I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
9
,
No
.
1
,
J
an
u
ar
y
201
8
,
p
p
.
77
~
80
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i1
.
p
p
77
-
80
77
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
/
ijeec
s
Applica
tion o
f
Ar
tif
icia
l N
eura
l N
et
w
o
rk
in
Ele
ctric
a
l
P
o
w
er
Sy
ste
m
P
.
P
a
la
nicha
m
y
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
A
M
ET
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
18
,
2
0
1
7
R
ev
i
s
ed
No
v
2
7
,
2
0
1
7
A
cc
ep
ted
Dec
1
9
,
2
0
1
7
T
h
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
u
se
d
to
d
e
tec
t
th
e
f
a
u
lt
in
e
lec
tri
c
a
l
m
a
c
h
in
e
s
a
n
d
c
a
n
in
c
re
a
se
th
e
f
u
n
c
ti
o
n
o
f
n
e
w
e
n
tr
y
d
e
tec
ti
o
n
w
h
e
n
c
o
m
p
a
re
d
to
th
e
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
.
In
p
ro
p
o
se
d
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
h
a
s
in
c
re
a
se
d
th
e
p
re
c
isio
n
a
n
d
sta
b
il
it
y
o
f
s
y
ste
m
p
e
rf
o
r
m
a
n
c
e
.
T
h
e
ti
m
e
-
a
r
e
a
v
ib
ra
ti
o
n
sig
n
s
o
f
a
p
iv
o
ti
n
g
m
a
c
h
in
e
w
it
h
o
rd
i
n
a
r
y
a
n
d
f
l
a
w
e
d
a
p
p
a
ra
tu
se
s
a
re
h
a
n
d
led
f
o
r
h
ig
h
li
g
h
t
e
x
trac
ti
o
n
.
T
h
e
se
p
a
ra
ted
e
le
m
e
n
ts
f
ro
m
u
n
iq
u
e
a
n
d
p
r
e
p
ro
c
e
ss
e
d
sig
n
s
a
re
u
ti
li
z
e
d
a
s
c
o
n
tri
b
u
ti
o
n
s
to
b
o
t
h
c
las
sif
iers
in
v
ie
w
o
f
A
N
Ns
a
n
d
S
V
M
s
f
o
r
tw
o
-
c
las
s
(ty
p
ica
l
o
r
b
lam
e
)
a
c
k
n
o
w
led
g
m
e
n
t.
T
h
e
q
u
a
n
t
it
y
o
f
h
u
b
s
in
t
h
e
c
o
n
c
e
a
led
lay
e
r,
i
f
th
e
re
sh
o
u
ld
b
e
a
n
o
c
c
u
rre
n
c
e
o
f
A
N
Ns
,
a
n
d
th
e
e
x
ten
d
b
a
sis
w
o
rk
se
c
ti
o
n
p
a
r
a
m
e
ter,
in
th
e
e
v
e
n
t
o
f
S
V
M
s,
a
lo
n
g
sid
e
th
e
c
h
o
ice
o
f
in
f
o
rm
a
ti
o
n
c
o
m
p
o
n
e
n
ts
a
re
e
n
h
a
n
c
e
d
u
ti
li
z
i
n
g
g
e
n
e
ti
c
a
lg
o
rit
h
m
(GA
s).
K
ey
w
o
r
d
s
:
E
lectr
ical
Ma
ch
i
n
es
E
x
tr
ac
tio
n
a
n
d
SVMs
Neu
r
al
Net
w
o
r
k
P
er
f
o
r
m
a
n
ce
Stab
ilit
y
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
:
P
.
P
alan
ich
a
m
y
,
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics,
A
ME
T
Un
i
v
er
s
it
y
,
C
h
en
n
ai.
1.
I
NT
RO
D
UCT
I
O
N
I
n
v
ec
to
r
m
ac
h
i
n
es
h
as
t
w
o
-
c
lass
is
s
u
es
—
i
n
w
h
ic
h
th
e
i
n
f
o
r
m
at
io
n
ar
e
is
o
lated
b
y
a
h
y
p
er
p
lan
e
ch
ar
ac
ter
ized
b
y
v
ar
io
u
s
b
o
ls
t
er
v
ec
to
r
s
.
A
co
n
ci
s
e
p
r
esen
t
atio
n
o
f
SVM
i
s
e
x
h
ib
ited
h
e
r
e
f
o
r
cu
l
m
i
n
atio
n
.
P
er
u
s
es
ar
e
allu
d
ed
to
th
e
i
n
s
t
r
u
ctio
n
al
e
x
er
cise
s
o
n
SVM
s
f
o
r
p
o
in
ts
o
f
in
ter
e
s
t.
T
h
e
SV
M
ca
n
b
e
co
n
s
id
er
ed
to
m
a
k
e
a
li
n
e
o
r
h
y
p
er
p
la
n
e
b
et
w
ee
n
t
w
o
ar
r
an
g
e
m
e
n
ts
o
f
in
f
o
r
m
atio
n
f
o
r
g
r
o
u
p
in
g
.
I
f
t
h
er
e
s
h
o
u
ld
ar
is
e
a
n
o
cc
u
r
r
en
ce
o
f
t
w
o
-
d
i
m
e
n
s
io
n
a
l c
ir
cu
m
s
ta
n
ce
,
th
e
ac
ti
v
it
y
o
f
th
e
SVM
ca
n
b
e
clar
if
ied
e
f
f
e
ctiv
el
y
w
it
h
n
o
lo
s
s
o
f
s
i
m
p
l
if
icatio
n
.
P
ro
ble
m
Descript
io
n
I
t
is
n
ec
es
s
ar
y
to
id
en
ti
f
y
f
a
u
lt
in
elec
tr
ical
m
ac
h
i
n
es
an
d
p
o
w
er
s
y
s
te
m
lin
e
s
d
u
r
in
g
o
p
er
atio
n
to
en
s
u
r
e
co
n
t
in
u
o
u
s
r
eliab
le
o
p
er
atio
n
o
f
p
o
w
er
s
y
s
te
m
s
.
C
o
n
v
en
t
io
n
al
f
a
u
lt
id
en
t
if
ica
t
io
n
m
et
h
o
d
o
lo
g
ies
b
ased
SVM’
s
a
n
d
G
A
ca
n
n
o
t
id
en
ti
f
y
p
r
o
b
le
m
s
o
r
f
a
u
lts
in
lar
g
e
p
o
w
er
s
y
s
te
m
s
a
n
d
th
e
s
e
m
et
h
o
d
s
ar
e
co
m
p
le
x
.
B
a
ck
g
ro
un
d
C
o
n
d
itio
n
v
ie
w
in
g
o
f
m
ac
h
in
es
is
g
ai
n
i
n
g
m
o
r
e
s
ig
n
i
f
ica
n
c
e
in
i
n
d
u
s
tr
y
d
u
e
to
th
e
n
ee
d
to
ex
p
an
d
d
ep
en
d
ab
ilit
y
a
n
d
to
d
i
m
i
n
is
h
in
g
co
n
ce
i
v
ab
le
lo
s
s
o
f
cr
e
atio
n
b
ec
au
s
e
o
f
m
ac
h
i
n
e
b
r
ea
k
d
o
w
n
[
1
]
.
T
h
e
u
tili
za
t
io
n
o
f
v
i
b
r
atio
n
an
d
ac
o
u
s
tic
o
u
t
f
lo
w
(
A
E
)
s
i
g
n
s
i
s
v
er
y
r
eg
u
lar
i
n
t
h
e
f
ie
ld
o
f
co
n
d
itio
n
ch
ec
k
i
n
g
o
f
p
iv
o
tin
g
ap
p
ar
atu
s
.
B
y
co
n
t
r
asti
n
g
t
h
e
s
i
g
n
s
o
f
a
m
ac
h
in
e
r
u
n
n
i
n
g
i
n
t
y
p
ical
a
n
d
f
la
w
ed
co
n
d
it
io
n
s
,
id
en
ti
f
icatio
n
o
f
d
ef
icie
n
cie
s
l
ik
e
m
a
s
s
u
n
b
alan
ce
,
r
o
to
r
r
u
b
,
s
h
a
f
t
m
is
ali
g
n
m
en
t,
eq
u
ip
d
i
s
ap
p
o
in
t
m
e
n
ts
a
n
d
b
ea
r
in
g
i
m
p
er
f
ec
tio
n
s
i
s
co
n
ce
iv
ab
le
[
2
]
.
T
h
ese
s
i
g
n
s
ca
n
li
k
e
w
is
e
b
e
u
tili
ze
d
to
id
en
ti
f
y
t
h
e
b
eg
in
n
i
n
g
d
is
ap
p
o
in
t
m
e
n
ts
o
f
t
h
e
m
ac
h
i
n
e
p
ar
ts
,
t
h
r
o
u
g
h
t
h
e
o
n
-
li
n
e
c
h
ec
k
i
n
g
f
r
a
m
e
w
o
r
k
,
d
i
m
i
n
i
s
h
i
n
g
th
e
lik
e
lih
o
o
d
o
f
d
is
astro
u
s
h
ar
m
a
n
d
th
e
d
o
w
n
ti
m
e
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
9
,
No
.
1
,
J
an
u
ar
y
201
8
:
7
7
–
80
78
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
ANNs)
h
a
v
e
b
ee
n
co
n
n
ec
ted
in
m
ec
h
a
n
ized
r
ec
o
g
n
i
tio
n
an
d
an
al
y
s
is
o
f
m
ac
h
in
e
co
n
d
itio
n
s
r
eg
ar
d
in
g
th
ese
a
s
g
r
o
u
p
i
n
g
o
r
s
p
ec
u
l
atio
n
is
s
u
e
s
i
n
v
ie
w
o
f
ta
k
i
n
g
in
e
x
a
m
p
le
f
r
o
m
illu
s
tr
atio
n
s
o
r
ex
p
er
i
m
e
n
tal
i
n
f
o
r
m
atio
n
d
i
s
p
la
y
i
n
g
[
4
]
.
I
n
an
y
ca
s
e,
t
h
e
cu
s
to
m
ar
y
n
eu
r
a
l
s
y
s
te
m
ap
p
r
o
ac
h
es
h
av
e
i
m
p
ed
i
m
en
ts
o
n
s
p
ec
u
la
tio
n
o
f
f
er
i
n
g
a
s
ce
n
d
to
m
o
d
el
s
th
a
t
ca
n
o
v
er
f
it
to
t
h
e
p
r
ep
ar
atio
n
in
f
o
r
m
a
tio
n
[
5
]
.
T
h
is
lack
is
b
ec
au
s
e
o
f
th
e
s
tr
ea
m
lin
in
g
ca
lcu
l
a
tio
n
s
u
tili
ze
d
as
a
p
ar
t
o
f
A
NNs
f
o
r
d
eter
m
in
at
io
n
o
f
p
ar
am
eter
s
an
d
t
h
e
f
ac
t
u
al
m
e
asu
r
es
u
s
ed
to
ch
o
o
s
e
t
h
e
m
o
d
el.
A
s
o
f
late,
b
o
ls
ter
v
ec
to
r
m
ac
h
in
e
s
(
SVMs),
in
v
ie
w
o
f
f
ac
t
u
al
lear
n
i
n
g
h
y
p
o
t
h
esi
s
,
ar
e
p
ic
k
i
n
g
u
p
ap
p
licatio
n
s
i
n
t
h
e
r
a
n
g
e
s
o
f
m
a
ch
in
e
le
ar
n
in
g
,
P
C
v
is
io
n
an
d
e
x
a
m
p
le
ac
k
n
o
w
le
d
g
m
e
n
t
d
u
e
to
h
ig
h
e
x
ac
tn
e
s
s
an
d
g
r
ea
t
s
p
ec
u
latio
n
ab
ilit
y
[
6
]
.
A
r
ec
u
r
r
en
t
th
e
f
u
n
ctio
n
s
o
f
v
ar
io
u
s
v
ib
r
atio
n
s
b
ased
s
ig
n
al
s
,
attain
ed
u
n
d
er
b
o
th
n
o
r
m
al
a
n
d
lig
h
t
lo
ad
s
an
d
at
lo
w
an
d
h
i
g
h
s
a
m
p
li
n
g
r
ates,
ar
e
e
x
a
m
i
n
ed
.
T
h
e
r
esu
lts
ex
p
lai
n
th
e
e
f
f
ec
ti
v
en
e
s
s
o
f
t
h
e
e
x
tr
ac
ted
f
ea
t
u
r
es
f
r
o
m
t
h
e
atta
in
e
d
an
d
p
r
ep
r
o
ce
s
s
ed
s
ig
n
al
s
i
n
a
n
al
y
s
i
s
o
f
t
h
e
m
ac
h
i
n
e
co
n
d
it
io
n
.
P
r
ed
ictiv
e
Dir
ec
t
P
o
w
er
C
o
n
tr
o
l
(
P
DP
C
)
o
f
Gr
id
-
C
o
n
n
ec
ted
Du
al
-
A
ct
iv
e
B
r
id
g
e
Mu
lt
ilev
el
I
n
v
er
ter
i
s
ex
p
lain
ed
in
[
7
]
.
P
r
o
p
o
r
tio
n
al
I
n
te
g
r
al
E
s
ti
m
ato
r
o
f
th
e
Stato
r
R
e
s
is
ta
n
ce
f
o
r
Dir
ec
t
T
o
r
q
u
e
C
o
n
tr
o
l
I
n
d
u
ct
io
n
Mo
to
r
Dr
iv
e
i
s
d
is
c
u
s
s
ed
in
[
8
]
.
C
o
m
p
ar
is
o
n
P
er
f
o
r
m
a
n
ce
s
o
f
I
n
d
ir
ec
t
Fiel
d
Or
ien
ted
C
o
n
tr
o
l
f
o
r
T
h
r
ee
-
P
h
ase
I
n
d
u
ct
io
n
Mo
to
r
Dr
iv
es
is
p
r
esen
ted
i
n
[
9
]
.
Sen
s
o
r
le
s
s
C
o
n
tr
o
l
o
f
B
L
DC
Mo
to
r
u
s
i
n
g
F
u
zz
y
lo
g
ic
co
n
t
r
o
ller
f
o
r
So
lar
p
o
w
er
Ge
n
er
at
io
n
is
d
is
c
u
s
s
ed
in
[
1
0
]
.
Fig
u
r
e
1
.
Flo
w
C
h
ar
t
o
f
D
iag
n
o
s
tic
P
r
o
ce
d
u
r
e
1
.
1
.
Vec
t
o
r
M
a
chines
I
n
v
ec
to
r
m
ac
h
i
n
es
h
as
t
w
o
-
c
lass
is
s
u
es
—
i
n
w
h
ic
h
th
e
i
n
f
o
r
m
at
io
n
ar
e
is
o
lated
b
y
a
h
y
p
er
p
lan
e
ch
ar
ac
ter
ized
b
y
v
ar
io
u
s
b
o
ls
t
er
v
ec
to
r
s
.
A
co
n
ci
s
e
p
r
esen
t
atio
n
o
f
SVM
i
s
e
x
h
ib
ited
h
e
r
e
f
o
r
cu
l
m
i
n
atio
n
.
P
er
u
s
es
ar
e
allu
d
ed
to
th
e
i
n
s
t
r
u
ctio
n
al
e
x
er
cise
s
o
n
SVM
s
f
o
r
p
o
in
ts
o
f
in
ter
e
s
t.
T
h
e
SV
M
ca
n
b
e
co
n
s
id
er
ed
to
m
a
k
e
a
li
n
e
o
r
h
y
p
er
p
la
n
e
b
et
w
ee
n
t
w
o
ar
r
an
g
e
m
e
n
ts
o
f
in
f
o
r
m
atio
n
f
o
r
g
r
o
u
p
in
g
.
I
f
t
h
er
e
s
h
o
u
ld
ar
is
e
a
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
p
p
lica
tio
n
o
f A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
in
E
lectrica
l P
o
w
e
r
S
ystem
(
P
.
P
a
la
n
ich
a
my
)
79
o
cc
u
r
r
en
ce
o
f
t
w
o
-
d
i
m
e
n
s
io
n
a
l c
ir
cu
m
s
ta
n
ce
,
th
e
ac
ti
v
it
y
o
f
th
e
SVM
ca
n
b
e
clar
if
ied
e
f
f
e
cti
v
el
y
w
it
h
n
o
lo
s
s
o
f
s
i
m
p
l
if
icatio
n
.
I
n
F
ig
u
r
e
4
,
a
p
r
o
g
r
ess
io
n
o
f
f
o
c
u
s
es
f
o
r
t
w
o
d
is
ti
n
ct
cla
s
s
es
o
f
in
f
o
r
m
atio
n
ar
e
ap
p
ea
r
ed
,
cir
cles
(
class
A
n
)
a
n
d
s
q
u
ar
es
(
class
B
)
.
T
h
e
SVM
e
n
d
ea
v
o
r
s
to
p
u
t
a
d
ir
ec
t
li
m
i
t
(
s
tr
o
n
g
lin
e)
b
et
w
ee
n
t
h
e
t
w
o
u
n
iq
u
e
clas
s
es,
a
n
d
ar
r
an
g
e
it
s
u
c
h
t
h
at
t
h
e
ed
g
e
(
s
p
o
k
en
to
b
y
s
p
ec
k
ed
lin
e
s
)
is
a
u
g
m
en
ted
.
T
h
e
SVM
tr
ies
to
ar
r
an
g
e
th
e
li
m
i
t
w
ith
th
e
en
d
g
o
al
t
h
at
th
e
s
ep
ar
atio
n
b
et
w
ee
n
th
e
li
m
i
t
an
d
th
e
clo
s
est
in
f
o
r
m
a
tio
n
p
o
in
t
i
n
ea
c
h
cla
s
s
is
m
a
x
i
m
al.
T
h
e
l
i
m
it
i
s
t
h
e
n
p
u
t
a
m
id
s
t
th
is
ed
g
e
b
et
w
ee
n
t
h
e
t
w
o
f
o
cu
s
e
s
.
T
h
e
class
i
f
icatio
n
o
f
v
ec
to
r
m
ac
h
i
n
es i
s
s
h
o
w
n
i
n
f
i
g
u
r
e
2
.
Fig
u
r
e
2
.
C
lass
if
ica
tio
n
o
f
Ve
cto
r
Ma
ch
in
es
1
.
2
.
P
r
o
po
s
ed
Art
if
icia
l N
eura
l N
et
wo
rk
A
N
Ns
h
av
e
b
ee
n
p
r
o
d
u
ce
d
as
p
ar
allel
ap
p
r
o
p
r
iated
ar
r
an
g
e
m
o
d
el
s
i
n
l
i
g
h
t
o
f
o
r
g
a
n
i
c
lear
n
i
n
g
p
r
o
ce
d
u
r
e
o
f
th
e
h
u
m
a
n
ce
r
eb
r
u
m
.
T
h
er
e
ar
e
v
ar
io
u
s
u
s
e
s
o
f
A
NNs
i
n
i
n
f
o
r
m
atio
n
i
n
v
esti
g
atio
n
,
d
esig
n
ac
k
n
o
w
led
g
m
e
n
t
a
n
d
co
n
tr
o
l.
Am
o
n
g
v
ar
io
u
s
s
o
r
ts
o
f
A
N
Ns,
m
u
lt
ila
y
er
p
er
ce
p
tr
o
n
(
M
L
P
)
n
eu
r
al
s
y
s
te
m
s
ar
e
v
er
y
m
ai
n
s
tr
ea
m
an
d
u
t
ili
z
ed
f
o
r
th
e
p
r
esen
t
w
o
r
k
.
I
n
th
is
p
ap
er
,
th
e
ter
m
s
A
NN
a
n
d
ML
P
h
av
e
b
ee
n
u
tili
ze
d
r
ec
ip
r
o
ca
ll
y
w
it
h
o
u
t
d
if
f
er
e
n
t
s
o
r
ts
o
f
n
e
u
r
al
s
y
s
te
m
s
.
M
L
P
s
co
m
p
r
is
e
o
f
a
n
i
n
f
o
r
m
atio
n
la
y
er
o
f
s
o
u
r
ce
h
u
b
s
,
at
least
o
n
e
co
n
c
ea
led
lay
er
s
o
f
ca
lc
u
latio
n
h
u
b
s
o
r
"
n
eu
r
o
n
s
"
an
d
a
y
ield
la
y
er
.
T
h
e
q
u
an
tit
y
o
f
h
u
b
s
i
n
t
h
e
in
f
o
r
m
at
io
n
an
d
th
e
y
ie
ld
la
y
er
s
r
el
y
o
n
u
p
o
n
th
e
q
u
a
n
ti
t
y
o
f
i
n
f
o
r
m
atio
n
an
d
y
ie
ld
f
ac
to
r
s
s
ep
ar
atel
y
.
T
h
e
q
u
an
tit
y
o
f
s
h
r
o
u
d
ed
la
y
er
s
an
d
th
e
q
u
a
n
ti
t
y
o
f
h
u
b
s
i
n
ea
ch
co
n
ce
aled
la
y
er
in
f
l
u
en
ce
t
h
e
s
p
ec
u
latio
n
ca
p
ac
it
y
o
f
t
h
e
s
y
s
te
m
.
Fo
r
m
o
r
e
m
o
d
est
n
u
m
b
er
o
f
co
n
ce
aled
la
y
er
s
a
n
d
n
e
u
r
o
n
s
,
th
e
ex
ec
u
tio
n
m
a
y
n
o
t b
e
s
u
f
f
icie
n
t.
T
h
e
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
i
s
s
h
o
w
n
in
f
i
g
u
r
e
3
.
Fig
u
r
e
3
.
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
2.
SI
M
UL
AT
I
O
N
R
E
S
UL
T
S
T
ab
le
1
s
h
o
w
s
t
h
e
cla
s
s
i
f
ica
tio
n
r
es
u
lt
s
f
o
r
ea
ch
o
f
th
e
s
en
s
o
r
lo
ca
tio
n
s
u
s
i
n
g
th
e
f
i
r
s
t
9
i
n
p
u
t
f
ea
t
u
r
es
(
1
–
9
)
.
T
h
e
test
ac
h
iev
e
m
en
t
w
a
s
h
ig
h
er
w
i
th
SVM
s
in
all
ca
s
e
s
as
id
e
f
r
o
m
f
lag
3
w
h
er
e
b
o
th
w
er
e
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
9
,
No
.
1
,
J
an
u
ar
y
201
8
:
7
7
–
80
80
1
0
0
%.
Fo
r
b
o
th
class
if
ier
s
,
tes
t
ac
h
iev
e
m
e
n
t
w
as
u
n
s
u
itab
le
b
y
a
n
d
lar
g
e.
T
h
e
ca
lcu
latio
n
t
i
m
e
(
o
n
a
P
C
w
i
th
P
en
tiu
m
I
I
I
p
r
o
ce
s
s
o
r
o
f
5
3
3
MH
z
an
d
6
4
MB
R
A
M)
f
o
r
p
r
ep
ar
in
g
t
h
e
cla
s
s
i
f
ier
s
ar
e
ad
d
itio
n
all
y
ap
p
ea
r
ed
,
h
o
w
ev
er
i
m
m
ed
iate
ex
a
m
i
n
at
io
n
i
s
tr
o
u
b
leso
m
e
b
ec
a
u
s
e
o
f
co
n
tr
ast
in
co
d
e
p
r
o
d
u
ctiv
it
y
.
I
n
an
y
ca
s
e,
i
t
o
u
g
h
t
to
b
e
s
p
ec
if
ied
t
h
at
th
e
d
is
ti
n
ctio
n
in
ca
lcu
la
tio
n
ti
m
e
ca
u
g
h
t
b
e
i
m
p
er
ati
v
e
i
f
th
e
p
r
ep
ar
atio
n
is
d
o
n
e
d
is
co
n
n
ec
ted
.
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
D
if
f
e
r
en
t
Sen
s
o
r
L
o
ca
tio
n
D
a
t
a
se
t
I
n
p
u
t
f
e
a
t
u
r
e
s
S
t
r
a
i
g
h
t
A
N
N
S
t
r
a
i
g
h
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
T
e
st
su
c
c
e
ss %
T
r
a
i
n
i
n
g
t
i
me
(S)
T
e
st
su
c
c
e
ss %
T
r
a
i
n
i
n
g
t
i
me
(
s)
S
i
g
n
a
l
1
S
i
g
n
a
l
2
S
i
g
n
a
l
3
S
i
g
n
a
l
4
S
i
g
n
a
l
5
S
i
g
n
a
l
6
S
i
g
n
a
l
7
1
-
9
1
-
9
1
-
9
1
-
9
1
-
9
1
-
9
1
-
9
88
95
1
0
0
87
48
56
87
28
1
4
11
26
13
7
.
0
2
91
97
10
88
75
77
1
0
0
1
.
5
0
.
2
8
9
0
.
3
6
8
0
.
6
8
5
0
.
9
9
8
0
.
7
5
6
0
.
6
5
8
3.
CO
NCLU
SI
O
N
T
h
e
p
ar
ts
o
f
v
ar
io
u
s
v
ib
r
atio
n
s
ig
n
als,
g
o
tten
u
n
d
er
b
o
th
t
y
p
ical
an
d
lig
h
t
lo
ad
s
an
d
at
lo
w
a
n
d
h
i
g
h
test
i
n
g
r
ates,
h
a
v
e
b
ee
n
r
esear
ch
ed
.
T
h
e
ar
r
an
g
e
m
e
n
t
e
x
ac
t
n
ess
o
f
SVMs
w
as
s
u
p
er
io
r
to
o
f
A
NN
s
,
w
i
th
o
u
t
GA
.
W
it
h
G
A
-
b
ased
ch
o
ice,
t
h
e
ex
h
ib
itio
n
s
o
f
b
o
th
cla
s
s
i
f
i
er
s
w
er
e
s
i
m
i
lar
at
ab
o
u
t
1
0
0
%,
ev
en
w
it
h
v
ar
io
u
s
lo
ad
co
n
d
itio
n
s
an
d
i
n
s
p
ec
ti
n
g
r
ates,
u
tili
zi
n
g
j
u
s
t
t
h
r
ee
co
m
p
o
n
en
ts
.
Fo
r
SVM
s
w
it
h
s
i
x
co
m
p
o
n
e
n
t
s
,
1
0
0
%
ar
r
an
g
e
m
en
t
ac
h
ie
v
e
m
en
t
w
as
ac
co
m
p
lis
h
ed
in
al
l
ex
p
er
i
m
e
n
ts
e
v
e
n
w
it
h
a
co
ar
s
e
r
an
g
e
a
n
d
s
tep
s
i
ze
o
f
t
h
e
class
i
f
ier
p
ar
a
m
eter
.
RE
F
E
R
E
NC
E
S
[1
]
Ka
lo
g
iro
u
S
A
.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
in
re
n
e
w
a
b
le
e
n
e
rg
y
s
y
ste
m
s
a
p
p
li
c
a
ti
o
n
s:
a
re
v
ie
w
.
Ren
e
wa
b
le
a
n
d
su
sta
in
a
b
le en
e
rg
y
re
v
iews
.
2
0
0
1
;
5
.
(
4
);
3
7
3
-
4
0
1
.
[2
]
Ka
lo
g
iro
u
,
S
A
.
A
p
p
li
c
a
ti
o
n
s
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
s
in
e
n
e
rg
y
s
y
ste
m
s.
En
e
rg
y
Co
n
v
e
rs
io
n
a
n
d
M
a
n
a
g
e
me
n
t
.
1
9
9
9
;
4
0
.
(1
0
);
1
0
7
3
-
1
0
8
7
.
[3
]
Hs
u
Y
Y,
a
n
d
C
h
e
n
C
R.
T
u
n
i
n
g
o
f
p
o
w
e
r
sy
ste
m
sta
b
il
ize
rs
u
sin
g
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
.
IE
EE
tra
n
sa
c
ti
o
n
s
o
n
e
n
e
rg
y
c
o
n
v
e
rs
io
n
.
1
9
9
1
;
6
.
(4
)
;
6
1
2
-
6
1
9
.
[4
]
Ch
e
m
si
M
,
A
g
b
o
ss
o
u
K
a
n
d
Ca
r
d
e
n
a
s
A
.
Ne
u
ra
l
n
e
tw
o
rk
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
lg
o
rit
h
m
c
o
n
tr
o
l
f
o
r
P
EM
f
u
e
l
c
e
ll
i
n
re
sid
e
n
ti
a
l
a
p
p
li
c
a
ti
o
n
s.
In
El
e
c
tri
c
a
l
Po
we
r
a
n
d
En
e
rg
y
C
o
n
fer
e
n
c
e
(
EP
EC).
2
0
1
6
;
1
-
6.
[5
]
Id
ris
N H.
S
a
li
m
N
A
,
M
u
h
a
m
a
d
A
F
,
M
a
h
m
u
d
M
N,
Ya
sin
Z
M
a
n
d
A
b
W
a
h
a
b
N.
A
p
p
li
c
a
ti
o
n
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
s
to
th
e
Id
e
n
ti
f
ica
ti
o
n
o
f
P
o
w
e
r
S
y
ste
m
S
tab
il
it
y
d
u
e
to
T
r
a
n
sm
is
sio
n
L
in
e
Ou
tag
e
s.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
imu
l
a
ti
o
n
S
y
ste
ms
,
S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
.
2
0
1
6
;
1
7
.
(
4
1
)
.
[6
]
Ib
ra
h
im
M
,
Je
m
e
i
S
,
W
i
m
m
e
r
G
,
a
n
d
Hiss
e
l
D.
No
n
l
in
e
a
r
a
u
to
re
g
r
e
ss
iv
e
n
e
u
ra
l
n
e
tw
o
rk
in
a
n
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
stra
teg
y
f
o
r
b
a
tt
e
r
y
/u
lt
ra
-
c
a
p
a
c
it
o
r
h
y
b
rid
e
lec
tri
c
a
l
v
e
h
icle
s.
El
e
c
tric P
o
we
r S
y
ste
ms
Res
e
a
rc
h
2
0
1
6
;
1
3
6
;
2
6
2
-
2
6
9
.
[7
]
G
o
h
,
H.
H.,
A
id
a
,
A
.
,
Lee
,
S
.
S
.
,
S
im
,
S
.
Y.,
&
G
o
h
,
K.
C.
(2
0
1
7
).
P
re
d
ictiv
e
Dir
e
c
t
P
o
w
e
r
Co
n
tro
l
(
P
D
P
C)
o
f
G
rid
-
Co
n
n
e
c
ted
Du
a
l
-
A
c
ti
v
e
Bri
d
g
e
M
u
lt
il
e
v
e
l
In
v
e
rter
(D
A
BM
I).
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Po
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
(
IJ
PE
DS
)
,
8
(4
)
.
[8
]
Ch
a
u
d
h
a
ri,
J.
G
.
,
Bo
d
k
h
e
,
S
.
B
.
,
&
Aw
a
re
,
M
.
V
.
(
2
0
1
7
).
P
ro
p
o
r
ti
o
n
a
l
I
n
teg
ra
l
Esti
m
a
to
r
o
f
th
e
S
tato
r
Re
sista
n
c
e
f
o
r
Dire
c
t
T
o
rq
u
e
Co
n
tro
l
In
d
u
c
t
io
n
M
o
to
r
Driv
e
.
In
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
)
.
[9
]
A
z
iri
,
H.,
P
a
tak
o
r,
F
.
A
.
,
S
u
laim
a
n
,
M
.
,
&
S
a
ll
e
h
,
Z.
(2
0
1
7
).
Co
m
p
a
riso
n
P
e
rf
o
rm
a
n
c
e
s
o
f
In
d
irec
t
F
ield
Orie
n
ted
Co
n
tr
o
l
f
o
r
T
h
re
e
-
P
h
a
se
In
d
u
c
ti
o
n
M
o
t
o
r
Driv
e
s.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Po
we
r
El
e
c
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
(
IJ
PE
DS
)
,
8
(4
)
.
[1
0
]
S
u
n
d
a
ra
m
,
A
.
,
&
Ra
m
e
sh
,
G
.
P
.
S
e
n
so
r
les
s
Co
n
tro
l
o
f
BLDC
M
o
to
r
u
si
n
g
F
u
z
z
y
lo
g
ic
c
o
n
tro
ll
e
r
f
o
r
S
o
lar
p
o
w
e
r
G
e
n
e
r
a
ti
o
n
.
I
n
ter
n
a
ti
o
n
a
l
jo
u
rn
a
l
o
f
M
C
sq
u
a
re
sc
ien
ti
fi
c
re
se
a
rc
h
(
IJ
M
S
R)
,
9
(2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.