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.
8
,
No
.
2
,
A
p
r
il
201
8
,
p
p
.
1010
~
1
0
1
7
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
2
.
p
p
1
0
1
0
-
1017
1010
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
H
ig
h
-
Per
for
m
a
n
ce
u
sing
Ne
ura
l N
etw
o
rk
s in Dire
ct
To
rque
Co
ntrol for
Asy
nchro
no
us M
a
chine
Z
i
neb M
ek
ri
ni,
Sed
di
k
B
ri
M
a
teria
ls
a
n
d
In
str
u
m
e
n
tatio
n
(
M
IM
),
Hig
h
S
c
h
o
o
l
o
f
T
e
c
h
n
o
lo
g
y
,
M
o
u
lay
Is
m
a
il
Un
iv
e
rsit
y
,
M
e
k
n
e
s
,
M
o
ro
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
8
,
2
0
1
7
R
ev
i
s
ed
Dec
2
6
,
2
0
1
7
A
cc
ep
ted
J
an
6
,
2
0
1
8
T
h
is
a
rti
c
le i
n
v
e
sti
g
a
tes
so
lu
ti
o
n
f
o
r
th
e
b
ig
g
e
st p
ro
b
lem
o
f
th
e
Dire
c
t
T
o
rq
u
e
Co
n
tr
o
l
o
n
t
h
e
a
sy
n
c
h
ro
n
o
u
s
m
a
c
h
in
e
t
o
h
a
v
e
th
e
h
ig
h
d
y
n
a
m
ic
p
e
rf
o
r
m
a
n
c
e
w
it
h
v
e
r
y
si
m
p
le
h
y
ste
re
sis
c
o
n
tr
o
l
sc
h
e
m
e
.
T
h
e
Co
n
v
e
n
ti
o
n
a
l
Dire
c
t
T
o
rq
u
e
Co
n
tr
o
l
(CDT
C)
su
ff
e
rs
f
ro
m
so
m
e
d
ra
w
b
a
c
k
s
su
c
h
a
s
h
ig
h
c
u
rre
n
t,
f
lu
x
a
n
d
to
rq
u
e
rip
p
le,
a
s
we
ll
a
s
f
lu
x
c
o
n
tro
l
a
t
v
e
r
y
lo
w
sp
e
e
d
.
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
n
i
n
telli
g
e
n
t
a
p
p
r
o
a
c
h
to
im
p
ro
v
e
th
e
d
irec
t
to
r
q
u
e
c
o
n
tro
l
o
f
in
d
u
c
ti
o
n
m
a
c
h
in
e
w
h
ich
is
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
s
c
o
n
tro
l
.
T
h
e
p
rin
c
i
p
le,
th
e
n
u
m
e
rica
l
p
ro
c
e
d
u
r
e
a
n
d
th
e
p
e
rf
o
rm
a
n
c
e
s
o
f
th
is
m
e
th
o
d
a
re
p
re
se
n
ted
.
S
im
u
latio
n
s
re
su
lt
s
s
h
o
w
th
a
t
th
e
p
ro
p
o
se
d
A
NN
-
D
TC
stra
teg
y
e
ffe
c
ti
v
e
l
y
re
d
u
c
e
s
th
e
to
rq
u
e
a
n
d
f
lu
x
rip
p
les
a
t
l
o
w
s
w
it
c
h
in
g
fre
q
u
e
n
c
y
,
c
o
m
p
a
re
d
w
it
h
F
u
z
z
y
L
o
g
i
c
DT
C
a
n
d
T
h
e
Co
n
v
e
n
ti
o
n
a
l
DT
C.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
As
y
n
c
h
r
o
n
o
u
s
m
ac
h
i
n
e
E
lectr
o
m
a
g
n
etic
f
lu
x
Flu
x
r
ip
p
le
T
o
r
q
u
e
r
ip
p
le
Co
p
y
rig
h
t
©
2
0
1
8
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
:
Z
i
n
eb
Me
k
r
i
n
i,
Ma
ter
ials
an
d
I
n
s
tr
u
m
e
n
tatio
n
(
MI
M)
,
Hig
h
Sc
h
o
o
l o
f
T
ec
h
n
o
lo
g
y
,
Mo
u
la
y
I
s
m
ail
U
n
i
v
er
s
it
y
,
Me
k
n
e
s
,
Mo
r
o
cc
o
.
E
m
ail: z
i
n
eb
.
m
e
k
r
in
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
as
y
n
ch
r
o
n
o
u
s
m
ac
h
i
n
e
i
s
o
n
e
o
f
th
e
m
o
s
t
w
id
el
y
u
s
ed
m
ac
h
in
e
s
i
n
i
n
d
u
s
tr
ial
ap
p
licat
io
n
s
d
u
e
to
its
r
eliab
ilit
y
,
r
elati
v
el
y
lo
w
c
o
s
t
an
d
m
o
d
est
m
ai
n
te
n
an
ce
r
eq
u
ir
e
m
e
n
t
[
1
]
.
A
d
v
a
n
ce
d
tec
h
n
iq
u
es
o
f
ar
ti
f
icia
l
in
telli
g
e
n
ce
co
n
tr
o
l
ar
e
b
ec
o
m
i
n
g
in
cr
ea
s
in
g
l
y
f
a
m
iliar
i
n
v
ar
io
u
s
f
ield
s
o
f
ap
p
licati
o
n
in
r
ec
en
t
y
ea
r
s
.
A
r
ti
f
icial
i
n
telli
g
e
n
ce
is
a
s
cien
ti
f
ic
d
is
cip
lin
e
r
elate
d
to
k
n
o
w
led
g
e
p
r
o
ce
s
s
in
g
an
d
r
ea
s
o
n
i
n
g
,
w
it
h
th
e
ai
m
o
f
Ma
ch
i
n
e
to
p
er
f
o
r
m
f
u
n
ctio
n
s
n
o
r
m
all
y
ass
o
ciate
d
w
it
h
h
u
m
an
in
tel
lig
e
n
ce
s
u
ch
a
s
u
n
d
er
s
t
an
d
in
g
,
r
ea
s
o
n
i
n
g
,
d
ialo
g
u
e,
ad
ap
tatio
n
,
lear
n
i
n
g
[
1
]
.
T
h
e
n
eu
r
al
n
et
w
o
r
k
i
s
w
ell
k
n
o
w
n
f
o
r
its
lear
n
in
g
ab
ilit
y
a
n
d
ap
p
r
o
x
i
m
atio
n
to
an
y
ar
b
itra
r
y
co
n
tin
u
o
u
s
f
u
n
c
tio
n
.
R
ec
e
n
tl
y
,
n
eu
r
al
n
et
w
o
r
k
s
ar
e
s
h
o
w
i
n
g
g
o
o
d
p
r
o
m
is
e
f
o
r
ap
p
licatio
n
in
p
o
w
er
elec
tr
o
n
ics
a
n
d
m
o
tio
n
co
n
tr
o
l
s
y
s
te
m
s
.
I
t
h
as
b
ee
n
p
r
o
p
o
s
ed
in
t
h
e
li
ter
atu
r
e
t
h
at
n
e
u
r
al
n
et
w
o
r
k
s
ca
n
b
e
ap
p
lied
to
p
ar
am
eter
id
en
t
if
ica
tio
n
an
d
s
tate
e
s
ti
m
atio
n
o
f
as
y
n
c
h
r
o
n
o
u
s
m
o
to
r
co
n
tr
o
l s
y
s
te
m
s
[
2
]
.
A
n
e
u
r
al
n
et
w
o
r
k
is
a
s
y
s
te
m
o
f
i
n
ter
co
n
n
ec
ted
n
o
n
li
n
e
ar
o
p
er
ato
r
s
,
r
ec
eiv
in
g
s
i
g
n
al
s
f
r
o
m
t
h
e
o
u
ts
id
e
t
h
r
o
u
g
h
i
ts
i
n
p
u
t
s
,
a
n
d
d
eliv
er
in
g
o
u
tp
u
t
s
i
g
n
al
s
,
w
h
i
ch
ar
e
in
f
ac
t th
e
ac
ti
v
ities
o
f
ce
r
tain
n
eu
r
o
n
s
[
3
]
.
Fo
r
th
e
ap
p
licatio
n
s
co
n
s
id
er
ed
in
t
h
is
,
t
h
e
s
e
i
n
p
u
t
a
n
d
o
u
tp
u
t
s
ig
n
al
s
co
n
s
is
t
o
f
n
u
m
er
ical
s
eq
u
e
n
ce
s
.
Ne
u
r
al
n
et
w
o
r
k
s
ar
e
d
is
cr
ete
ti
m
e
n
o
n
lin
ea
r
f
i
lter
s
[
4
]
.
T
h
ey
m
a
y
b
e
s
tatic
(
o
r
n
o
n
-
lo
o
p
ed
)
o
r
d
y
n
a
m
ic
(
o
r
lo
o
p
ed
)
.
T
h
e
DT
C
m
et
h
o
d
is
c
h
ar
ac
te
r
ized
b
y
its
s
i
m
p
le
i
m
p
le
m
en
tatio
n
a
n
d
f
ast
d
y
n
a
m
ic
r
esp
o
n
s
e.
T
h
is
co
n
tr
o
l
h
as
s
o
m
e
d
i
s
ad
v
a
n
ta
g
es,
v
ar
iab
le
s
w
itc
h
i
n
g
f
r
eq
u
en
c
y
b
e
h
av
io
r
an
d
h
i
g
h
t
to
r
q
u
e
r
ip
p
les
[
5
]
.
An
ad
d
itio
n
al
r
o
b
u
s
t
co
n
tr
o
l
ter
m
i
s
u
s
ed
b
y
a
co
n
tr
o
l
la
w
an
d
ad
ap
tiv
e
la
w
s
i
n
t
h
e
N
eu
r
al
Net
w
o
r
k
,
th
e
ad
v
an
ta
g
e
o
f
t
h
is
tec
h
n
o
lo
g
y
is
th
e
f
aste
s
t
r
esp
o
n
s
e
t
i
m
e,
e
li
m
i
n
atio
n
o
f
r
ip
p
le
an
d
p
er
f
o
r
m
an
ce
as
t
h
e
D
C
m
ac
h
in
e
[
6
]
,
[
7
]
.
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
Hig
h
-
P
erfo
r
ma
n
ce
u
s
in
g
N
eu
r
a
l Netw
o
r
k
s
in
Dir
ec
t To
r
q
u
e
C
o
n
tr
o
l fo
r
….
(
Zin
eb
Mekri
n
i)
1011
T
h
e
A
NNs a
r
e
ca
p
ab
le
o
f
lear
n
in
g
t
h
e
d
esire
d
m
ap
p
in
g
b
et
w
ee
n
t
h
e
in
p
u
ts
a
n
d
o
u
tp
u
t
s
s
i
g
n
al
s
o
f
t
h
e
s
y
s
te
m
w
it
h
o
u
t
k
n
o
w
i
n
g
th
e
ex
ac
t
m
a
th
e
m
atica
l
m
o
d
el
o
f
th
e
s
y
s
te
m
.
Si
n
ce
th
e
ANNs
d
o
n
o
t
u
s
e
th
e
m
at
h
e
m
a
tical
m
o
d
el
o
f
t
h
e
s
y
s
te
m
,
t
h
e
s
a
m
e.
T
h
e
A
NN
s
ar
e
ex
ce
lle
n
t
est
i
m
a
to
r
s
in
n
o
n
l
in
e
ar
s
y
s
te
m
s
[
6
-
8
]
.
Var
io
u
s
A
N
N
b
ased
co
n
tr
o
l
s
t
r
ateg
ies
h
a
v
e
b
ee
n
d
ev
elo
p
ed
f
o
r
d
ir
ec
t
to
r
q
u
e
co
n
tr
o
l
i
n
d
u
c
tio
n
m
o
to
r
d
r
iv
e
to
o
v
er
co
m
e
th
e
s
c
h
e
m
e
d
r
a
w
b
a
ck
.
I
n
th
i
s
p
ap
er
,
n
eu
r
al
n
et
wo
r
k
f
lu
x
p
o
s
itio
n
es
ti
m
a
tio
n
,
s
ec
to
r
s
elec
tio
n
an
d
s
w
itc
h
in
g
v
ec
to
r
s
elec
t
io
n
s
c
h
e
m
e
ar
e
p
r
o
p
o
s
ed
.
I
n
th
i
s
p
ap
er
,
w
e
p
r
esen
t
a
n
e
w
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
D
T
C
(
A
NN
-
DT
C
)
s
ch
e
m
e
in
s
ec
tio
n
1
o
f
an
As
y
n
c
h
r
o
n
o
u
s
m
ac
h
i
n
e
t
o
i
m
p
r
o
v
e
m
o
to
r
to
r
q
u
e
p
er
f
o
r
m
a
n
ce
.
Fo
r
t
h
is
p
u
r
p
o
s
e,
t
h
e
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN)
is
e
m
b
ed
d
ed
to
co
n
v
e
n
tio
n
a
l
DT
C
s
ch
e
m
e
in
Sectio
n
2
.
Mo
r
e
d
etailed
in
f
o
r
m
a
tio
n
ab
o
u
t
A
N
N
b
ased
s
ch
e
m
e
is
p
r
esen
ted
in
th
e
Sectio
n
3
o
f
th
e
p
ap
er
.
T
h
e
Sectio
n
4
p
r
esen
t
th
e
s
i
m
u
latio
n
s
w
it
h
Ma
b
lab
/Si
m
u
li
n
k
s
o
f
t
w
ar
e
a
n
d
th
e
r
esu
lt
s
o
f
t
h
e
m
et
h
o
d
s
a
r
e
d
is
cu
s
s
ed
a
n
d
co
m
p
ar
ed
w
i
th
th
e
co
n
v
e
n
tio
n
al
DT
C
an
d
f
u
zz
y
lo
g
ic
i
n
t
h
e
Se
ctio
n
5
.
2.
P
RINCI
P
L
E
S O
F
ART
I
F
I
C
I
AL
N
E
URA
L
N
E
T
WO
RK
T
h
e
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
s
ar
e
u
n
i
v
er
s
al
o
f
n
o
n
li
n
ea
r
f
u
n
ctio
n
s
[
8
]
.
On
e
o
f
t
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
f
ea
t
u
r
es
o
f
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
s
(
A
N
N)
is
th
e
ir
ab
il
i
t
y
to
lear
n
a
n
d
i
m
p
r
o
v
e
t
h
ei
r
o
p
er
atio
n
u
s
i
n
g
a
tr
ain
i
n
g
d
ata
[
9
]
.
T
h
e
b
asic
ele
m
en
ts
o
f
a
n
A
NN
ar
e
th
e
n
e
u
r
o
n
s
t
h
at
co
r
r
esp
o
n
d
to
co
m
p
u
tin
g
n
o
d
es.
E
ac
h
n
o
d
e
p
er
f
o
r
m
s
t
h
e
m
u
ltip
licat
io
n
o
f
i
ts
i
n
p
u
t
s
i
g
n
als
b
y
co
n
s
tan
t
w
ei
g
h
t
s
,
s
u
m
s
u
p
t
h
e
r
es
u
lts
,
a
n
d
m
ap
s
t
h
e
s
u
m
to
a
n
o
n
li
n
ea
r
f
u
n
c
tio
n
; t
h
e
r
esu
lt is
th
e
n
tr
an
s
f
er
r
ed
to
its
o
u
tp
u
t a
n
d
a
n
ac
ti
v
atio
n
f
u
n
ctio
n
i
s
i
n
te
g
r
ed
as
s
h
o
w
n
in
Fi
g
u
r
e
1
.
T
h
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
a
n
e
u
r
o
n
is
g
iv
en
b
y
:
(
1
)
W
h
er
e
(
x
1
,
x
2
…
x
N)
ar
e
t
h
e
in
p
u
t
s
i
g
n
a
ls
o
f
t
h
e
n
e
u
r
o
n
,
(
w
1
,
w
2
,
…
w
N)
ar
e
t
h
eir
co
r
r
esp
o
n
d
in
g
w
ei
g
h
ts
a
n
d
b
a
b
ias p
ar
am
ete
r
.
Φ
is
a
tan
g
e
n
t si
g
m
o
id
f
u
n
ct
io
n
an
d
y
i
s
th
e
o
u
tp
u
t si
g
n
al
o
f
th
e
n
eu
r
o
n
.
Fig
u
r
e
1
.
R
ep
r
esen
tatio
n
o
f
t
h
e
ar
tif
icial
n
eu
r
o
n
A
N
N
h
a
s
a
v
er
y
s
ig
n
i
f
ica
n
t
r
o
le
in
t
h
e
f
ield
o
f
ar
ti
f
icial
i
n
telli
g
e
n
ce
.
T
h
e
ar
tif
icial
n
e
u
r
o
n
s
lear
n
f
r
o
m
t
h
e
d
ata
f
ed
t
a
n
d
k
ee
p
o
n
d
ec
r
ea
s
i
n
g
th
e
er
r
o
r
.
On
ce
t
r
ain
ed
p
r
o
p
er
ly
,
t
h
eir
r
es
u
lts
a
r
e
v
er
y
m
u
ch
s
a
m
e
r
esu
lt
s
r
eq
u
ir
ed
f
r
o
m
t
h
e
m
,
t
h
u
s
r
ef
er
r
ed
to
as u
n
i
v
er
s
al.
T
h
e
ap
p
licatio
n
o
f
th
e
DT
C
tech
n
iq
u
e
f
o
r
p
o
w
er
s
u
p
p
l
y
b
y
a
v
o
lta
g
e
in
v
er
ter
h
a
s
t
w
o
l
ev
el,
eig
h
t
v
ec
to
r
s
a
n
d
s
i
x
a
n
g
u
lar
s
ec
to
r
s
,
th
e
n
a
co
n
v
e
n
tio
n
al
s
e
lecto
r
(
s
w
itc
h
in
g
tab
le)
t
w
e
lv
e
s
ec
t
o
r
s
w
i
ll
b
e
g
iv
e
n
.
I
t
h
as
b
ee
n
p
r
o
p
o
s
ed
a
n
eu
r
o
n
a
l
s
elec
to
r
o
f
th
e
d
ir
ec
t
co
n
tr
o
l
s
eq
u
en
ce
s
o
f
th
e
t
wo
-
lev
el
in
v
er
ter
w
it
h
th
r
ee
in
p
u
t
s
an
d
t
h
r
ee
o
u
tp
u
t
s
.
2
.
1
.
Neuro
n
Net
w
o
rk
Co
ns
t
ruct
i
o
n St
ep
T
h
e
n
eu
r
al
n
et
w
o
r
k
s
tr
u
ctu
r
e
A
N
N
is
s
h
o
w
n
in
Fi
g
u
r
e
2
.
T
h
e
in
p
u
ts
o
f
th
e
n
eu
r
al
s
elec
t
o
r
ar
e
th
e
s
tates
o
f
f
lu
x
,
to
r
q
u
e,
an
d
a
n
g
u
lar
p
o
s
itio
n
o
f
t
h
e
s
tato
r
f
lu
x
v
ec
to
r
.
T
h
e
o
u
tp
u
ts
ar
e
t
h
e
s
t
ates
o
f
t
h
e
s
w
itc
h
es
o
f
th
e
i
n
v
er
te
r
s
w
i
th
t
w
o
le
v
el
s
r
esp
ec
tiv
el
y
.
)
.
.(
1
b
x
W
Y
i
i
N
i
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
1
0
1
0
–
1017
1012
Fig
u
r
e
2
.
Neu
r
al
n
et
w
o
r
k
ar
c
h
itectu
r
e
2
.
2
.
Neura
l
Net
w
o
rk
Co
ntr
o
llers
f
o
r
DT
C
s
che
m
e
A
n
e
u
r
al
n
et
w
o
r
k
is
a
m
ac
h
in
e
li
k
e
h
u
m
a
n
b
r
ain
w
i
th
p
r
o
p
er
ties
o
f
lear
n
in
g
ca
p
a
b
ilit
y
a
n
d
g
en
er
aliza
tio
n
.
T
h
e
y
r
eq
u
ir
e
a
lo
t
o
f
tr
ai
n
i
n
g
to
u
n
d
er
s
ta
n
d
t
h
e
m
o
d
el
o
f
t
h
e
p
la
n
t.
T
h
e
b
asic
p
r
o
p
er
ty
o
f
t
h
is
n
et
w
o
r
k
i
s
th
a
t
it
is
ab
le
to
ap
p
r
o
x
im
a
te
co
m
p
licated
n
o
n
lin
ea
r
f
u
n
ctio
n
s
[
1
0
]
.
T
h
e
aim
is
to
r
ep
lace
th
e
alg
o
r
ith
m
f
o
r
s
elec
ti
n
g
th
e
s
t
ates
o
f
t
h
e
i
n
v
er
ter
s
w
itc
h
es
s
u
p
p
l
y
i
n
g
a
M
A
S
co
n
tr
o
lled
b
y
DT
C
b
y
a
n
eu
r
al
n
et
w
o
r
k
(
R
N)
ca
p
ab
le
o
f
g
e
n
e
r
atin
g
i
n
t
h
e
s
a
m
e
w
a
y
t
h
e
lo
g
ic
s
i
g
n
a
ls
o
f
t
h
e
co
n
tr
o
l
o
f
t
h
e
in
v
er
ter
s
w
i
tch
e
s
.
I
n
d
ir
ec
t
to
r
q
u
e
co
n
tr
o
l
s
ch
em
e,
n
e
u
r
al
n
et
w
o
r
k
i
s
u
s
e
d
as
a
s
ec
to
r
s
elec
to
r
.
T
h
e
d
ir
ec
t
to
r
q
u
e
n
eu
r
al
co
n
tr
o
ller
is
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
Fig
u
r
e
3
.
Sch
e
m
atic
o
f
DT
C
u
s
in
g
Ne
u
r
al
-
Ne
t
w
o
r
k
co
n
tr
o
lle
r
T
ab
le
1
.
Sw
itch
in
g
L
o
g
ic
C
o
n
d
i
t
i
o
n
f
o
r
f
l
u
x
1
0
C
o
n
d
i
t
i
o
n
f
o
r
t
o
r
q
u
e
1
0
-
1
I
n
th
i
s
co
n
tr
o
l
s
tr
ateg
y
,
th
e
c
o
m
p
ar
ato
r
s
ar
e
s
w
itc
h
ed
b
y
a
n
eu
r
o
n
al
co
n
tr
o
ller
w
h
o
s
e
in
p
u
t
s
ar
e
to
r
q
u
e,
s
tato
r
f
lu
x
a
n
d
an
g
le
p
o
s
itio
n
.
T
h
e
o
u
tp
u
t
is
th
e
p
u
ls
es
allo
w
i
n
g
to
co
n
tr
o
l
th
e
in
v
er
ter
s
w
itch
e
s
,
f
o
r
g
en
er
ati
n
g
t
h
is
n
eu
r
al
co
n
tr
o
ll
er
b
y
Ma
tlab
/
S
i
m
u
l
in
k
o
r
s
e
lectin
g
1
0
h
id
d
en
la
y
er
s
a
n
d
3
lay
er
s
o
f
o
u
tp
u
ts
w
it
h
th
e
ac
ti
v
atio
n
f
u
n
ctio
n
s
o
f
'
ta
n
s
ig
'
an
d
'
p
u
r
eli
n
'
r
esp
ec
ti
v
el
y
; T
h
e
to
r
q
u
e
an
d
f
l
u
x
er
r
o
r
s
ar
e
m
u
l
tip
lied
b
y
th
e
co
n
s
tan
t
v
al
u
e
an
d
w
h
ic
h
ar
e
g
i
v
en
a
s
in
p
u
ts
alo
n
g
w
it
h
t
h
e
f
lo
w
p
o
s
it
io
n
i
n
f
o
r
m
atio
n
to
th
e
n
e
u
r
al
n
et
w
o
r
k
co
n
tr
o
ller
.
Ou
tp
u
t
o
f
th
e
co
n
tr
o
ller
is
co
m
p
ar
ed
with
t
h
e
p
r
ev
io
u
s
s
w
itc
h
i
n
g
s
ta
tes
o
f
in
v
er
ter
.
T
h
e
S
s
s
s
*
s
s
s
*
T
S
e
e
e
C
C
C
*
*
e
e
C
C
e
e
e
C
C
C
*
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
Hig
h
-
P
erfo
r
ma
n
ce
u
s
in
g
N
eu
r
a
l Netw
o
r
k
s
in
Dir
ec
t To
r
q
u
e
C
o
n
tr
o
l fo
r
….
(
Zin
eb
Mekri
n
i)
1013
s
w
itc
h
in
g
lo
g
ic
g
i
v
e
n
b
elo
w
in
t
h
e
T
ab
le
1
d
ev
elo
p
ed
f
r
o
m
t
h
e
o
u
tp
u
t
s
i
g
n
als
o
f
h
y
s
te
r
esis
co
m
p
ar
ato
r
s
;
r
ep
r
esen
t th
e
i
n
cr
e
m
e
n
t (
d
ec
r
em
en
t)
o
f
th
e
f
l
u
x
(
to
r
q
u
e
)
[
1
1
]
,
[
1
2
]
.
T
h
e
n
eu
r
al
n
et
w
o
r
k
is
o
r
g
a
n
iz
ed
in
la
y
er
s
:
a
n
i
n
p
u
t
la
y
er
,
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
er
s
,
an
d
an
o
u
tp
u
t
la
y
er
[
1
2
]
.
A
n
o
d
e
i
n
th
e
h
id
d
en
la
y
er
h
a
s
t
w
o
f
u
n
ctio
n
s
.
T
h
e
f
ir
s
t
is
to
"
s
u
m
m
ar
ize"
th
e
i
n
f
o
r
m
atio
n
t
h
a
t
co
m
e
s
i
n
as
in
p
u
t,
th
e
s
ec
o
n
d
is
to
ap
p
ly
a
tr
an
s
f
er
f
u
n
ctio
n
to
th
is
s
u
m
a
n
d
th
u
s
p
r
o
v
id
e
th
is
r
es
u
lt
to
th
e
o
u
tp
u
t
n
o
d
es
(
o
r
t
h
e
n
o
d
e
o
f
an
o
t
h
er
h
id
d
en
la
y
er
i
f
t
h
er
e
is
o
n
e)
.
Fi
g
u
r
e
4
s
h
o
w
s
t
h
e
p
r
o
p
o
s
ed
n
eu
r
al
n
et
w
o
r
k
f
o
r
DT
C
s
ch
e
m
e
in
w
h
ic
h
,
i
n
p
u
t
,
o
u
tp
u
t
a
n
d
h
id
d
en
la
y
er
s
ar
e
s
h
o
w
n
.
T
h
e
er
r
o
r
s
ig
n
al
s
a
n
d
s
ta
to
r
f
l
u
x
a
n
g
le
ar
e
g
iv
e
n
to
in
p
u
t la
y
er
.
S
w
itc
h
in
g
s
tate
in
f
o
r
m
at
i
o
n
is
tak
e
n
f
r
o
m
t
h
e
o
u
tp
u
t la
y
er
.
Fig
u
r
e
4
.
R
ep
r
esen
tatio
n
o
f
t
h
e
ar
tif
icial
n
eu
r
o
n
I
n
th
i
s
ca
s
e,
th
e
i
n
p
u
ts
o
f
t
h
e
n
eu
r
al
n
et
w
o
r
k
ar
e
th
e
p
o
s
it
io
n
o
f
t
h
e
s
tato
r
f
l
u
x
v
ec
to
r
r
ep
r
esen
ted
b
y
th
e
co
r
r
esp
o
n
d
in
g
s
ec
to
r
n
u
m
b
er
,
th
e
d
if
f
er
en
ce
b
et
w
ee
n
it
s
esti
m
ated
v
al
u
e
an
d
its
r
e
f
er
en
ce
v
al
u
e
an
d
t
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
est
i
m
at
ed
elec
tr
o
m
a
g
n
etic
to
r
q
u
e
a
n
d
th
e
to
r
q
u
e
o
r
t
h
r
ee
n
e
u
r
o
n
s
t
h
er
e
ar
e
in
t
h
e
i
n
p
u
t
la
y
er
.
3.
SI
M
UL
AT
I
O
N
M
O
DE
L
AN
D
ST
RU
CT
UR
E
O
F
DT
C
S
YST
E
M
B
ASE
D
ANN
T
h
e
A
NN
is
tr
ain
ed
b
y
a
lear
n
in
g
alg
o
r
it
h
m
w
h
ic
h
p
er
f
o
r
m
s
th
e
ad
ap
tatio
n
o
f
w
eig
h
ts
o
f
t
h
e
n
et
w
o
r
k
iter
ati
v
el
y
u
n
til
th
e
er
r
o
r
b
et
w
ee
n
tar
g
et
v
ec
to
r
s
an
d
th
e
o
u
tp
u
t
o
f
th
e
A
N
N
is
less
th
an
a
n
er
r
o
r
g
o
al.
T
h
e
m
o
s
t
p
o
p
u
lar
lear
n
i
n
g
a
lg
o
r
ith
m
f
o
r
m
u
ltil
a
y
er
n
e
t
wo
r
k
s
is
t
h
e
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
a
n
d
it
s
v
ar
ian
t
s
[
1
2
]
.
T
h
e
latter
is
im
p
le
m
e
n
ted
b
y
m
an
y
A
NN
s
o
f
t
w
ar
e
p
ac
k
a
g
es
s
u
ch
as
t
h
e
n
e
u
r
al
n
et
w
o
r
k
to
o
lb
o
x
f
r
o
m
M
A
T
L
A
B
[
1
3
]
,
[
1
4
]
.
U
s
in
g
B
ac
k
P
r
o
p
ag
atio
n
al
g
o
r
i
th
m
Ne
u
r
al
Ne
t
w
o
r
k
w
as
tr
ain
ed
w
it
h
e
x
a
m
p
le
w
h
ic
h
is
g
iv
e
n
i
n
M
A
T
L
A
B
NN
d
esig
n
.
T
h
e
Fig
u
r
e
5
s
h
o
w
s
th
e
co
m
p
le
te
s
tr
u
c
tu
r
al
b
l
o
ck
s
o
f
t
h
e
Neu
r
al
Net
w
o
r
k
co
n
tr
o
ller
.
Fig
u
r
e
5
.
Gen
er
al
s
tr
u
ct
u
r
e
o
f
DT
C
-
A
NN
co
n
tr
o
l
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
1
0
1
0
–
1017
1014
T
h
e
b
lo
ck
n
eu
r
al
n
et
w
o
r
k
co
n
t
en
t t
w
o
la
y
er
1
an
d
2
illu
s
tr
ate
d
in
Fig
u
r
e
6.
T
h
e
b
lo
ck
n
eu
r
al
n
et
w
o
r
k
o
f
l
a
y
er
1
is
g
i
v
en
b
y
t
h
e
Fi
g
u
r
e
7
.
Fig
u
r
e
6
.
B
lo
ck
n
eu
r
al
n
e
t
w
o
r
k
la
y
er
1
an
d
la
y
er
2
Fig
u
r
e
7
.
Su
b
B
lo
ck
n
e
u
r
al
n
et
w
o
r
k
la
y
er
1
T
h
e
b
lo
ck
n
eu
r
al
n
et
w
o
r
k
o
f
l
a
y
er
2
is
g
i
v
en
b
y
Fi
g
u
r
e
8
:
Fig
u
r
e
8
.
Su
b
B
lo
ck
n
e
u
r
al
n
et
w
o
r
k
la
y
er
2
T
o
s
tu
d
y
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
f
u
zz
y
lo
g
ic
o
f
d
i
re
ct
to
r
q
u
e
co
n
tr
o
l
g
iv
e
n
b
y
[
1
5
]
,
[
1
6
]
an
d
n
eu
r
al
n
et
w
o
r
k
s
w
itc
h
in
g
tab
le
w
it
h
d
ir
ec
t
to
r
q
u
e
co
n
tr
o
l
s
tr
ateg
y
,
th
e
s
i
m
u
la
tio
n
o
f
t
h
e
s
y
s
t
e
m
w
as
co
n
d
u
cted
u
s
i
n
g
.
Si
m
u
latio
n
r
es
u
lts
f
o
r
a
DT
C
s
y
s
te
m
w
h
e
n
co
n
tr
o
lli
n
g
t
h
e
i
n
d
u
ct
io
n
m
ac
h
in
e
is
g
i
v
en
b
y
Fi
g
u
r
e
9
a
n
d
Fig
u
r
e
1
0
.
I
t
ca
n
b
e
s
ee
n
t
h
at
th
e
r
ip
p
le
in
to
r
q
u
e
w
it
h
F
u
zz
y
lo
g
ic
DT
C
F
L
DT
C
an
d
Ne
u
r
al
Net
w
o
r
k
DT
C
A
N
N_
DT
C
co
n
tr
o
l is less
t
h
a
n
0
.
3
N
m
.
Fig
u
r
e
9
.
E
lectr
o
m
a
g
n
etic
T
o
r
q
u
e
u
s
i
n
g
Neu
r
al
Net
w
o
r
k
Fig
u
r
e
1
0
.
E
lectr
o
m
a
g
n
et
ic
T
o
r
q
u
e
u
s
i
n
g
Fu
zz
y
L
o
g
ic
D
ir
ec
t T
o
r
q
u
e
co
n
tr
o
l
B
y
F
L
DT
C
an
d
ANN_
DT
C
tech
n
iq
u
e
p
r
esen
ted
b
y
F
ig
u
r
e
s
1
1
an
d
1
2
,
th
e
s
tato
r
f
lu
x
a
r
e
th
e
f
as
t
r
esp
o
n
s
e
in
tr
an
s
ien
t
s
tate
an
d
th
e
r
ip
p
le
in
s
tead
y
s
tate
is
r
ed
u
ce
d
r
em
ar
k
ab
l
y
co
m
p
ar
e
d
w
ith
co
n
v
e
n
tio
n
al
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
Hig
h
-
P
erfo
r
ma
n
ce
u
s
in
g
N
eu
r
a
l Netw
o
r
k
s
in
Dir
ec
t To
r
q
u
e
C
o
n
tr
o
l fo
r
….
(
Zin
eb
Mekri
n
i)
1015
DT
C
,
th
e
f
l
u
x
ch
a
n
g
es
t
h
r
o
u
g
h
b
ig
o
s
c
illatio
n
an
d
t
h
e
to
r
q
u
e
r
ip
p
le
is
b
ig
g
er
i
n
F
L
DT
C
.
N
o
tice
th
at
s
tato
r
f
l
u
x
v
ec
to
r
d
escr
ib
es a
tr
aj
ec
to
r
y
al
m
o
s
t c
ir
c
u
lar
in
F
ig
u
r
e
13
.
Fig
u
r
e
1
1
.
Stato
r
Flu
x
u
s
i
n
g
N
eu
r
al
Net
w
o
r
k
Dir
ec
t T
o
r
q
u
e
co
n
tr
o
l
Fig
u
r
e
1
2
.
Stato
r
Flu
x
u
s
i
n
g
F
u
zz
y
lo
g
ic
Dir
ec
t T
o
r
q
u
e
co
n
tr
o
l
Fig
u
r
e
1
3
.
Stato
r
f
lu
x
tr
aj
ec
to
r
y
u
s
in
g
Ne
u
r
al
Net
w
o
r
k
F
ig
u
r
e
1
4
.
Stato
r
C
u
r
r
en
t
u
s
i
n
g
Neu
r
al
Net
w
o
r
k
Dir
ec
t T
o
r
q
u
e
co
n
tr
o
l
Fig
u
r
e
1
5
.
E
v
o
lu
tio
n
o
f
Sp
ee
d
u
s
i
n
g
Ne
u
r
al
Net
w
o
r
k
Dir
ec
t T
o
r
q
u
e
co
n
tr
o
l
T
h
e
Fig
u
r
es
1
4
an
d
1
5
s
h
o
w
th
e
s
tead
y
s
tate
c
u
r
r
en
t
r
esp
o
n
s
e
a
n
d
s
p
ee
d
o
f
t
h
e
F
L
DT
C
an
d
A
N
N_
DT
C
h
as
n
eg
l
ig
ib
le
r
ip
p
le
in
s
tato
r
cu
r
r
en
t
a
n
d
a
n
ea
r
l
y
s
in
u
s
o
id
al
w
a
v
e
f
o
r
m
w
h
ile
as
w
it
h
co
n
v
e
n
tio
n
al
DT
C
t
h
e
s
tato
r
cu
r
r
en
t h
a
s
co
n
s
id
er
ab
l
y
v
er
y
h
ig
h
r
ip
p
le
[
1
7
]
.
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
1
0
1
0
–
1017
1016
I
n
co
m
p
ar
is
o
n
s
t
u
d
y
,
w
e
h
a
v
e
co
m
p
ar
ed
t
h
e
s
i
m
u
latio
n
s
r
esu
l
ts
o
f
n
e
u
r
al
n
et
w
o
r
k
w
it
h
o
th
er
s
m
et
h
o
d
s
DT
C
co
n
tr
o
l
m
eth
o
d
s
lik
e
th
e
co
n
v
en
tio
n
al
Dir
ec
t
T
o
r
q
u
e
C
o
n
tr
o
l.
T
h
e
co
m
p
ar
i
s
o
n
r
es
u
lts
ar
e
class
i
f
ied
as
f
o
llo
w
s
in
t
h
e
T
ab
le
2
:
T
ab
le
2
.
C
o
m
p
ar
is
o
n
s
tu
d
y
b
et
w
ee
n
co
n
v
en
tio
n
al
DT
C
an
d
Neu
r
al
Net
w
o
r
k
DT
C
C
o
n
v
e
n
t
i
o
n
a
l
D
i
r
e
c
t
T
o
r
q
u
e
C
o
n
t
r
o
l
D
i
r
e
c
t
T
o
r
q
u
e
C
o
n
t
r
o
l
b
a
se
d
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
P
r
o
p
o
se
d
i
n
t
h
e
mi
d
-
1
9
8
0
s
b
y
I
.
T
a
k
a
h
a
sh
i
P
r
o
p
o
se
d
b
y
M
c
C
u
l
l
o
c
h
(
n
e
u
r
o
p
h
y
si
o
l
o
g
i
st
)
e
t
P
i
t
t
s
(
l
o
g
i
c
i
a
n
)
I
t
i
s ro
b
u
s
t
a
g
a
i
n
st
t
h
e
p
a
r
a
me
t
r
i
c
v
a
r
i
a
t
i
o
n
s o
f
t
h
e
ma
c
h
i
n
e
I
t
i
s ro
b
u
s
t
a
g
a
i
n
st
t
h
e
p
a
r
a
me
t
r
i
c
v
a
r
i
a
t
i
o
n
s o
f
t
h
e
mac
h
i
n
e
I
t
s st
r
u
c
t
u
r
e
i
s
si
m
p
l
e
a
n
d
r
e
q
u
i
r
e
s n
o
me
c
h
a
n
i
c
a
l
se
n
so
r
.
I
t
s st
r
u
c
t
u
r
e
i
s
si
m
p
l
e
a
n
d
r
e
q
u
i
r
e
s n
o
me
c
h
a
n
i
c
a
l
se
n
so
r
.
T
h
e
f
a
st
t
o
r
q
u
e
a
n
d
f
l
u
x
d
y
n
a
mi
c
s
T
h
e
f
a
st
t
o
r
q
u
e
a
n
d
f
l
u
x
d
y
n
a
m
i
c
s
A
t
l
o
w
sp
e
e
d
s,
t
h
e
f
l
u
x
i
s
d
i
f
f
i
c
u
l
t
t
o
c
o
n
t
r
o
l
.
F
i
x
e
t
h
e
sw
i
t
c
h
i
n
g
f
r
e
q
u
e
n
c
y
.
T
h
e
u
n
d
u
l
a
t
i
o
n
s o
f
t
h
e
t
o
r
q
u
e
a
n
d
f
l
u
x
a
r
o
u
n
d
t
h
e
h
y
st
e
r
e
si
s b
a
n
d
s
H
a
v
e
f
a
st
f
l
u
x
a
n
d
t
o
r
q
u
e
r
e
sp
o
n
se
s w
i
t
h
l
e
ss d
i
s
t
o
r
t
i
o
n
.
4.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
an
i
m
p
r
o
v
e
m
e
n
t
f
o
r
d
ir
ec
t
to
r
q
u
e
co
n
tr
o
l
alg
o
r
ith
m
o
f
a
s
y
n
c
h
r
o
n
o
u
s
m
ac
h
in
e
i
s
p
r
o
p
o
s
ed
u
s
i
n
g
i
n
telli
g
e
n
t
n
e
u
r
al
n
et
w
o
r
k
ap
p
r
o
ac
h
es
w
h
i
ch
co
n
s
is
ts
o
f
r
ep
laci
n
g
t
h
e
s
w
itc
h
in
g
s
elec
to
r
b
lo
ck
an
d
t
h
e
t
w
o
h
y
s
ter
esis
c
o
n
tr
o
ller
s
.
Si
m
u
latio
n
s
s
h
o
w
t
h
at
t
h
e
p
r
o
p
o
s
ed
s
tr
ateg
y
h
a
s
b
etter
p
er
f
o
r
m
a
n
ce
s
th
an
th
e
C
o
n
v
en
tio
n
al
DT
C
a
n
d
Fu
zz
y
lo
g
ic
DT
C
.
T
h
e
co
m
p
ar
i
s
o
n
o
f
th
e
n
e
u
r
al
n
et
w
o
r
k
w
it
h
o
th
er
r
esu
lts
f
u
zz
y
lo
g
ic
o
r
th
e
co
n
v
e
n
tio
n
al
DT
C
h
a
v
e
t
h
e
s
a
m
e
r
es
u
lts
,
w
h
ic
h
e
n
ab
led
u
s
to
v
alid
ate
m
et
h
o
d
s
o
f
i
m
p
r
o
v
i
n
g
th
e
s
tr
ate
g
y
o
f
th
e
Dir
ec
t
T
o
r
q
u
e
C
o
n
tr
o
l
b
ased
o
n
Ne
u
r
al
Net
w
o
r
k
p
r
o
p
o
s
ed
.
T
h
e
A
NN
-
DT
C
s
ch
e
m
e
p
er
f
o
r
m
a
n
ce
h
as
b
ee
n
tes
ted
b
y
s
i
m
u
latio
n
s
w
h
ic
h
is
s
h
o
w
n
as
d
y
n
a
m
ic
r
esp
o
n
s
es
ar
e
t
h
e
f
a
s
ter
i
n
tr
an
s
ie
n
t
s
ta
te
an
d
t
h
e
to
r
q
u
e
r
ip
p
le
in
s
tead
y
s
tate
ar
e
r
ed
u
ce
d
r
em
ar
k
ab
l
y
w
h
en
co
m
p
ar
ed
w
it
h
th
e
co
n
v
e
n
tio
n
al
DT
C
f
o
r
lo
ad
ed
an
d
u
n
lo
ad
ed
co
n
d
itio
n
s
.
T
h
e
m
ai
n
i
m
p
r
o
v
e
m
e
n
ts
s
h
o
w
n
ar
e:
a.
R
ed
u
ctio
n
o
f
to
r
q
u
e
an
d
cu
r
r
e
n
t r
ip
p
les in
tr
a
n
s
ie
n
t a
n
d
s
tea
d
y
s
tate
r
esp
o
n
s
e.
b.
No
f
lu
x
d
r
o
p
p
in
g
s
ca
u
s
ed
b
y
s
ec
to
r
ch
an
g
e
s
ci
r
cu
lar
tr
aj
ec
to
r
y
.
c.
Fas
t stato
r
f
lu
x
r
esp
o
n
s
e
i
n
tr
a
n
s
ie
n
t sta
te.
RE
F
E
R
E
NC
E
S
[1
]
A
b
b
o
u
A
,
M
a
h
m
o
u
d
i
H,
“
P
e
rf
o
rm
a
n
c
e
o
f
a
s
e
n
so
rles
s
sp
e
e
d
c
o
n
tro
l
f
o
r
in
d
u
c
ti
o
n
m
o
to
r
u
si
n
g
DTF
C
stra
t
e
g
y
a
n
d
in
telli
g
e
n
t
tec
h
n
iq
u
e
s”
,
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
S
y
ste
ms
,
V
o
l
5
;
N°
3
;
p
p.
64
-
81
,
2
0
0
9
.
[2
]
X
u
e
z
h
i
W
u
;
L
ip
e
i
H
u
a
n
g
,
“
Dire
c
t
to
rq
u
e
c
o
n
tr
o
l
o
f
th
re
e
-
lev
e
l
in
v
e
rte
r
u
sin
g
n
e
u
ra
l
n
e
two
rk
s
a
s
s
wit
c
h
in
g
v
e
c
to
r
se
lec
to
r”,
In
d
u
stry
A
p
p
li
c
a
ti
o
n
s
Co
n
f
e
re
n
c
e
.
2
0
0
1
,
p
p
.
9
3
9
–
9
4
4
.
[3
]
Cirri
n
c
io
n
e
,
G
,
Cirr
in
c
io
n
e
,
M
,
C
h
u
a
n
L
u
,
P
u
c
c
i,
“
M
.
Dire
c
t
T
o
rq
u
e
Co
n
tro
l
o
f
I
n
d
u
c
ti
o
n
M
o
to
rs
b
y
Us
e
o
f
T
h
e
GM
R
Ne
u
ra
l
Ne
two
rk
”
,
Ne
u
ra
l
N
e
tw
o
rk
s,
P
ro
c
e
e
d
in
g
s o
f
th
e
I
n
tern
a
ti
o
n
a
l
Jo
i
n
t
Co
n
f
e
re
n
c
e
,
p
p
.
2
0
-
2
4
.
[4
]
Z.
M
e
k
rin
i,
a
n
d
S
.
Bri,
“
F
u
z
z
y
L
o
g
ic
A
p
p
li
c
a
ti
o
n
f
o
r
In
telli
g
e
n
t
C
o
n
tro
l
o
f
A
n
As
y
n
c
h
ro
n
o
u
s
M
a
c
h
i
n
e
”
,
In
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
E
E
CS
)
,
V
o
l
7
,
N°
1
,
p
p
.
61
-
70
,
Ju
ly
2
0
1
7
[5
]
F
a
ti
h
Ko
rk
m
a
z
,
M
.
F
a
ru
k
Ca
k
ır
,
İ
s
m
a
il
T
o
p
a
lo
ğ
lu
,
Rıza
G
u
rb
u
z
,
“
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
Ba
se
d
DT
C
Driv
e
r
f
o
r
P
M
S
M
”
,
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
stru
me
n
t
a
ti
o
n
a
n
d
C
o
n
tro
l
S
y
st
e
ms
(
I
J
ICS
)
,
V
o
l
3
;
N°
1
,
p
p
.
1
-
7.
J
a
n
u
a
ry
2
0
1
3
[6
]
S
rin
iv
a
sa
Ra
o
jallu
ri
,
Dr.B.
V
.
S
a
n
k
e
r
Ra
m
,
“
Dire
c
t
T
o
rq
u
e
Co
n
tro
l
Ba
se
d
o
n
S
p
a
c
e
V
e
c
to
r
M
o
d
u
latio
n
w
it
h
A
d
a
p
ti
v
e
S
tato
r
F
lu
x
O
b
se
rv
e
r
f
o
r
In
d
u
c
ti
o
n
M
o
to
rs”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
a
n
d
Ap
p
li
c
a
ti
o
n
s (
IJ
ER
A)
,
Vo
l
2
;
N°
6,
p
p
.
2
9
7
-
3
0
2
,
2
0
1
2
.
[7
]
S
u
re
sh
Ku
m
a
r
Ch
il
u
k
a
,
S
.
Na
g
a
rju
n
a
Ch
a
ry
,
E
Ch
a
n
d
ra
M
o
h
a
n
G
o
u
d
,
“
Dire
c
t
T
o
rq
u
e
C
o
n
tr
o
l
Us
in
g
Ne
u
ra
l
Ne
tw
o
rk
A
p
p
ro
a
c
h
.
P
a
tel
”,
IJ
S
RD
-
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
f
o
r
S
c
ien
ti
fi
c
Res
e
a
rc
h
&
De
v
e
lo
p
me
n
t
.
V
o
l
2
;
N°
4
,
p
p
.
2
3
6
-
2
3
8
,
A
p
r
-
2
0
1
3
.
[8
]
Z.
M
e
k
rin
i,
a
n
d
S
.
Bri
,
“
A
M
o
d
u
la
r
A
p
p
ro
a
c
h
a
n
d
S
im
u
latio
n
o
f
a
n
A
s
y
n
c
h
ro
n
o
u
s
M
a
c
h
in
e
”
,
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
V
o
l
6
,
N°
2
,
p
p
.
1
3
8
5
-
1
3
9
4
,
2
0
1
6
.
[9
]
Ch
a
n
d
n
i
A
.
P
a
rm
a
r1
P
ro
f
.
Am
i
T
,
“
S
p
e
e
d
Co
n
tro
l
T
e
c
h
n
iq
u
e
f
o
r
In
d
u
c
ti
o
n
M
o
to
r
-
A
Re
v
ie
w
.
P
a
tel
,”
IJ
S
RD
-
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
f
o
r
S
c
ien
ti
fi
c
Res
e
a
rc
h
&
De
v
e
lo
p
me
n
t
,
V
o
l
2
,
N°
8
,
p
p
.
6
8
2
-
6
8
6
,
2
0
1
4
.
[1
0
]
Na
re
n
d
ra
,
K.S
.
a
n
d
P
a
rt
h
a
sa
ra
th
y
,
K,
“
Id
e
n
ti
f
ica
ti
o
n
a
n
d
Co
n
tr
o
l
o
f
D
y
n
a
m
ica
l
S
y
ste
m
s
Us
in
g
N
e
u
ra
l
Ne
t
w
o
rk
s”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
Ne
t
wo
rk
s,
Vo
l
1,
p
p
4
-
2
7
,
2
0
1
3
.
[1
1
]
M
.
Cirstea
,
A
.
Din
u
,
J.
K
h
o
r,
M
.
M
c
c
o
rm
ick
,
“
N
e
u
ra
l
a
n
d
F
u
z
z
y
L
o
g
ic
Co
n
tro
l
o
f
Driv
e
s
a
n
d
P
o
w
e
r
S
y
ste
m
s.
Ne
w
n
e
s
”,
An
imp
rin
t
o
f
El
se
v
ier
S
c
ien
c
e
Fi
rs
t
p
u
b
li
s
h
e
d
,
4
1
2
p
a
g
e
s,
2
0
0
2
.
[1
2
]
Z.
M
e
k
rin
i,
a
n
d
S
.
Bri,
“
P
e
rf
o
rm
a
n
c
e
o
f
a
n
In
d
irec
t
F
ield
-
Orie
n
ted
Co
n
tro
l
f
o
r
A
s
y
n
c
h
ro
n
o
u
s
M
a
c
h
in
e
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IJ
ET
)
,
V
o
l
8
,
N°
2
,
p
p
.
7
2
6
-
7
3
3
,
2
0
1
6
.
[1
3
]
G
ra
w
b
o
w
sk
i,
P
.
Z.
,
Ka
z
m
ier
k
o
ws
k
i,
M
.
P
,
Bo
se
,
B
.
K.
a
n
d
Blaa
b
jerg
,
F
,
“
S
im
p
le
Dire
c
t
-
T
o
rq
u
e
Ne
u
ro
F
u
z
z
y
Co
n
tr
o
l
o
f
P
W
M
-
In
v
e
rter
-
F
e
d
In
d
u
c
ti
o
n
M
o
to
r
Driv
e
”
,
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
In
d
u
stria
l
El
e
c
tr
o
n
ics
,
V
o
l
4
7
,
p
p
.
8
6
3
-
8
7
0
,
2
0
0
7
.
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
Hig
h
-
P
erfo
r
ma
n
ce
u
s
in
g
N
eu
r
a
l Netw
o
r
k
s
in
Dir
ec
t To
r
q
u
e
C
o
n
tr
o
l fo
r
….
(
Zin
eb
Mekri
n
i)
1017
[1
4
]
Ra
jes
h
Ku
m
a
r,
R.
A
.
G
u
p
ta,
S
.
V.
Bh
a
n
g
a
le,
H
i
m
a
n
sh
u
G
o
th
w
a
,
“
Arti
fi
c
ia
l
Ne
u
r
a
l
Ne
two
rk
Ba
se
d
Dire
c
tt
o
rq
u
e
Co
n
tro
l
Of
In
d
u
c
ti
o
n
M
o
to
r
Dr
ive
s
”
,
Co
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
in
El
e
c
tri
c
a
l
S
c
ien
c
e
s (ICT
ES
2
0
0
7
)
.
I
n
d
ia
,
p
p
.
3
6
1
-
3
6
7
,
2
0
0
7
.
[1
5
]
G
h
o
u
il
i,
J
a
n
d
Ch
e
rit
i,
“
I
n
d
u
c
ti
o
n
mo
to
r
d
y
n
a
mic
n
e
u
ra
l
sta
t
o
r
fl
u
x
e
stima
ti
o
n
u
si
n
g
a
c
ti
v
e
a
n
d
re
a
c
ti
v
e
p
o
we
r
fo
r
d
ire
c
t
to
rq
u
e
c
o
n
tro
l”
,
P
o
w
e
r
El
e
c
tro
n
ics
S
p
e
c
ialists Co
n
f
e
re
n
c
e
,
p
p
.
5
0
1
–
5
0
5
,
1
9
9
9
.
[1
6
]
A
.
Ba
-
ra
z
z
o
u
k
,
A
.
Ch
e
rit
i
a
n
d
G
.
Oliv
ier,
“
A
Ne
u
ra
l
Ne
t
w
o
rk
s
Ba
s
e
d
F
iel
d
Orie
n
te
d
C
o
n
tr
o
l
S
c
h
e
m
e
F
o
r
In
d
u
c
ti
o
n
M
o
to
r”
,
IEE
E
In
d
u
stry
Ap
p
li
c
a
ti
o
n
s S
o
c
iety
An
n
u
a
l
M
e
e
ti
n
g
Ne
w
Or
lea
n
s,
L
o
u
isi
a
n
a
,5
-
9
,
Oc
to
b
e
r
1
9
9
7
[1
7
]
R.
T
o
u
f
o
u
ti
S
.
M
e
z
ian
e
,
H.
Be
n
a
ll
a
,
“
Dire
c
t
T
o
rq
u
e
Co
n
tr
o
l
f
o
r
I
n
d
u
c
ti
o
n
M
o
to
r
Us
in
g
F
u
z
z
y
L
o
g
ic
”,
ICGS
T
T
ra
n
s
.
V
o
l
6
,
N°
2,
p
p
.
17
-
24
J
u
n
e
,
2
0
0
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.