I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
d
van
c
e
s
i
n
A
p
p
li
e
d
S
c
ie
n
c
e
s
(
I
JA
A
S
)
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
, pp.
702
~
710
I
S
S
N
:
2252
-
8814
,
D
O
I
:
10.11591/
ij
a
a
s
.
v14.
i
3
.
pp702
-
710
702
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
aas
.i
ae
s
c
or
e
.c
om
A
r
t
i
f
i
c
i
al
n
e
u
r
al
n
e
t
w
o
r
k
b
ase
d
se
n
so
r
l
e
ss
p
osi
t
i
on
e
st
i
m
at
i
on
an
d
d
i
r
e
c
t
t
or
q
u
e
c
on
t
r
ol
f
o
r
st
e
p
p
e
r
m
ot
or
N
agas
r
id
h
ar
A
r
is
e
,
T
h
ir
u
ve
e
d
u
la
M
ad
h
u
B
ab
u
, S
r
in
id
h
i
G
ol
la
p
u
d
i,
T
ar
u
n
K
u
m
ar
D
om
m
e
t
i,
A
b
h
is
h
e
k
K
u
m
m
ar
i,
M
ah
it
h
S
h
am
b
u
k
ar
i
D
e
pa
r
t
m
e
nt
of
E
l
e
c
t
r
i
c
a
l
a
nd E
l
e
c
t
r
oni
c
s
E
ngi
ne
e
r
i
ng,
T
e
e
ga
l
a
K
r
i
s
hna
R
e
ddy
E
ngi
ne
e
r
i
ng C
ol
l
e
ge
,
H
yde
r
a
ba
d
, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
N
ov 11, 2024
R
e
vi
s
e
d
M
a
y 14, 2025
A
c
c
e
pt
e
d
J
un 8, 2025
This
study
describes
and
illustrates
how
sensorless
location
estima
tion
is
achieved
through
the
applicati
on
of
artificial
neural
network
(ANN)
c
ontrol.
Control
stepper
motor
torque
directly
.
Using
stepper
motors
directly
l
eads
to
a
lot
of
problems;
therefore,
automated
control
systems
are
now
com
monly
preferred
.
Stepper
motors
have
several
drawbacks
when
used
di
rectly,
including
the
potential
for
steps
to
occasiona
lly
be
missing
while
the
motors
are
running.
When
physical
sensors
are
not
available,
the
prop
osed
method
estimat
es
rotor
positi
on
and
speed
using
electrical
signals
and
ANN
algorit
hms.
Simul
ation
and
experiment
results
demonst
rate
accurate
p
ositio
n
estimat
ion
(±
1.5°
)
and
efficient
torque
control.
The
sensorles
s
direct
torque
control
(DTC)
-
ANN
approach
increases
the
performance,
reliabilit
y,
and
cost
of
stepper
motors
in
robotics,
computer
numerical
control
(CNC)
machines,
and 3D prin
ting.
K
e
y
w
o
r
d
s
:
A
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
k
D
ir
e
c
t
to
r
que
c
ont
r
ol
P
os
it
io
n e
s
ti
m
a
ti
on
S
e
ns
or
le
s
s
c
ont
r
ol
S
te
ppe
r
m
ot
or
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
N
a
ga
s
r
id
ha
r
A
r
is
e
D
e
pa
r
tm
e
nt
of
E
le
c
tr
ic
a
l
a
nd E
le
c
tr
oni
c
s
E
ngi
ne
e
r
in
g, T
e
e
ga
la
K
r
is
hna
R
e
ddy E
ngi
ne
e
r
in
g C
ol
le
ge
M
e
e
r
pe
t,
H
yde
r
a
ba
d, 500097,
I
ndi
a
E
m
a
il
:
s
r
id
ha
r
0106@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
M
ot
or
s
in
ope
n
c
ir
c
le
s
c
a
n
r
e
ve
r
be
r
a
te
,
but
c
lo
s
e
d
-
c
ir
c
le
m
ot
or
s
be
a
r
num
e
r
ous
f
a
c
to
r
s
a
nd
m
us
t
be
c
oupl
e
d
to
a
n
e
nc
ode
r
, a
nd
s
tr
uc
tu
r
in
g
a
nd
ope
r
a
ti
ng
a
n
unr
e
s
tr
ic
te
d
c
ir
c
le
m
ot
or
c
a
n
be
pr
e
c
ar
io
us
.
S
ti
ll
,
th
is
in
f
lu
e
nc
e
c
a
n
be
m
in
im
iz
e
d
by
u
s
in
g
s
e
ns
or
le
s
s
po
s
it
io
n
e
s
ti
m
a
ti
on
s
te
ppe
r
m
ot
or
s
w
it
h
a
n
a
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
k
(
A
N
N
)
c
ont
r
ol
le
r
.
S
e
ns
or
le
s
s
pos
it
io
n
e
s
ti
m
a
ti
on
c
ons
ta
nt
ly
knows
th
e
e
xa
c
t
po
s
it
io
n
a
nd
s
pe
e
d
of
th
e
r
ot
or
;
th
e
r
e
f
or
e
,
s
pe
e
d
a
nd
pos
it
io
ni
ng
m
ode
c
ont
r
ol
a
r
e
s
ig
ni
f
ic
a
nt
ly
im
pr
ove
d.
S
te
ppe
r
m
o
to
r
s
a
r
e
e
m
pl
oye
d i
n a
va
r
ie
ty
o
f
ope
r
a
ti
ons
, i
nc
lu
di
ng
3D
pr
in
te
r
s
, c
om
put
e
r
nume
r
ic
a
l
c
ont
r
ol
(
C
N
C
)
m
a
c
hi
ne
s
, a
nd
c
lo
th
m
a
c
hi
ne
s
.
T
he
y'
r
e
a
ls
o
in
c
r
e
a
s
in
gl
y
us
e
d
in
m
a
nuf
a
c
tu
r
in
g
a
s
s
oc
ia
ti
ons
,
s
im
il
a
r
to
pa
c
ki
ng
bot
tl
e
s
a
nd
a
li
gni
ng
f
a
c
to
r
s
in
s
om
e
m
a
c
hi
ne
di
li
ge
nc
e
to
m
a
ke
ge
a
r
s
.
I
n
th
is
s
tu
dy,
th
e
va
r
ia
bl
e
di
s
in
c
li
na
ti
on
s
te
ppe
r
m
ot
or
is
e
m
pl
oye
d.
I
t
ha
s
a
nonma
gn
e
ti
c
r
ot
or
m
a
de
of
s
of
t
ir
on.
W
he
n
th
e
s
t
e
ppe
r
e
ngi
ne
ge
t
s
a
pa
lp
it
a
ti
on
f
la
g, i
t
p
iv
ot
s
a
t
a
s
e
tt
le
d point
i
n
t
he
he
a
di
ng de
c
id
e
d by the
s
te
ppe
r
e
ngi
ne
. T
he
s
te
ppe
r
m
ot
or
i
s
m
a
de
up
o
f
s
ta
to
r
te
e
th
a
nd
r
ot
or
te
e
th
,
e
a
c
h
w
it
h
a
s
pe
c
if
ic
num
be
r
of
te
e
th
to
s
ui
t
th
e
s
te
ppe
r
m
ot
or
'
s
de
s
ig
n.
I
n
th
is
s
tu
dy, we
'
ve
us
e
d
a
n 8/
6 pole
va
r
ia
bl
e
r
e
lu
c
ta
nc
e
.
T
o de
te
r
m
in
e
t
he
r
ot
or
'
s
pos
it
io
n, a
s
e
r
ie
s
of
vol
ta
ge
be
a
ts
i
s
t
r
a
ns
f
e
r
r
e
d t
o t
he
m
ot
or
w
in
di
ngs
w
hi
le
th
e
m
ot
or
is
s
ta
ti
ona
r
y
a
s
w
e
ll
,
a
nd
th
e
r
ot
or
lo
c
a
ti
on
in
f
or
m
a
ti
on
is
d
e
duc
e
d
ba
s
e
d
on
th
e
m
os
t
e
le
va
t
e
d
c
ur
r
e
nt
va
lu
e
th
a
t
w
a
s
obs
e
r
ve
d
[
1]
.
A
bba
s
e
t
al
.
[
2]
e
xa
m
in
e
de
ve
lo
pm
e
nt
s
in
th
e
f
le
e
tl
y
gr
ow
in
g
a
r
e
a
o
f
s
e
ns
or
le
s
s
c
ont
r
ol
s
ty
le
s
us
in
g
e
le
c
tr
ic
e
ngi
ne
s
,
w
hi
c
h
a
r
e
be
in
g
a
dva
nc
e
d
by
a
dva
nc
e
m
e
nt
s
w
it
hi
n
th
e
f
ie
ld
s
of
di
gi
ta
l
s
ig
na
l
pr
oc
e
s
s
in
g
a
nd
e
le
c
tr
ic
a
l
e
qui
pm
e
nt
.
K
um
a
r
[
3]
il
lu
s
tr
a
te
s
how
to
us
e
L
a
bV
ie
w
to
c
ont
r
ol
a
s
te
ppe
r
m
ot
or
'
s
pos
it
io
n.
A
ne
w
s
e
ns
or
le
s
s
a
ppr
oa
c
h
f
or
a
s
s
e
s
s
in
g
th
e
s
ta
r
ti
ng
r
ot
or
pos
it
io
n
in
hybr
id
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
A
r
ti
fi
c
ia
l
ne
ur
al
ne
tw
or
k
ba
s
e
d s
e
ns
or
l
e
s
s
po
s
it
io
n e
s
ti
m
at
io
n a
nd dir
e
c
t
to
r
que
…
(
N
agas
r
id
har
A
r
is
e
)
703
s
te
ppi
ng
m
ot
or
s
is
de
s
c
r
ib
e
d
[
4]
.
T
h
e
s
ugg
e
s
te
d
a
ppr
oa
c
h
w
a
s
e
s
ta
bl
is
he
d
on
th
e
c
or
r
e
la
ti
ons
a
m
ong
th
e
m
a
xi
m
a
l
pr
in
c
ip
le
s
of
e
le
c
tr
om
ot
iv
a
ti
on
c
r
e
a
te
d
in
w
in
di
ng
s
th
a
t
a
r
e
not
ge
ne
r
a
t
e
d
a
nd
r
ot
or
pos
it
io
n
w
he
ne
ve
r
a
s
e
c
ti
on of
w
in
di
ng ge
ts
e
xc
it
e
d by a
D
C
vol
ta
ge
s
o
ur
c
e
.
A
n
e
nha
nc
e
d
d
ua
l
-
w
in
di
ng
de
pe
nda
bl
e
m
a
gne
ti
z
e
d
a
c
tu
a
to
r
,
known
a
s
a
f
a
ul
t
-
to
le
r
a
nt
pe
r
m
a
ne
nt
m
a
gne
t
m
ot
or
(
F
T
P
M
M
)
,
or
ie
nt
a
ti
on
e
s
ti
m
a
te
of
th
e
s
e
n
s
or
le
s
s
c
ont
r
ol
le
r
w
it
h
dyn
a
m
ic
pa
r
a
m
e
te
r
s
e
le
c
ti
on
vi
a
ba
c
k
e
le
c
tr
om
ot
iv
e
f
or
c
e
(
E
M
F
)
gr
a
di
e
nt
[
5]
.
S
he
n
e
t
al
.
[
6]
e
s
ta
bl
is
h
a
ut
il
it
y
f
or
c
ont
r
ol
li
ng
a
th
r
e
e
-
pha
s
e
s
te
pp
e
r
m
a
c
hi
ne
th
a
t
us
e
s
th
e
T
I
2000
M
ode
l
D
S
P
T
M
S
320F
2812
a
nd
de
s
c
r
ib
e
s
th
e
s
pe
c
ia
l
ha
r
dw
a
r
e
a
nd
s
of
twa
r
e
be
hi
nd
th
e
s
y
s
te
m
.
T
he
s
w
it
c
he
d
r
e
lu
c
ta
n
c
e
m
o
to
r
(
S
R
M
)
pa
r
a
m
e
te
r
s
a
r
e
a
c
qui
r
e
d
us
in
g
th
e
qui
c
k
f
ie
ld
pr
ogr
a
m
'
s
num
e
r
ic
a
l
c
om
put
a
ti
on
of
th
e
m
a
gne
ti
c
f
ie
ld
a
nd
th
e
n
in
c
lu
d
e
d
in
a
M
A
T
L
A
B
/S
im
ul
in
k
m
ode
l
of
a
n
S
R
M
w
it
h
a
s
ta
to
r
pol
e
to
r
ot
or
te
e
th
r
a
ti
o
of
12/
8.
C
a
s
e
s
w
it
h
va
r
yi
ng
num
be
r
s
of
s
ta
to
r
c
oi
l
tu
r
ns
ha
ve
be
e
n i
nve
s
ti
ga
te
d, a
nd t
he
be
s
t
opt
io
n i
s
e
s
ta
bl
is
he
d
[
7]
.
R
a
ja
n a
nd L
a
th
a
[
8]
p
r
e
s
e
nt
s
e
ns
or
le
s
s
r
ot
or
pos
it
io
n
e
s
ti
m
a
ti
on
of
a
n
S
R
M
,
w
it
h
th
e
pos
it
io
n
c
om
put
e
d
vi
a
th
e
a
da
pt
iv
e
ne
ur
o
-
f
uz
z
y
in
f
e
r
e
nc
e
s
y
s
te
m
(
A
N
F
I
S
)
.
A
s
e
n
s
or
le
s
s
r
ot
or
pos
it
io
n
e
s
ti
m
a
te
a
ppr
oa
c
h
ba
s
e
d
on
a
n
A
N
N
[
9]
is
de
s
c
r
ib
e
d
to
c
om
pl
e
te
ly
m
e
e
t
th
e
S
R
M
'
s
po
s
it
io
n
f
e
e
db
a
c
k
r
e
qui
r
e
m
e
nt
.
A
M
A
T
L
A
B
s
im
ul
a
ti
on
e
nvi
r
onm
e
nt
is
ut
il
iz
e
d
to
c
r
e
a
te
a
n
e
ur
a
l
ne
twor
k
a
nd
s
im
ul
a
te
th
e
s
ugge
s
te
d
s
e
n
s
or
-
le
s
s
te
c
hni
que
,
w
hi
c
h
yi
e
ld
s
a
good
out
c
om
e
.
A
ne
w
a
ppr
oa
c
h
[
10]
f
or
e
s
ti
m
a
ti
ng
th
e
in
it
ia
l
r
ot
or
pos
it
io
n
o
f
a
s
ur
f
a
c
e
-
m
ount
e
d
pe
r
m
a
ne
nt
m
a
gne
t
s
ync
hr
onous
m
ot
or
(
S
M
-
P
M
S
M
)
th
a
t
is
s
i
m
pl
e
r
a
nd
m
or
e
pr
e
c
is
e
th
a
n
us
in
g
pos
it
io
n
or
c
ur
r
e
nt
s
e
ns
or
s
.
T
h
e
s
pe
e
d
e
s
ti
m
a
to
r
f
or
s
pe
e
d
s
e
ns
or
-
le
s
s
d
ir
e
c
t
to
r
que
c
ont
r
ol
(
D
T
C
)
of
a
th
r
e
e
-
pha
s
e
in
duc
ti
on
m
ot
or
is
pr
e
s
e
nt
e
d,
ba
s
e
d
on
th
e
c
ons
ta
nt
V
/F
c
ont
r
ol
a
ppr
oa
c
h
a
nd
a
n
A
N
N
[
11]
.
W
he
n
c
om
p
a
r
e
d
to
c
onve
nt
io
na
l
vol
ta
ge
li
f
t
a
ppr
oa
c
h
e
s
s
uc
h
a
s
s
upe
r
li
f
t
c
onve
r
te
r
s
a
nd
tr
a
di
ti
ona
l
boos
t
c
onv
e
r
te
r
s
,
ul
tr
a
-
li
f
t
c
onve
r
te
r
s
pr
oduc
e
e
xt
r
e
m
e
ly
la
r
ge
out
put
tr
a
ns
f
e
r
ga
in
s
w
it
h
ge
om
e
tr
ic
de
ve
lo
pm
e
nt
.
W
he
n
c
om
pa
r
e
d,
it
ha
s
a
s
m
a
ll
e
r
f
oot
pr
in
t
a
nd
is
m
or
e
e
f
f
ic
ie
nt
.
T
he
f
unc
ti
oni
ng
of
a
n
ul
tr
a
-
li
f
t
c
onve
r
te
r
is
in
ve
s
ti
ga
te
d
us
in
g
c
ont
in
uous
c
onduc
ti
on mode
[
12]
.
T
he
c
ont
r
ol
te
c
hni
q
ue
a
nd
A
N
N
s
tr
u
c
tu
r
e
a
r
e
u
s
e
d
t
o
c
a
l
c
ul
a
t
e
a
nd
r
e
or
ga
ni
z
e
t
he
e
s
ti
m
a
t
e
d
s
t
a
to
r
c
ur
r
e
nt
e
qua
t
io
n.
A
n
e
xt
e
nde
d
K
a
lm
a
n
f
il
te
r
(
E
K
F
)
-
b
a
s
e
d
hi
g
h
-
pe
r
f
or
m
a
n
c
e
s
e
n
s
or
l
e
s
s
c
ont
r
ol
w
a
s
us
e
d
to
a
nt
ic
i
pa
t
e
s
t
a
to
r
r
e
s
i
s
ta
n
c
e
i
n
a
f
a
ul
t
-
to
le
r
a
nt
P
M
S
M
m
ot
or
s
ys
te
m
[
13]
.
C
onve
nt
io
n
a
l
D
T
C
is
o
ne
of
th
e
e
xc
e
ll
e
nt
c
ont
r
o
l
s
tr
a
te
gi
e
s
a
v
a
il
a
b
le
to
c
ont
r
ol
th
e
t
or
que
of
t
he
in
du
c
ti
on
m
a
c
hi
ne
(
I
M
)
[
14]
.
A
c
r
o
s
s
o
ve
r
c
ons
ona
nt
c
on
c
e
a
lm
e
nt
s
tr
a
te
gy
[
15]
i
s
di
s
pl
a
ye
d
f
or
u
pgr
a
di
ng
th
e
a
d
a
pt
a
bi
li
ty
of
vi
r
t
ua
l
s
yn
c
hr
ono
us
ge
ne
r
a
to
r
(
V
S
G
)
,
w
hi
c
h
i
s
ba
s
ic
a
ll
y
c
o
m
po
s
e
d
of
a
vol
t
a
ge
c
ons
on
a
nt
c
o
nt
r
ol
c
ir
c
l
e
a
nd
a
la
t
ti
c
e
c
ur
r
e
nt
-
c
ont
r
ol
l
e
d
c
ir
c
l
e
.
A
s
tr
a
ig
ht
f
or
w
a
r
d
a
n
d
s
tr
ong
e
le
c
tr
om
a
gne
ti
c
to
r
q
ue
-
b
a
s
e
d
de
m
o
ns
tr
a
ti
on
v
e
r
s
a
ti
le
f
r
a
m
e
w
or
k
s
pe
e
d
e
s
ti
m
a
to
r
in
a
n
o
ve
r
h
a
ng
ps
e
udo
s
ubor
di
n
a
te
c
r
it
ic
is
m
c
on
tr
ol
le
r
f
or
s
e
n
s
or
le
s
s
s
ur
f
a
c
e
m
ount
c
ha
ng
e
le
s
s
m
a
gne
t
in
lo
w
-
s
p
e
e
d
a
nd
s
to
p
z
o
ne
s
,
it
s
e
xe
c
ut
i
on
i
s
a
dva
n
c
e
d
by
p
a
r
a
ll
e
l
po
w
e
r
pl
a
nt
(
S
M
P
M
S
M
)
dr
iv
e
[
1
6]
.
T
oge
t
he
r
w
i
th
th
e
pr
in
c
i
pl
e
s
a
n
d
c
r
it
e
r
i
a
of
th
e
s
e
c
ond
-
de
gr
e
e
s
li
di
n
g
-
m
ode
s
p
e
c
t
a
to
r
c
om
put
a
ti
on
r
e
l
yi
ng
upo
n
th
e
s
u
pe
r
-
twi
s
ti
n
g
t
e
c
h
ni
qu
e
,
a
s
e
c
ond
-
de
gr
e
e
f
le
xi
bl
e
s
li
di
ng
-
m
o
de
s
pe
c
ta
to
r
s
tr
a
t
e
gy
[
17]
w
a
s
pr
e
s
e
nt
e
d.
A
hi
ghe
r
-
or
d
e
r
s
li
di
ng
m
ode
o
bs
e
r
v
e
r
-
ba
s
e
d
(
S
M
O
)
vi
gor
o
us
ba
c
k
s
te
p
pi
ng
c
ont
r
ol
is
pr
op
os
e
d
i
n
[
18]
,
f
or
s
e
n
s
or
le
s
s
s
pe
e
d
c
ont
r
ol
of
a
n
in
s
id
e
c
ha
n
ge
l
e
s
s
m
a
gn
e
t
s
y
nc
hr
on
ous
e
ngi
n
e
(
I
P
M
S
M
)
.
A
di
a
gr
a
m
of
a
f
e
w
s
or
ts
of
f
o
ot
in
g
e
ngi
n
e
s
f
or
e
l
e
c
tr
ic
ve
hi
c
le
s
(
E
V
s
)
a
nd
hybr
i
d
e
le
c
tr
ic
v
e
hi
c
le
(
H
E
V
s
)
,
a
s
w
e
ll
a
s
a
ta
ll
te
m
por
a
l
e
xe
c
ut
io
n
s
p
e
e
d s
e
n
s
or
le
s
s
f
o
ot
in
g dr
iv
e
c
ont
r
ol
[
1
9]
.
T
he
e
xp
a
nd
e
d
K
a
lm
a
n
c
ha
nn
e
l
c
a
l
c
ul
a
t
e
s
th
e
a
r
e
a
a
nd
s
p
e
e
d
e
s
s
e
nt
i
a
l
f
or
f
ie
ld
-
ba
s
e
d
m
a
n
a
g
e
m
e
nt
.
T
he
s
tr
e
a
m
s
a
s
w
e
l
l
a
s
th
e
pol
a
r
it
i
e
s
of
th
e
s
te
ppe
r
m
ot
or
'
s
t
w
o
s
t
a
ge
s
a
r
e
c
h
e
c
k
e
d
a
nd
ut
il
i
z
e
d
f
or
s
t
a
te
e
s
ti
m
a
ti
on
th
r
ough
a
n
a
m
pl
if
i
e
d
K
a
lm
a
n
c
h
a
nne
l.
T
he
a
nt
i
c
i
pa
te
d
po
s
it
io
n
i
s
c
om
pa
r
e
d
to
th
e
e
xp
e
c
t
ed
pos
it
io
n,
a
n
d
th
e
e
ngi
n
e
is
h
a
lt
e
d a
t
th
e
w
a
nt
e
d
a
r
e
a
[
20]
.
A
s
ta
t
e
ga
ug
e
a
ppr
oa
c
h
f
or
c
lo
s
e
d
-
lo
op
ope
r
a
ti
on
of
ha
lf
-
br
e
e
d
s
t
e
ppe
r
e
ngi
n
e
s
(
H
S
M
s
)
,
w
hi
c
h
a
r
e
c
o
m
m
onl
y
ut
il
iz
e
d
a
s
a
c
tu
a
to
r
s
ove
r
a
w
i
de
e
xt
e
nd
of
ope
r
a
ti
ona
l
s
p
e
e
ds
.
T
he
pr
opo
s
e
d
in
no
va
ti
o
n
p
e
r
m
it
s
f
or
c
lo
s
e
d
-
lo
op
c
ont
r
ol
of
H
S
M
s
w
it
h
out
th
e
u
ti
li
z
a
ti
on
of
a
ny
a
ddi
ti
ona
l
s
e
n
s
or
s
[
21]
.
P
hy
s
i
c
s
-
g
ui
de
d
ne
ur
a
l
n
e
twor
k
(
P
G
N
N
)
f
e
e
df
or
w
a
r
d
c
ont
r
ol
l
e
r
[
22]
f
or
H
S
M
s
th
a
t
c
a
n
le
a
r
n
th
e
im
p
a
c
t
of
e
c
to
pi
c
p
ow
e
r
s
f
r
om
in
f
or
m
a
ti
o
n
a
nd
r
e
dr
e
s
s
f
or
t
he
m
,
dr
iv
in
g
in
e
xp
a
nd
e
d
pr
e
c
i
s
io
n.
W
i
nd,
P
V
,
a
nd
b
a
tt
e
r
y
-
b
a
s
e
d
c
r
o
s
s
ove
r
vi
ta
li
ty
f
r
a
m
e
w
or
ks
c
r
e
a
te
po
w
e
r
f
or
s
ta
n
d
-
a
lo
n
e
A
C
m
ic
r
ogr
id
a
ppl
i
c
a
ti
on
s
[
23]
.
A
s
e
ns
or
l
e
s
s
D
T
C
f
r
a
m
e
w
or
k
bui
lt
on
a
n
e
ur
a
l
a
r
r
a
n
ge
m
e
nt
.
T
hi
s
a
r
r
a
ng
e
m
e
nt
i
s
pl
a
nn
e
d
to
h
a
ndl
e
th
e
w
or
k
of
s
e
le
c
ti
ng
t
he
id
e
a
l
e
xc
h
a
ngi
ng
s
ta
t
e
f
or
a
n
a
c
c
e
pt
a
nc
e
e
n
gi
ne
b
a
s
e
d
o
n
da
t
a
a
ppr
oxi
m
a
te
l
y
it
s
e
l
e
c
tr
om
a
gn
e
ti
c
t
or
que
a
nd
s
ta
t
or
f
lu
x
(
po
s
it
io
n
a
nd
gr
e
a
tn
e
s
s
)
.
I
n
r
e
a
li
ty
,
due
t
o
it
s
lo
ng
c
om
put
a
ti
on
ti
m
e
,
th
i
s
a
ppr
oa
c
h,
w
hi
c
h
l
e
ve
r
a
ge
s
a
s
ta
nda
r
d
e
x
c
ha
ng
e
ta
bl
e
,
i
s
un
a
c
c
e
pt
a
bl
e
f
or
o
ne
-
li
n
e
a
n
d
r
e
a
l
-
ti
m
e
c
ont
r
ol
[
24]
.
T
he
c
oor
di
n
a
te
t
or
que
c
ont
r
ol
(
D
T
C
)
a
ppr
oa
c
h
i
s
in
s
pe
c
te
d
f
or
th
is
e
ngi
n
e
e
r
in
g.
S
in
c
e
e
x
tr
a
in
ve
r
t
e
r
s
t
a
te
s
a
r
e
a
c
c
e
s
s
ib
l
e
i
n
th
e
th
r
e
e
-
le
v
e
l
in
ve
r
te
r
,
vol
t
a
ge
d
e
te
r
m
i
na
ti
o
n
a
lt
e
r
n
a
ti
v
e
s
a
r
e
e
xt
e
n
de
d
[
25]
.
T
he
a
im
of
th
is
r
e
s
e
a
r
c
h
is
o
ne
te
c
hni
que
f
or
de
te
r
m
in
in
g
th
e
lo
c
a
ti
on
of
s
te
ppe
r
m
ot
or
s
w
it
hout
th
e
us
a
ge
of
a
ddi
ti
ona
l
s
e
n
s
or
s
is
ANN
-
ba
s
e
d
s
e
n
s
or
le
s
s
pos
it
io
n
e
s
ti
m
a
ti
on.
S
te
ppe
r
m
ot
or
s
a
r
e
uni
que
be
c
a
u
s
e
th
e
y
ope
r
a
te
in
ti
ny,
a
c
c
ur
a
te
in
c
r
e
m
e
nt
s
,
w
hi
c
h
m
a
k
e
s
th
e
m
id
e
a
l
f
or
a
ppl
ic
a
ti
ons
li
ke
r
obot
ic
s
a
nd
3D
pr
in
te
r
s
w
he
r
e
pr
e
c
is
io
n
is
c
r
uc
ia
l.
S
in
c
e
e
xt
e
r
na
l
s
e
ns
or
s
a
r
e
n
ot
r
e
qui
r
e
d,
th
is
te
c
hnol
ogy
s
a
v
e
s
m
one
y
a
nd
s
pa
c
e
by
tr
a
c
ki
ng
th
e
m
ot
or
'
s
lo
c
a
ti
on
by
m
oni
to
r
in
g
th
e
e
le
c
tr
ic
a
l
im
pul
s
e
s
in
s
id
e
th
e
m
ot
or
.
I
n
o
r
de
r
t
o
be
tt
e
r
r
e
gul
a
te
th
e
m
ot
or
'
s
m
ot
io
ns
,
th
is
a
ppr
oa
c
h
e
s
ti
m
a
te
s
th
e
m
ot
or
'
s
lo
c
a
ti
on
ba
s
e
d
on
it
s
in
he
r
e
nt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
702
-
710
704
pr
ope
r
ti
e
s
.
W
it
hout
r
e
qui
r
in
g
a
ddi
ti
ona
l
e
qui
pm
e
nt
,
it
'
s
a
c
le
v
e
r
m
e
th
od
to
gua
r
a
nt
e
e
th
e
m
ot
or
r
e
a
c
he
s
th
e
de
s
ir
e
d l
oc
a
ti
on, ma
ki
ng i
t
a
n a
ppe
a
li
ng c
hoi
c
e
f
or
e
ngi
ne
e
r
s
w
is
hi
ng t
o opti
m
iz
e
t
he
ir
c
r
e
a
ti
ons
.
2.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
T
hi
s
r
e
s
e
a
r
c
h
a
im
s
to
e
nha
nc
e
by
in
te
gr
a
ti
ng
D
T
C
te
c
hni
que
s
w
it
h
A
N
N
-
ba
s
e
d
pos
it
io
n
e
s
ti
m
a
ti
on
to
a
s
s
e
s
s
s
te
ppe
r
m
ot
or
pe
r
f
or
m
a
nc
e
in
s
e
ns
or
le
s
s
s
e
tt
in
gs
.
R
e
a
l
-
ti
m
e
to
r
que
c
ont
r
ol
,
da
ta
-
dr
iv
e
n
pos
it
io
n
e
s
ti
m
a
te
,
a
nd
a
na
ly
ti
c
a
l
m
ode
li
ng
of
to
r
que
ge
ne
r
a
ti
on
a
r
e
th
e
th
r
e
e
m
a
in
pi
ll
a
r
s
of
th
e
m
e
th
odol
ogy.
A
n
e
f
f
e
c
ti
ve
a
nd
r
e
li
a
bl
e
m
ot
or
c
ont
r
ol
s
ys
te
m
a
ppr
opr
ia
te
f
or
r
obot
ic
s
a
nd
a
ut
om
a
ti
on
a
ppl
ic
a
ti
ons
is
c
ons
tr
uc
te
d w
it
h t
he
he
lp
of
e
a
c
h c
om
pon
e
nt
.
2.1.
A
r
t
if
ic
ia
l
n
e
u
r
al
n
e
t
w
or
k
-
b
as
e
d
p
os
it
io
n
e
s
t
im
at
io
n
A
n
A
N
N
m
a
y
r
e
c
ogni
z
e
a
n
obj
e
c
t'
s
pos
it
io
n
in
a
r
a
nge
of
a
ppl
ic
a
ti
ons
,
in
c
lu
di
ng
r
obot
ic
s
a
nd
na
vi
ga
ti
on,
by
m
a
ni
pul
a
ti
ng
r
ot
or
pos
it
io
n
a
nd
s
pe
e
d
w
it
hout
th
e
us
e
of
a
s
e
n
s
or
.
T
h
e
s
y
s
te
m
is
tr
a
in
e
d
on
la
be
le
d
da
ta
s
e
t
s
w
it
h
in
put
s
c
or
r
e
s
ponding
to
known
lo
c
a
ti
ons
a
nd
is
c
a
pa
bl
e
of
in
te
r
pr
e
ti
ng
a
va
r
ie
ty
of
da
ta
f
or
m
a
ts
,
in
c
lu
di
ng
s
e
ns
or
r
e
a
di
ngs
.
U
s
in
g
a
r
e
a
l
-
ti
m
e
c
ont
r
ol
s
ig
na
l,
F
ig
ur
e
1
de
m
ons
tr
a
te
s
th
e
ba
s
ic
bl
o
c
k
di
a
gr
a
m
of
th
e
ANN
c
ont
r
ol
le
r
.
A
N
N
c
a
n
f
or
e
s
e
e
th
e
s
t
e
ppe
r
m
ot
or
'
s
pos
it
io
n,
r
e
m
ovi
ng
th
e
ne
e
d
f
or
m
a
nua
l
f
e
a
tu
r
e
de
s
ig
n. T
he
y c
a
n be
m
or
e
noi
s
e
-
r
e
s
i
s
ta
nt
, m
a
ki
ng t
he
m
e
xc
e
ll
e
nt
f
or
a
c
ti
ve
a
r
e
a
s
.
T
he
r
e
qui
r
e
m
e
nt
f
or
c
os
tl
y s
e
n
s
or
s
c
a
n be
d
e
c
r
e
a
s
e
d by r
e
ly
in
g on pr
e
di
c
ti
ve
m
ode
li
ng.
A
N
N
C
O
N
T
R
O
L
D
R
I
V
E
R
S
T
E
P
P
E
R
M
O
T
O
R
F
ig
ur
e
1. B
a
s
ic
bl
oc
k di
a
gr
a
m
of
a
n
A
N
N
c
ont
r
ol
le
r
2.2.
D
ir
e
c
t
t
or
q
u
e
c
on
t
r
ol
st
r
at
e
gy
T
o
a
ugm
e
nt
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
s
te
pp
e
r
m
ot
or
,
th
e
t
or
que
s
houl
d
be
a
dj
us
t
e
d
in
s
t
a
nt
ly
;
th
e
r
e
f
or
e
,
D
T
C
is
u
s
e
d.
I
t
e
m
pl
oys
hi
gh
-
pe
r
f
or
m
a
nc
e
va
r
i
a
bl
e
-
f
r
e
que
nc
y
s
pe
e
d
c
ont
r
ol
te
c
hnol
ogy.
I
t
e
m
pl
oys
m
in
im
um
c
ont
r
ol
s
tr
uc
tu
r
e
s
a
nd
th
e
di
r
e
c
t
c
ont
r
ol
a
ppr
oa
c
h.
T
he
D
T
C
s
tr
a
te
gy
is
us
e
d
ba
s
e
d
on
th
e
m
ot
or
'
s
pa
r
a
m
e
te
r
s
,
a
nd
it
a
s
s
um
e
s
th
a
t
th
e
r
ot
or
f
lu
x
is
c
ons
ta
nt
a
nd
th
a
t
th
e
to
r
que
m
a
y
be
di
r
e
c
tl
y
c
ont
r
ol
le
d
by
m
odi
f
yi
ng
th
e
s
ta
to
r
vol
ta
ge
.
D
T
C
is
s
im
pl
e
a
nd outpe
r
f
or
m
s
ot
he
r
c
om
m
onl
y
us
e
d
te
c
hni
que
s
,
m
a
ki
ng
it
s
ui
ta
bl
e
f
o
r
r
obo
ti
c
s
ys
te
m
s
.
T
he
f
unda
m
e
nt
a
l
not
io
n
unde
r
ly
in
g
D
T
C
is
to
r
e
gul
a
te
bot
h
to
r
que
a
nd f
lu
x.
2.3.
T
or
q
u
e
e
q
u
at
io
n
A
qua
li
ta
ti
ve
te
c
hni
qu
e
is
not
a
lwa
y
s
a
ppr
opr
ia
te
f
or
de
a
li
ng
w
it
h
s
te
ppe
r
m
ot
or
c
ir
c
ui
tr
y
c
ha
r
a
c
te
r
is
ti
c
s
.
F
ig
ur
e
2
de
m
on
s
tr
a
te
s
th
e
to
r
que
po
s
it
io
ni
ng
c
ha
r
a
c
te
r
is
ti
c
s
.
S
o,
a
th
e
or
y
b
a
s
e
d
on
m
a
gn
e
ti
c
e
ne
r
gy
a
nd
c
o
-
e
ne
r
gy
w
il
l
b
e
e
xa
m
in
e
d
in
or
de
r
to
unde
r
s
ta
nd
th
e
pr
oc
e
s
s
of
to
r
que
c
r
e
a
ti
on
us
in
g
a
dyna
m
ic
m
e
th
od.
T
he
a
na
ly
s
is
be
gi
ns
w
it
h
a
n
id
e
a
l
s
it
ua
ti
on
in
w
hi
c
h
th
e
r
ot
or
a
nd
s
ta
to
r
c
or
e
s
a
r
e
m
a
gne
ti
c
a
ll
y s
a
tu
r
a
te
d.
F
ig
ur
e
2. T
or
que
pos
it
io
ni
ng c
ha
r
a
c
te
r
is
ti
c
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
A
r
ti
fi
c
ia
l
ne
ur
al
ne
tw
or
k
ba
s
e
d s
e
ns
or
l
e
s
s
po
s
it
io
n e
s
ti
m
at
io
n a
nd dir
e
c
t
to
r
que
…
(
N
agas
r
id
har
A
r
is
e
)
705
2.3.1.
C
as
e
I
:
in
f
in
it
e
ly
p
e
r
m
e
ab
le
c
or
e
s
A
c
c
or
di
ng
to
A
m
pe
r
e
’
s
la
w
,
th
e
pos
it
io
n
of
th
e
a
ir
ga
p'
s
H
g
-
m
a
gne
ti
c
f
or
c
e
m
a
gni
tu
de
,
th
e
c
or
e
s
'
HI
-
m
a
gne
ti
c
f
or
c
e
m
a
gni
tu
de
,
a
nd
th
e
c
or
e
s
'
l
-
to
ta
l
e
le
c
tr
om
a
g
ne
ti
c
pa
th
H
i
(
l
)
=
0
w
he
n
th
e
pe
r
m
e
a
bi
li
ty
of
c
or
e
s
i
s
ve
r
y hi
gh.
∮
H
.
dl
=
nI
(
1)
∮
H
.
dl
=
H
g
(
g
2
)
⁄
+
H
g
(
g
2
)
⁄
+
H
i
(
l
)
=
H
g
(
g
)
+
H
i
(
l
)
(
2
)
∮
H
.
dl
=
H
g
(
g
)
(
3
)
H
g
.
g
=
n
IH
g
=
nI
g
,
Bg
=
μ
0
H
g
&
Hg
=
Bg
μ
0
(
4
)
S
ubs
ti
tu
te
H
g i
n (
4)
,
Bg
=
μ
0
nI
g
.
Bg
=
∅
A
⁄
=
∅
xw
(
5
)
∅
=
μ
0
n
I
x
w
g
(
6
)
F
lu
x l
in
ka
ge
,
φ
=
n∅
(
7
)
φ
=
xw
μ
0
n
2
I
g
(
8
)
∆
φ
=
w
μ
0
n
2
I∞
g
(
9
)
E
m
f
,
=
∆
φ
∆
t
=
−
w
μ
0
n
2
I
g
.
∆
x
∆
t
,
,
∆
Pi
=
I
|
e
|
∆
t
(1
0
)
∆
Pi
=
w
μ
0
n
2
I
2
g
∆
x
(1
1
)
∆
Pi
=
B
g
2
.
gw
∆
x
μ
0
(1
2
)
W
he
r
e
,
μ
0
-
pe
r
m
e
a
bi
li
ty
in
th
e
ga
p
le
ngt
h,
le
t
w
be
th
e
th
ic
kne
s
s
of
th
e
pr
e
s
s
c
om
pone
nt
'
s
tr
a
n
s
ve
r
s
e
l
e
ngt
h
a
nd x be
t
he
di
s
ta
nc
e
be
twe
e
n t
he
pr
e
s
s
pi
e
c
e
a
nd t
he
r
ot
or
te
e
th
a
c
r
os
s
t
he
ove
r
la
ppe
d s
e
c
to
r
,
th
e
pr
oduc
t
xw
r
e
pr
e
s
e
nt
s
th
e
e
f
f
e
c
ti
ve
ove
r
la
ppi
ng
a
r
e
a
,
a
nd
a
n
in
c
r
e
m
e
nt
a
l
di
s
pl
a
c
e
m
e
nt
∆
x
a
t
ti
m
e
∆
t
is
a
s
s
um
e
d.
T
he
s
our
c
e
'
s
e
f
f
or
t
is
pa
r
ti
a
ll
y
tr
a
ns
f
or
m
e
d
in
to
m
e
c
ha
ni
c
a
l
w
or
k,
w
it
h
th
e
r
e
m
a
in
in
g
por
ti
on
goi
ng
to
w
a
r
d
s
tr
e
ngt
he
ni
ng
th
e
m
a
gne
ti
c
f
ie
ld
of
e
ne
r
gy
in
th
e
ga
ps
.
∆
P
i
is
tr
a
ns
f
or
m
e
d
in
to
th
e
e
le
c
tr
ic
it
y
of
th
e
m
a
gne
ti
c
f
ie
ld
, w
he
r
e
a
s
t
he
r
e
m
a
in
in
g ha
lf
o
f
P
i
i
s
t
r
a
ns
f
or
m
e
d i
n
to
m
e
c
ha
ni
c
a
l
w
or
k
.
T
he
m
e
c
ha
ni
c
a
l
w
or
k i
s
e
qua
l
to
th
e
f
or
c
e
'
f
'
t
im
e
s
a
di
s
ta
nc
e
∆
x
,
a
nd c
om
pa
r
in
g
(
13
)
a
nd (
14
).
∆
Wm
=
1
2
⁄
∆
Pi
=
1
2
⁄
Bg
2
μ
0
.
g
.
w
∆
x
(1
3
)
f
=
1
2
⁄
B
g
2
μ
0
gw
(1
4
)
S
ubs
ti
tu
te
(
14)
t
o B
g,
f
=
1
2
⁄
μ
0
2
n
2
I
2
g
2
μ
0
gw
,
f
=
1
2
⁄
w
μ
0
2
n
2
I
2
g
2
(1
5
)
M
a
gne
ti
c
e
ne
r
gy
Wm
=
fx
,
Wm
=
1
2
⁄
B
g
2
μ
0
g
×
w
Wm
=
1
2
⁄
μ
0
n
2
I
2
g
xw
(1
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
702
-
710
706
C
om
pa
r
e
(
1
3)
a
nd (
15
)
,
f
=
[
∂
w
m
∂
x
]
I
=
c
o
n
s
t
a
n
t
(
in
r
ig
or
ous
f
or
m
)
.
f
=
−
[
∂
w
m
∂
x
]
∅
=
c
o
n
s
t
a
n
t
(
c
oi
l
r
e
s
is
ta
nc
e
i
s
not
z
e
r
o)
2.3.2.
C
as
e
I
I
:
c
on
s
t
an
t
p
e
r
m
e
ab
il
it
ie
s
I
n
th
e
in
f
in
it
y
pe
r
m
e
a
bl
e
c
or
e
s
,
e
s
pe
c
ia
ll
y
in
th
e
voi
d
s
doe
s
a
f
ie
ld
of
m
a
gne
t
s
s
how
s
up.
W
he
n
c
e
nt
e
r
s
a
r
e
of
li
m
it
e
d
pe
ne
tr
a
bi
li
ty
,
th
e
a
tt
r
a
c
ti
ve
vi
ta
li
ty
s
how
s
up
m
or
e
ove
r
in
th
e
c
e
nt
e
r
s
a
nd
s
pa
c
e
s
ot
he
r
th
a
n t
he
hol
e
s
. T
h
e
m
a
gne
ti
c
e
n
e
r
gy
,
ω
m
=
½
LI
2
,
Em
f
,
e
=
−
∆
Ψ
∆
t
.
φ
=
LI
(1
7
)
e
=
−
I
∆
L
∆
t
(1
8
)
∆
Pi
=
I
2
∆
L
(1
9
)
I
nc
r
e
a
s
e
i
n t
he
m
a
gne
ti
c
e
n
e
r
gy
∆
ω
m
=
½
∆
Pi
.
∆
ω
m
=
½
I
2
∆
L
(
20
)
M
e
c
ha
ni
c
a
l
w
or
k,
∆
P
D
=
f
∆
(
21)
C
om
pa
r
in
g (
20)
a
nd
(
21)
,
f
∆
x
=
½
I
2
∆
L
.
f
=
½
I
2
∆
L
∆
x
(
22)
T
he
w
or
k done
by t
w
o powe
r
s
uppl
ie
s
dur
in
g
∆
t
,
∆
Pi
=
−
(
e
1
I
1
+
e
2
I
2
)
∆
t
=
−
[
−
I
1
∆
L
1
∆
t
−
I
1
I
2
∆
M
∆
t
−
I
2
2
∆
L
2
∆
t
−
I
1
I
2
∆
M
∆
t
]
∆
Pi
=
I
1
2
∆
L
1
+
I
2
2
∆
L
2
+
2
I
1
I
2
∆
m
T
he
i
nc
r
e
m
e
nt
of
m
a
gne
ti
c
e
ne
r
gy,
∆
wm
=
½
∆
Pi
=
½
[
I
1
2
∆
L
1
+
I
2
2
∆
L
2
]
+
I
1
I
2
∆
m
M
e
c
ha
ni
c
a
l
out
put
,
∆
Po
=
T
∆
θ
(
23)
A
s
,
T
=
½
I
1
2
∂
L
1
∂
θ
+
½
I
2
2
∂
L
2
∂
θ
+
I
1
I
2
∂
M
∂
θ
T
or
que
c
a
n be
e
xpr
e
s
s
e
d
.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
F
ig
ur
e
3
de
m
ons
tr
a
te
s
th
e
s
im
ul
a
ti
on
di
a
gr
a
m
of
s
e
n
s
or
le
s
s
po
s
it
io
n
e
s
ti
m
a
ti
on
f
or
a
s
t
e
ppe
r
m
ot
or
us
in
g
a
n
ANN
c
ont
r
ol
le
r
.
F
ig
ur
e
4
de
m
ons
tr
a
te
s
th
e
c
ur
r
e
nt
f
r
om
th
e
s
te
ppe
r
m
ot
or
,
w
hi
c
h
m
e
a
n
s
th
a
t
w
h
e
n
th
e
s
uppl
y
vol
ta
ge
is
gi
ve
n
to
th
e
s
e
ns
or
le
s
s
pos
it
io
n
e
s
ti
m
a
ti
on
of
th
e
s
te
ppe
r
m
ot
or
c
ir
c
ui
t,
it
w
il
l
c
onve
r
t
th
e
DC
vol
ta
ge
to
th
e
AC
vol
ta
ge
by
us
in
g
th
e
c
onve
r
te
r
.
T
he
to
r
que
out
put
of
th
e
c
ir
c
ui
t
c
a
n
a
ls
o
be
obs
e
r
ve
d
by
us
in
g
a
n
A
N
N
-
ba
s
e
d
c
ont
r
ol
le
r
to
e
li
m
in
a
te
th
e
non
-
li
ne
a
r
di
s
r
upt
in
g
to
r
que
s
a
t
lo
w
s
pe
e
d,
a
nd
de
pe
ndi
ng
on
th
e
c
ur
r
e
nt
,
pos
it
io
n
of
th
e
m
ot
or
,
a
nd
s
pe
e
d
of
th
e
s
t
e
ppe
r
m
ot
or
'
s
c
ur
r
e
nt
,
it
i
s
id
e
a
ll
y
s
in
us
oi
da
l
but
i
s
f
r
e
que
nt
ly
a
ppr
oxi
m
a
te
d
by
a
n
e
xh
a
us
ti
ve
s
te
p
w
a
ve
f
or
m
.
A
f
ul
l
-
s
te
p
w
a
v
e
f
or
m
is
a
c
r
ude
a
ppr
oxi
m
a
ti
on of
t
he
s
in
us
oi
da
l.
F
ig
ur
e
5
de
m
ons
tr
a
te
s
a
s
in
us
oi
da
l
out
put
to
r
que
w
a
ve
f
or
m
of
a
s
te
ppe
r
m
ot
or
,
e
xhi
bi
ti
ng
a
c
ir
c
ul
a
r
r
ot
a
ti
ng ma
gne
ti
c
f
ie
ld
i
n s
pa
c
e
. T
hi
s
i
nc
r
e
a
s
e
s
s
te
ppe
r
m
ot
or
r
ot
a
ti
ona
l
s
ta
bi
li
ty
a
nd dim
in
is
he
s
m
ot
or
out
put
to
r
que
va
r
ia
ti
ons
.
F
ig
ur
e
6
s
how
s
th
e
out
put
w
a
ve
f
or
m
f
o
r
th
e
s
pe
e
d.
T
he
s
p
e
e
d
of
a
s
te
ppe
r
m
ot
or
is
e
s
ta
bl
is
he
d
by
th
e
pul
s
e
f
r
e
que
nc
y
(
H
z
)
c
onve
y
e
d
to
th
e
dr
iv
e
r
.
O
ut
put
of
th
e
s
pe
e
d
ba
s
e
d
on
th
e
m
ot
or
pos
it
io
n a
nd t
he
r
ot
a
ti
ona
l
s
pe
e
d of
t
he
s
te
pp
e
r
m
ot
or
, w
hi
c
h i
s
c
a
lc
ul
a
te
d vi
a
t
he
pul
s
e
f
r
e
que
nc
y.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
A
r
ti
fi
c
ia
l
ne
ur
al
ne
tw
or
k
ba
s
e
d s
e
ns
or
l
e
s
s
po
s
it
io
n e
s
ti
m
at
io
n a
nd dir
e
c
t
to
r
que
…
(
N
agas
r
id
har
A
r
is
e
)
707
M
V
I
A
1
A
2
B
1
B
2
C
1
C
2
D
1
D
2
a
1
a
2
b
1
b
2
c
1
c
2
d
1
d
2
V
I
S
p
e
e
d
F
l
u
x
N
_
R
e
f
f
l
u
x
N
V
E
C
T
O
R
C
O
N
T
R
O
L
g
a
1
a
2
b
1
b
2
c
1
c
2
d
1
d
2
4
p
h
a
s
e
(
8
p
o
l
e
s
)
g
+
-
4
1
5
V
m
m
I
(
A
)
T
e
(
N
m
)
S
p
e
e
d
(
R
P
M
)
c
u
r
r
e
n
t
T
o
r
q
u
e
s
p
e
e
d
T
r
T
L
A
+
A
-
B
+
B
-
C
+
C
-
D
+
D
-
D
i
s
c
r
e
t
e
T
s
=
T
s
s
.
p
o
w
e
r
g
u
i
S
p
e
e
d
_
r
e
f
V
e
c
t
o
r
C
o
n
t
r
o
l
(
A
N
N
C
o
n
t
r
o
l
)
C
o
n
v
e
r
t
e
r
M
e
a
s
S
p
e
e
d
_
e
s
t
S
t
e
p
p
e
r
m
o
t
o
r
D
a
t
a
A
c
q
u
i
s
a
t
i
o
n
F
ig
ur
e
3. S
im
ul
a
ti
on dia
gr
a
m
of
s
e
ns
or
le
s
s
pos
it
io
n e
s
ti
m
a
ti
on
f
or
a
s
te
ppe
r
m
ot
or
us
in
g
ANN
c
ont
r
ol
F
ig
ur
e
4. O
ut
put
w
a
ve
f
or
m
of
th
e
c
ur
r
e
nt
of
th
e
s
te
ppe
r
m
ot
or
F
ig
ur
e
5. O
ut
put
w
a
ve
f
or
m
s
of
t
or
que
F
ig
ur
e
6. O
ut
put
w
a
ve
f
or
m
of
th
e
s
pe
e
d of
t
he
s
te
ppe
r
m
ot
or
4.
C
O
N
C
L
U
S
I
O
N
S
ubs
e
que
nt
ly
,
a
M
a
r
ty
r
c
ont
r
ol
le
r
is
us
e
d
f
or
e
s
ti
m
a
ti
ng
th
e
lo
c
a
ti
on
of
a
s
te
ppe
r
m
ot
or
,
a
s
s
e
e
n
by
th
e
w
a
ve
f
or
m
s
of
s
pe
e
d,
to
r
que
,
a
nd
c
ur
r
e
nt
a
bove
.
A
la
r
ge
nu
m
be
r
of
s
ubbl
oc
ks
w
e
r
e
e
m
pl
oye
d
,
a
s
w
e
ll
a
s
th
e
s
w
it
c
hi
ng
ta
bl
e
a
nd
ve
c
to
r
c
ont
r
ol
bl
oc
k.
I
t
is
us
e
d
to
b
oos
t
m
ot
or
pe
r
f
or
m
a
nc
e
,
r
e
duc
e
m
ot
or
no
is
e
,
im
pr
ove
pr
oc
e
s
s
a
c
c
ur
a
c
y,
a
nd
e
xt
e
nd
m
ot
or
e
ndur
a
nc
e
.
W
he
n
ope
r
a
ti
ng
th
e
s
te
ppe
r
m
ot
or
,
it
m
a
y
f
a
il
to
f
ol
lo
w
a
pul
s
e
c
om
m
a
nd
w
he
n
th
e
s
te
ppi
ng
r
a
te
or
in
e
r
ti
a
l
l
oa
d
is
to
o
hi
gh;
th
e
s
e
ty
pe
s
of
e
r
r
or
s
c
a
n
b
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
702
-
710
708
a
voi
de
d
by
us
in
g
th
e
ANN
c
ont
r
ol
,
w
hi
c
h
is
a
ls
o
us
e
d
to
e
s
ti
m
a
te
th
e
r
e
a
l
-
ti
m
e
pos
it
io
n
of
th
e
s
te
ppe
r
m
ot
o
r
r
ot
or
.
B
y
doi
ng
s
o,
th
e
m
ot
or
'
s
ove
r
a
ll
pe
r
f
or
m
a
nc
e
a
nd
e
f
f
ic
ie
nc
y
c
a
n
be
im
pr
ove
d
.
S
te
pp
e
r
m
ot
or
s
a
r
e
w
id
e
ly
us
e
d
in
in
dus
tr
ia
l
a
nd
m
a
ny
c
ons
um
e
r
a
ppl
ic
a
ti
ons
.
A
dva
nc
e
d
a
ppr
oa
c
he
s
,
in
c
lu
di
ng
f
uz
z
y
s
li
di
ng
obs
e
r
ve
r
s
,
S
M
O
,
A
N
F
I
S
,
a
nd
f
uz
z
y
lo
gi
c
c
ont
r
ol
,
a
r
e
a
ll
in
c
lu
de
d
in
th
e
s
ugge
s
te
d
f
ut
ur
e
f
r
a
m
e
w
or
k
f
or
s
e
ns
or
le
s
s
s
pe
e
d c
ont
r
ol
s
y
s
te
m
s
. T
hi
s
s
e
e
k
s
t
o m
a
xi
m
iz
e
pe
r
f
or
m
a
nc
e
w
hi
le
ke
e
pi
ng c
os
ts
dow
n by boos
ti
ng
s
pe
e
d c
ont
r
ol
pr
e
c
is
io
n w
it
hout
r
a
is
in
g phys
ic
a
l
e
xpe
n
s
e
s
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
T
hi
s
r
e
s
e
a
r
c
h w
a
s
f
unde
d by
T
e
e
g
a
la
K
r
is
hna
R
e
ddy E
ngi
ne
e
r
in
g C
ol
le
ge
.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
N
a
ga
s
r
id
ha
r
A
r
is
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
hi
r
uve
e
dul
a
M
a
dhu
B
a
bu
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
S
r
in
id
hi
G
ol
la
pudi
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
a
r
un K
um
a
r
D
om
m
e
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
bhi
s
he
k K
um
m
a
r
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
M
a
hi
th
S
ha
m
buka
r
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
A
ut
hor
s
s
ta
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
a
va
il
a
bl
e
f
r
om
th
e
c
or
r
e
s
ponding
a
ut
hor
,
[
NA
]
,
upon
r
e
a
s
ona
bl
e
r
e
que
s
t.
R
E
F
E
R
E
N
C
E
S
[
1]
H
.
T
a
na
ka
,
F
.
T
a
t
s
ut
a
,
a
nd
S
.
N
i
s
hi
ka
t
a
,
“
A
s
e
n
s
or
l
e
s
s
i
ni
t
i
a
l
r
ot
or
pos
i
t
i
on
e
s
t
i
m
a
t
i
on
m
e
t
hod
f
or
t
w
o
-
pha
s
e
hybr
i
d
s
t
e
ppi
n
g
m
ot
or
s
,”
i
n
2013
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
l
e
c
t
r
i
c
al
M
ac
hi
ne
s
and
Sy
s
t
e
m
s
,
I
E
E
E
,
2013,
pp.
734
–
737.
doi
:
10.1109/
I
C
E
M
S
.2013.6754487.
[
2]
A
.
H
.
R
.
A
bba
s
,
A
.
A
bdul
a
z
i
z
,
A
.
H
.
A
l
a
w
a
di
,
P
.
B
.
E
.
P
r
a
bha
ka
r
,
S
.
K
um
a
r
C
,
a
nd
L
.
W
a
dhw
a
,
“
A
dva
nc
e
m
e
nt
s
i
n
s
e
ns
or
l
e
s
s
c
ont
r
ol
t
e
c
hni
que
s
f
or
e
l
e
c
t
r
i
c
dr
i
ve
s
,”
E
3S W
e
b of
C
onf
e
r
e
nc
e
s
, vol
. 540, 2024, doi
:
10.1051/
e
3s
c
onf
/
202454002010.
[
3]
P
.
R
.
K
um
a
r
,
“
P
os
i
t
i
on
c
ont
r
ol
of
a
s
t
e
ppe
r
m
ot
or
us
i
ng
L
a
bV
I
E
W
,”
i
n
20
18
3r
d
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
R
e
c
e
nt
T
r
e
nds
i
n
E
l
e
c
t
r
oni
c
s
,
I
nf
or
m
at
i
on
and
C
om
m
uni
c
at
i
on
T
e
c
hnol
ogy
,
I
E
E
E
,
2018,
pp.
1551
–
1554.
doi
:
10.1109/
R
T
E
I
C
T
42901.2018.9012597.
[
4]
Y
.
A
nz
a
i
,
S
.
N
i
s
hi
ka
t
a
,
a
nd
F
.
T
a
t
s
ut
a
,
“
S
t
udi
e
s
on
a
s
e
ns
or
l
e
s
s
i
ni
t
i
a
l
r
ot
o
r
pos
i
t
i
on
e
s
t
i
m
a
t
i
ng
m
e
t
hod
f
o
r
hybr
i
d
s
t
e
ppi
ng
m
ot
or
s
,”
i
n
2009
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
l
e
c
t
r
i
c
al
M
ac
hi
ne
s
and
Sy
s
t
e
m
s
,
I
E
E
E
,
2009,
pp.
1
–
4.
doi
:
10.1109/
I
C
E
M
S
.2009.5382705.
[
5]
Y
.
L
i
u,
J
.
Z
hu,
Z
.
W
a
ng,
a
nd
Y
.
L
i
a
ng,
“
S
t
udy
of
r
ot
or
pos
i
t
i
on
e
s
t
i
m
a
t
i
on
a
l
gor
i
t
hm
ba
s
e
d
on
ba
c
k
-
E
M
F
vol
t
a
ge
f
or
dua
l
-
w
i
ndi
ng
f
a
ul
t
-
t
ol
e
r
a
nt
pe
r
m
a
ne
nt
m
a
gne
t
m
ot
or
,”
A
ut
om
at
i
k
a
,
vol
.
63,
no.
3,
pp.
496
–
510,
2022
,
doi
:
10.1080/
00051144.2022.2051975.
[
6]
B
. Y
. S
he
n, K
. J
. C
he
n, a
nd X
.
C
. G
ua
n, “
C
ont
r
ol
of
t
hr
e
e
-
pha
s
e
s
t
e
ppe
r
m
ot
or
ba
s
e
d on
D
S
P
,”
A
ppl
i
e
d M
e
c
hani
c
s
and M
at
e
r
i
al
s
,
vol
. 738
–
739, pp. 1094
–
1098, 2015, doi
:
10.4028/
w
w
w
.s
c
i
e
nt
i
f
i
c
.ne
t
/
a
m
m
.738
-
739.1094.
[
7]
V
.
N
.
A
nt
i
pov,
A
.
D
.
G
r
oz
ov,
a
nd
A
.
V
.
I
va
nova
,
“
S
w
i
t
c
he
d
r
e
l
uc
t
a
nc
e
m
ot
or
f
or
a
t
r
ol
l
e
ybus
t
r
a
c
t
i
on
a
ppl
i
c
a
t
i
on:
de
s
i
gn
a
n
d
m
ode
l
i
ng,”
i
n
2020
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
l
e
c
t
r
i
c
al
M
ac
hi
ne
s
,
I
E
E
E
,
2020,
pp.
1820
–
1825.
doi
:
10.1109/
I
C
E
M
49940.2020.9270914.
[
8]
K
.
K
.
R
a
j
a
n
a
nd
P
.
L
a
t
ha
,
“
A
da
pt
i
ve
ne
ur
o
f
uz
z
y
i
nf
e
r
e
nc
e
s
ys
t
e
m
ba
s
e
d
s
e
n
s
or
l
e
s
s
r
ot
or
pos
i
t
i
on
e
s
t
i
m
a
t
i
on
of
S
R
M
,”
A
R
P
N
J
our
nal
of
E
ngi
ne
e
r
i
ng and A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 10, no. 4, pp. 1920
–
1926, 20
15.
[
9]
J
.
A
.
M
a
kw
a
na
,
P
.
A
ga
r
w
a
l
,
a
nd
S
.
P
.
S
r
i
va
s
t
a
va
,
“
A
N
N
ba
s
e
d
s
e
n
s
or
l
e
s
s
r
ot
or
pos
i
t
i
on
e
s
t
i
m
a
t
i
on
f
or
t
he
s
w
i
t
c
he
d
r
e
l
uc
t
a
nc
e
m
ot
or
,”
i
n
2011
N
i
r
m
a
U
ni
v
e
r
s
i
t
y
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
ngi
ne
e
r
i
ng
,
I
E
E
E
,
2011,
pp.
1
–
6.
doi
:
10.1109/
N
U
i
C
onE
.2011.6153281.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
A
r
ti
fi
c
ia
l
ne
ur
al
ne
tw
or
k
ba
s
e
d s
e
ns
or
l
e
s
s
po
s
it
io
n e
s
ti
m
at
io
n a
nd dir
e
c
t
to
r
que
…
(
N
agas
r
id
har
A
r
is
e
)
709
[
10]
F
.
J
.
A
na
yi
a
nd
M
.
M
.
A
.
A
l
I
b
r
a
he
e
m
i
,
“
E
s
t
i
m
a
t
i
on
of
r
ot
or
pos
i
t
i
on
f
o
r
pe
r
m
a
ne
nt
m
a
gne
t
s
ync
hr
onous
m
ot
or
a
t
s
t
a
nds
t
i
l
l
us
i
ng
s
e
ns
or
l
e
s
s
vol
t
a
ge
c
ont
r
ol
s
c
he
m
e
,
”
I
E
E
E
/
A
SM
E
T
r
ans
ac
t
i
ons
on
M
e
c
ha
t
r
oni
c
s
,
vol
.
25,
no.
3,
pp.
1612
–
1621,
2020,
doi
:
10.1109/
T
M
E
C
H
.2020.2981193.
[
11]
N
.
P
i
m
kum
w
ong
a
nd
M
.
S
.
W
a
ng,
“
O
nl
i
ne
s
p
e
e
d
e
s
t
i
m
a
t
i
on
us
i
ng
a
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
or
k
f
or
s
pe
e
d
s
e
ns
or
l
e
s
s
di
r
e
c
t
t
or
que
c
ont
r
ol
of
i
nduc
t
i
on m
ot
or
ba
s
e
d on c
ons
t
a
nt
V
/
F
c
ont
r
ol
t
e
c
hni
que
,”
E
ne
r
gi
e
s
,
vol
. 11, no. 8, 2018, doi
:
10.3390/
e
n11082176.
[
12]
T
.
M
.
B
a
bu,
K
.
C
he
nc
hi
r
e
ddy,
J
.
R
ohi
ni
,
M
.
S
.
S
uha
s
,
D
.
A
j
i
t
e
s
h,
a
nd
K
.
R
a
hu
l
,
“
H
i
gh
vol
t
a
ge
DC
-
DC
c
onve
r
t
e
r
w
i
t
h
s
t
a
nda
l
one
a
ppl
i
c
a
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
ppl
i
e
d
P
ow
e
r
E
ngi
ne
e
r
i
ng
,
vol
.
12,
no.
4,
p.
384,
D
e
c
.
2023,
doi
:
10.11591/
i
j
a
pe
.v12.i
4.pp384
-
390.
[
13]
C.
-
F
.
W
u
a
nd
S
.
-
K
.
L
i
n,
“
A
nove
l
s
e
ns
or
l
e
s
s
i
ni
t
i
a
l
r
ot
or
pos
i
t
i
on
e
s
t
i
m
a
t
i
on
m
e
t
hod
f
or
pe
r
m
a
ne
nt
m
a
gne
t
s
ync
hr
onous
m
ot
or
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
P
ow
e
r
E
l
e
c
t
r
oni
c
s
and
D
r
i
v
e
Sy
s
t
e
m
s
,
vol
.
8,
no.
1,
pp.
156
–
166,
2017
,
doi
:
10.11591/
i
j
pe
ds
.v8.i
1.pp156
-
166.
[
14]
N
.
E
.
O
ua
nj
l
i
e
t
al
.
,
“
M
ode
r
n
i
m
pr
ove
m
e
nt
t
e
c
hni
que
s
of
di
r
e
c
t
t
or
que
c
ont
r
ol
f
or
i
nduc
t
i
on
m
ot
or
dr
i
ve
s
-
a
r
e
vi
e
w
,”
P
r
ot
e
c
t
i
on
and C
ont
r
ol
of
M
ode
r
n P
ow
e
r
S
y
s
t
e
m
s
, vol
. 4, no. 11, 2019, doi
:
10.1186/
s
416
01
-
019
-
0125
-
5.
[
15]
M
.
T
hi
r
uve
e
dul
a
a
nd
K
.
A
s
oka
n,
“
H
a
r
m
oni
c
s
r
e
duc
t
i
on
i
n
vi
r
t
ua
l
s
ync
h
r
onous
ge
ne
r
a
t
or
us
i
ng
f
uz
z
y
l
ogi
c
c
ont
r
ol
l
e
r
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
E
ngi
ne
e
r
i
ng
T
e
c
hnol
ogy
and
M
anage
m
e
nt
S
c
i
e
nc
e
s
,
vol
.
8,
no.
1,
pp.
159
–
167,
2024,
doi
:
10.46647/
i
j
e
t
m
s
.2024.v08i
01.020.
[
16]
K
.
K
.
P
r
a
bha
ka
r
a
n
a
nd
A
.
K
a
r
t
hi
ke
ya
n,
“
E
l
e
c
t
r
o
m
a
gne
t
i
c
t
or
que
-
ba
s
e
d
m
od
e
l
r
e
f
e
r
e
nc
e
a
da
pt
i
ve
s
ys
t
e
m
s
pe
e
d
e
s
t
i
m
a
t
or
f
or
s
e
ns
or
l
e
s
s
s
ur
f
a
c
e
m
ount
pe
r
m
a
ne
nt
m
a
gne
t
s
ync
hr
onous
m
ot
or
dr
i
ve
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
ndus
t
r
i
al
E
l
e
c
t
r
oni
c
s
,
vol
.
67,
no. 7, pp. 5936
–
5947, 2020, doi
:
10.1109/
T
I
E
.2020.2965499.
[
17]
G
.
Y
a
o,
Y
.
C
he
ng,
Z
.
W
a
ng,
a
nd
Y
.
X
i
a
o,
“
S
t
udy
on
a
s
e
c
ond
-
or
de
r
a
da
pt
i
v
e
s
l
i
di
ng
-
m
ode
obs
e
r
ve
r
c
ont
r
ol
a
l
gor
i
t
hm
f
or
t
he
s
e
ns
or
l
e
s
s
pe
r
m
a
ne
nt
m
a
gne
t
s
yn
c
hr
onous
m
ot
or
,”
P
r
oc
e
s
s
e
s
, vol
. 11, no. 6, 20
23, doi
:
10.3390/
pr
11061636.
[
18]
S
. W
u, J
. Z
ha
ng, a
nd B
.
C
ha
i
, “
A
da
pt
i
ve
s
upe
r
-
t
w
i
s
t
i
ng s
l
i
di
ng m
od
e
obs
e
r
ve
r
ba
s
e
d r
obus
t
b
a
c
ks
t
e
ppi
ng
s
e
n
s
or
l
e
s
s
s
pe
e
d
c
ont
r
ol
f
or
I
P
M
S
M
,”
I
SA
T
r
ans
ac
t
i
ons
, vol
. 92, pp. 155
–
165, 2019, doi
:
10.1016/
j
.i
s
a
t
r
a
.2019.02.007.
[
19]
S
.
J
.
R
i
nd,
M
.
J
a
m
i
l
,
a
nd
A
.
A
m
j
a
d,
“
E
l
e
c
t
r
i
c
m
ot
or
s
a
nd
s
p
e
e
d
s
e
ns
or
l
e
s
s
c
ont
r
ol
f
or
e
l
e
c
t
r
i
c
a
nd
hybr
i
d
e
l
e
c
t
r
i
c
ve
hi
c
l
e
s
:
a
r
e
vi
e
w
,”
i
n
2018
53
r
d
I
nt
e
r
nat
i
onal
U
ni
v
e
r
s
i
t
i
e
s
P
ow
e
r
E
ngi
ne
e
r
i
ng
C
onf
e
r
e
nc
e
,
I
E
E
E
,
2018,
pp.
1
–
6.
doi
:
10.1109/
U
P
E
C
.2018.8541871.
[
20]
N
.
M
.
T
om
y
a
nd
J
.
F
r
a
nc
i
s
,
“
F
i
e
l
d
or
i
e
nt
e
d
s
e
ns
or
l
e
s
s
pos
i
t
i
on
c
ont
r
ol
of
a
hy
br
i
d
s
t
e
ppe
r
m
ot
or
w
i
t
h
e
xt
e
nde
d
K
a
l
m
a
n
f
i
l
t
e
r
,”
i
n
2016 10t
h I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on I
nt
e
l
l
i
ge
nt
Sy
s
t
e
m
s
and C
ont
r
ol
, I
E
E
E
,
2016, pp. 1
–
5. doi
:
10.1109/
I
S
C
O
.2016.7727056.
[
21]
T
.
D
.
H
oa
ng,
A
.
D
a
s
,
S
.
K
oe
ke
ba
kk
e
r
,
a
nd
S
.
W
e
i
l
a
nd,
“
S
e
ns
or
l
e
s
s
f
i
e
l
d
-
or
i
e
nt
e
d
e
s
t
i
m
a
t
i
on
of
hybr
i
d
s
t
e
ppe
r
m
ot
or
s
i
n
hi
gh
-
pe
r
f
or
m
a
nc
e
pa
pe
r
ha
ndl
i
ng,”
i
n
2019
I
E
E
E
C
onf
e
r
e
nc
e
on
C
ont
r
ol
T
e
c
hnol
ogy
and
A
ppl
i
c
at
i
ons
,
I
E
E
E
,
2019,
pp.
252
–
257.
doi
:
10.1109/
C
C
T
A
.2019.8920549.
[
22]
D
.
F
a
n,
M
.
B
ol
de
r
m
a
n,
S
.
K
oe
ke
ba
kke
r
,
H
.
B
ut
l
e
r
,
a
nd
M
.
L
a
z
a
r
,
“
P
hys
i
c
s
–
gui
de
d
ne
ur
a
l
ne
t
w
or
ks
f
or
i
nve
r
s
i
on
–
ba
s
e
d
f
e
e
df
or
w
a
r
d
c
ont
r
ol
a
ppl
i
e
d
t
o
hybr
i
d
s
t
e
ppe
r
m
ot
or
s
*,”
i
n
2023
I
E
E
E
C
onf
e
r
e
nc
e
on
C
ont
r
ol
T
e
c
hnol
ogy
and
A
ppl
i
c
at
i
ons
,
I
E
E
E
, 2023, pp. 1153
–
1158. doi
:
10.1109/
C
C
T
A
54093.2023.10252460.
[
23]
N
.
A
r
i
s
e
,
V
.
B
hoom
i
ka
,
N
.
A
.
R
e
ddy,
S
.
H
a
r
i
ka
,
a
nd
A
.
K
ou
s
hi
k,
“
P
ow
e
r
g
e
ne
r
a
t
i
on
of
w
i
nd
-
PV
-
ba
t
t
e
r
y
ba
s
e
d
hybr
i
d
e
ne
r
gy
s
ys
t
e
m
f
or
s
t
a
nda
l
one
a
c
m
i
c
r
ogr
i
d
a
ppl
i
c
a
t
i
ons
,”
i
n
2023
5t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
Sm
ar
t
S
y
s
t
e
m
s
and
I
nv
e
nt
i
v
e
T
e
c
hnol
ogy
, I
E
E
E
, 2023, pp. 261
–
266. do
i
:
10.1109/
I
C
S
S
I
T
55814.2023.10060
963.
[
24]
I
.
M
e
s
s
a
i
f
,
E
.
M
.
B
e
r
kouk,
a
nd
N
.
S
a
a
di
a
,
“
S
e
ns
or
-
l
e
s
s
D
T
C
of
i
nduc
t
i
on
m
o
t
or
us
i
ng
i
m
pr
ove
d
ne
ur
a
l
ne
t
w
or
k
s
w
i
t
c
hi
ng
s
t
a
t
e
s
e
l
e
c
t
or
c
ont
r
ol
l
e
r
,”
A
r
c
hi
v
e
s
of
C
ont
r
ol
Sc
i
e
nc
e
s
, vol
. 20, no. 4, pp. 435
–
456,
2010, doi
:
10.2478/
v10170
-
010
-
0025
-
4.
[
25]
X
. D
.
T
or
o, S
. C
a
l
l
s
, M
.
G
. J
a
yne
, P
. A
. W
i
t
t
i
ng, A
. A
r
i
a
s
, a
nd J
. L
.
R
om
e
r
a
l
, “
D
i
r
e
c
t
t
or
que
c
ont
r
ol
of
a
n i
nduc
t
i
on m
ot
or
us
i
ng a
t
hr
e
e
-
l
e
ve
l
i
nve
r
t
e
r
a
nd
f
uz
z
y
l
ogi
c
,
”
I
E
E
E
I
nt
e
r
nat
i
onal
Sy
m
pos
i
um
on
I
ndus
t
r
i
al
E
l
e
c
t
r
oni
c
s
,
vol
.
2,
pp.
923
–
927,
2004
,
doi
:
10.1109/
I
S
I
E
.2004.1571937.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Nagasridhar
Arise
received
the
B.Tech.
and
M.Tech.
from
JNTU
Hyderabad,
India,
in
2007
and
2012
,
respectively.
He
is
presently
working
as
a
n
Assistant
Professor
in
Teegala
Krishna
Reddy
Engineering
Colleg
e,
Hyderabad,
India.
He
ha
s
worked
as
an
Assistant
Professor
in
Praveenya
Institute
of
Marine
Engineering
and
Maritime
Studies
College,
Vizag,
India.
He
has
11
years
of
experie
nce
teachin
g
and
3
y
ears
of
experie
nce
in
the
industry.
His
area
of
interest
includes
power
systems,
power
qual
ity,
and
hybrid
energy
systems.
He
has
presented
technical
papers
in
various
national
and
in
ternational
journals
and
conferences. H
e can be con
tacted at
email:
sridhar01
06@
gmail.co
m
.
Thiruveedula
Madhu
Babu
received
B.Tech
.
from
JNTU
Hyder
abad,
India,
in
2010
and
M.Tech
.
from
NIT
Calicut
in
2013
,
respectively,
and
pursui
ng
a
Ph.D.
at
Annamalai
University,
India.
He
is
presently
working
as
an
assistant
professo
r
and
HOD
in
Teegala
Krishna
Reddy
Engineering
College,
Hyderabad,
India
.
He
has
presented
technical
papers
in
various
national
and
international
journals
and
conferences.
He
can
be
contacted
at
email:
madhumk448@gmail.com
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
3
,
S
e
pt
e
m
be
r
20
25
:
702
-
710
710
Srinidhi
Gollapudi
is
presently
a
UG
student
in
Electrical
a
nd
Electronics
Engineering
at
Teegala
Krishna
R
eddy
Engineering
College,
Hyder
abad,
Telangana,
India.
She
has
presented
technical
papers
at
various
internationa
l
confere
nc
es
.
Her
areas
of
interest
include
power
electroni
cs,
power
quality,
and
multilevel
inverters
.
She
developed
a
single
-
phase
inverter
at
Teegala
Krishna
Reddy
Engineering
College,
Hyderabad.
She
can
be
contacted
at email
: srini
dhimegh
ana677@
gmail.co
m
.
Tarun
Kumar
Dommeti
is
presently
a
UG
student
in
Electrical
a
nd
Electronics
Engineering
at
Teegala
Krishna
Reddy
Engineering
College,
Hy
derabad,
India.
He
has
presented
technical
papers
at
various
national
and
international
co
nferences.
His
areas
of
interest
include
power
electroni
cs,
power
quality,
and
multilevel
inverters
.
He
can
be
contact
ed
at email
: tarunk
umar.dom
meti@
gmail.co
m
.
Abhishek
Kummari
is
presently
a
UG
student
in
Electrical
a
nd
Electronics
Engineering
at
Teegala
Krishna
Reddy
Engineering
College,
Hy
derabad,
India.
He
has
presented
technical
papers
at
various
national
and
international
co
nferences.
His
areas
of
interest
include
power
electronics,
power
quality
,
and
multilevel
inverters
.
He
can
be
contacted
at email
:
abhi1711
2003@
gmail.co
m
.
Mahith
Shambukari
is
presently
a
UG
student
in
Electrical
and
Electronics
Engineering
at
Teegala
Krishna
Reddy
Engineering
College,
Hy
derabad,
India.
He
has
presented
technical
papers
in
various
national
and
internationa
l
c
onferen
ces
.
His
area
of
interest
includes
power
electroni
cs,
power
quality
,
and
multileve
l
inverters
.
He
can
be
contacted
at email
: Mahit
h1314@
gmail.co
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.