I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
,
p
p
.
3
4
3
~3
5
0
I
SS
N:
2252
-
8814
343
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AAS
Fault Iden
tif
i
ca
ti
o
n in Sub
-
s
tatio
n
b
y
Using
Neuro
-
F
uzz
y
Techniqu
e
Anirud
h Ya
da
v
1
,
Vina
y
K
um
a
r
H
a
rit
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
S
.
H.I.
A
.
T
.
S
,
A
ll
a
h
a
b
a
d
,
U.
P
.
,
I
n
d
ia
2
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
De
lh
i
T
e
c
h
n
ica
l
Un
iv
e
rsity
,
Ne
w
De
lh
i
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
6
,
2
0
1
7
R
ev
i
s
ed
No
v
1
7
,
2
0
1
7
A
cc
ep
ted
No
v
2
2
,
2
0
1
7
F
a
u
lt
i
d
e
n
ti
f
ica
ti
o
n
a
n
d
it
s
d
iag
n
o
sis
is
a
n
im
p
o
rtan
t
issu
e
in
p
re
se
n
t
sc
e
n
a
rio
o
f
p
o
w
e
r
s
y
ste
m
,
a
s
h
u
g
e
a
m
o
u
n
t
o
f
e
lec
tri
c
p
o
w
e
r
is
u
ti
li
z
e
d
.
Ra
n
d
o
m
t
y
p
e
s
o
f
f
a
u
lt
s
o
c
c
u
r
in
su
b
sta
ti
o
n
,
w
h
ich
lea
d
s
to
irreg
u
lar
a
n
d
d
isc
o
n
ti
n
u
e
su
p
p
ly
o
f
p
o
w
e
r
f
ro
m
g
e
n
e
ra
ti
n
g
to
c
o
n
su
m
e
r
p
o
in
t
.
F
a
u
lt
d
e
tec
ti
o
n
is
a
n
im
p
o
rtan
t
c
o
n
c
e
p
t
o
f
p
o
w
e
r
s
y
ste
m
w
h
ich
is
to
b
e
stu
d
ied
a
n
d
n
e
w
m
e
th
o
d
h
a
s
to
d
e
v
e
lo
p
f
o
r
f
a
u
lt
d
e
tec
ti
o
n
a
n
d
r
e
m
o
v
a
l
o
f
it
.
T
h
is
p
a
p
e
r
p
ro
p
o
s
e
d
o
n
-
l
in
e
f
a
u
lt
d
e
tec
ti
o
n
a
n
d
i
d
e
n
ti
f
ica
ti
o
n
o
f
f
a
u
lt
-
ty
p
e
b
y
u
sin
g
Ne
u
ro
-
F
u
z
z
y
m
e
th
o
d
in
su
b
sta
ti
o
n
.
Co
m
b
in
a
ti
o
n
o
f
Artif
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
(
A
NN
)
a
n
d
F
u
z
z
y
L
o
g
ic
(F
L
)
,
re
su
lt
s
in
g
a
in
in
g
le
a
rn
in
g
c
a
p
a
b
il
it
ies
o
f
f
u
z
z
y
lo
g
ic
.
V
a
riatio
n
o
f
c
u
rre
n
t
a
c
c
o
rd
i
n
g
to
f
a
u
lt
is
u
se
d
f
o
r
i
d
e
n
ti
f
ica
ti
o
n
.
F
u
z
z
y
c
o
n
tr
o
ll
e
r
d
isp
lay
o
u
tp
u
t
c
o
n
d
it
i
o
n
in
f
o
rm
o
f
(0
,
1
).
He
re
,
sin
g
le
li
n
e
-
to
g
ro
u
n
d
(L
G
)
f
a
u
lt
,
li
n
e
-
to
-
l
in
e
(L
L
)
fa
u
lt
,
d
o
u
b
le
li
n
e
-
to
g
r
o
u
n
d
(L
LG
)/L
LL
f
a
u
lt
a
re
c
o
n
sid
e
re
d
.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN)
Fu
zz
y
l
o
g
ic
(
F
L
)
Gr
ap
h
ical
u
s
er
i
n
ter
f
ac
e
(
GUI
)
Su
b
s
tat
io
n
Co
p
y
rig
h
t
©
201
7
In
s
t
it
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
:
An
ir
u
d
h
Yad
av
,
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
S
.
H.I.
A
.
T
.
S
,
A
ll
a
h
a
b
a
d
,
U.
P
.
,
In
d
ia.
E
m
ail:
id
-
e
r.
a
n
iru
d
h
5
3
@g
m
a
il
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Du
e
to
p
r
ese
n
t
d
ev
elo
p
m
e
n
t
i
n
all
-
ar
o
u
n
d
w
o
r
ld
,
co
n
s
u
m
p
t
io
n
a
n
d
d
e
m
a
n
d
o
f
th
e
elec
tr
i
c
p
o
w
er
i
s
in
cr
ea
s
ed
to
lar
g
e
e
x
te
n
d
.
T
h
is
d
e
m
a
n
d
h
a
s
to
m
ee
t
w
it
h
t
h
e
le
v
el
o
f
q
u
alit
y
an
d
w
i
th
o
u
t
i
n
ter
r
u
p
tio
n
s
.
A
p
o
w
er
d
is
tr
ib
u
t
io
n
i
s
a
co
m
p
l
ex
p
r
o
ce
s
s
w
h
ic
h
i
n
v
o
lv
e
s
h
u
g
e
g
en
er
ati
n
g
p
la
n
ts
,
lar
g
e
le
n
g
th
o
f
tr
an
s
m
is
s
io
n
lin
e
a
n
d
d
if
f
er
e
n
t le
v
el
o
f
s
u
b
s
tatio
n
s
.
I
n
t
h
i
s
w
h
o
le
p
r
o
ce
s
s
o
f
elec
tr
ic
p
o
w
er
tr
an
s
f
er
,
v
o
lt
ag
e
is
s
tep
-
u
p
/s
tep
-
d
o
w
n
at
d
if
f
er
en
t
lev
el
as
p
er
r
eq
u
ir
e
m
en
t.
Fo
r
ex
a
m
p
le,
elec
tr
ic
p
o
w
er
is
n
o
r
m
all
y
g
e
n
er
ated
in
r
an
g
e
o
f
1
1
-
2
5
KV
in
p
o
w
er
s
tatio
n
.
T
h
en
it is
s
tep
-
u
p
to
HV/E
HV/U
HV
lev
els (
3
3
/6
6
KV)
f
o
r
tr
an
s
m
itt
in
g
p
o
w
er
th
r
o
u
g
h
tr
an
s
m
is
s
io
n
l
in
e
f
o
r
lo
n
g
d
is
tan
ce
.
T
h
ese
li
n
es
ar
e
ter
m
i
n
ati
n
g
i
n
to
s
u
b
s
tatio
n
at
t
h
e
v
o
lta
g
e
lev
e
l
o
f
2
2
KV/1
1
KV/6
.
6
KV
etc
f
o
r
p
o
w
er
d
i
s
tr
ib
u
tio
n
to
lo
ad
p
o
in
ts
th
r
o
u
g
h
a
d
is
tr
ib
u
tio
n
n
et
wo
r
k
o
f
lin
es.
A
t
lo
ad
p
o
in
t
(
lo
ca
liti
es,
i
n
d
u
s
tr
ial
ar
ea
,
v
illa
g
e
etc.
)
,
a
tr
an
s
f
o
r
m
er
f
u
r
t
h
er
r
e
d
u
ce
s
th
e
v
o
lta
g
e
lev
el
to
4
1
5
V
to
p
r
o
v
id
e
th
e
s
u
p
p
l
y
to
lo
w
te
n
s
io
n
(
L
T
)
f
ee
d
er
s
to
in
d
iv
id
u
als
co
n
s
u
m
er
,
eit
h
er
at
2
4
0
V
(
f
o
r
s
in
g
le
p
h
a
s
e
s
u
p
p
l
y
)
o
r
4
1
5
V
(
f
o
r
t
h
r
ee
-
p
h
ase
s
u
p
p
le)
.
An
o
v
er
h
ea
d
li
n
e
o
r
an
u
n
d
er
g
r
o
u
n
d
ca
b
le
is
u
s
ed
i
n
f
ee
d
er
.
Dep
en
d
in
g
u
p
o
n
d
e
n
s
it
y
o
f
c
o
n
s
u
m
er
s
,
le
n
g
t
h
o
f
1
1
KV
f
e
ed
er
is
g
en
er
all
y
u
p
to
3
k
m
in
u
r
b
an
ar
ea
w
h
ile
len
g
th
is
m
u
ch
lar
g
er
(
u
p
to
2
0
-
3
0
k
m
)
in
r
u
r
al
ar
ea
s
.
T
h
u
s
,
it
is
n
ec
ess
ar
y
to
h
a
v
e
f
a
u
lt
h
an
d
lin
g
s
y
s
te
m
f
o
r
co
n
tin
u
o
u
s
an
d
r
eliab
le
elec
tr
i
c
p
o
w
er
s
u
p
p
l
y
.
I
n
teg
r
ati
n
g
o
f
A
r
ti
f
icia
l
n
eu
r
o
n
Net
w
o
r
k
(
A
N
N)
an
d
f
u
zz
y
l
o
g
ic
(
FL
)
,
ca
lled
Neu
r
o
-
f
u
zz
y
n
et
w
o
r
k
s
.
I
n
t
h
is
n
et
w
o
r
k
,
o
u
tp
u
t
o
r
w
ei
g
h
t
o
f
A
NN
s
er
v
e
s
a
s
f
u
zz
y
s
ets
a
n
d
it
h
a
v
e
n
eu
r
o
n
t
h
at
ca
l
led
f
u
zz
y
n
e
u
r
o
n
s
.
Var
iatio
n
o
f
c
u
r
r
en
t,
ac
co
r
d
in
g
to
f
a
u
lt
is
u
s
ed
f
o
r
id
en
ti
f
ica
tio
n
.
Fu
zz
y
co
n
tr
o
ller
d
is
p
la
y
o
u
tp
u
t
co
n
d
itio
n
i
n
f
o
r
m
o
f
(
0
,
1
)
i.e
.
0
f
o
r
n
o
r
m
al
co
n
d
itio
n
an
d
1
f
o
r
f
a
u
lt c
o
n
d
itio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
:
3
4
3
–
3
5
0
344
2.
SUB
ST
A
T
I
O
N
A
s
u
p
p
le
m
e
n
tar
y
s
ta
tio
n
f
o
r
elec
tr
icit
y
g
en
er
at
io
n
,
tr
a
n
s
m
is
s
io
n
an
d
d
is
tr
ib
u
t
io
n
s
y
s
t
e
m
w
h
er
e
v
o
ltag
e
lev
el
is
s
tep
-
u
p
/s
tep
-
d
o
w
n
w
it
h
t
h
e
h
elp
o
f
tr
an
s
f
o
r
m
er
.
Dep
en
d
i
n
g
u
p
o
n
v
o
lta
g
e,
th
eir
ap
p
licatio
n
in
p
o
w
er
s
y
s
te
m
a
n
d
m
eth
o
d
u
s
ed
to
b
u
ild
th
e
m
,
th
e
s
e
s
u
b
s
ta
tio
n
ar
e
cla
s
s
i
f
ied
i
n
v
ar
io
u
s
t
y
p
e
s
li
k
e
tr
an
s
m
is
s
io
n
s
u
b
s
tatio
n
s
,
d
is
tr
ib
u
tio
n
s
u
b
s
ta
tio
n
,
C
o
n
v
er
ter
s
u
b
s
ta
tio
n
,
s
w
i
tch
i
n
g
s
u
b
s
tatio
n
s
etc.
So
m
e
o
f
t
h
e
ele
m
e
n
ts
o
f
s
u
b
s
tatio
n
ar
e
s
h
o
w
n
i
n
F
i
g
u
r
e
2
(
a)
.
CB
CB
CB
CB
CB
CB
CB
CB
CB
F
E
E
D
E
R
1
F
E
E
D
E
R
2
Fig
u
r
e
2
(
a)
.
L
ay
o
u
t o
f
S
u
b
s
t
atio
n
Su
b
s
tat
io
n
s
co
n
s
i
s
t
o
f
s
w
itc
h
i
n
g
an
d
p
r
o
tectio
n
s
y
s
te
m
,
tr
an
s
f
o
r
m
er
s
,
r
ela
y
s
,
cir
cu
i
t
b
r
ea
k
er
s
f
ee
d
er
s
f
o
r
s
u
p
p
l
y
e
lectr
ic
p
o
w
er
to
s
m
all
ar
ea
.
T
h
e
y
m
a
y
b
e
o
n
t
h
e
s
u
r
f
ac
e
i
n
f
e
n
ce
d
en
clo
s
u
r
es,
u
n
d
er
g
r
o
u
n
d
o
r
lo
ca
ted
in
s
p
ec
ial
-
p
u
r
p
o
s
e
b
u
il
d
in
g
.
Feed
er
o
f
S
u
b
s
ta
tio
n
i
t
i
s
u
n
ec
o
n
o
m
ical
an
d
n
o
n
-
r
eliab
le
to
co
n
n
ec
t
t
h
e
co
n
s
u
m
er
s
to
th
e
h
ig
h
-
v
o
ltag
e
tr
a
n
s
m
i
s
s
io
n
l
in
e
n
et
w
o
r
k
d
ir
ec
tl
y
,
i
f
t
h
e
y
n
o
t
r
eq
u
ir
e
h
u
g
e
a
m
o
u
n
t
s
o
f
p
o
w
er
.
So
,
th
e
d
is
tr
ib
u
tio
n
su
b
s
ta
tio
n
r
ed
u
ce
s
v
o
lta
g
e
le
v
el
to
a
s
u
i
tab
le
f
o
r
lo
ca
l
co
n
s
u
m
er
s
li
k
e
s
m
all
in
d
u
s
tr
ies,
h
o
u
s
es
etc
w
h
ic
h
f
ed
b
y
u
s
i
n
g
f
ee
d
er
s
.
T
h
e
f
ee
d
er
s
o
f
s
u
b
s
tatio
n
ar
e
s
h
o
r
t in
le
n
g
t
h
.
3.
F
AULT
A
b
n
o
r
m
al
co
n
d
itio
n
s
o
cc
u
r
wh
ile
tr
an
s
m
itti
n
g
p
o
w
er
is
ca
ll
ed
elec
tr
ical
f
au
lt
s
.
T
h
ey
ar
e
c
ateg
o
r
ized
in
to
S
y
m
m
etr
ical
f
a
u
lt
s
an
d
Un
s
y
m
m
e
tr
ical
f
a
u
lts
.
Ag
ain
,
U
n
s
y
m
m
e
tr
ical
f
a
u
lts
ar
e
class
i
f
ied
as
Sin
g
le
li
n
e
-
to
g
r
o
u
n
d
(
L
G)
f
a
u
lt,
li
n
e
-
to
-
l
in
e
(
L
G)
f
au
l
t
an
d
d
o
u
b
le
lin
e
/LL
L
–
g
r
o
u
n
d
f
au
l
t.
O
u
t
o
f
all
f
a
u
lts
,
L
G
f
au
lt
i
s
m
o
s
t se
v
er
e.
A
cc
o
r
d
in
g
to
f
a
u
lts
,
v
ar
io
u
s
w
av
e
f
o
r
m
s
s
h
o
w
in
g
v
ar
iatio
n
o
f
cu
r
r
e
n
t a
r
e:
F
ig
u
r
e
3
.
(
a)
W
av
ef
o
r
m
o
f
C
u
r
r
en
t a
t N
o
-
f
a
u
lt
C
o
n
d
itio
n
Fig
u
r
e
3
(
b
)
.
W
av
ef
o
r
m
o
f
C
u
r
r
en
t a
t
L
G
Fa
u
lt
C
o
n
d
itio
n
Fig
u
r
e
3
(
c)
.
W
av
ef
o
r
m
o
f
C
u
r
r
en
t a
t
L
L
Fa
u
lt
C
o
n
d
itio
n
Fig
u
r
e
3
(
d
)
.
W
av
ef
o
r
m
o
f
c
u
r
r
en
t
at
L
L
L
f
au
lt
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
F
a
u
lt I
d
e
n
tifi
ca
tio
n
in
S
u
b
-
S
ta
tio
n
b
y
Usi
n
g
n
e
u
r
o
-
F
u
z
z
y
Tech
n
iq
u
e
…
(
A
n
r
u
d
h
Ya
d
a
v
)
345
4.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
(
ANN)
An
ar
tif
ic
ial
n
e
u
r
o
n
n
et
w
o
r
k
w
h
ic
h
d
ep
en
d
o
n
r
elatio
n
s
h
ip
b
et
w
ee
n
p
ast,
p
r
esen
t
an
d
f
u
tu
r
e
co
n
d
itio
n
h
eld
i
n
a
n
y
s
y
s
te
m
.
T
h
ese
n
et
w
o
r
k
s
co
n
s
i
s
t
o
f
i
n
p
u
t
n
o
d
es
o
r
i
n
p
u
t
la
y
er
i
f
n
e
u
r
o
n
s
,
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
er
o
f
n
eu
r
o
n
s
,
an
d
f
in
al
la
y
er
o
f
o
u
tp
u
t
n
e
u
r
o
n
s
.
Nu
m
er
ical
v
al
u
e
w
h
ich
i
s
ass
o
ciate
d
to
ea
ch
co
n
n
ec
tio
n
is
ca
lled
w
ei
g
h
t.
T
h
is
n
et
w
o
r
k
i
s
co
m
p
o
s
ed
o
f
s
i
m
p
le
ele
m
e
n
t o
p
er
atin
g
in
p
ar
allel.
So
m
e
f
ac
to
r
w
h
ich
g
i
v
e
ad
v
a
n
tag
e
to
ANN:
a.
T
h
ese
n
et
w
o
r
k
s
ar
e
n
o
n
-
lin
ea
r
w
h
ic
h
m
a
k
e
ab
le
to
class
i
f
y
b
et
w
ee
n
d
if
f
er
e
n
t p
atter
n
s
.
b.
T
h
ese
ar
e
ad
ap
tiv
e,
ca
n
tak
e
d
ata
an
d
lear
n
f
r
o
m
it.
c.
T
h
ey
ca
n
b
e
ea
s
il
y
g
e
n
er
alize
d
d.
A
N
N
is
a
p
ar
allel
d
is
tr
ib
u
ted
i
n
f
o
r
m
atio
n
p
r
o
ce
s
s
i
n
g
n
et
w
o
r
k
.
4
.
1
Art
if
icia
l N
euro
n M
o
del
Her
e,
p
r
o
ce
s
s
in
g
n
e
u
r
o
n
co
m
p
u
tes
t
h
e
w
ei
g
h
ted
s
u
m
o
f
it
s
in
p
u
t
s
a
n
d
o
u
tp
u
t
ac
co
r
d
in
g
to
w
h
et
h
er
th
is
w
e
ig
h
ted
s
u
m
i
s
ab
o
v
e
o
r
b
elo
w
a
ce
r
tain
t
h
r
es
h
o
ld
.
T
h
i
s
m
o
d
el
is
g
o
v
er
n
ed
b
y
E
q
u
ati
o
n
:
y
k
=
f
(
u
k
−
θ
k
)
…….
(
i)
whe
r
e
u
k
=
∑
w
kj
x
j
…….
.
(
ii)
x
1
,
,
x
2,
x
3,
……….
x
p
–
I
n
p
u
t
s
ig
n
al
w
k1
,w
k2
,
…….
w
kp
–
W
eig
h
t o
f
n
e
u
r
o
n
k
u
k
-
li
n
ea
r
l
y
co
m
b
i
n
ed
o
u
tp
u
t
4
.
2
L
ea
rning
in ANN
Dif
f
er
en
t
lear
n
in
g
p
r
o
ce
s
s
ar
e
u
s
ed
w
h
ich
d
ep
en
d
u
p
o
n
c
o
m
p
atib
il
it
y
to
d
i
f
f
er
en
t
tas
k
.
A
n
eu
r
al
n
et
w
o
r
k
u
s
es e
i
th
er
s
u
p
er
v
i
s
e
d
o
r
u
n
s
u
p
er
v
i
s
ed
lear
n
i
n
g
.
4
.
2
.
1
Su
perv
is
ed
lea
rn
ing
I
n
s
u
p
er
v
i
s
ed
lear
n
in
g
,
th
e
n
et
w
o
r
k
w
h
ic
h
is
p
r
o
v
id
ed
w
i
th
ex
a
m
p
le
a
n
d
d
esire
d
o
u
tp
u
t
is
o
b
tain
ed
.
T
h
en
n
et
w
o
r
k
w
ei
g
h
t is
m
o
d
if
ied
to
m
i
n
i
m
ize
t
h
e
d
if
f
er
en
ce
b
et
w
ee
n
n
et
w
o
r
k
o
u
tp
u
t a
n
d
d
esire
d
o
u
tp
u
t.
4
.
2
.
2
Uns
u
perv
is
ed
lea
rni
ng
An
in
p
u
t
s
i
g
n
a
l
is
o
n
l
y
g
i
v
en
in
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
,
an
d
th
e
n
et
w
o
r
k
w
eig
h
t
is
c
h
an
g
e
th
r
o
u
g
h
p
r
ed
ef
in
ed
alg
o
r
ith
m
,
w
h
ich
u
s
u
a
l
l
y
g
r
o
u
p
s
t
h
e
d
ata
in
t
o
b
u
n
d
le
o
f
s
a
m
e
i
n
f
o
r
m
ati
o
n
.
A
f
ee
d
f
o
r
w
ar
d
n
et
w
o
r
k
i
s
m
o
s
t
co
m
m
o
n
n
et
w
o
r
k
u
s
ed
f
o
r
s
u
p
er
v
i
s
ed
lear
n
in
g
.
Mu
lti
-
la
y
er
P
er
ce
p
tio
n
(
ML
P
)
n
et
w
o
r
k
i
s
m
o
s
t
p
o
p
u
lar
o
f
all
n
e
u
r
o
n
n
e
t
w
o
r
k
.
M
L
P
is
m
o
s
t
p
o
p
u
lar
n
eu
r
al
n
et
w
o
r
k
t
y
p
e
w
h
ic
h
is
u
s
e
d
an
d
g
e
n
er
all
y
s
h
o
r
t
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
m
o
d
el
ar
e
b
ased
o
n
it.
A
p
er
ce
p
tr
o
n
is
th
e
b
asic
n
e
u
r
o
n
(
u
n
it)
o
f
th
e
n
et
w
o
r
k
.
T
h
e
ML
P
n
e
t
w
o
r
k
co
n
s
is
ts
o
f
s
ev
er
al
la
y
er
s
o
f
n
e
u
r
o
n
s
.
E
ac
h
n
eu
r
o
n
i
n
a
p
ar
tic
u
lar
la
y
er
is
co
n
n
ec
ted
to
ea
c
h
n
eu
r
o
n
o
f
o
th
er
la
y
er
.
Feed
b
ac
k
co
n
n
ec
tio
n
s
ar
e
ab
s
en
t
.
4
.
3
Arc
hite
ct
ure
o
f
ANN
m
o
de
l
Fig
u
r
e
4
(
a)
.
A
r
ch
itect
u
r
e
o
f
ANN
Mo
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
:
3
4
3
–
3
5
0
346
4
.
4
ANN
in M
AT
L
AB
A
n
e
u
r
al
n
et
w
o
r
k
ca
n
tr
ai
n
ed
to
p
er
f
o
r
m
a
p
ar
ticu
lar
f
u
n
ctio
n
b
y
ad
j
u
s
tin
g
t
h
e
v
al
u
es
o
f
t
h
e
w
e
ig
h
ts
b
et
w
ee
n
ele
m
en
t
s
.
T
h
e
tr
ain
i
n
g
o
f
ANN
i
n
M
A
T
L
A
B
is
d
o
n
e
b
y
u
s
i
n
g
g
r
ap
h
ical
to
o
ls
to
s
o
lv
e
p
r
o
b
le
m
s
i
n
f
u
n
ctio
n
f
i
tti
n
g
,
p
atter
n
r
ec
o
g
n
itio
n
a
n
d
clu
s
ter
in
g
.
Gr
ap
h
ic
al
User
I
n
ter
f
ac
e
(
GUI
)
is
d
es
ig
n
ed
to
b
e
s
i
m
p
l
e
an
d
u
s
er
f
r
ien
d
l
y
.
GUI
ar
e
u
s
e
f
o
r
cr
ea
tin
g
f
u
n
ctio
n
in
ANN.
T
h
e
f
o
llo
w
i
n
g
f
u
n
ct
io
n
s
ar
e:
a.
n
cto
o
l
-
Ne
u
r
al
n
et
w
o
r
k
clas
s
if
i
ca
tio
n
to
o
l
b.
n
f
to
o
l
-
Op
en
Ne
u
r
al
Net
w
o
r
k
f
itti
n
g
to
o
l
c.
n
n
to
o
l
-
Op
en
Net
w
o
r
k
/Data
M
an
ag
er
d.
n
n
tr
ai
n
to
o
l
-
Ne
u
r
al
Net
w
o
r
k
t
r
ain
in
g
to
o
l
e.
n
p
r
to
o
l
-
Net
w
o
r
k
p
atter
n
r
ec
o
g
n
itio
n
to
o
l
f.
v
ie
w
-
Vie
w
a
n
eu
r
al
n
et
w
o
r
k
I
n
all
f
u
n
c
tio
n
,
”
n
f
to
o
l”
f
u
n
ctio
n
is
u
s
ed
to
cr
ea
te
th
e
A
NN
m
o
d
el.
5.
F
U
Z
Z
Y
L
O
G
I
C
I
n
1
9
6
0
,
L
o
tf
i
A
.
Z
ed
e
n
d
ev
e
l
o
p
s
a
m
at
h
e
m
atica
l
r
u
le
a
n
d
f
u
n
ct
io
n
s
f
o
r
p
r
o
v
id
in
g
n
at
u
r
al
lan
g
u
a
g
e
q
u
er
ies,
ca
lled
f
u
zz
y
lo
g
ic.
I
t
is
s
et
o
f
co
n
v
en
tio
n
al
o
r
B
o
o
lean
lo
g
ic.
I
t
p
r
o
v
id
e
a
m
eth
o
d
o
f
ca
lcu
late
in
ter
m
ed
iate
v
a
lu
e
s
b
et
w
ee
n
a
b
s
o
lu
te
tr
u
e
a
n
d
ab
s
o
lu
te
f
a
ls
e
co
n
d
itio
n
w
it
h
in
r
an
g
e
o
f
0
.
0
-
1
.
0
.
I
t
is
p
o
s
s
ib
le
to
ca
lcu
late
th
e
d
e
g
r
ee
to
w
h
ic
h
an
ite
m
i
s
a
m
e
m
b
er
b
y
f
u
zz
y
lo
g
ic.
T
h
ey
p
r
o
v
id
e
p
o
w
er
f
u
l
m
a
th
e
m
atica
l
to
o
ls
w
h
ic
h
h
elp
i
n
m
o
d
elin
g
a
n
d
co
n
tr
o
llin
g
n
u
n
ce
r
tain
s
y
s
te
m
i
n
d
i
f
f
er
e
n
t
f
ield
s
.
F
u
z
z
y
s
e
ts
ar
e
f
ac
i
litato
r
s
i
n
g
i
v
i
n
g
ap
p
r
o
x
i
m
a
te
r
ea
s
o
n
i
n
d
ec
is
i
o
n
-
m
a
k
in
g
w
it
h
o
u
t
co
m
p
lete
a
n
d
p
r
ec
is
e
d
ata.
T
h
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
o
f
f
u
zz
y
an
d
B
o
o
lean
s
et
s
is
d
if
f
er
e
n
t
f
r
o
m
ea
c
h
ot
h
er
.
I
t a
ls
o
allo
w
s
g
i
v
in
g
w
i
d
e
r
an
g
e
o
f
ap
p
licatio
n
i
n
d
if
f
er
en
t f
ield
s
.
5
.
1
.
F
uzzy
Set
s
A
s
e
t
in
w
h
ic
h
w
h
o
le
ele
m
e
n
t
s
h
a
v
e
d
eg
r
ee
o
f
m
e
m
b
er
s
h
ip
,
is
a
f
u
zz
y
s
ets
i.e
.
an
ele
m
e
n
t
o
f
s
et
ca
b
b
e
f
u
ll
m
e
m
b
er
o
r
a
p
ar
tial
m
e
m
b
er
.
Fo
llo
w
i
n
g
m
et
h
o
d
is
u
s
ed
to
d
ef
in
e
a
cr
is
p
s
et:
-
a.
A
s
u
b
s
et
U
o
f
a
s
e
t
S
i
s
a
m
ap
p
in
g
f
r
o
m
ele
m
e
n
ts
o
f
S
to
t
h
e
s
et
{0
,
1
}.
T
h
is
is
r
ep
r
esen
ted
b
y
U
: S>
{0
,
1
}.
b.
A
m
ap
p
in
g
i
s
r
ep
r
esen
ted
b
y
o
n
e
o
r
d
er
ed
p
air
f
o
r
ea
ch
elem
en
t
S
w
h
er
e
t
h
e
f
ir
s
t
ele
m
e
n
t
is
f
r
o
m
t
h
e
s
et
S
an
d
th
e
s
ec
o
n
d
ele
m
e
n
t
f
r
o
m
s
et
{0
,
1
}.
T
h
e
v
alu
e
ze
r
o
r
ep
r
esen
ts
n
o
n
-
m
e
m
b
er
s
h
i
p
an
d
v
alu
e
1
r
ep
r
esen
t
m
e
m
b
er
s
h
ip
.
5
.
2
.
M
e
m
ber
s
hi
p f
un
ct
io
n
A
m
at
h
e
m
atica
l
f
u
n
ctio
n
w
h
ic
h
d
ef
in
e
s
t
h
e
d
eg
r
ee
o
f
a
n
ele
m
en
t’
s
m
e
m
b
er
s
h
ip
in
f
u
s
s
y
s
et
is
ca
lled
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
.
Fo
r
a
n
y
s
et
X,
a
m
e
m
b
er
s
h
ip
f
u
n
cti
o
n
o
n
X
is
a
n
y
f
u
n
ctio
n
f
r
o
m
X
to
th
e
r
ea
l
u
n
it
in
ter
v
a
l
[
0
,
1
]
.
I
t
ca
n
r
ep
r
esen
t
a
f
u
zz
y
s
et
Å
an
d
d
e
n
o
ted
b
y
µ
A
.
Her
e,
o
u
tp
u
t
co
m
es
in
0
,
1
f
o
r
m
w
h
er
e
v
al
u
e
0
m
ea
n
s
X
in
n
o
t
a
m
e
m
b
er
o
f
f
u
zz
y
s
et
a
n
d
v
alu
e
1
m
ea
n
s
is
m
e
m
b
er
o
f
t
h
e
f
u
zz
y
s
et.
T
h
e
v
alu
e
b
et
w
ee
n
0
an
d
1
ch
ar
ac
ter
ize
f
u
zz
y
m
e
m
b
er
,
w
h
ic
h
b
elo
n
g
to
f
u
zz
y
s
et
p
ar
tiall
y
.
5
.
3
F
uzzy
in
M
AT
L
AB
Fu
z
z
y
L
o
g
ic
T
o
o
lb
o
x
is
a
co
l
lectio
n
i
f
i
n
-
b
u
il
t
f
u
n
ctio
n
o
f
MA
T
L
A
B
.
I
t
p
r
o
v
id
es
to
o
ls
f
o
r
cr
ea
tin
g
an
d
ed
itin
g
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
.
I
n
f
u
zz
y
to
o
l
b
o
x
,
GUI
i
s
d
esig
n
ed
to
b
e
s
i
m
p
le.
Fo
llo
w
i
n
g
s
tep
s
is
to
b
e
tak
en
to
cr
ea
te
f
u
zz
y
lo
g
ic
s
y
s
te
m
:
-
a.
T
y
p
e
Fu
zz
y
in
co
m
m
an
d
w
i
n
d
o
w
.
FIS
ed
ito
r
w
i
n
d
o
w
o
p
en
s
.
b.
C
lic
k
o
n
ed
it,
s
et
in
p
u
t a
n
d
o
u
tp
u
t.
T
h
en
s
et
t
h
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
.
c.
Go
to
ed
it,
click
o
n
r
u
le.
R
u
le
E
d
ito
r
W
in
d
o
w
o
p
en
s
.
Se
t th
e
r
u
le
ac
co
r
d
in
g
to
r
eq
u
ir
e
m
e
n
t
s
.
d.
Af
ter
Sett
in
g
r
u
le,
s
av
e
t
h
e
w
i
n
d
o
w
a
n
d
p
u
t
F
u
zz
y
lo
g
ic
C
o
n
tr
o
ller
o
n
m
o
d
el
w
i
n
d
o
w
f
o
r
m
Si
m
u
li
n
k
lib
r
ar
y
.
e.
Sp
ec
if
y
o
u
r
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
a
s
FI
L
f
ile
o
r
s
tr
u
c
tu
r
e
f.
Af
ter
th
a
t RUN t
h
e
m
o
d
el
a
n
d
g
et
o
u
tp
u
t a
cc
o
r
d
in
g
to
o
u
r
r
u
les.
6.
NE
URO
-
F
U
Z
Z
Y
M
O
DE
L
A
co
m
b
in
at
io
n
o
f
ANN
a
n
d
f
u
zz
y
lo
g
ic
f
o
r
ar
ti
f
icial
i
n
telli
g
e
n
ce
is
r
e
s
u
l
t in
n
e
u
r
o
0
f
u
zz
y
m
o
d
el.
I
t is
a
lin
g
u
is
tic
m
o
d
el
w
h
ic
h
u
s
es
a
s
et
o
f
I
f
-
T
h
e
n
f
u
zz
y
r
u
les.
I
t
is
t
h
e
s
y
s
te
m
w
h
ic
h
s
y
n
c
h
r
o
n
izes
t
w
o
tech
n
iq
u
es
;
r
es
u
lt
in
h
u
m
a
n
-
l
ik
e
r
ea
s
o
n
i
n
g
ca
p
ab
ilit
y
o
f
f
u
zz
y
s
y
s
te
m
s
w
i
th
t
h
e
lear
n
i
n
g
ab
ilit
y
o
f
n
eu
r
al
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
F
a
u
lt I
d
e
n
tifi
ca
tio
n
in
S
u
b
-
S
ta
tio
n
b
y
Usi
n
g
n
e
u
r
o
-
F
u
z
z
y
Tech
n
iq
u
e
…
(
A
n
r
u
d
h
Ya
d
a
v
)
347
n
et
w
o
r
k
.
Ne
u
r
o
-
f
u
zz
y
h
y
b
r
id
izatio
n
is
w
id
el
y
ter
m
ed
as
Fu
zz
y
Neu
r
al
Net
w
o
r
k
(
FN
N)
o
r
Neu
r
o
-
Fu
zz
y
S
y
s
te
m
(
N
FS
)
.
B
lo
ck
d
iag
r
a
m
r
ep
r
esen
t
in
g
n
e
u
r
o
-
f
u
zz
y
m
o
d
el
s
h
o
w
n
in
F
ig
u
r
e
6
(
a)
.
Fig
u
r
e
6
(
a)
.
B
lo
ck
Diag
r
a
m
R
ep
r
esen
tin
g
Ne
u
r
o
-
f
u
zz
y
Mo
d
el
7.
M
E
T
H
O
DO
L
O
G
Y
US
E
D
Fig
u
r
e
7
r
ep
r
esen
ts
th
e
f
lo
w
c
h
ar
t u
s
ed
f
o
r
ac
h
ie
v
i
n
g
o
b
j
ec
tiv
e
o
f
th
is
w
o
r
k
.
Fig
u
r
e
7
.
Flo
w
C
h
ar
t o
f
Mo
d
e
l
8.
RE
SU
L
T
S
I
n
th
i
s
s
i
m
u
latio
n
,
th
e
f
ee
d
er
o
f
d
is
tr
ib
u
tio
n
s
u
b
s
tatio
n
is
d
esig
n
ed
.
Her
e,
w
e
id
en
ti
f
y
s
h
o
r
t
cir
cu
it
f
au
lt a
t s
u
b
s
tatio
n
.
A
s
i
m
u
la
te
s
u
b
-
s
tatio
n
f
ee
d
er
s
ar
e
s
h
o
w
n
in
F
i
g
u
r
e
8
(
a)
.
Fig
u
r
e
8
(
a)
.
Sim
u
lat
io
n
B
lo
ck
o
f
Su
b
s
ta
tio
n
Dis
tr
ib
u
tio
n
s
u
b
-
s
tatio
n
S
y
s
te
m
m
o
d
eli
n
g
Fu
zz
y
m
o
d
el
Fo
r
Fau
l
t id
en
ti
f
i
ca
tio
n
(
O/p
in
0
,
1
f
o
r
m
)
Dis
p
la
y
An
al
y
s
i
s
No
r
m
al
/
A
b
n
o
r
m
al
cu
r
r
en
t d
ata
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
Mo
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
:
3
4
3
–
3
5
0
348
Af
ter
s
i
m
u
latio
n
,
w
e
f
ee
d
th
e
o
u
tp
u
t
cu
r
r
e
n
t
to
ANN
as
i
n
p
u
t.
A
f
ter
p
r
o
ce
s
s
in
g
A
NN
o
u
t
p
u
t
is
u
s
ed
as
i
n
p
u
t
f
o
r
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
.
Fin
all
y
,
f
u
zz
y
co
n
tr
o
lle
r
g
i
v
es
o
u
tp
u
t
i
n
f
o
r
m
(
0
,
1
)
.
Var
io
u
s
o
u
tp
u
t
o
f
Neu
r
o
-
F
u
zz
y
m
o
d
el
is
s
h
o
w
n
b
elo
w
in
T
ab
les.
T
ab
le
1
.
Ou
tp
u
t v
al
u
e
o
f
A
NN
T
ab
le
2
.
Ou
tp
u
t o
f
F
u
zz
y
f
o
r
Sin
g
le
Feed
er
T
ab
le
s
h
o
w
s
t
h
e
r
esu
l
t
,
w
h
e
n
f
au
lts
o
cc
u
r
o
n
B
o
th
f
ee
d
er
T
ab
le
3
.
Ou
tp
u
t
w
h
e
n
Fa
u
lt O
cc
u
r
in
Feed
er
1
T
ab
le
4
.
Ou
tp
u
t
w
h
e
n
Fa
u
lt O
cc
u
r
in
Feed
er
2
T
ab
le
5
.
Ou
tp
u
t
Valu
e
s
o
f
F
u
z
z
y
,
w
h
e
n
Fa
u
lts
o
cc
u
r
o
n
B
o
th
Feed
er
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
F
a
u
lt I
d
e
n
tifi
ca
tio
n
in
S
u
b
-
S
ta
tio
n
b
y
Usi
n
g
n
e
u
r
o
-
F
u
z
z
y
Tech
n
iq
u
e
…
(
A
n
r
u
d
h
Ya
d
a
v
)
349
Fau
lt
C
las
s
if
icatio
n
o
n
t
h
e
B
asis
o
f
Ne
u
r
o
Fu
zz
y
O
u
tp
u
t
Her
e
0
s
h
o
w
s
n
o
n
-
f
a
u
lt
co
n
d
itio
n
an
d
1
s
h
o
w
s
f
a
u
lt
-
co
n
d
itio
n
T
ab
le
5
.
Fau
lt C
las
s
i
f
icatio
n
S
.
N
o
A
B
C
G
T
Y
P
E
O
F
F
A
U
L
T
1
1
0
0
1
A
-
G
2
0
1
0
1
B
-
G
3
0
0
1
1
C
-
G
4
1
1
0
0
A
-
B
5
0
1
1
0
B
-
C
6
1
0
1
0
A
-
C
7
1
1
0
1
A
-
B
-
G
8
0
1
1
1
B
-
C
-
G
9
1
0
1
1
A
-
C
-
G
10
1
1
1
0
A
-
B
-
C/
A
-
B
-
C
-
G
Fig
u
r
e
9
.
Dis
p
la
y
f
o
r
I
d
en
tif
ic
atio
n
o
f
Fa
u
lt
9.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
id
en
tif
icatio
n
o
f
f
a
u
lt
u
s
in
g
n
e
u
r
o
-
f
u
zz
y
m
eth
o
d
h
as
b
ee
n
d
o
n
e
in
r
ea
l
ti
m
e.
I
t
is
p
r
o
v
ed
to
b
e
a
f
ast,
r
o
b
u
s
t
ap
p
r
o
ac
h
as
o
u
tp
u
t
is
i
n
0
,
1
f
o
r
m
t
h
at
w
o
u
ld
p
er
f
o
r
m
f
o
r
v
ar
io
u
s
p
o
w
er
s
y
s
te
m
co
n
d
itio
n
.
F
u
r
t
h
er
r
ef
i
n
e
m
en
t
o
f
n
eu
r
o
-
f
u
zz
y
m
o
d
el
ca
n
i
m
p
le
m
en
t
i
n
a
n
r
ea
l
p
o
w
er
s
y
s
t
e
m
to
d
ia
g
n
o
s
is
o
f
f
au
lts
.
I
n
t
h
is
p
ap
er
,
n
eu
r
o
-
f
u
zz
y
tech
n
iq
u
e
s
h
o
w
s
ca
p
ab
ilit
y
o
f
esti
m
ati
n
g
th
e
f
au
lt
an
d
t
h
eir
t
y
p
es.
Gr
o
u
n
d
cu
r
r
en
t c
an
ea
s
il
y
d
is
ti
n
g
u
i
s
h
t
h
e
t
y
p
e
o
f
f
au
lt o
cc
u
r
.
W
e
co
n
clu
d
e
f
o
llo
w
i
n
g
:
a.
T
h
r
ee
lin
e
an
d
g
r
o
u
n
d
cu
r
r
en
t
m
ea
s
u
r
e
m
e
n
t
s
ar
e
s
u
f
f
icie
n
t to
i
m
p
le
m
e
n
t t
h
i
s
tech
n
iq
u
e
b.
T
ec
h
n
iq
u
e
is
ab
le
to
id
en
ti
f
y
a
ll t
y
p
es o
f
s
h
o
r
t c
ir
cu
i
t f
a
u
lt
s
ac
cu
r
atel
y
,
at
m
u
lti
-
f
a
u
lt c
o
n
d
it
io
n
.
c.
T
h
e
ac
cu
r
ac
y
o
f
th
i
s
m
e
th
o
d
is
v
er
y
h
i
g
h
an
d
n
o
t
d
ep
en
d
en
t
o
n
th
e
t
y
p
e
o
f
tr
an
s
ie
n
ts
en
co
u
n
ter
ed
d
u
r
in
g
a
f
au
l
t.
RE
F
E
R
E
NC
E
[1
]
W
e
n
-
Hu
i
Ch
e
n
,
Ch
ih
-
W
e
n
L
iu
A
n
d
M
e
n
-
S
h
e
n
T
sa
i
,
“
On
L
in
e
F
a
u
lt
Dia
g
n
o
sis
o
f
Distrib
u
ti
o
n
S
u
b
sta
ti
o
n
Us
in
g
H
y
b
rid
Ca
u
se
-
Ef
fe
c
t
Ne
t
w
o
rk
A
n
d
F
u
z
z
y
Ru
led
-
Ba
se
d
M
e
th
o
d
,
”
I
n
P
ro
c
.
IEE
E
P
o
w
e
r
En
g
.
S
o
c
.
W
in
ter
M
e
e
ti
n
g
,
Ja
n
.
2
0
0
0
.
[2
]
K
.
K
.
Li
,
L
.
L
.
L
a
i
,
A
n
d
A
.
K
.
Da
v
id
,
“
A
p
p
li
c
a
ti
o
n
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
In
F
a
u
lt
L
o
c
a
ti
o
n
T
e
c
h
n
iq
u
e
,
”
In
t
.
Jo
u
rn
a
l
o
f
En
g
in
e
e
rin
g
In
telli
g
e
n
t
S
y
ste
m
s
,
V
o
l
.
1
,
No
.
3
,
P
p
.
2
2
6
–
2
3
1
,
A
p
r2
0
0
0
.
[3
]
M
.
S
.
P
a
sa
n
d
A
n
d
H
.
K
.
Zad
e
h
,
“
T
ra
n
s
m
is
sio
n
L
in
e
F
a
u
lt
De
tec
ti
o
n
a
n
d
P
h
a
se
S
e
lec
ti
o
n
Us
in
g
ANN
,
”
In
t
.
Co
n
f
.
o
n
P
o
w
e
r
S
y
ste
m
T
ra
n
sie
n
t
,
P
p
1
-
6
,
Ja
n
.
2
0
0
3
.
[4
]
P
.
K
.
Da
sh
A
n
d
S
.
R
.
S
a
m
a
n
tra
y
,
“
A
n
A
c
c
u
ra
te
F
a
u
lt
Clas
sif
ica
ti
o
n
A
lg
o
rit
h
m
Us
in
g
A
M
in
ima
l
Ra
d
ial
Ba
sis
F
u
n
c
ti
o
n
Ne
u
ra
l
Ne
tw
o
rk
”
,
P
u
b
li
sh
e
d
In
En
g
g
.
In
tell
ig
e
n
t
S
y
ste
m
,
V
o
l
.
4
,
P
p
.
2
0
5
-
2
1
0
,
2
0
0
4
.
[5
]
P
.
K
.
W
o
n
g
,
“
Ne
u
ra
l
Ne
t
w
o
rk
A
p
p
li
c
a
ti
o
n
s
In
P
o
w
e
r
S
y
st
e
m
s
,
”
In
t
.
Jo
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
In
te
l
li
g
e
n
t
S
y
ste
m
s
,
V
o
l
.
1
,
No
.
3
,
P
p
.
1
3
3
–
1
5
8
,
De
c
.
1
9
9
3
.
[6
]
K
.
G
a
y
a
tri
A
n
d
N
.
Ku
m
a
ra
p
p
a
n
,
“
Co
m
p
a
ra
ti
v
e
S
tu
d
y
o
f
F
a
u
lt
Id
e
n
ti
f
ica
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
n
Eh
v
L
in
e
s
Us
in
g
Disc
re
te
Wav
e
l
e
t
T
ra
n
s
f
o
r
m
a
n
d
F
o
u
rier
T
ra
n
sf
o
rm
Ba
s
e
d
A
n
n
,
”
In
t
.
J
.
Of
El
e
c
t
.
Co
m
p
.
A
n
d
S
y
st
e
m
En
g
g
.
V
o
l
.
5
3
,
No
.
3
,
2
0
0
8
,
P
p
.
1
2
7
–
1
3
6
.
[7
]
M
.
P
ir
o
u
ti
,
A
.
A
F
a
ti
h
A
n
d
I
.
B
.
S
a
d
ik
,
“
F
a
u
lt
I
d
e
n
ti
f
ica
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
f
o
r
S
h
o
rt
M
e
d
iu
m
V
o
l
tag
e
Un
d
e
rg
ro
u
n
d
Ca
b
le Ba
se
d
On
A
NN
,
”
Jo
u
rn
a
l
Of
El
e
c
tri
c
a
l
En
g
g
.
V
o
l
.
5
9
,
No
.
5
,
P
p
.
2
7
2
-
2
7
6
,
2
0
0
8
.
[8
]
A
.
B
e
rn
ier
,
M
.
D’h
u
z
z
o
,
L
.
S
a
n
so
n
a
n
d
M
.
S
a
v
a
sta
n
,
“
A
N
e
u
ra
l
,
Ne
t
w
o
rk
A
p
p
ro
a
c
h
F
o
rid
e
n
ti
f
ica
ti
o
n
a
n
d
F
a
u
lt
Dia
g
n
o
sis
on
Dy
n
a
m
ic S
y
ste
m
s
,
”
IEE
E
T
ra
n
s
.,
V
o
l
.
2
,
No
.
5
,
P
p
.
5
6
4
-
5
6
9
,
1
9
9
3
[9
]
Z
.
W
a
n
g
,
Yilu
L
i
,
P
.
J
.
G
ri
ff
in
,
N
.
C
.
Wan
g
,
T
.
Y
.
G
u
o
,
F
.
T
.
C
.
Hu
a
n
g
,“
A
rti
f
icia
l
In
telli
g
e
n
c
e
in
P
o
w
e
r
Eq
u
ip
m
e
n
t
F
a
u
lt
Dia
g
n
o
sis
,
”
IE
EE
T
ra
n
s
. o
n
P
o
w
e
r
De
li
v
e
r,
V
o
l
.
3
,
No
.
8
,
P
p
2
4
7
-
2
5
2
,
2
0
0
0
[1
0
]
S
a
m
u
e
l
N
.
Ha
m
il
to
n
A
n
d
A
le
x
O
ra
il
o
g
lu
, “
On
-
L
in
e
T
e
st
F
o
r
F
a
u
l
t
-
S
e
c
u
re
F
a
u
lt
I
De
n
ti
f
ica
ti
o
n
,
”
IE
EE
T
ra
n
sa
c
ti
o
n
s
o
n
(
V
L
S
I
)
S
y
ste
m
s
,
V
o
l
.
8
,
No
.
4
,
P
p
.
4
4
7
-
4
5
2
,
A
u
g
u
st
2
0
0
0
.
[1
1
]
M
a
ro
u
f
P
iro
u
ti
,
“
Ne
u
ra
l
Ne
tw
o
rk
Ba
se
d
F
a
u
lt
L
o
c
a
ti
o
n
Esti
m
a
to
r
f
o
r
S
h
o
rt
M
e
d
iu
m
V
o
l
tag
e
Un
d
e
rg
ro
u
n
d
Ca
b
le
,
”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
El
e
c
tri
c
a
l
P
o
w
e
r
En
g
g
.
V
o
l
.
2
,
No
.
5
,
P
p
.
3
4
0
-
3
4
4
,
2
0
0
8
.
[1
2
]
M
.
T
o
g
a
m
i
,
N
.
A
b
e
,
T
.
Kitah
a
sh
i
,
A
n
d
H
.
Og
a
w
a
,
“
On
T
h
e
A
p
p
li
c
a
ti
o
n
o
f
A
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
i
q
u
e
t
o
F
a
u
l
t
Dia
g
n
o
sis Of
P
o
w
e
r
Distrib
u
ti
o
n
L
in
e
s,”
IEE
E
T
ra
n
s
. o
n
P
W
RD
,
Vo
l.
1
0
,
No
.
4
,
P
p
.
1
9
2
7
–
1
9
3
6
,
1
9
9
5
.
[1
3
]
K
.
H
.
Kim
A
n
d
J
.
K
.
P
a
rk
,
“
A
p
p
li
c
a
ti
o
n
o
f
Hie
ra
rc
h
ica
l
Ne
u
ra
l
Ne
tw
o
rk
s
to
F
a
u
lt
Di
a
g
n
o
sis
o
f
P
o
w
e
r
S
y
ste
m
s,”
El
e
c
tri
c
a
l
P
o
w
e
r
&
En
e
rg
y
S
y
ste
m
s
,
V
o
l
.
1
5
,
N
o
.
2
,
P
p
.
6
5
–
7
0
,
1
9
9
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
:
3
4
3
–
3
5
0
350
[1
4
]
S
.
Ra
h
m
a
n
,
“
A
rti
f
icia
l
In
telli
g
e
n
c
e
in
El
e
c
tri
c
P
o
w
e
r
S
y
ste
m
s:
A
S
u
rv
e
y
o
f
T
h
e
Ja
p
a
n
e
s
e
In
d
u
str
y
”
,
IEE
E
T
ra
n
s
.
on
P
o
w
e
r
S
y
ste
m
s
,
V
o
l
.
8
,
No
.
3
,
P
p
.
1
2
1
1
–
2
2
1
8
.
[1
5
]
Za
d
e
h
L
.
A
., "
F
u
z
z
y
S
e
ts"
,
In
f
o
r
m
a
t
.
Co
n
tr
o
l
,
N
o
.
8
,
1
9
6
5
,
P
p
.
3
3
8
-
3
5
3
.
[1
6
]
H
.
W
.
Ha
n
g
,
Da
v
id
,
“
In
telli
g
e
n
t
S
y
ste
m
Id
e
n
ti
f
ies
a
n
d
L
o
c
a
te
s
T
ra
n
s
m
is
sio
n
F
a
u
lt
s
,
”
In
ter
n
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
El
e
c
tri
c
a
l
P
o
w
e
r
En
g
g
.
,
V
o
l
.
3
,
P
p
.
2
0
1
-
2
0
5
,
1
9
9
7
.
[1
7
]
K
.
P
.
W
o
n
g
,
“
A
rti
f
icia
l
In
telli
g
e
n
c
e
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
s
A
p
p
li
c
a
ti
o
n
s
in
P
o
w
e
r
S
y
ste
m
s
”
,
IEE
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
on
A
d
v
a
n
c
e
s
in
P
o
w
e
r
S
y
ste
m
Co
n
tro
l
,
Op
e
ra
ti
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t
,
V
o
l
.
7
,
No
.
1
0
,
P
p
.
3
7
-
4
6
.
1
9
9
3
.
[1
8
]
M
.
Ke
z
u
n
o
v
ic
,
“
In
telli
g
e
n
t
S
y
ste
m
s
in
P
ro
tec
ti
o
n
En
g
i
n
e
e
rin
g
”
,
P
o
w
e
r
S
y
ste
m
Tec
h
n
o
lo
g
y
,
P
ro
c
e
e
d
in
g
s
o
f
P
o
w
e
r
Co
n
f
,
Vo
l
.
2
,
P
p
.
8
0
1
-
8
0
6
.
De
c
.
2
0
0
0
.
[1
9
]
T
.
T
a
k
a
g
i
,
M
.
S
u
g
e
n
o
,
"
F
u
z
z
y
Id
e
n
ti
f
ica
ti
o
n
o
f
S
y
st
e
m
s
A
n
d
Its
A
p
p
li
c
a
ti
o
n
s
t
o
M
o
d
e
li
n
g
a
n
d
Co
n
tr
o
l"
,
IEE
E
T
ra
n
s
.
S
y
s
,
M
a
n
,
Cy
b
e
r
,
V
o
l
.
SMC
-
1
5
,
1
9
8
5
,
P
p
.
1
1
6
-
1
3
2
.
[2
0
]
D
.
W
a
ik
a
r
A
n
d
F
Ra
h
m
a
n
,
“
As
se
ss
m
e
n
t
o
f
A
rti
f
icia
l
In
telli
g
e
n
c
e
T
e
c
h
n
iq
u
e
s
f
o
r
P
o
w
e
r
S
y
st
e
m
P
ro
tec
ti
o
n
”
,
En
e
rg
y
M
a
n
a
g
e
m
e
n
t
a
n
d
P
o
w
e
r
De
li
v
e
r
y
,
P
ro
c
e
e
d
in
g
s
Of
EM
P
D
,
Vo
l
.
2
,
P
p
.
4
3
6
–
4
4
1
,
M
a
rc
h
1
9
9
8
.
B
I
O
G
RAP
H
Y
O
F
AUTHO
RS
Er.
V
i
n
a
y
Ku
m
a
r
Ha
rit
re
c
e
iv
e
d
B.
T
e
c
h
De
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
R
G
E
Co
ll
e
g
e
M
e
e
ru
t,
U
P
(In
d
ia)
i
n
2
0
0
7
.
He
h
a
s
re
c
e
iv
e
d
M
.
T
e
c
h
in
E
lec
tri
c
al
P
o
w
e
r
sy
st
e
m
M
a
n
a
g
e
m
e
n
t
f
ro
m
Ja
m
ia
M
il
li
a
Isla
m
ia,
De
lh
i
(In
d
ia)
in
2
0
0
9
.
He
is
w
o
rk
in
g
a
s
a
n
Ju
n
io
r
En
g
in
e
e
r
i
n
Ne
w
De
lh
i
M
u
n
icip
a
l
Co
u
n
c
il
a
t
Ne
w
De
lh
i
sin
c
e
2
0
0
9
.
He
is
c
u
rre
n
t
p
u
rsi
n
g
P
h
.
D
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
De
lh
i
T
e
c
h
n
ica
l
Un
iv
e
rsit
y
,
De
lh
i.
His
a
re
a
s
o
f
in
tere
st
a
r
e
P
o
w
e
r
S
y
ste
m
,
S
m
a
rt
G
rid
,
H
y
b
rid
P
o
w
e
r
S
y
ste
m
,
P
o
w
e
r
Qu
a
li
ty
.
E
m
a
il
:
-
p
a
n
c
h
sh
e
e
lb
o
u
d
h
@liv
e
.
c
o
m
Er.
A
n
iru
d
h
Ya
d
a
v
re
c
e
iv
e
d
th
e
B
.
T
e
c
h
De
g
r
e
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
G
B
T
U,
L
u
c
k
n
o
w
(In
d
ia)
i
n
2
0
1
2
.
He
h
a
s
re
c
e
iv
e
d
th
e
M
.
T
e
c
h
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
(
P
o
w
e
r
S
y
ste
m
)
f
ro
m
D
e
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
S
.
H
.
I.
A
.
T
.
S
,
A
ll
a
h
a
b
a
d
,
U.P
.
(In
d
ia)
.
Em
a
il
id
-
e
r.
a
n
iru
d
h
5
3
@g
m
a
il
.
c
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.