Professional Documents
Culture Documents
Abstract - This paper investigates an artificial neural network PMSM drive proved better in performance. Khan et al [7]
(ANN)-based field-oriented control (NN-FOC) for a surface- proposed a novel neural-network-based self-tuned controller
mounted permanent magnet synchronous machine (SPMSM) for IPMSM drives. However, only minimal improvement
drive. The ANN was trained by using the modified Levenberg- was observed. J. Moreno et al [8] applied a neural network
Marquardt MLM algorithm. The novel Maximum Torque per
control in hybrid vehicle energy management system to
Ampere (MTPA) and flux weakening (FW) approach are
undertaken for electric vehicle (EV) application. The proposed minimize the discharge of the batteries. The experiment was
control is validated in simulation tests and compared with a PI- validated in both simulation and hardware. Z. Chen et al. [9]
based field-oriented control (PI-FOC). The simulation results utilized two neural-based modules that are trained by
show that the maximum operating speed of the proposed control dynamic programming (DP) to optimally manage the energy
is improved by 48% compared to the PI-FOC based control. between engine and battery in power-split hybrid electric
Consequently the proposed neural NN-FOC controller can be a vehicle.
potential replacement of the existing control schemes, such as
PID, fuzzy logic, or others, and provides adequate traction control These abovementioned results show that there is still no
in advanced electric drives, particularly in electric vehicle EV research conducted on an artificial neural network-based
application. vector control for PMSM including both flux weakening
Keywords: surface-mounted permanent magnet synchronous control and electric vehicle EV implementation. Thus, this
machine (SPMSM), Neural-based field-oriented control (NN- paper proposes the new neural-based vector control NN-
FOC), electric vehicle EV application, Maximum Torque per FOC for surface-mounted permanent magnet synchronous
Ampere (MTPA) control, flux weakening (FW) control, modified machine (SPMSM) with flux weakening control. The
Levenberg-Marquardt MLM algorithm SPMSM motor drive with the proposed control will be
I. INTRODUCTION validated through simulation.
In general, the current industries often use a PI-based The rest of this paper is organized as follows. Section 2
field-oriented control (PI-FOC) to operate PMSMs. The gives the full descriptions of PMSM model while Section 3
advantage of the PI controller is its simplicity and ease of introduces the conventional PI-based vector control and
understanding. However, recent studies show that such proposed neural network vector control with full
control strategy is experiencing the following bottlenecks descriptions on training algorithm. Section 4 introduces
related to difficulty to obtain the optimal PI coefficients that novel maximum torque per ampere (MTPA) and flux
satisfy both stability and performance and limited stability weakening approaches. Section 5 shows the simulation
and performance [1-2]. Up to now, as to overcome these result of the proposed NN-FOC control for SPMSM drive.
obstacles, various control schemes were proposed. Lee et al. Finally, the conclusion of the paper is provided in Section 6.
[1] proposed an adaptive H∞ controller to enhance the II. MATHEMATICAL PMSM MODEL
stability in system under parameter perturbations and
external disturbances. Mishra et al. [3] and Kamel et al. [4] The concept of the mathematical PMSM model begins with
utilized a fuzzy logic controller to drive the PMSM. Lu et al. the stator d- and q-axis flux linkage equations, which are
[5] employed a self-constructing recurrent fuzzy neural written as:
network (SCRFNN) to control the PMSM online. The ªOsd º ª Lsd .isd O fd º
proposed SCRFNN was incorporated with two control « O » « L .i » (1)
¬ sq ¼ ¬ sq sq ¼
schemes: self-constructing fuzzy neural network and
where Lsd,sq are the stator d- and q-axis inductances and
recurrent neural network. Xia et al. [6] presented a novel
equal to Lmd,mq + Lls while λfd is the flux linkage constant
direct torque and flux control for matrix converter based
of the stator d-axis winding due to flux produced by the
PMSM drive. The study investigated all matrix converter
magnets in the rotor, where it is assumed that the d-axis is
switching states to control input and output variable. Four
always aligned with the rotor magnetic axis, which is a-axis.
switching schemes were based on the tables, which have
optimal selections of switching. Compared with the In terms of the aforementioned flux linkage equation, the
conventional PI based controller, the matrix converter based stator winding voltages can be written as follows.
ª dO º
R i t sd Ze Osq »
Ho Pham Huy Anh is with Faculty of Electrical and Electronics ªvsd º « s sd dt
Engineering (FEEE), Ho Chi Minh City University of Technology, VNU- «v » « » (2)
HCM, Viet Nam (e-mail: hphanh@hcmut.edu.vn) ¬ sq ¼ « R i t d Osq Z O »
Cao Van Kien is is with Faculty of Electrical and Electronics «¬ s sq dt
e sd »
¼
Engineering (FEEE), Ho Chi Minh City University of Technology, VNU-
HCM, Viet Nam (e-mail: kiencv@hcmut.edu.vn) in which ωe denotes the electrical angular velocity in
Tran Thien Huan is with Ho Chi Minh City University of Technology electrical rad/s. The electrical angular velocity can be
and Education (HCM-UTE), Viet Nam (e-mail: huantt@hcmute.edu.vn) calculated by multiplying the electromechanical angular
Pham Quoc Khanh is with Industrial University of HCM City, Viet
Nam (e-mail: phamquockhanh@iuh.edu.vn)
velocity, ωmech, with the pole pairs, p. If (1) and (2) are § Rs Ze Lq · § 1 ·
¨ ¸
combined, the equation becomes d § isd · Ld Ld ¸ § isd · ¨¨ Ld ¸§ vsd ·
¨ ¸ ¨¨ ¨ ¸ ¸¨
¸¸ (7)
ªvsd º ª Rs Lsd P Ze Lsq º ªisd º ª 0 º dt ¨© isq ¸¹ L Rs ¸ ¨© isq ¸¹ ¨ 1 ¨
¸ © vsq ZeO f ¹
¨Z d ¸ ¨ ¸
«v » « ZL ¨ e Lq Lq ¹¸
Rs Lsq P »¼ «¬isq »¼ «¬O fd Ze »¼
(3)
© © Ld ¹ u
¬ sq ¼ ¬ e sd B
A
with P represents the derivative with respect to time. Under in which isd and isq are the stator d- and q-axis currents; A
a balanced sinusoidal steady state condition, the terms represents the system matrix; B is the input matrix; and u
associated with the time derivative are neglected. Thus, the signifies the input vector. As illustrated, (7) is in a
dq currents become DC. As a result, (3) in steady state can continuous state-space form. Since the controller will be
be rewritten as, implemented in a digital controller, the discretization of (7)
is required and obtained by utilizing either a zero-order or
ªvsd º ª Rs Ze Lsq º ªisd º ª 0 º first-order hold discrete equivalent mechanism as shown as,
«v » «Z L « »« » (4)
¬ sq ¼ ¬ e sd Rs »¼ ¬ isq ¼ ¬O fd Ze ¼
ªisd kTs Ts º ªisd kTs º ª vsd kTs 0 º
« » A« » B« » (8)
The electro-magnetic torque for synchronous machines is «¬isq kTs Ts »¼ i
¬ sq kTs ¼ «¬vsq kTs Ze O fd »¼
described as
in which Ts denotes the sampling period. For Ts is present
Tem
p
2
Osd isq Osq isd (5) on both sides, the equation further simplifies into
Figure 1.PMSM conventional PI- and neural network NN-based FOC control
697
2018 4th International Conference on Green Technology and Sustainable Development (GTSD)
defineV k edq k
Then, these outputs of the input layer feed forward to
¦ U edq k m ¦ V k
N N 2
698
2018 4th International Conference on Green Technology and Sustainable Development (GTSD)
In the constant power region, a control called flux test, parameter variation test, and flux weakening test. Note
weakening control is used. This control sacrifices the current that the initial load torque of 0.1 Nm is used.
to increase a motor’s speed range by producing the flux
First, the acceleration and deceleration test is conducted
against the flux that is produced by the magnet. This control
as follows. At t = 0.56 s, the input speed is increased from 0
is very important because usually, without this control in
rad/sec to 100 rad/sec, and then stays at 100 rad/sec for 1
HEV application, the maximum vehicle speed is only around
second. At t = 1.56s, the speed is decreased to 50 rad/sec and
50 or 60 mph. The main objective is applied NN-FOC to
retains its value for 1 second. At t = 2.56 s, the speed is
translate the reference torque into optimal d- and q-axis
increased to 200 rad/sec and decreases again to 100 rad/sec
currents for MTPA control and into adequate d- and q-axis
at t = 3.56 s. After the acceleration and deceleration test, the
currents for FW control.
load torque is varied as follows. At t = 4.36 s, the load
If the speed exceeds the base speed, the motor operation torque is changed from 0.1 to 0.3 Nm. At t = 5 s, the load
is in the second section. This section operates between the torque is dropped to 0.1 Nm. Eventually, the parameter
base speed and ω2, which is a rated speed. The rated speed is variation test is conducted as follows. At t = 5.5 s, the stator
a speed where voltage-limit ellipse, current-limit circle, and resistance, synchronous inductance, and flux linkage
constant torque curve meet. When the motor is in this constant is changed as, the stator resistance is doubled while
region, MTPA control cannot be used. Instead, the reference the inductance and flux linkage constant is reduced 20%.
torque moves along the voltage-limit ellipse within the
Lastly, the flux weakening control is tested for both
current-limit circle to prevent the back-EMF to exceed the
controllers. At t = 6.75 s, the reference speed is accelerated
maximum voltage. Therefore, optimal control cannot be
at a rate of 150 rad/s until it reached just slightly below the
used.
maximum speed, which is about 400 rad/s. At t = 9.75 s, the
B. Proposed MTPA Algorithm reference speed was decreased to 200 rad/s to check whether
the control can return to normal control from the flux
This paper proposes MTPA control since it uses both d-
weakening control.
and q-axis currents for control. Moreover it help to minimize
the copper loss, which is one of dominant losses in the The traction result of speed, dq currents, abc currents,
PMSM motor [10] and eventually it is quite simple relative and normalized system voltage for both conventional PI and
to other approaches. proposed neural network NN controller are shown in
following figures (from Figure 3 to Figure 8), respectively.
The concept of MTPA control begins with the stator dq
voltage equations of PMSMs (4) and the electromagnetic As the figures show, both controllers perform similarly
torque equation (5). The detailed explanations of these until the flux weakening test. As Fig. 3 shows, when the
equations were covered in previous section. reference speed is about 250 rad/s, the conventional PI-FOC
control loses the stability. Even though the PI gains for
In case the motor is SPMSM, the electro-dynamic torque
conventional control are changed in numerous times, none of
equation is only dependent on the q-axis current because the
the PI gains could solve the problem. Nevertheless, unlike
stator dq inductances are almost equal to each other; thus,
the conventional control, proposed neural NN-FOC control
the reluctance torque, which is the second portion of (5), is
exhibits very stable speed traction in high speed region.
ignored. Thereby, the electro-magnetic torque of SPMSM
When the SPMSM motor reaches 400 rad/sec, as Fig. 4
can be written as
shows, the d-axis current is producing the negative value to
prevent the back-EMF to exceed the maximum voltage as
Tem
p
2
O fd isq (21) presented in Fig. 8.
699
2018 4th International Conference on Green Technology and Sustainable Development (GTSD)
Figure 4. Proposed NN-FOC control related to d- and q-axis current Figure 7. Conventional PI-FOC control related to abc current traction of
traction of SPMSM (simulation) SPMSM (simulation)
Figure 5. Conventional PI-FOC control related to d- and q-axis current Figure 8. Proposed NN-FOC control related to normalized amplitude of
traction of SPMSM (simulation) voltage of SPMSM (simulation)
VI. CONCLUSIONS
This paper proposes a novel neural-based field-oriented
control (NN-FOC) for a surface-mounted permanent magnet
synchronous machine (SPMSM) drive. The neural model is
trained by modified Levenberg-Marquardt MLM algorithm.
Furthermore the novel Maximum Torque per Ampere
(MTPA) and flux weakening (FW) approaches are
undertaken for PMSM-based electric vehicle (EV)
application. The proposed control is validated in simulation
tests and compared with a PI-based field-oriented control
(PI-FOC). The simulation results show that the proposed
neural NN-FOC controller demonstrates quite better
performance than the conventional PI-FOC control and then
provides an excellent traction method applied in advanced
electric drives.
Figure 6. Proposed NN-FOC control of abc current traction of SPMSM
(simulation) ACKNOWLEDGEMENTS
This paper is funded by Vietnam National Foundation for
Science and Technology Development (NAFOSTED) under
grant number MDT 107.01-2018.10 and by Vietnam
National University Ho Chi Minh City (VNU-HCM).
700
2018 4th International Conference on Green Technology and Sustainable Development (GTSD)
701