I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
1445
~
1
4
5
2
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
2
.
pp
1
4
4
5
-
1452
1445
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
The neur
a
l
netw
o
rk
-
ba
sed co
n
trol
sy
ste
m
o
f
dire
ct
c
urrent
m
o
tor
driv
er
T
ro
ng
-
T
ha
ng
Ng
uy
en
F
a
c
u
lt
y
o
f
En
e
rg
y
En
g
in
e
e
rin
g
,
Th
u
y
lo
i
Un
iv
e
rsity
,
V
ietn
a
m
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
9
,
2
0
1
8
R
ev
i
s
ed
No
v
12
,
2
0
1
8
A
cc
ep
ted
Dec
3
,
2
0
1
8
T
h
is
a
rti
c
le
a
i
m
s
to
p
ro
p
o
se
a
n
a
d
a
p
ti
v
e
c
o
n
tro
l
sy
st
e
m
f
o
r
th
e
d
irec
t
c
u
rre
n
t
m
o
to
r
d
riv
e
r
b
a
se
d
o
n
t
h
e
n
e
u
ra
l
n
e
tw
o
rk
.
T
h
e
c
o
n
tro
l
sy
ste
m
c
o
n
s
ists
o
f
tw
o
n
e
u
ra
l
n
e
tw
o
rk
s:
th
e
f
irst
n
e
u
ra
l
n
e
tw
o
rk
is
u
se
d
to
e
sti
m
a
te
th
e
s
p
e
e
d
o
f
th
e
d
irec
t
c
u
rre
n
t
m
o
to
r
a
n
d
t
h
e
se
c
o
n
d
n
e
u
ra
l
n
e
tw
o
rk
is
u
se
d
a
s
a
c
o
n
tr
o
ll
e
r.
T
h
e
p
lan
t
i
n
t
h
is
re
se
a
rc
h
in
c
l
u
d
e
s
m
o
to
r
a
n
d
th
e
d
riv
e
r
c
ircu
it
so
it
is
a
c
o
m
p
lex
m
o
d
e
l.
It
is
d
iff
icu
lt
to
d
e
term
in
e
th
e
e
x
a
c
t
p
a
ra
m
e
ters
o
f
th
e
p
lan
t
so
it
is
d
iff
icu
lt
to
b
u
il
d
th
e
c
o
n
tro
ll
e
r.
T
o
so
lv
e
th
e
a
b
o
v
e
d
iff
ic
u
lt
ies
,
th
e
a
u
th
o
r
p
ro
p
o
se
s
a
n
a
d
a
p
ti
v
e
c
o
n
t
ro
l
sy
st
e
m
b
a
se
d
o
n
th
e
n
e
u
ra
l
n
e
tw
o
rk
to
c
o
n
tro
l
t
h
e
p
la
n
t
re
a
c
h
t
h
e
h
ig
h
q
u
a
li
ty
in
t
h
e
c
a
se
o
f
u
n
k
n
o
w
in
g
th
e
p
a
ra
m
e
ters
o
f
th
e
p
lan
t.
T
h
e
re
su
lt
s
a
re
th
a
t
th
e
c
o
n
tro
l
q
u
a
li
ty
o
f
th
e
s
y
ste
m
is
v
e
r
y
g
o
o
d
,
t
h
e
re
sp
o
n
se
sp
e
e
d
a
lw
a
y
s
f
o
ll
o
w
s
th
e
d
e
sire
d
sp
e
e
d
a
n
d
t
h
e
tran
siti
o
n
ti
m
e
is
s
m
a
ll
.
T
h
e
si
m
u
latio
n
re
su
lt
s
o
f
th
e
n
e
u
ra
l
n
e
tw
o
rk
c
o
n
tro
l
s
y
ste
m
a
re
sh
o
w
n
a
n
d
c
o
m
p
a
r
e
d
w
it
h
th
a
t
o
f
a
P
ID
c
o
n
tro
ll
e
r
to
d
e
m
o
n
stra
te
th
e
a
d
v
a
n
tag
e
s o
f
th
e
p
ro
p
o
se
d
m
e
th
o
d
.
K
ey
w
o
r
d
s
:
A
d
ap
tiv
e
C
o
n
tr
o
l
s
tr
u
ctu
r
e
DC
m
o
to
r
Neu
r
al
n
et
w
o
r
k
P
I
D
co
n
tr
o
l
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
r
o
n
g
-
T
h
a
n
g
N
g
u
y
e
n
,
Facu
lt
y
o
f
E
n
er
g
y
E
n
g
i
n
ee
r
in
g
,
T
h
u
y
lo
i U
n
iv
er
s
it
y
,
1
7
5
T
ay
So
n
,
Do
n
g
Da,
Han
o
i
,
Vietn
a
m
.
E
m
ail:
n
g
u
y
en
tr
o
n
g
t
h
a
n
g
@
tl
u
.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
Dir
ec
t
C
u
r
r
en
t
(
DC
)
m
o
t
o
r
is
o
n
e
o
f
a
tr
ad
itio
n
a
l
elec
tr
ic
m
o
to
r
.
I
n
co
m
p
ar
is
o
n
to
th
e
o
th
er
elec
tr
ic
m
o
to
r
s
u
ch
as
b
r
u
s
h
l
ess
DC
m
o
to
r
s
[
1
]
,
in
d
u
ctio
n
m
ac
h
i
n
e
[
2
]
,
[
3
]
,
th
e
DC
m
o
to
r
h
as
s
u
p
er
io
r
f
ea
t
u
r
es
s
u
c
h
a
s
t
h
e
lar
g
e
ele
ctr
o
m
a
g
n
etic
to
r
q
u
e,
t
h
e
s
i
m
p
le
co
n
tr
o
l
s
tr
u
c
tu
r
e
a
n
d
t
h
e
ad
j
u
s
t
ab
ilit
y
o
f
t
h
e
s
p
ee
d
in
a
w
id
e
r
a
n
g
e.
T
h
u
s
,
t
h
e
D
C
m
o
to
r
is
s
t
ill
v
er
y
p
o
p
u
lar
i
n
t
h
e
ap
p
licatio
n
o
f
i
n
d
u
s
tr
ial
ar
ea
s
r
eq
u
ir
ed
th
e
h
i
g
h
-
q
u
alit
y
m
o
tio
n
,
s
u
ch
as
m
i
n
i
n
g
,
tr
an
s
p
o
r
tatio
n
,
s
te
el
r
o
llin
g
,
etc.
So
,
t
h
e
p
er
f
o
r
m
an
ce
d
ev
elo
p
m
en
t
o
f
m
o
to
r
ap
p
licatio
n
s
i
s
v
er
y
i
m
p
o
r
ta
n
t.
T
h
er
e
ar
e
m
a
n
y
r
es
ea
r
ch
f
o
r
co
n
tr
o
llin
g
D
C
Mo
t
o
r
s
s
u
c
h
as
[
4
]
-
[
7
]
,
th
e
m
o
s
t
co
m
m
o
n
m
et
h
o
d
is
u
s
in
g
t
h
e
P
r
o
p
o
r
tio
n
al
–
I
n
teg
r
al
–
Der
iv
at
i
v
e
(
P
I
D)
co
n
tr
o
ller
s
.
Ho
w
e
v
er
,
in
s
ev
er
al
w
o
r
k
in
g
m
o
d
es
o
f
th
e
DC
m
o
to
r
,
th
e
c
h
ar
ac
ter
is
t
ics
o
f
th
e
DC
m
o
to
r
ar
e
n
o
n
li
n
ea
r
s
o
t
h
e
P
I
D
co
n
t
r
o
ller
is
n
o
t s
u
itab
le,
th
e
q
u
alit
y
co
n
tr
o
l is lo
w
.
T
h
er
e
is
s
o
m
e
r
esear
ch
ab
o
u
t
co
n
tr
o
llin
g
t
h
e
n
o
n
li
n
ea
r
o
b
j
ec
ts
s
u
ch
a
s
th
e
b
ac
k
s
tep
p
i
n
g
co
n
tr
o
l
m
et
h
o
d
[
8
]
,
th
e
s
lid
in
g
m
o
d
e
co
n
tr
o
l
m
et
h
o
d
[
9
]
,
th
e
lin
ea
r
izatio
n
tech
n
iq
u
e
[
1
0
]
,
etc.
T
h
e
li
m
ita
tio
n
s
o
f
t
h
e
ab
o
v
e
m
eth
o
d
s
ar
e
th
at
t
h
e
d
if
f
ic
u
lt
p
r
o
b
le
m
w
it
h
t
h
e
ch
o
ice
o
f
ap
p
r
o
p
r
iate
L
y
ap
u
n
o
v
f
u
n
ctio
n
a
n
d
th
e
ch
atter
i
n
g
p
h
e
n
o
m
en
o
n
'
s
e
x
is
ten
ce
.
T
h
er
e
is
a
s
o
lu
tio
n
to
co
n
tr
o
l
th
e
DC
m
o
to
r
th
at
h
as
ac
h
iev
ed
h
i
g
h
-
q
u
alit
y
,
s
u
c
h
as
t
h
e
co
n
tr
o
l
m
et
h
o
d
b
ased
o
n
th
e
f
lat
n
es
s
p
r
in
cip
le
[
1
1
]
.
Ho
w
e
v
er
,
th
e
li
m
itatio
n
o
f
t
h
is
s
o
lu
tio
n
is
t
h
e
n
ee
d
o
f
k
n
o
w
i
n
g
ex
ac
tl
y
t
h
e
p
ar
a
m
eter
s
o
f
t
h
e
DC
m
o
to
r
.
T
o
o
v
er
co
m
e
all
t
h
e
li
m
ita
tio
n
s
o
f
t
h
e
p
r
ev
io
u
s
m
et
h
o
d
,
in
t
h
is
s
tu
d
y
,
th
e
a
u
t
h
o
r
p
r
o
p
o
s
es
a
s
o
l
u
tio
n
to
b
u
ild
a
co
n
tr
o
l
s
y
s
te
m
b
a
s
ed
o
n
t
h
e
Neu
r
al
Net
w
o
r
k
o
f
Mo
d
el
R
e
f
er
e
n
ce
A
d
ap
tiv
e
A
r
ch
itect
u
r
e.
T
h
e
ad
v
an
ta
g
es
o
f
co
n
tr
o
l
s
y
s
te
m
s
u
s
in
g
n
e
u
r
al
n
et
w
o
r
k
ar
e
t
h
at
th
e
s
y
s
te
m
ca
n
co
n
tr
o
l
b
o
t
h
li
n
ea
r
a
n
d
n
o
n
li
n
ea
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
4
4
-
1452
1446
o
b
j
ec
ts
.
T
h
e
s
y
s
te
m
ca
n
w
o
r
k
w
ell
w
i
th
o
u
t
k
n
o
w
i
n
g
th
e
p
a
r
a
m
eter
s
ev
e
n
w
it
h
o
u
t
k
n
o
w
i
n
g
t
h
e
s
tr
u
ct
u
r
e
o
f
th
e
p
lan
t.
T
h
e
co
n
tr
o
ller
ca
n
a
d
j
u
s
t,
to
ad
ap
t its
elf
to
th
e
d
if
f
er
en
t stat
u
s
o
f
t
h
e
p
lan
t.
2.
B
UIL
DI
NG
T
H
E
DR
I
V
E
R
CIRCU
I
T
2
.
1
.
T
he
s
t
ruct
ure
a
nd
t
he
equa
t
io
n o
f
t
he
DC
m
o
t
o
r
T
h
e
d
iag
r
am
o
f
a
s
ep
a
r
atel
y
e
x
cited
DC
Mo
to
r
is
p
r
esen
ted
as Fig
u
r
e
1
[
1
1
]
,
it in
clu
d
es:
a.
T
h
e
f
ield
w
i
n
d
in
g
s
ar
e
in
th
e
s
tato
r
,
th
e
y
ar
e
u
s
ed
to
ex
cite
t
h
e
f
ie
ld
f
l
u
x
.
b.
T
h
e
ar
m
at
u
r
e
co
ils
ar
e
o
n
th
e
r
o
to
r
,
th
ey
ar
e
s
u
p
p
lied
cu
r
r
en
t
v
ia
b
r
u
s
h
an
d
t
h
e
co
m
m
u
tato
r
.
Fig
u
r
e
1
.
T
h
e
d
iag
r
am
o
f
a
s
e
p
ar
ately
e
x
cited
DC
Mo
to
r
T
h
e
m
at
h
e
m
atica
l e
q
u
a
tio
n
s
o
f
DC
Mo
to
r
s
ar
e
as f
o
llo
w
s
:
c.
T
h
e
v
o
ltag
e
eq
u
atio
n
:
E
dt
di
L
i
R
u
a
a
a
a
a
(
V)
(
1
)
W
h
er
e
a
u
is
th
e
ar
m
atu
r
e
v
o
ltag
e
;
a
a
L
R
,
is
th
e
ar
m
atu
r
e
r
esi
s
ta
n
ce
an
d
in
d
u
ctan
ce
.
d.
T
h
e
elec
tr
o
m
o
ti
v
e
eq
u
atio
n
:
).
.
(
f
af
E
i
L
K
E
(
V)
(
2
)
W
h
er
e
ω
is
th
e
s
p
ee
d
o
f
th
e
r
o
to
r
,
K
E
is
th
e
co
ef
f
icie
n
t
o
f
v
o
ltag
e,
f
i
is
th
e
w
in
d
i
n
g
f
ield
cu
r
r
en
t,
af
L
is
th
e
f
ield
ar
m
at
u
r
e
m
u
t
u
al
i
n
d
u
ctan
ce
.
e.
T
h
e
m
o
tio
n
eq
u
atio
n
:
f
m
L
e
T
B
T
T
dt
d
J
(
N.
m
)
(
3
)
W
h
er
e
J
is
th
e
in
er
t
ia,
e
T
is
th
e
e
lectr
o
m
ec
h
a
n
ical
to
r
q
u
e,
L
T
is
t
h
e
to
r
q
u
e
w
h
ic
h
i
m
p
ac
t
to
th
e
s
h
a
f
t,
m
B
is
th
e
co
ef
f
icie
n
t o
f
t
h
e
v
is
co
u
s
f
r
ictio
n
,
f
T
is
th
e
co
u
lo
m
b
f
r
ictio
n
to
r
q
u
e.
f.
T
h
e
elec
tr
o
m
ec
h
an
ica
l to
r
q
u
e
eq
u
atio
n
:
a
f
af
a
T
e
i
i
L
i
K
T
).
.
(
(
N.
m
)
(
4
)
W
h
er
e
T
K
is
th
e
co
ef
f
icie
n
t o
f
t
h
e
to
r
q
u
e.
2
.
2
.
B
uil
din
g
t
he
po
w
er
circ
uit
T
h
e
f
ield
w
in
d
i
n
g
is
co
n
n
ec
t
ed
to
a
co
n
s
tan
t
DC
v
o
lta
g
e
s
o
u
r
ce
.
T
o
co
n
tr
o
l
th
e
m
o
to
r
s
p
ee
d
,
w
e
o
n
l
y
n
ee
d
to
ch
an
g
e
th
e
c
u
r
r
en
t
s
u
p
p
lied
to
th
e
ar
m
a
tu
r
e
co
il
o
f
DC
m
o
to
r
,
ac
co
r
d
in
g
to
(
4
)
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
n
eu
r
a
l
n
etw
o
r
k
-
b
a
s
ed
c
o
n
tr
o
l sys
tem
o
f d
ir
ec
t c
u
r
r
en
t m
o
to
r
d
r
iver
(
T
r
o
n
g
-
Th
a
n
g
N
g
u
ye
n
)
1447
elec
tr
o
m
ec
h
a
n
ical
to
r
q
u
e
(
Te
)
w
ill
b
e
c
h
a
n
g
ed
.
A
cc
o
r
d
in
g
to
(
3
)
,
i
f
t
h
e
e
lectr
o
m
ec
h
a
n
ical
to
r
q
u
e
Te
is
ch
an
g
ed
,
th
e
m
o
to
r
s
p
ee
d
is
ch
an
g
ed
.
I
n
ad
d
itio
n
,
to
i
n
cr
ea
s
e
th
e
f
l
ex
ib
ilit
y
,
t
h
e
D
C
m
o
to
r
m
u
s
t
b
e
ab
le
to
r
ev
er
s
e
th
e
r
o
tatio
n
.
So
,
th
e
p
o
w
er
cir
cu
it
is
co
n
n
ec
ted
in
t
h
e
H
f
o
r
m
,
it
h
as
f
o
u
r
s
w
itc
h
e
s
Q1
-
Q4
.
I
f
w
e
n
ee
d
th
e
D
C
m
o
to
r
r
o
tates
r
ig
h
t,
w
e
co
n
tr
o
l
Q1
a
n
d
Q4
ar
e
o
n
,
Q2
a
n
d
Q3
ar
e
o
f
f
.
C
o
n
v
e
r
s
el
y
,
i
f
w
e
n
ee
d
t
h
e
D
C
m
o
to
r
r
o
tates
le
f
t,
w
e
co
n
tr
o
l Q
1
an
d
Q4
ar
e
o
f
f
,
Q2
an
d
Q3
a
r
e
o
n
.
T
h
e
p
o
w
er
cir
cu
it o
f
t
h
e
DC
m
o
to
r
is
s
h
o
w
n
in
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
T
h
e
p
o
w
er
cir
cu
it o
f
th
e
DC
m
o
to
r
I
n
th
e
p
o
w
er
cir
c
u
it,
to
c
h
an
g
e
th
e
c
u
r
r
en
t
f
ed
i
n
to
t
h
e
ar
m
atu
r
e
co
il
a
i
,
w
e
c
h
a
n
g
e
th
e
p
u
ls
e
f
ed
in
to
th
e
s
w
itc
h
es
b
ased
o
n
P
u
ls
e
-
W
id
th
Mo
d
u
latio
n
(
P
W
M)
m
eth
o
d
.
T
h
e
P
W
M
is
a
m
et
h
o
d
,
w
h
ich
is
t
h
at
u
s
i
n
g
a
r
ec
ta
n
g
u
lar
p
u
ls
e
w
a
v
e
w
it
h
t
h
e
v
al
u
e
o
f
w
id
t
h
(
T
)
is
v
ar
iab
le
a
n
d
t
h
e
v
a
lu
e
o
f
d
u
t
y
c
y
cle
(
D
)
is
co
n
s
ta
n
t.
T
h
e
g
r
ap
h
ex
a
m
p
le
o
f
th
e
P
W
M
m
o
d
u
latio
n
i
s
s
h
o
w
n
in
F
ig
u
r
e
3
.
Fig
u
r
e
3
.
T
h
e
g
r
ap
h
o
f
th
e
P
W
M
m
o
d
u
latio
n
3.
B
UIL
DI
NG
T
H
E
CO
N
T
RO
L
SYS
T
E
M
B
ASE
D
O
N
T
H
E
NE
U
RAL
N
E
T
WO
RK
3
.
1
.
T
he
co
ntr
o
l o
bje
c
t
On
t
h
e
b
asi
s
o
f
t
h
e
p
o
w
er
co
n
t
r
o
l c
ir
cu
it,
w
e
d
e
f
i
n
e
t
h
e
co
n
tr
o
l o
b
j
ec
t,
th
e
in
p
u
t
is
th
e
v
al
u
e
o
f
w
id
t
h
p
u
ls
e
w
i
th
th
e
r
an
g
e
v
al
u
e
is
(
0
-
1
)
,
th
e
o
u
tp
u
t
i
s
t
h
e
m
o
to
r
s
p
ee
d
.
T
o
r
ep
r
esen
t
th
e
r
ela
ti
o
n
s
h
ip
b
et
w
ee
n
th
e
in
p
u
t
a
n
d
th
e
o
u
tp
u
t
o
f
th
e
co
n
tr
o
l
o
b
j
ec
t,
w
e
r
u
n
t
h
e
s
y
s
te
m
in
t
h
e
ca
s
e
th
e
p
u
ls
e
w
id
t
h
v
alu
e
c
h
an
g
e
s
f
r
o
m
0
.
6
to
1
,
th
e
r
esu
lt is
s
h
o
w
n
in
Fig
u
r
e
4
.
T
h
e
Fig
u
r
e
4
s
h
o
w
s
th
a
t
i
f
t
h
e
p
u
ls
e
w
id
t
h
in
cr
ea
s
e
s
,
t
h
e
m
o
to
r
s
p
ee
d
i
n
cr
ea
s
es
an
d
i
f
t
h
e
p
u
ls
e
w
id
t
h
d
ec
r
ea
s
es
,
th
e
m
o
to
r
s
p
ee
d
d
ec
r
ea
s
es.
Ho
w
e
v
er
,
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
p
u
ls
e
w
id
t
h
(
t
h
e
i
n
p
u
t
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
4
4
-
1452
1448
th
e
co
n
tr
o
l o
b
j
ec
t)
an
d
th
e
s
p
ee
d
(
th
e
o
u
tp
u
t o
f
t
h
e
co
n
tr
o
l o
b
j
ec
t)
is
a
co
m
p
lex
r
elatio
n
s
h
i
p
s
o
it is
d
if
f
icu
l
t to
d
eter
m
in
e
t
h
e
e
x
ac
t
eq
u
atio
n
o
f
t
h
is
r
elatio
n
s
h
ip
.
T
h
u
s
,
t
h
e
au
t
h
o
r
p
r
o
p
o
s
es
th
e
co
n
tr
o
l
s
o
lu
tio
n
b
ased
o
n
n
eu
r
al
n
et
w
o
r
k
,
b
ec
au
s
e
t
h
e
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
is
h
i
g
h
l
y
ad
ap
tab
le
an
d
s
elf
-
ad
j
u
s
t
f
it
th
e
s
tat
u
s
o
f
t
h
e
co
n
tr
o
l o
b
j
ec
t.
Fig
u
r
e
4
.
T
h
e
th
e
g
r
ap
h
o
f
th
e
p
u
ls
e
w
id
t
h
an
d
th
e
m
o
to
r
p
ee
d
3.
2
.
T
he
m
o
del r
ef
er
ence
co
ntr
o
l sy
s
t
e
m
us
i
ng
neura
l ne
t
w
o
rk
I
n
th
e
d
y
n
a
m
ic
s
y
s
te
m
s
,
th
e
d
is
tu
r
b
an
ce
,
f
r
ictio
n
a
n
d
u
n
k
n
o
w
n
p
ar
a
m
eter
ar
e
th
e
m
ai
n
r
ea
s
o
n
s
to
r
ed
u
ce
th
e
co
n
tr
o
l
q
u
alit
y
.
T
o
s
o
lv
e
th
at
p
r
o
b
lem
,
i
n
th
i
s
r
esear
ch
,
th
e
au
t
h
o
r
b
u
ild
s
an
ar
tif
ici
a
l
n
e
u
r
al
n
et
w
o
r
k
f
o
r
co
n
tr
o
llin
g
th
e
s
y
s
te
m
.
A
n
eu
r
al
n
et
w
o
r
k
i
n
cl
u
d
es
m
an
y
s
i
m
p
le
co
m
p
o
n
e
n
t
s
,
th
ese
co
m
p
o
n
e
n
t
s
ar
e
th
e
s
in
g
le
-
i
n
p
u
t
n
e
u
r
o
n
o
r
th
e
Mu
ltip
le
-
I
n
p
u
t N
e
u
r
o
n
,
ar
e
s
h
o
w
n
a
s
th
e
Fig
u
r
e
5
[
1
2
]
.
Fig
u
r
e
5
.
T
h
e
co
m
p
o
n
en
t
o
f
n
eu
r
al
n
et
w
o
r
k
:
(
a)
th
e
ca
s
e
o
f
s
in
g
le
-
i
n
p
u
t
,
(
b
)
th
e
ca
s
e
o
f
m
u
ltip
le
-
i
n
p
u
t
I
n
th
e
ca
s
e
o
f
s
i
n
g
er
-
i
n
p
u
t,
t
h
e
o
u
tp
u
t o
f
t
h
e
n
e
u
r
o
n
is
ca
lc
u
l
ated
as
(
5
):
(
5
)
W
h
er
e
p
is
t
h
e
s
ca
lar
in
p
u
t,
w
is
th
e
s
ca
lar
w
e
ig
h
t,
b
i
s
t
h
e
b
ias,
f
is
th
e
tr
an
s
f
er
f
u
n
c
tio
n
,
a
is
th
e
s
ca
lar
n
eu
r
o
n
o
u
tp
u
t.
T
h
e
s
ca
lar
weig
h
t
w
a
n
d
th
e
b
ias
b
ar
e
ad
j
u
s
ted
b
y
t
h
e
lear
n
in
g
r
u
l
e
in
o
r
d
er
f
o
r
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
n
e
u
r
o
n
in
p
u
t
an
d
n
eu
r
o
n
o
u
tp
u
t
m
ee
ts
th
e
m
i
s
s
io
n
g
o
al.
T
h
e
tr
an
s
f
er
f
u
n
c
tio
n
i
s
a
lin
ea
r
o
r
a
n
o
n
li
n
ea
r
f
u
n
ct
io
n
,
t
h
e
tr
an
s
f
er
f
u
n
ctio
n
is
c
h
o
s
en
b
y
t
h
e
d
esi
g
n
er
.
I
n
th
e
ca
s
e
o
f
m
u
lt
ip
le
-
i
n
p
u
t,
th
e
n
eu
r
o
n
n
et
w
o
r
k
i
n
cl
u
d
es
R
in
p
u
ts
.
T
h
u
s
,
p
is
th
e
v
ec
to
r
w
h
ic
h
in
cl
u
d
es
R
in
p
u
ts
p
1
, p
2
,.., p
R
.
w
is
t
h
e
w
ei
g
h
t
m
a
tr
ix
w
h
ic
h
i
n
clu
d
e
s
w
1,
1
, w
1,
2
,.., w
1,
R
.T
h
e
d
iag
r
a
m
i
s
s
h
o
w
n
i
n
Fig
u
r
e
4
(
b
)
,
th
e
o
u
tp
u
t o
f
th
e
n
eu
r
o
n
n
e
t
w
o
r
k
i
s
ca
lcu
lated
as (
6
)
:
(
6
)
Usu
al
l
y
,
a
n
eu
r
al
n
et
w
o
r
k
h
as
s
ev
er
al
la
y
er
s
.
E
ac
h
la
y
er
h
a
s
a
b
ias
v
ec
to
r
(
b
)
an
d
a
w
ei
g
h
t
m
atr
i
x
(
w
)
an
d
a
n
o
u
tp
u
t
v
ec
to
r
(
a
)
.
E
x
a
m
p
le,
Fi
g
u
r
e
6
s
h
o
w
s
th
e
n
et
w
o
r
k
n
eu
r
al
w
it
h
t
h
r
ee
la
y
er
s
,
t
h
e
o
u
tp
u
t
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
n
eu
r
a
l
n
etw
o
r
k
-
b
a
s
ed
c
o
n
tr
o
l sys
tem
o
f d
ir
ec
t c
u
r
r
en
t m
o
to
r
d
r
iver
(
T
r
o
n
g
-
Th
a
n
g
N
g
u
ye
n
)
1449
th
e
f
ir
s
t
la
y
er
is
th
e
in
p
u
t
o
f
t
h
e
s
ec
o
n
d
la
y
er
,
t
h
e
o
u
tp
u
ts
o
f
s
ec
o
n
d
la
y
er
i
s
th
e
in
p
u
t
o
f
t
h
e
t
h
ir
d
la
y
er
.
T
h
e
o
u
tp
u
t la
y
er
is
at
o
n
ce
w
it
h
wh
o
s
e
o
u
tp
u
t is t
h
e
n
et
w
o
r
k
o
u
t
p
u
t,
th
e
o
th
er
la
y
er
s
ar
e
n
a
m
e
d
h
id
d
en
la
y
er
.
Fig
u
r
e
6
.
T
h
e
n
eu
r
al
n
et
w
o
r
k
w
it
h
t
h
r
ee
la
y
er
s
A
n
u
m
b
er
o
f
n
eu
r
al
n
et
w
o
r
k
c
o
n
tr
o
l a
r
ch
itect
u
r
es
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
[
1
3
]
-
[
1
5
]
.
I
n
th
i
s
r
e
s
ea
r
ch
,
t
h
e
au
th
o
r
w
i
ll
u
s
e
th
e
Mo
d
el
R
e
f
er
en
ce
C
o
n
tr
o
l
A
r
c
h
itect
u
r
e
[
1
6
]
,
[
1
7
]
f
o
r
co
n
tr
o
llin
g
th
e
d
r
iv
er
cir
cu
it
o
f
DC
m
o
to
r
.
T
h
e
co
n
tr
o
l
ar
ch
itect
u
r
e
is
s
h
o
w
n
in
th
e
Fi
g
u
r
e
7
.
I
t
is
i
n
cl
u
d
ed
t
w
o
n
e
u
r
al
n
e
t
w
o
r
k
s
:
t
h
e
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
an
d
t
h
e
n
e
u
r
al
n
et
w
o
r
k
p
lan
t
m
o
d
el.
T
h
e
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
cr
ea
tes
th
e
s
u
ita
b
le
co
n
tr
o
l
s
i
g
n
al
f
ed
in
to
t
h
e
p
la
n
t
i
n
o
r
d
er
to
co
n
tr
o
l
th
e
p
lan
t
o
u
tp
u
t
v
al
u
e
as
clo
s
e
as
p
o
s
s
ib
le
to
th
e
d
esire
d
v
alu
e.
T
h
is
d
esire
d
v
alu
e
is
d
eter
m
i
n
ed
b
y
t
h
e
r
ef
er
en
ce
m
o
d
el.
T
h
e
co
n
tr
o
l
er
r
o
r
b
etw
ee
n
t
h
e
p
lan
t
o
u
tp
u
t
v
al
u
e
a
n
d
th
e
r
e
f
er
en
ce
m
o
d
el
o
u
tp
u
t
v
al
u
e
i
s
u
s
ed
in
t
h
e
ad
ap
tiv
e
al
g
o
r
ith
m
to
ad
j
u
s
t th
e
co
n
tr
o
ller
p
ar
am
eter
s
.
I
n
r
ea
lit
y
,
th
e
p
la
n
t
p
ar
a
m
et
er
s
ar
e
u
n
k
n
o
w
n
,
s
o
th
e
ad
ap
tiv
e
alg
o
r
it
h
m
u
p
d
ates
th
e
co
n
tr
o
ller
p
ar
am
eter
s
in
o
r
d
er
th
at
th
e
c
o
n
tr
o
l
er
r
o
r
asy
m
p
to
ticall
y
eq
u
als
ze
r
o
.
T
h
e
d
eta
iled
M
o
d
el
R
ef
er
en
ce
C
o
n
tr
o
l
Stru
ct
u
r
e
is
s
h
o
w
n
i
n
t
h
e
Fi
g
u
r
e
8
.
Fig
u
r
e
7
.
T
h
e
m
o
d
el
r
ef
er
en
ce
co
n
tr
o
l a
r
ch
itectu
r
e
f
o
r
co
n
tr
o
llin
g
th
e
d
r
i
v
er
o
f
DC
m
o
to
r
Fig
u
r
e
8
.
T
h
e
d
etailed
m
o
d
el
r
ef
er
en
ce
co
n
tr
o
l str
u
ct
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
4
4
-
1452
1450
3.
3
.
T
ra
ini
ng
t
he
neura
l net
w
o
rk
T
h
e
co
n
tr
o
l
s
y
s
te
m
o
f
n
e
u
r
al
n
et
w
o
r
k
in
cl
u
d
es
t
w
o
p
ar
ts
.
T
h
e
f
ir
s
t
o
n
e
is
th
e
n
e
u
r
al
n
et
w
o
r
k
o
f
r
ef
er
en
ce
m
o
d
el
w
h
ic
h
i
s
u
s
ed
to
esti
m
ate
th
e
m
o
to
r
s
p
ee
d
.
T
h
e
s
ec
o
n
d
o
n
e
is
t
h
e
n
eu
r
al
n
e
t
w
o
r
k
o
f
co
n
tr
o
ller
,
w
h
ich
i
s
u
s
ed
to
g
en
er
ate
a
co
n
tr
o
l sig
n
al
f
o
r
co
n
t
r
o
llin
g
t
h
e
p
lan
t (
t
h
e
co
n
v
er
ter
)
.
T
o
s
et
th
e
co
n
tr
o
l
s
y
s
te
m
,
f
i
r
s
tl
y
w
e
m
u
s
t
tr
ai
n
th
e
n
e
u
r
a
l
n
et
w
o
r
k
p
lan
t
m
o
d
el.
Af
ter
th
e
p
lan
t
m
o
d
el
i
s
id
en
ti
f
ied
,
w
e
tr
ai
n
t
h
e
n
e
u
r
al
n
et
w
o
r
k
co
n
tr
o
ller
in
o
r
d
er
f
o
r
th
e
p
lan
t
o
u
tp
u
t
f
o
llo
w
s
th
e
r
ef
er
e
n
ce
m
o
d
el
o
u
tp
u
t.
I
n
th
i
s
r
esear
ch
,
w
e
s
et
th
e
s
e
n
e
u
r
al
n
e
t
w
o
r
k
s
in
cl
u
d
ed
t
w
o
la
y
er
s
,
t
h
e
ac
ti
v
atio
n
f
u
n
ct
io
n
s
o
f
th
e
h
id
d
en
la
y
er
is
s
ig
m
o
id
f
u
n
ct
io
n
,
th
e
ac
t
iv
at
io
n
f
u
n
ctio
n
s
o
f
t
h
e
o
u
tp
u
t
la
y
er
i
s
a
lin
ea
r
f
u
n
ctio
n
.
T
h
ese
n
eu
r
al
n
e
t
w
o
r
k
s
ar
e
tr
ain
ed
b
y
b
ac
k
-
p
r
o
p
ag
ati
o
n
u
p
d
ate
r
u
les.
T
h
e
tr
ain
in
g
r
esu
lts
o
f
t
h
e
n
eu
r
al
n
e
t
w
o
r
k
ar
e
s
h
o
w
n
in
F
ig
u
r
e
9
.
Fig
u
r
e
9
.
T
h
e
tr
ain
in
g
r
es
u
lt
s
o
f
th
e
n
eu
r
al
n
et
w
o
r
k
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
4
.
1
.
T
he
co
ntr
o
l sche
m
es
T
o
d
em
o
n
s
tr
ate
t
h
e
ad
v
a
n
ta
g
e
o
f
th
e
p
r
o
p
o
s
ed
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
,
w
e
r
u
n
th
e
s
i
m
u
latio
n
i
n
t
w
o
ca
s
es:
th
e
P
I
D
co
n
tr
o
ller
,
an
d
t
h
e
n
e
u
r
al
n
et
w
o
r
k
co
n
tr
o
ller
.
T
h
e
co
n
tr
o
l
s
y
s
te
m
s
tr
u
ctu
r
es
ar
e
s
h
o
w
n
i
n
Fig
u
r
e
1
0
.
(
a)
(
b
)
Fig
u
r
e
1
0
.
T
h
e
co
n
tr
o
l sch
e
m
e
s
:
(
a)
in
th
e
ca
s
e
o
f
P
I
D
co
n
tr
o
ller
,
(
b
)
in
th
e
ca
s
e
o
f
n
e
u
r
al
n
et
w
o
r
k
co
n
tr
o
ller
T
h
e
p
ar
am
eter
s
o
f
th
e
P
I
D
co
n
tr
o
ller
ar
e
d
eter
m
i
n
ed
b
y
th
e
p
r
o
ce
s
s
o
f
e
x
p
er
i
m
e
n
t
an
d
m
an
y
ti
m
e
s
o
f
t
h
e
ad
j
u
s
t
m
en
t,
t
h
e
o
p
ti
m
al
p
ar
am
eter
s
o
f
th
e
P
I
D
co
n
tr
o
ll
er
ar
e
as
f
o
llo
w
s
:
K
p
=0
.
0
2
,
K
i
=0
.
0
5
,
K
d
=0
.
T
h
e
DC
m
o
to
r
p
ar
a
m
eter
s
ar
e
s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
T
h
e
DC
Mo
to
r
P
ar
am
eter
s
Ra(
)
L
a
(
H
)
R
f
(
)
L
f
(
H
)
L
a
f
(
H
)
J(
k
g
.
m^
2
)
B
m(
N
.
m.s)
T
f
(
N
.
m)
2
.
6
1
0
.
0
3
1
2
7
2
.
5
1
6
1
1
.
1
2
0
.
0
3
1
0
.
0
0
3
2
0
.
4
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
n
eu
r
a
l
n
etw
o
r
k
-
b
a
s
ed
c
o
n
tr
o
l sys
tem
o
f d
ir
ec
t c
u
r
r
en
t m
o
to
r
d
r
iver
(
T
r
o
n
g
-
Th
a
n
g
N
g
u
ye
n
)
1451
4
.
2
.
T
he
s
i
m
ula
t
io
n r
esu
lt
s
I
n
th
e
ca
s
e
o
f
t
h
e
P
I
D
co
n
tr
o
ller
,
th
e
s
i
m
u
latio
n
r
es
u
lts
o
f
t
h
e
co
n
tr
o
l s
y
s
te
m
ar
e
s
h
o
w
n
i
n
Fig
u
r
e
1
0
.
I
n
th
e
ca
s
e
o
f
th
e
n
e
u
r
al
n
e
t
w
o
r
k
co
n
tr
o
ller
,
th
e
s
i
m
u
lat
io
n
r
esu
lt
s
o
f
th
e
co
n
tr
o
l
s
y
s
te
m
ar
e
s
h
o
w
n
in
Fig
u
r
e
1
1
.
E
ac
h
s
i
m
u
la
tio
n
r
e
s
u
lt
co
n
s
is
t
s
o
f
th
e
f
o
llo
w
i
n
g
ch
ar
ac
ter
is
tic
s
:
t
h
e
d
esire
d
s
p
e
ed
,
th
e
ac
t
u
al
s
p
ee
d
o
f
th
e
DC
m
o
to
r
.
I
n
ad
d
itio
n
,
to
ex
p
r
ess
th
e
o
b
j
ec
tiv
it
y
o
f
th
e
s
i
m
u
latio
n
r
es
u
lts
,
t
h
e
s
i
m
u
latio
n
r
es
u
lt
s
also
s
h
o
w
t
h
e
g
r
ap
h
o
f
t
h
e
ar
m
a
tu
r
e
cu
r
r
en
t,
th
e
lo
ad
to
r
q
u
e.
T
h
e
s
i
m
u
lat
io
n
r
esu
l
ts
s
h
o
w
t
h
at:
I
n
th
e
ca
s
e
o
f
P
I
D
co
n
tr
o
ller
,
th
e
s
y
s
te
m
h
a
s
also
m
et
t
h
e
co
n
tr
o
l
r
eq
u
ir
e
m
en
ts
.
Ho
w
ev
er
,
t
h
e
q
u
alit
y
o
f
co
n
tr
o
l
is
n
o
t
as
g
o
o
d
.
Fo
r
ex
a
m
p
le,
th
e
o
v
er
s
h
o
o
t
is
h
ig
h
,
th
e
tr
a
n
s
itio
n
ti
m
e
i
s
lo
n
g
.
I
n
th
e
ca
s
e
o
f
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
,
th
e
q
u
alit
y
o
f
th
e
s
y
s
t
e
m
h
as
i
m
p
r
o
v
ed
a
lo
t.
T
h
e
o
v
er
s
h
o
o
t
is
lo
w
,
t
h
e
tr
an
s
itio
n
ti
m
e
i
s
s
m
all.
T
h
e
s
i
m
u
lat
io
n
r
es
u
lt
s
i
n
th
e
ca
s
e
o
f
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
ller
as sh
o
w
n
in
Fig
u
r
e
1
2
.
Fig
u
r
e
1
1
.
T
h
e
s
i
m
u
latio
n
r
es
u
lts
i
n
t
h
e
ca
s
e
o
f
P
I
D
co
n
tr
o
ller
Fig
u
r
e
1
2
.
T
h
e
s
i
m
u
latio
n
r
es
u
lts
i
n
t
h
e
ca
s
e
o
f
n
eu
r
al
n
et
wo
r
k
co
n
tr
o
ller
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
4
4
-
1452
1452
5.
CO
NCLU
SI
O
N
I
n
th
i
s
r
esear
ch
,
th
e
a
u
th
o
r
h
as
s
u
cc
ee
d
ed
in
b
u
ild
i
n
g
th
e
n
eu
r
al
n
et
w
o
r
k
-
b
ased
m
o
d
el
r
ef
er
en
ce
co
n
tr
o
l s
y
s
te
m
f
o
r
co
n
tr
o
llin
g
th
e
d
r
iv
er
cir
c
u
it o
f
th
e
DC
m
o
to
r
.
T
h
e
s
y
s
te
m
h
a
s
co
n
tr
o
lle
d
th
e
co
n
tr
o
l o
b
j
ec
t
ac
h
iev
ed
th
e
h
ig
h
-
q
u
alit
y
in
th
e
co
n
d
itio
n
s
w
it
h
o
u
t
k
n
o
w
i
n
g
t
h
e
p
ar
a
m
eter
s
a
n
d
s
tr
u
ct
u
r
e
o
f
th
e
co
n
tr
o
l
o
b
j
ec
t.
T
h
e
r
esu
lt
s
h
av
e
b
ee
n
v
er
if
ied
th
r
o
u
g
h
th
e
s
i
m
u
latio
n
o
n
Ma
tlab
an
d
co
m
p
ar
ed
in
th
e
tr
ad
itio
n
al
P
I
D
co
n
tr
o
ller
.
T
h
e
r
esu
lt
s
s
h
o
w
t
h
at
th
e
q
u
al
it
y
o
f
th
e
p
r
o
p
o
s
ed
n
eu
r
al
co
n
tr
o
l
s
y
s
te
m
h
as
b
ee
n
g
r
ea
tl
y
i
m
p
r
o
v
ed
.
T
h
e
r
esp
o
n
s
e
s
p
ee
d
o
f
th
e
DC
m
o
to
r
al
w
a
y
s
f
o
llo
w
s
t
h
e
d
esire
d
s
p
ee
d
w
it
h
th
e
s
h
o
r
t
tr
an
s
itio
n
ti
m
e.
T
h
e
s
u
cc
e
s
s
o
f
t
h
i
s
r
esear
c
h
w
il
l
b
e
th
e
b
asis
f
o
r
f
u
r
th
er
r
e
s
ea
r
ch
.
I
n
t
h
e
n
ex
t
r
esear
ch
,
th
e
au
th
o
r
w
ill
i
n
s
tall
t
h
e
n
eu
r
al
n
et
w
o
r
k
co
n
tr
o
l a
l
g
o
r
ith
m
o
n
th
e
m
icr
o
co
n
tr
o
ller
f
o
r
co
n
tr
o
llin
g
th
e
r
ea
l p
lan
t.
RE
F
E
R
E
NC
E
S
[1
]
P
a
rk
,
J.
S
.
,
&
L
e
e
,
K.
D.
“
De
si
g
n
a
n
d
Im
p
le
m
e
n
tatio
n
o
f
BL
DC M
o
to
r
w
it
h
In
teg
ra
ted
Driv
e
Circu
it
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
(
I
J
PE
DS
)
,
8
(3
),
1
1
0
9
-
1
1
1
6
,
2
0
1
7
.
[2
]
A
b
d
e
lh
a
k
,
B.
,
&
Ba
c
h
ir,
B.
“
A
Hig
h
G
a
in
Ob
se
r
v
e
r
B
a
se
d
S
e
n
so
rles
s
No
n
li
n
e
a
r
Co
n
tr
o
l
of
In
d
u
c
ti
o
n
M
a
c
h
in
e
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
5
(3
),
3
0
5
,
2
0
1
5
.
[3
]
G
u
n
a
b
a
lan
,
R.
,
&
S
u
b
b
iah
,
V
.
,
“
S
p
e
e
d
S
e
n
s
o
rles
s
V
e
c
to
r
C
o
n
tr
o
l
o
f
In
d
u
c
ti
o
n
M
o
t
o
r
Driv
e
w
it
h
P
I
a
n
d
F
u
z
z
y
Co
n
tr
o
ll
e
r
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
5
(3
),
3
1
5
,
2
0
1
5
.
[4
]
Bo
sc
o
,
M
a
y
c
o
n
Ch
i
m
in
i,
e
t
a
l,
"
Esti
m
a
ti
o
n
o
f
P
a
ra
m
e
ters
a
n
d
Tu
n
i
n
g
o
f
a
S
p
e
e
d
P
I
o
f
P
e
rm
a
n
e
n
t
M
a
g
n
e
t
DC
M
o
to
r
u
sin
g
Dif
f
e
r
e
n
ti
a
l
Ev
o
lu
t
io
n
,
"
El
e
c
tric
M
a
c
h
in
e
s
a
n
d
Dr
i
v
e
s
Co
n
fer
e
n
c
e
(
IEM
DC)
,
IEE
E
In
ter
n
a
ti
o
n
a
l
,
p
p
.
1
-
6
,
2
0
1
7
.
[5
]
Ya
o
,
Jia
n
y
o
n
g
,
Zo
n
g
x
ia
Jia
o
,
a
n
d
Da
w
e
i
M
a
,
"
A
d
a
p
ti
v
e
Ro
b
u
s
t
Co
n
tro
l
o
f
DC
M
o
to
rs
w
it
h
Ex
ten
d
e
d
S
tate
Ob
se
rv
e
r
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
d
u
stria
l
El
e
c
tro
n
ics
,
Vo
l
6
1
.
7
,
p
p
.
3
6
3
0
-
3
6
3
7
,
2
0
1
4
.
[6
]
X
u
e
,
Din
g
y
u
,
Ch
u
n
n
a
Zh
a
o
,
a
n
d
Ya
n
g
Qu
a
n
Ch
e
n
,
"
F
ra
c
ti
o
n
a
l
Ord
e
r
P
ID
Co
n
tro
l
o
f
a
DC
-
M
o
to
r
w
it
h
El
a
stic
S
h
a
f
t
:
A
Ca
s
e
S
tu
d
y
,
"
Ame
ric
a
n
Co
n
tro
l
Co
n
fer
e
n
c
e
,
IEE
E,
p
p
.
1
-
6
,
2
0
0
6
.
[7
]
T
h
o
m
a
s,
Ne
e
n
u
,
a
n
d
Dr
P
.
P
o
o
n
g
o
d
i,
"
P
o
siti
o
n
Co
n
tr
o
l
o
f
DC
M
o
t
o
r
u
si
n
g
G
e
n
e
ti
c
A
lg
o
rit
h
m
Ba
s
e
d
P
ID
Co
n
tr
o
ll
e
r
,"
Pro
c
e
e
d
in
g
s o
f
th
e
W
o
rld
C
o
n
g
re
ss
o
n
E
n
g
in
e
e
rin
g
,
v
o
l.
2
,
p
p
.
1
-
3
,
2
0
0
9
.
[8
]
T
ra
b
e
lsi,
R.
,
Kh
e
d
h
e
r,
A
.
,
M
im
o
u
n
i,
M
.
F
.
,
&
M
'
sa
h
li
,
F
.
Ba
c
k
ste
p
p
in
g
C
on
tr
o
l
f
o
r
a
n
I
n
d
u
c
ti
o
n
M
o
to
r
u
si
n
g
a
n
A
d
a
p
ti
v
e
S
li
d
in
g
Ro
t
o
r
-
f
lu
x
Ob
se
rv
e
r
,”
El
e
c
tric P
o
we
r S
y
ste
ms
Re
se
a
rc
h
,
93
,
1
-
1
5
,
2
0
1
2
.
[9
]
A
b
d
e
l
m
a
d
ji
d
,
G
.
,
S
e
g
h
ir,
B.
M
.
,
A
h
m
e
d
,
S
.
,
&
Yo
u
c
e
f
,
M
.
“
S
e
n
so
rles
s
S
li
d
i
n
g
M
o
d
e
V
e
c
to
r
C
o
n
t
ro
l
o
f
In
d
u
c
ti
o
n
M
o
to
r
Driv
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
2
(3
),
2
7
7
,
2
0
1
2
.
[1
0
]
Ya
z
d
a
n
p
a
n
a
h
,
R.
,
S
o
lt
a
n
i,
J.,
&
M
a
rk
a
d
e
h
,
G
.
A
.
“
No
n
li
n
e
a
r
To
r
q
u
e
a
n
d
S
tato
r
F
lu
x
Co
n
tr
o
ll
e
r
f
o
r
In
d
u
c
ti
o
n
M
o
to
r
Driv
e
Ba
se
d
on
A
d
a
p
ti
v
e
In
p
u
t
–
o
u
t
p
u
t
F
e
e
d
b
a
c
k
L
in
e
a
riza
ti
o
n
a
n
d
S
li
d
in
g
M
o
d
e
Co
n
tro
l
,
”
En
e
rg
y
Co
n
v
e
rs
io
n
a
n
d
ma
n
a
g
e
me
n
t
,
49
(
4
),
5
4
1
-
5
5
0
,
2
0
0
8
.
[1
1
]
T
ro
n
g
,
T
.
N.,
“
T
h
e
Co
n
tr
o
l
S
tr
u
c
tu
re
f
o
r
DC
M
o
to
r
Ba
s
e
d
o
n
t
h
e
F
latn
e
ss
Co
n
tr
o
l
,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r
El
e
c
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
(
IJ
PE
DS
)
,
8
(4
)
,
1
8
1
4
-
1
8
2
1
,
2
0
1
7
.
[1
2
]
Ha
g
a
n
,
M
.
T
.
,
De
m
u
th
,
H.
B.
,
&
Je
sú
s,
O.
D.,
“
A
n
In
tro
d
u
c
ti
o
n
to
t
h
e
u
se
o
f
Ne
u
ra
l
N
e
t
w
o
rk
s
in
Co
n
tro
l
S
y
st
e
m
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
R
o
b
u
st
a
n
d
No
n
li
n
e
a
r
Co
n
tr
o
l:
IFA
C
‐
Af
fi
li
a
ted
J
o
u
rn
a
l
,
12
(1
1
),
9
5
9
-
9
8
5
,
2
0
0
2
.
[1
3
]
Hu
n
t
K.
J.,
S
b
a
r
b
a
ro
D.
,
Z
b
ik
o
w
s
k
i
R.
,
a
n
d
G
a
w
th
ro
p
P
.
J.:
"
Ne
u
ra
l
Ne
tw
o
r
k
s
f
o
r
Co
n
tr
o
l
S
y
ste
m
s
-
a
S
u
r
v
e
y
,"
Au
to
m
a
ti
c
a
,
2
8
,
(6
)
,
p
p
.
1
0
8
3
-
1
1
1
2
,
1
9
9
2
.
[1
4
]
Hu
ss
a
in
M
.
A
.
:
"
Re
v
ie
w
o
f
th
e
A
p
p
li
c
a
ti
o
n
s
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
in
Ch
e
m
ica
l
P
r
o
c
e
ss
Co
n
tr
o
l
-
S
im
u
latio
n
a
n
d
On
li
n
e
Im
p
lem
e
n
tatio
n
,"
A
rti
¯
c
ia
l
In
telli
g
e
n
c
e
in
En
g
in
e
e
rin
g
,
1
3
,
p
p
.
5
5
-
68
,
1
9
9
9
.
[1
5
]
De
n
a
i
M
.
A
.
,
P
a
li
s
F
.
,
a
n
d
Zeg
h
b
i
b
,
A
.
:
"
M
o
d
e
li
n
g
a
n
d
C
o
n
tr
o
l
o
f
N
on
-
li
n
e
a
r
S
y
st
e
m
s
u
sin
g
S
o
f
t
Co
m
p
u
ti
n
g
T
e
c
h
n
iq
u
e
s
,
"
Ap
p
l
ied
S
o
ft
Co
mp
u
ti
n
g
,
In
P
re
ss
,
2
0
0
6
.
[1
6
]
Do
u
ra
tso
s,
I.
,
&
G
o
m
m
,
J.
B.
(2
0
0
7
).
Ne
u
ra
l
Ne
t
w
o
rk
Ba
se
d
M
o
d
e
l
Re
f
e
re
n
c
e
A
d
a
p
ti
v
e
Co
n
tro
l
f
o
r
P
r
o
c
e
ss
e
s
w
it
h
T
i
m
e
De
l
a
y
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
In
f
o
rm
a
ti
o
n
a
n
d
S
y
ste
ms
S
c
i
e
n
c
e
s
,
3
(1
),
1
6
1
-
1
7
9
.
[1
7
]
Ng
u
y
e
n
T
ro
n
g
,
T
.
,
&
Ng
u
y
e
n
Du
c
,
M
.
“
S
li
d
in
g
S
u
rf
a
c
e
in
Co
n
se
n
su
s
P
r
o
b
lem
o
f
M
u
lt
i
-
A
g
e
n
t
Rig
i
d
M
a
n
ip
u
lato
r
s
w
it
h
Ne
u
ra
l
Ne
tw
o
rk
Co
n
tro
ll
e
r
,”
En
e
rg
ies
,
10
(
1
2
),
2
1
2
7
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.