This article presents a closed loop control of DC series motor fed by DC chopper controlled by an PID controller based intelligent control using ANN (Artificial Neural Network). The PIDANN controller performances are analyzed in both steady state and dynamic operating condition with various set speed and various load torque. Here two different motor parameters are taken for analysis (220V and 110V motor parameters). The static and dynamic performances are taken for comparison with conventional PID controller and existing work. The steady state stability analysis of the system also made using the transfer function model. The equation model is also done to analysis the performances by set speed change and load torque change. The proposed controller have better control over the conventional PID controller and the reported existing work. This system is initially simulated using MATLAB / Simulink and then experimental setup done using P89V51RD2BN microcontroller.
1. Introduction
DC series motor in industrial environment has increased, due to the high performance and high starting torque as suitable drive system. The intelligent control based on Artificial Neural Network (ANN), has been utilized for various applications including motor control. This controller has made the control of complex nonlinear systems with uncertainty or unmodeled dynamics as simple as possible
[1]
. The conventional controllers like PI and PID controllers were widely used earlier for chopper control and motor control applications. But it does not give satisfactory results when control parameters, loading conditions and the motor itself are changed. Intelligent control techniques involving ANN were found to be simpler for implementation and powerful in control applications. MATLAB/ Simulink is used to analyze the performance of the proposed controllers
[2
,
3]
.
The training patterns were generated using conventional PI controller and the effectiveness of the proposed scheme was illustrated using simulation studies and the designed controller was implemented in a low cost 8051based embedded system and the results are documented
[4]
. A comparison was made with PI, fuzzy, and ANN controllers that were implemented in an embedded system for closedloop speed control of DC drive fed by a bucktype DCDC power converter. It was found that the PI based ANN controller has a better control
[5]
. A fuzzy controller for closed loop control of DC drive fed by fourquadrant chopper is designed and the fuzzy controller was implemented in a lowcost 8051 microcontroller based embedded system. The dynamic response of DC motor with fuzzy controller was tested and found to be satisfactory
[6]
. DC series motor drive fed by a single phase controlled rectifier (AC to DC converter) and controlled by fuzzy logic was presented. It has been concluded that the fuzzy logic controller provides better control
[7]
. A fuzzy controller for closed loop control of DC series motor drive fed by DCDC converter was designed. The fuzzy based DCDC drive can have better control
[8

10]
.
A robust PIDlike NeuroFuzzy controller has an ability to compensate for parameter variation, was proposed and applied to the speed control of the indirect vectorcontrolled induction motor. Simulation and experimental results confirm that the system has good dynamic performance
[11]
. The efficient speed controller for a DC servo motor based on neural noncausal inverse modeling of the motor was developed
[12]
. The random training for the neural networks was accomplished online, which enables better absorption of system uncertainties into the neural controller
[13]
. Different hybrid techniques using PID and ANN controller were discussed for DC series motor and separately excited motor
[14

18]
. The stability analysis method based on the higher ordered derivatives of universal learning networks and its application to a DC motor system were described
[19

21]
. FuzzyNeuro control architecture was applied for some special electrical machines like brush less DC motor, permanent magnet DC motor and switched reluctance motor in order to obtain the precise speed control and better performances
[22

24]
.
In this present work the DC series motor with two different parameters are controlled by DCDC buck converter. The PID controller performance is enhanced by Artificial Neural Network. Initially the equation and transfer function model of the DC series motor with DCDC converter is developed and simulated using MATLAB/ Simulink. Then the system is implemented with a NXP 80C51 family Microcontroller.
2. Proposed System
The block diagram of the proposed system with Hybrid PIDANN controller is shown in
Fig. 1
. The system consists of DCDC buck converter (DC chopper) to drive the DC series motor. The system has two loops, namely an inner ON/OFF current control loop and an outer PIDANN speed control loop. The actual current of the motor is sensed by a LEM current sensor and given to the comparator. The comparator compares the actual and reference current and gives the signal to the gate. The gate blocks the PWM signal whenever the motor current exceeds the reference current (I
_{Lref}
).
Block diagram of the proposed system
The PWM coming from the ANN controller is given as first input to the logical AND gate. The actual current and the reference current are compared with a comparator and the comparator output is given to the second input to the AND gate. The comparator output is logical 1 when the actual current within the limit of the reference current. The comparator output is logical 0 when the actual current exceeds the limit. In such a way that the PWM from ANN controller comes out of the logical AND gate when the actual current within the limit. Otherwise the AND gate blocks the PWM and protect the motor from over current. This controller is called as ON/OFF type current controller. Then the PWM is given to the DCDC buck converter through the gate and isolator.
In outer speed control loop, the actual speed ω(k) is sensed by pulse type speed sensor and which is given to the f to v converter and this voltage is used for speed feedback to the ADC and then given to the microcontroller. The error signal e(k) is obtained by comparing actual speed ω(k) with reference speed ωr(k). The change in error Δe(k) can be calculated from the present error e(k) and pervious error e
_{pervious}
(k).
In Hybrid PIDANN controller the error and change in error are given as input. The output of the controller is denoted as duty cycle dc(k). The change in duty cycle Δdc(k) can be calculated from the new duty cycle dc(k) and previous duty cycle dc
_{pervious}
(k). The PWM signal is generated by the Hybrid PIDANN controller. The PWM signal was generated, by comparing the repeating sequence and the duty cycle from the controller. Then the PWM signal controls the output voltage of DCDC converter. The output voltage of the DCDC buck converter is varied from zero to maximum of input voltage applied, so wide range of speed control possible from zero to the rated speed. The input and output gain of the PIDANN controller can be estimated by simulation
[8
,
9]
.
3. Modeling of DC Series Motor with DC Chopper System
Fig. 2
shows the chopper controlled DC series motor circuit. The chopper gain (Duty Cycle) is considered as δ. The transfer function of the system can be obtained from the basic voltage and torque equation
Chopper Controlled DC Series Motor
The motor voltage equation can be written as
where, i
_{a}
is the motor current, R
_{arm}
and R
_{se}
are the armature and series field resistance respectively. L
_{arm}
and L
_{se}
are the armature and series field inductance respectively and M is the mutual inductance. e
_{b}
and e
_{res}
are the back emf and emf due to residual magnetic flux respectively.
The torque equation of DC series motor is
where,
J
is the moment of inertia,
B
is the friction coefficient,
T_{L}
is the load torque and ω is the angular speed.
Considering
I_{a}
=
I_{se}
(
I_{se}
= Series field current) and ω as the motor speed then the emfs and deflecting torque can be written as
where, K
_{af}
is the armature voltage constant and K
_{res}
is the residual magnetism voltage constant.
The transfer function for DC series motor could no longer be valid due to its nonlinear characteristics. In order to obtain the transfer function, the operating point is considered as armature current I
_{a0}
, armature voltage V
_{a0}
, load torque T
_{L0}
, back emf E
_{b0}
and residual emf E
_{res0}
.
Considering the small perturbations around the operating points as Δi
_{a}
, Δv
_{a}
, Δt
_{d}
, Δω, Δv
_{s}
, Δt
_{l}
, Δe
_{b}
and Δe
_{res}
, then the parameters can be written as

ia= Δia+Ia0;va= Δva+Va0

td= Δtd+Td0;ω= Δω+ω0

vs= Δvs+Vs0;tl= Δtl+Tl0

eb= Δeb+Eb0;eres= Δeres+Eres0
Since the quantities (Δi
_{a}
)
^{2}
and (Δi
_{a}
) (Δω) are very small the above Eqs. (1) to (5) can be linearized to
The linear equations can be transformed by the Laplace transform as
Also from Eq. (2)
Substituting (8) and (9) in equ (10) can be written as
Solving equ (13), the motor current can be obtained as
From equ (11) and (14)
Equating the Eqs. (15) and (12)
Assume that there is no changes in the load torque then Δ
T_{L}
(
s
) = 0 , the equ (16) reduced to
The Eq. (17) is the open loop transfer function of DC series motor. The motor is fed by DCDC converter, therefore the transfer function of chopper fed DC series motor is become,
Substituting the Eqs. (17) and (19) in (18)
The Eq. (20) is the transfer function for chopper fed DC series motor.
4. Design of PID and PIDANN Controllers
 4.1 PID controller design and stability analysis
The PID controller improves the steady state and transient response. It is the combination of proportional control action, integral control action and derivative control action. The Proportional control action stabilizes the gain but produces a steady state error, the integral action reduces the steady state error and the derivative action reduces the rate of change of error. The transfer function of PID controller is given in Eq. (21)
where K
_{p}
is the proportional gain, T
_{i}
is the integral time and T
_{d}
is the derivative time.
Substituting the Eqs. (20) and (21) in (22)
where,

a0=KpVs2kafIa0

a1=KpVs2kafIa0Ti

a2=KpVs2kafIa0TiTd

b0= 0b1=Ti[(BRa+Kafω0B) + (2kafIa0) (kafIa0+kres)]

b2=Ti(JRa+kafω0J+BLa) andb3=TiJLa
The PID controller parameters are determined by ZieglerNichols method. In this method, the controller has to run by taking only K
_{p}
value, increase the K
_{p}
value of the controller until the system, selfoscillating with constant amplitude, then take the controller gain. According to ZieglerNichols procedure, the ultimate gain
K_{u}
and the ultimate period of oscillation
P_{u}
, are used to find the parameters of the PID controller. The values of
K_{u}
and
P_{u}
are obtained from the system with MATLAB/Simulink. The K
_{p}
, T
_{i}
and T
_{d}
values are determined using
Table 1
[3]
.
ZieglerNichols method to determine Kp, Ti and Td
ZieglerNichols method to determine Kp, Ti and Td
Fig. 3
shows the Frequency response of DC series motor with PID controller. The stability analysis of PID controller based DC series motor is carried out by bode plot method. The plot is obtained using the transfer function, given in Eq. 25. From the Bode plot it can be absorbed that the phase margin is 45° and the gain margin is 10dB, both gain margin and phase margin are positive, hence the system is stable.
Frequency response of DC series motor with PID controller
The system stability is also checked by Nyquist stability criterion. If G(s)H(s) (loop transfer function) contour in the G(s)H(s) plane corresponding to Nyquist contour in the S plane encircles the point 1+j0 in the anticlockwise direction as many time as the number of right half of S plane poles of G(s)H(s), then the closed loop system is stable. From the Nyquist plot shown in
Fig. 4
, it is examined that the Nyquist contour is not encircles the critical point 1+j0 and there is no poles on right half of the S plane, this implies that the system is stable.
Nyquist stability Plot for DC series motor with PID controller
Though the system with PID controller is stable, the performance of time response which is shown in
Fig. 5
is not good. In order to achieve the better transient and steady state response of the PID controller, it’s performance is enhanced by hybridization with ANN. The error, change in error and duty cycle are the training data for ANN controller and they are obtained from the simulated motordrive system with PID controller. The
Fig. 6
shows the mathematical modeling of DC series motor using MATLAB/Simulink. The complete simulation model of the drive system with PID controller is given in
Fig. 7
.
(a) Speed versus Time response for PID controller (b) Expanded part of overshoot; (c) Expanded part of speed drop with load change
Simulink model of DC series motor
Simulink Model of the system with PID controller
 4.2 Design of PID based artificial neural network controller (Hybrid PIDANN)
The neural network is based on nonlinear control algorithm that can be worked out because of its mathematical nature
[1]
. In this section, the solution of implementing PID controller in a neural network is discussed. The ANN controllers designed in most of the work use a complex network structure for the controller. The aim of this work is to design a simple ANN controller with as low neurons as possible while improving the performance of the controller. A two layer feed forward neural network is constructed with two neurons in the input layer and one in the output layer. As the inputs to the neuron controller is the error and change in error. The neurons are biased.
Generally in an Artificial Neural Network, each neuron has an activation function which specifies the output of a neuron to a given input. Neurons are ‘switches’ that output ‘1’ when they are sufficiently activated and ‘0’ when not activated. The activation functions used for the input neurons are pure linear activation function and for the output neurons are tangent sigmoid activation function. The network is trained for the set of inputs and desired outputs
[4]
. The training patterns are extracted from the designed PID controller. A Supervised back propagation Neural Networktraining algorithm is used with a fixed error goal
[5]
. The network is trained for an error goal of 0.0005. The error (e) and change in error (ce) are the inputs to the controller. The output corresponds to the change in the duty cycle for the motor control. The detail of the trained network is shown in
Fig. 8
. The complete simulation model of the drive system with Hybrid PIDANN controller is given in
Fig. 9
.
Structure of Trained Neural Network
Simulink model of the proposed system
5. Results and Discussion
 5.1 Simulation results
The proposed model has current controller and the Hybrid PIDANN speed controller have been simulated using MATLAB simulink toolbox. The controller was designed and DCDC converter fed DC series motor was tested with different motor parameter. The specifications of DC series motor for 220V and 110V are given in
Table 2
.
DC Series Motor Specifications
DC Series Motor Specifications
The speed variations and current variations for the step change in reference speed from 500rpm to 1000rpm at 4 sec and 1000rpm to 1500rpm at 7 sec with 10% load torque for 220V DC series motor with PID and PIDANN controller are shown in
Fig. 10
. Due to the inertia in the beginning the motor takes 0.3sec to reach the speed from 0 to 500rpm whereas in the second step it took 0.25sec only to reach the speed from 500 to 1000rpm. The Hybrid PIDANN controller performance was analyzed by changing the motor parameters as mentioned in the
Table 2
.
Fig. 11
shows the speed variations and current variations for the step change in reference speed from 500rpm to 1000rpm at 4 sec and 1000rpm to 1500rpm at 8 sec with 10% load torque for 110V DC series motor with PIDANN controller.
Performance of controller for speed variation at 4 sec. and at 7sec with 10% load torque for 220V motor
Performance of controller for speed variation at 4 sec and at 8 sec with 10% load torque for 110V motor
It is seen from the
Fig. 11
the Hybrid PIDANN controller regulates the speed at 1500 rpm. Also due to the inertia in the beginning the motor takes 0.21 sec to reach the speed from 0 to 500rpm whereas in the second step it took 0.15 sec only to reach from 500 to 1000rpm. The Hybrid PIDANN controller provides proper seed regulation for all the step speed changes. The comparative time domain parameters of 220V motor and 110V motor for speed variation of various set speeds are depicted in
Table 3
. From the comparative analysis in
table 3
shows the designed PIDANN controller performance is fairly good compared with the reported result in
[7

9]
.
Time domain specification of PID and PIDANN controller for different set speed change with 10% load
Time domain specification of PID and PIDANN controller for different set speed change with 10% load
The simulated result of motor speed and motor current for various load torque changes from 10% to 25%, 25% to 50% and 50% to 100% applied at 3sec, 5.5sec and 8sec respectively with rated speed with respect to time response with PID controller and PIDANN controller for 220V motor are shown in
Fig. 12
. Also the simulated result of motor speed and motor current for various load torque changes from 10% to 25%, 25% to 50% and 50% to 100% applied at 2sec, 4sec and 6sec respectively with rated speed with respect to time response with PIDANN controller for 110V motor is given in
Fig. 13
. The comparative time domain specification corresponding to these load changes for 220V and 110V are illustrated in
Table 4
for both the controller.
Performance of controller for load variation at 3 sec., 5.5 sec. and 8sec with rated speed for 220V motor
Performance of controller for load variation at 2 sec, 4 sec and 6 sec with rated speed for 110V motor
Time domain specification of ANN and PID controller for different load change with rated speed
Time domain specification of ANN and PID controller for different load change with rated speed
With respect to
Table 4
the overall performance of Hybrid PIDANN controller is evaluated. Up to 25% of load, the maximum speed drop and the recovery time is negligible in PIDANN controller. If the load increased from 25% to 100% its value increased slightly. The steady state error is also very less in PIDANN controller than the conventional PID controller. Therefore the PIDANN controller performance is superior comparing with
[7

9]
and designed PID controller performance during load changes from 10% to 100%.
The time domain performance of set speed changes and load disturbances are simulated and compared with both the controllers for 220V motor are shown in
Fig. 14
. The set speed is changed from 1000rpm to 1800rpm at 4sec. The load disturbance is at 7sec. between 10% and 50%. From the simulated result it is inferred that the Hybrid PIDANN controller gives better performance during speed changes and load disturbances. The performance comparison of proposed Hybrid PIDANN controller with conventional PID controller is given in
Table 5
.
Performance comparison of proposed system with PID controller for the rated speed and 10% load torque
Performance comparison of proposed system with PID controller for the rated speed and 10% load torque
Controllers performance for speed variation at 4 seconds and load disturbance at 7seconds for 220V motor
The speed regulation for various loaded conditions was compared for both controllers in
Fig. 15
. From the curve it is observed that in PID controller up to 50% of load the speed is maintaining constant, after 50 % of load the speed is decreases (4% of the rated speed). In Hybrid PIDANN controller up to 100% of load the speed is maintaining constant value. Thus the Hybrid PIDANN controller gives the better performance than the PID controller. The Hybrid PIDANN controller provides proper speed regulation to the system for the load changes from 10% to 100%. From the
Tables 3
,
4
and
5
it is seen that all the performance parameter value is lesser and few parameters are reduces to zero for hybrid PIDANN controller than the PID controller which shows that the dominance of developed Hybrid PIDANN controller.
Simulation result of speed regulation of the motor with PIDANN controller compared with conventional PID controller response for 220V motor
 5.2 Experimental results
The designed controllers were implemented with DCDC converter fed DC series motor by using the NXP 80C51 microcontroller (P89V51RD2BN) based Embedded System. The microcontroller (P89V51RD2BN) has an 80C51 compatible core and it has the features of 80C51 Central Processing Unit, 5V operating voltage from 0 to 40 MHz, 64 kB of onchip Flash program memory. It also has a PCA (Programmable Counter Array) with PWM and Capture/Compare functions.
In this experimental setup the speed is measured through the compact, high sensing accuracy type optical photo interrupter GP1L53V. This is a device where IR LED and phototransistor is coupled in to plastic housing. The gap between then allows interrupting signal with opaque material and this way switching the output from ON to OFF. It is a pulse type speed sensor. The pulse frequency then converted in to voltage signal by LM2917 frequency to voltage converter. The actual speed in terms of voltage is given to the 8bit ADC ADC0808CCN. Also the speed is captured as voltage signal using a cathode ray oscilloscope. This speed signal is used for speed feedback from the ADC output to the microcontroller.
The set speed variation is done with the help of potentiometer. The PWM is generated using the microcontroller. The PWM is generated at a frequency of 10 KHz. LEM make current sensor LTSR 25NP is used to sense the armature current and gives the output to the AND gate. The AND gate is used to allow the PWM when the actual current is less than the set current. Then the PWM is amplified and fed to the DCDC power converter through an optocoupler isolator CYN 171 and driver IC IR2110 chip.
The implementation is done for 1HP DC series motor. The rating of the motor is 1HP, 220V, 3.3A and 1500rpm. The power converter used for controlling the DC series motor is designed with the power MOSFET IRFP450. The rating of IRFP450 is 500V drain source voltage and 14A drain current. To improve the current rating two MOSETs are connected parallel in the power circuit. But actual current rating required for the 1HP motor is 3.3A only. The DCDC converter output is given to the DC series motor whose speed is to be controlled.
Fig. 16
shows the experimental setup of the proposed system.
Experimental setup of the proposed system
Figs. 17
and
18
show the experimental results of speed variation from standstill to rated speed using PID controller and Hybrid PIDANN controller respectively.
Fig. 19
shows the experimental responses of a DC series motor for step change in speed. The experimental speed regulation for different load changes with PIDANN controller for 220V motor is shown in
Fig. 20
. The controller effectively regulates the speed up to 100% of the load changes. The hardware performance comparison of proposed system with conventional PID controller is given in
Table 6
.
Experimental result of speed response with PID controller
Experimental result of speed response with PID  ANN controller
Experimental result of speed response for step change in speed with PIDANN controller
Experimental result of speed regulation of the motor with PIDANN controller response for 220V motor
Hardware performance comparison of proposed system with PID controller for the speed ωr=1800 rpm and ΔTL=10%
Hardware performance comparison of proposed system with PID controller for the speed ω_{r}=1800 rpm and ΔT_{L}=10%
6. Conclusion
The performance of the hybrid PIDANN controlled DCDC converter fed DC series motor is presented. The steady state and dynamic speed response of DC series motor with Hybrid PIDANN controller was estimated for various load torque and various speed and found that the speed can be controlled effectively. Even the motor parameters vary the controller works effectively and give the proper speed regulation. This advantage arises from the fact that the Artificial Neural Network has the property of generalization and the neural controller can have a smooth control surface. Also, the architecture of the designed neural network controller is simple and uses only two layers with three biased neurons. The hybrid PIDANN controller is easy to implement and reduces the computation burden in embedded systems. Finally the hardware also implemented and verified the hardware results with the simulated results, which almost follow the simulation results. Here the Hybrid PIDANN controller is reduced the computational time. Also the memory required for the program is reduced. The cost of the microcontroller is also less; therefore it can be implemented with economic in real world applications. Hence it can be recommended for all modern industrial drive applications using DC series motor. The analysis provides the various useful parameters and the information for effective use of proposed system.
BIO
I. Thangaraju received his B.E degree in Electrical and Electronics Engineering from University of Madras, India in 2000 and his M.E degree in Power Electronics and Drives from Anna UniversityChennai, India, in 2005. He obtained his Ph.D. degree in Electrical Engineering from Anna University Chennai, India, in 2013. He started his career as Lecturer and later was promoted as Assistant Professor in Electrical and Electronics Engineering department at Muthayammal Engineering College, Rasipuram, India. Then he was working as Assistant Engineer in Hydro Electric Power Station, TANGEDCO / Tamil Nadu Electricity Board, Mettur Dam, India for 5½ years. At present he is working as Assistant Professor in the department of Electrical and Electronics Engineering at Government College of Engineering, Bargur, Tamilnadu, India. He has published more than ten research papers in International Journals and conferences. His research interests include Intelligent controllers and drives for electrical applications. He is a member of IEEE and life member of ISTE.
M. Muruganandam received his B.E degree in Electrical and Electronics Engineering from the Periyar University Salem, India, in 2003, and his M.E degree Power Electronics and Drives from the Anna University of Chennai, India, in 2005. He obtained his Ph.D. degree at the Anna University Chennai, India in 2014. At present he is the Head of Electrical and Electronics Engineering Department (PG) of Muthayammal Engineering College, Rasipuram, Tamilnadu, India. He has been a member of the faculty at Centre for Advanced Research, Muthayammal Engineering College, Rasipuram, Tamilnadu, India since 2005. His research interests include fuzzy logic and neural network applications to power electronics and drives, machine modeling and Embedded Systems. He is a life member of ISTE.
M. Madheswaran received his BE Degree from Madurai Kamaraj University in 1990, an ME Degree from Birla Institute of Technology, Mesra, Ranchi, India in 1992, both in Electronics and Communication Engineering. He obtained his Ph.D. degree in Electronics Engineering from the Institute of Technology, Banaras Hindu University, Varanasi, India, in 1999. At present he is a Principal of Mahendra Engineering College, Mallasamudram West, Tiruchengode, Namakkal Dist. Tamilnadu, India. He has authored over hundred and forty five research publications in international and national journals and conferences. His areas of interest are theoretical modeling and simulation of highspeed semiconductor devices for integrated optoelectronics application, Biooptics and Biosignal Processing. He was awarded the Young Scientist Fellowship (YSF) by the State Council for Science and Technology, Tamilnadu, in 1994 and Senior Research Fellowship (SRF) by the Council of Scientific and Industrial Research (CSIR), Government of India in 1996. Also he has received YSF from SERC, Department of Science and Technology, Govt. of India. He is named in Marquis Who’s Who in Science and engineering in the year 2006. He is a life member of IETE, ISTE and IE (India) and also a senior member of IEEE.
Zurada J. M.
1992
Introduction to Artificial Neural Systems
Jaico Publishing House
Mumbai
Neural Network Tool Box User’s Guide, Version 3
The Mathworks Inc.
Massachusetts
Biswas S. N.
1996
‘Industrial Electronics’
Dhanpat Rai Publishing Company (P) Ltd.
Senthil Kumar N.
,
Sadasivam V.
,
Asan Sukriya H.M.
,
Balakrishnan S.
2008
“Design of low cost universal artificial neuron controller for chopper fed embedded DC drives”
Applied Soft Computing
Science Direct, Elsevier B.V.
8
1637 
1642
DOI : 10.1016/j.asoc.2008.01.001
Kumar N. Senthil
,
Sadasivam V.
,
Asan Sukriya H.M
2008
“A Comparative Study of PI, Fuzzy, and ANN Controllers for Chopperfed DC Drive with Embedded Systems Approach”
Electric Power Components and Systems
36
(7)
680 
695
DOI : 10.1080/15325000701881944
Muruganandam M.
,
Senthil Kumar N.
,
Sadasivam V.
2007
“A Lowcost Fourquadrant Chopperfed Embedded DC Drive Using Fuzzy Controller”
Inter National Journal of Electric Power Components and Systems
35
(8)
907 
920
DOI : 10.1080/15325000701199388
Yousef H.A.
,
Khalil H.M.
“A fuzzy logicbased control of series DC motor drives”
Proceedings of the IEEE International Symposium on
1014 Jul1995
2
517 
522
Muruganandam M.
,
Madheswaran M.
“Performance Analysis of Fuzzy Logic Controller Based DCDC Converter fed DC Series Motor”
IEEE international conference, Chinese Control and Decision Conference (CCDC 2009)
1635 
1640
Muruganandam M.
,
Madheswaran M.
Modeling and Simulation of Modified Fuzzy Logic Controller for Various types of DC motor Drives”
IEEE international conference on Control, Automation, Communication and Energy Conservation 2009
4th6th June 2009
Naik K. B.
,
Pandey S. D.
1989
“Analysis and Performance of a Chopper Fed DC Series Motor during SteadyState and Dynamic Operating Conditions”
Electric Power Systems Research
Science Direct, Science Direct, Elsevier
17
(2)
139 
147
Kim SangMin
,
Han WooYong
2006
“Induction motor servos drive using robust PIDlike NeuroFfuzzy controller”
Control Engineering Practice
Science Direct, Elsevier
14
(5)
481 
487
DOI : 10.1016/j.conengprac.2005.03.002
Rıza ozçalık H.
2006
“An Efficient DC Servo Motor Control Based on Neural Noncausal Inverse Modeling of the Plant”
SpringerVerlag Berlin Heidelberg
1075 
1083
Rubaai Ahmed
,
Kotaru Raj
2000
“Online Identification and Control of a DC Motor Using Learning Adaptation of Neural Networks”
IEEE Transaction on Industry applications
36
(3)
935 
942
DOI : 10.1109/28.845075
Ye Jun
2008
“Adaptive control of nonlinear PIDbased analog Neural Networks for a nonholonomic mobile robot”
Neuro computing
Science Direct, Elsevier
71
(79)
1561 
1565
Tu Diep Cong Thanh
,
Duong Chi Thien
“Hybrid Neuro  PID Controller of Pneumatic Artificial Muscle Manipulator for Knee Rehabilitation”
International Symposium on Electrical & Electronics Engineering 2007
HCM City, Vietnam
Oct 24, 25 2007
20 
29
Cozma Andrei
,
Pitica Dan
“Artificial Neural Network and PID Based Control System for DC Motor Drives”
IEEE, 11th International Conference on Optimization of Electrical and Electronic Equipment, OPTIM.2008
2224 May 2008
161 
166
Burridge Michael J.
,
Qu Zhihua
2003
“An improved nonlinear control design for series DC motors”
Computers & Electrical Engineering
Science Direct, Elsevier
29
(2)
273 
288
DOI : 10.1016/S00457906(01)000350
Wiem Jebri Jemai
,
Houssem Jerbi
,
Mohamed Naceur Abdelkrim
“Nonlinear State Feedback Design for Continuous Polynomial Systems”
International Journal of Control, Automation, and Systems
ICROS, KIEE and Springer 2011
9
(3)
566 
573
DOI : 10.1007/s125550110317x
Matsui Nobuyuki
,
Sugimoto Tomihiko
,
Maenaka Hiromi
1978
“Stability of choppercontrolled DC series motor under regenerative braking”
Electrical Engineering in Japan
Wiley
98
(5)
40 
47
Hussein Ahmed
,
Hirasawa Kotaro
,
Hu Jinglu
“Stability Analysis of a DC Motor System Using Universal Learning Networks”
IEEE International Joint Conference on Neural Networks 2004
2
1285 
1290
Wang GouJen
,
Fong ChuanTzueng
,
Chang Kang J.
2001
“NeuralNetworkBased SelfTuning PI Controller for Precise Motion Control of PMAC Motors”
IEEE Transactions on Industrial Electronics
48
(2)
408 
415
DOI : 10.1109/41.915420
Gencer Cetin
,
Saygin Ali
,
Coskun Ismail
2006
“DSP Based FuzzyNeural Speed Tracking Control of Brushless DC Motor”
SpringerVerlag Berlin Heidelberg
107 
116
ELKhouly F. M.
,
Sharaf A.M.
,
AbdelGhaffar A. S.
,
Mohammed A.A.
1994
“An Adaptive Neural Network Speed Controller for Permanent Magnet DC Motor Drives”
Proceedings of the 26th Southeastern Symposium on System Theory
416 
420
Salah Ali Brwene
,
Hasanien Hany M.
,
Galal Yasser
2011
“Speed Control of Switched Reluctance Motor Using Artificial Neural Network Controller”, Part 1
SpringerVerlag Berlin Heidelberg
250
6 
14