIITINEN, P.—POHKALAINEN, P.—LALU, J. : EPE J. 5 college of technology in 2004. His main research interests are
(Mar 1995), 14-18. in the field of Power Electronics and Intelligent Control of AC
[10] JANG, J.-S. R.—SUN, C.-T. : Neuro-Fuzzy Modeling and Con- drives. He is now the dean of Medina technical college, and
trol, Proc. IEEE 83 (Mar 1995), 378-406. President of technical vocational training council.

EXPORT - IMP ORT

of periodical s and of non-periodic ally
printed matters, book s and CD - ROM s

Krupinská 4 PO BOX 152, 852 99 Bratislava 5,Slovakia

s.r.o. s.r.o.
SLOVART G.T.G. GmbH tel.: ++ 421 2 638 39 472-3, fax.: ++ 421 2 63 839 485 SLOVART G.T.G. GmbH
e-mail: gtg@internet.sk, http://www.slovart-gtg.sk
EXPORT - IMPORT EXPORT - IMPORT