I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
10
, N
o.
4
,
D
e
c
e
m
be
r
2021
, pp.
1019
~
10
24
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
10
.i
4
.pp
1019
-
10
24
1019
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
S
u
p
p
or
t
ve
c
t
o
r
m
ac
h
i
n
e
b
ase
d
f
au
l
t
s
e
c
t
i
on
i
d
e
n
t
i
f
i
c
at
i
on
an
d
f
au
l
t
c
l
ass
i
f
i
c
at
i
on
sc
h
e
m
e
i
n
si
x p
h
as
e
t
r
an
sm
i
ss
i
on
l
i
n
e
A
.
N
ar
e
s
h
k
u
m
ar
1
,
M
.
S
u
r
e
s
h
K
u
m
ar
2
,
M
.
R
am
e
s
h
a
3
, B
h
ar
at
h
i
G
u
r
u
r
aj
4
, A
.
S
r
ik
a
n
t
h
5
1,5
Department of
Electrical and Electronics Engineering, Institute of Aeronautical Engineering, Hyderabad, India
2
Department of Aerospace Engineering
, Sandip Univ
ersity, Nashik, In
dia
3
Department of Electronics
and Communicati
on Engineering, GITAM
(Deemed to be University
)
, Bengaluru, India
4
Department of Electronics
and Communicati
on Engineering, AC
S College of En
gineering, Bengaluru,
India
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
A
pr
4
,
2021
R
e
vi
s
e
d
J
ul
24
,
2021
A
c
c
e
pt
e
d
A
ug
21
,
2021
The
higher
complexity
of
a
six
phase
transmission
system
(SPTS)
construct
ion
and
the
large
number
of
possib
le
faults
makes
the
protect
ion
task
challengi
ng.
Moreover,
the
reverse
&
forward
path
faults
in
SPTS
ca
nnot
be
detected
by
traditional
relay
as
it
be
comes
under
-
reach.
In
this
paper,
a
support
vector
machine
(SVM)
method
including
Haar
wavelets
fo
r
SPTS
fault
section
identification
and
fault
classification
is
focused.
The
positive
-
sequence
component
phase
angle
and
currents
at
middle
two
buses
are
used
to
formulate
a
suggested
method.
Feasibil
ity
of
suggested
SVM
is
teste
d
with
a
138
kV, 300
km,
60
Hz,
SPTS in MATLAB
based Simulink
platform.
Several
major
parameters
including
far
end
and
near
end
location
co
n
d
i
ti
o
n
s
ar
e
t
ak
e
n
t
o
i
nv
e
s
t
ig
a
t
e
t
h
e
re
a
c
h
s
e
tt
i
n
g
a
n
d
a
cc
u
r
a
cy
of
pr
o
p
o
se
d
S
V
M
.
T
hi
s
r
e
l
a
y
i
ng
m
e
t
h
o
d
c
a
n
de
t
e
c
t
t
h
e
ex
i
s
t
en
c
e
of
f
a
ul
t
i
n
r
e
v
e
rs
e
&
f
o
r
w
ar
d
path in 1 ms
time
.
K
e
y
w
o
r
d
s
:
F
a
ul
ts
S
ix
pha
s
e
t
r
a
ns
m
is
s
io
n
s
ys
te
m
S
uppor
t
ve
c
to
r
m
a
c
hi
ne
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
:
A
N
a
r
e
s
h K
um
a
r
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
I
ns
ti
tu
te
of
A
e
r
ona
ut
ic
a
l
E
ngi
ne
e
r
in
g
H
yde
r
a
ba
d, 500043, T
e
la
ng
a
na
, I
ndi
a
E
m
a
il
:
a
nka
m
na
r
e
s
h29@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
E
le
c
tr
ic
it
y
ha
s
be
c
om
e
th
e
uni
ve
r
s
a
l
dr
iv
e
r
f
or
s
oc
ia
l
e
c
onomi
c
de
ve
lo
pm
e
nt
s
.
D
ue
to
ur
ba
n
gr
ow
t
h
a
s
w
e
ll
a
s
c
ons
tr
a
in
ts
on
r
ig
ht
-
of
-
w
a
y,
th
e
r
e
a
r
e
li
m
it
s
on
in
s
ta
ll
in
g
la
te
s
t
tr
a
ns
m
is
s
io
n
li
ne
.
R
e
c
e
nt
ly
,
s
ix
pha
s
e
t
r
a
ns
m
is
s
io
n s
ys
te
m
(
S
P
T
S
)
i
s
be
in
g e
m
pl
oye
d t
o i
m
pr
o
ve
t
he
t
r
a
ns
m
is
s
io
n r
e
li
a
bi
li
ty
a
nd c
a
pa
c
it
y [
1
]
,
[
2]
.
S
P
T
S
m
us
t
be
e
qui
ppe
d
w
it
h
th
e
r
e
la
ys
to
e
ns
ur
e
c
ont
in
uous
m
oni
to
r
in
g
f
or
de
te
c
t
f
a
ul
ts
.
T
h
us
,
S
P
T
S
is
r
e
s
to
r
e
d
to
th
e
nor
m
a
l
c
ondi
ti
on
a
nd
pow
e
r
s
uppl
y
is
r
e
c
onne
c
te
d
f
or
lo
a
d
c
os
tu
m
e
r
s
in
th
e
lo
w
e
s
t
pos
s
ib
le
ti
m
e
le
a
di
ng
to
hi
gh
r
e
li
a
bi
li
ty
.
A
c
ons
id
e
r
a
bl
e
a
m
ount
of
li
te
r
a
tu
r
e
r
e
qui
r
e
d
to
s
tu
dy
w
it
h
th
e
c
om
pl
ic
a
ti
on
of
a
f
a
ul
t
s
e
c
ti
on
id
e
nt
if
i
c
a
ti
on
a
nd
f
a
ul
t
c
la
s
s
if
ic
a
ti
on
m
e
th
od.
T
o
e
ns
ur
e
a
c
c
ur
a
te
a
nd
f
a
s
te
r
de
te
c
ti
on
of
S
P
T
S
di
s
tu
r
ba
nc
e
s
, di
f
f
e
r
e
nt
m
oni
to
r
in
g s
c
he
m
e
s
ha
ve
b
e
e
n pr
e
s
e
nt
e
d by r
e
s
e
a
r
c
h
e
r
s
.
R
e
s
e
a
r
c
h
e
r
s
ove
r
th
e
w
o
r
ld
w
id
e
ha
ve
w
id
e
ly
s
tu
di
e
d
[
3
]
,
[
4]
di
f
f
e
r
e
nt
f
e
a
tu
r
e
s
of
S
P
T
S
v
iz
.
lo
w
e
r
a
udi
bl
e
noi
s
e
le
v
e
ls
,
d
e
c
r
e
a
s
e
d
r
a
di
o
in
te
r
f
e
r
e
nc
e
le
v
e
ls
,
le
s
s
e
r
c
or
ona
,
r
e
duc
e
d
c
onduc
to
r
s
ur
f
a
c
e
gr
a
di
e
nt
,
hi
ghe
r
e
f
f
ic
ie
nc
y,
good
vol
ta
ge
r
e
gul
a
ti
on,
th
e
r
m
a
l
lo
a
di
ng
c
a
pa
c
it
y
a
nd
be
tt
e
r
s
ur
ge
im
pe
da
nc
e
lo
a
di
ng.
S
om
e
r
e
c
e
nt
pa
pe
r
s
r
e
v
e
a
l
th
a
t
S
P
T
S
pe
r
f
or
m
s
e
xc
e
ll
e
nt
ly
in
obt
a
in
in
g
a
hi
gh
pow
e
r
tr
a
ns
m
is
s
io
n
c
a
p
a
c
it
y.
P
ubl
is
he
d
f
a
ul
t
s
ta
ti
s
ti
c
s
[
5
]
-
[
7]
c
le
a
r
ly
di
vul
ge
th
a
t
a
m
a
jo
r
it
y
of
S
P
T
S
f
a
ul
ts
a
r
e
s
hunt
f
a
ul
ts
.
I
n
th
e
pa
s
t
de
c
a
de
m
a
ny r
e
s
e
a
r
c
he
r
s
f
oc
u
s
e
d m
a
ny me
th
odol
ogi
e
s
f
or
f
a
ul
t
lo
c
a
ti
on
in
a
S
P
T
S
. R
e
s
e
a
r
c
h
e
r
s
m
a
de
a
w
or
k
on
f
uz
z
y
m
e
th
od
to
ge
t
th
e
f
a
ul
ty
l
o
c
a
t
io
n [
8
]
, [
9]
f
or
a
S
P
T
S
.
F
u
r
t
h
e
r
, a
r
e
s
e
a
r
c
h w
or
k
[
1
0]
, [
1
1
]
h
a
s
b
e
e
n d
o
n
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
4
,
D
e
c
e
m
be
r
2021:
1019
-
10
24
1020
w
i
t
h
r
e
a
l
-
t
i
m
e
v
a
li
d
a
t
i
on
f
o
r
s
o
l
v
in
g
f
a
u
l
t
i
s
s
u
e
s
i
n
S
P
T
S
b
y
S
un
il
K
e
t
a
l
.
A
n
ot
h
e
r
s
c
h
e
m
e
b
y
E
b
h
a
e
t
al
.
[
12
]
,
[
13]
im
pl
e
m
e
nt
e
d a
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
k t
o pr
e
di
c
t
th
e
f
a
ul
ts
i
n S
P
T
S
.
S
e
c
ti
on
id
e
nt
if
ic
a
ti
on/
di
s
c
r
im
in
a
ti
on/
di
r
e
c
ti
ona
l
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
ti
on
ha
ve
b
e
e
n
a
hot
to
pi
c
f
or
f
e
w
de
c
a
de
s
.
R
e
s
e
a
r
c
he
r
s
ha
v
e
e
xe
r
te
d
m
uc
h
e
f
f
or
t
ove
r
th
e
ye
a
r
s
e
xpl
or
in
g
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
ti
on
[
14
]
-
[
17]
.
A
ddi
ti
ona
ll
y,
va
r
io
us
c
ha
ll
e
ng
e
s
ha
ve
b
e
e
n
r
e
vi
e
w
e
d
in
S
P
T
S
w
it
h
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
ti
on
[
18
]
,
[
19]
.
A
lt
hough
th
e
a
f
or
e
s
a
id
s
c
he
m
e
s
,
r
e
m
a
r
ka
bl
y,
c
ont
r
ib
ut
e
d
in
th
e
di
r
e
c
ti
ona
l
r
e
la
yi
ng,
th
e
e
m
e
r
ge
nc
e
of
ne
w
s
tr
uc
tu
r
e
s
a
lo
ng
w
it
h
c
om
pl
e
xi
ty
of
S
P
T
S
ha
s
ne
c
e
s
s
it
a
t
e
d
th
e
us
a
g
e
of
in
te
ll
ig
e
nt
te
c
hni
que
s
in
th
e
di
r
e
c
ti
ona
l
r
e
la
yi
ng.
A
s
ui
ta
bl
e
a
nd
s
tr
a
ig
ht
f
or
w
a
r
d
m
e
th
od
b
a
s
e
d
on
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
S
V
M
)
w
it
h
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
ti
on
in
[
20
]
-
[
25]
f
or
di
r
e
c
ti
ona
l
r
e
la
yi
ng.
I
t
is
obs
e
r
ve
d
f
r
om
li
te
r
a
tu
r
e
s
ur
ve
y
th
a
t
no
pa
pe
r
e
xpl
oi
te
d
th
e
di
r
e
c
ti
ona
l
r
e
l
a
yi
ng
in
S
P
T
S
us
in
g
S
V
M
.
I
n
th
is
c
ont
e
xt
, a
m
a
id
e
n a
tt
e
m
pt
ha
s
be
e
n
don
e
in
th
is
pa
p
e
r
to
pr
e
s
e
nt
a
S
V
M
a
s
S
P
T
S
f
a
ul
te
d
li
ne
di
s
c
r
im
in
a
t
io
n
a
nd
f
a
ul
ty
pha
s
e
id
e
nt
if
ic
a
ti
on
is
s
ue
s
.
T
h
e
m
a
in
a
im
s
of
th
is
pa
pe
r
a
r
e
:
i)
S
tu
dyi
ng
th
e
f
a
ul
ts
in
th
r
e
e
s
e
c
ti
ons
,
ii
)
D
e
ve
lo
pi
ng
of
S
V
M
-
ba
s
e
d
f
o
r
di
r
e
c
ti
ona
l
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
t
io
n
m
e
th
od
s
in
S
P
T
S
A
s
m
a
l
le
r
a
m
ount
c
om
put
in
g
w
or
k
,
iv
)
D
e
te
c
ti
on
of
th
e
f
a
ul
ts
una
m
bi
guous
ly
, a
nd v)
E
nha
nc
e
m
e
nt
of
r
e
a
c
h s
e
tt
in
g a
nd a
c
c
ur
a
c
y
.
T
he
a
r
ti
c
le
s
ta
r
ts
w
it
h
in
tr
oduc
ti
on
f
ol
lo
w
e
d
by
th
e
r
e
vi
e
w
of
c
ur
r
e
nt
r
e
s
e
a
r
c
h
w
or
k
is
pr
e
s
e
nt
e
d.
N
e
xt
,
it
gi
v
e
s
th
e
S
P
T
S
de
ta
il
s
.
A
f
te
r
th
a
t,
it
de
ve
lo
ps
th
e
S
V
M
m
ode
l
a
nd
it
’
s
de
s
ig
ni
ng.
S
e
que
nt
ia
ll
y,
th
e
e
xpe
r
im
e
nt
a
l
r
e
s
ul
ts
a
r
e
pr
e
s
e
nt
e
d a
nd t
he
c
on
c
lu
di
ng r
e
m
a
r
ks
a
r
e
pr
ovi
de
d.
2.
S
Y
S
T
E
M
S
T
U
D
I
E
D
T
he
pr
opos
e
d
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
S
V
M
)
b
a
s
e
d
pr
ot
e
c
ti
on
r
e
la
yi
ng
ha
s
be
e
n
im
pl
e
m
e
nt
e
d
f
or
a
S
P
T
S
r
e
f
e
r
r
in
g
to
th
e
S
pr
in
gda
le
-
M
c
C
a
lm
ont
138
kV
,
60
H
z
li
ne
of
300
km
le
ngt
h
i
s
s
ho
w
n
in
F
ig
ur
e
1.
T
h
e
s
our
c
e
im
pe
da
nc
e
s
of
s
e
ndi
ng
te
r
m
in
a
l
a
nd
r
e
c
e
iv
in
g
te
r
m
i
na
l
a
r
e
2.02
+
j9
.03
Ω
a
nd
4
+
j1
7.88
Ω
,
r
e
s
pe
c
ti
ve
ly
.
T
he
c
ir
c
ui
t
of
S
P
T
S
is
im
pl
e
m
e
nt
e
d
in
M
A
T
L
A
B
ba
s
e
d
S
im
ul
in
k
pl
a
tf
or
m
us
in
g
di
s
tr
ib
ut
e
d
pa
r
a
m
e
te
r
l
in
e
s
a
nd
it
s
de
ta
il
s
a
r
e
s
how
n i
n T
a
bl
e
1.
T
he
s
pe
c
if
i
c
a
ti
ons
of
t
he
S
P
T
S
ha
ve
be
e
n a
dopt
e
d i
n t
hi
s
w
or
k
f
or
s
im
ul
a
ti
ng.
P
ha
s
e
a
ngl
e
of
pos
it
iv
e
-
s
e
que
nc
e
c
om
pone
nt
,
z
e
r
o
-
s
e
que
nc
e
c
om
pone
nt
a
nd
H
a
a
r
w
a
ve
le
t
c
ur
r
e
nt
s
in
S
P
T
S
dur
in
g
f
a
ul
ty
c
ondi
ti
on
in
s
e
c
ti
on
-
1
a
r
e
in
il
lu
s
tr
a
te
d
F
ig
ur
e
s
2
-
4,
r
e
s
pe
c
ti
ve
ly
.
T
he
out
li
ne
of
s
ugge
s
te
d
S
V
M
-
ba
s
e
d
di
r
e
c
ti
ona
l
r
e
la
yi
ng
a
nd
c
la
s
s
if
ic
a
ti
on
s
c
he
m
e
s
f
or
s
hunt
f
a
ul
ts
is
e
xe
m
pl
if
ie
d i
n F
ig
ur
e
5.
F
ig
ur
e
1. S
P
T
S
T
a
bl
e
1. S
P
T
S
pa
r
a
m
e
te
r
va
lu
e
s
P
a
r
a
m
e
t
e
r
U
ni
t
s
V
a
l
ue
s
N
um
be
r
of
C
i
r
c
ui
t
s
-
1
N
um
be
r
of
S
e
c
t
i
ons
-
3
N
um
be
r
of
P
ha
s
e
s
-
6
S
our
c
e
V
ol
t
a
ge
[
kV
]
138
B
a
s
e
P
ow
e
r
[
M
V
A
]
120
F
r
e
que
nc
y
[
H
z
]
60
E
a
r
t
h R
e
s
i
s
t
i
vi
t
y
[Ω
-
m]
150
L
i
ne
L
e
ngt
h
[
km
]
300
S
hor
t
C
i
r
c
ui
t
C
a
pa
c
i
t
y [
M
V
A
]
-
1350
S
our
c
e
X
/
R
R
a
t
i
o
-
9
L
oa
d a
t
B
us
[
kW
]
120
[
kV
A
R
]
120
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Suppor
t
v
e
c
to
r
m
a
c
hi
ne
bas
e
d f
aul
t
s
e
c
ti
on i
de
nt
if
ic
at
io
n and faul
t
c
la
s
s
if
ic
at
io
n …
(
A
. N
ar
e
s
h k
um
ar
)
1021
F
ig
ur
e
2. P
ha
s
e
a
ngl
e
of
pos
it
iv
e
s
e
qu
e
nc
e
c
om
pone
nt
i
n S
P
T
S
dur
in
g f
a
ul
ty
c
ondi
ti
on
F
ig
ur
e
3
.
Z
e
r
o s
e
que
nc
e
c
om
pone
nt
of
c
ur
r
e
nt
of
S
P
T
S
dur
in
g f
a
ul
ty
c
ondi
ti
on
F
ig
ur
e
4
.
H
a
a
r
w
a
ve
le
t
c
ur
r
e
nt
s
of
S
P
T
S
dur
in
g f
a
ul
ty
c
ondi
ti
o
n
F
ig
ur
e
5. F
lo
w
of
pr
opos
e
d w
or
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
4
,
D
e
c
e
m
be
r
2021:
1019
-
10
24
1022
3.
T
E
C
H
N
I
Q
U
E
U
S
E
D
T
he
s
uppor
t
ve
c
to
r
m
a
c
hi
n
e
(
S
V
M
)
is
de
ve
lo
pe
d
f
r
om
th
e
th
e
or
y
of
s
t
a
ti
s
ti
c
a
l
le
a
r
ni
ng
c
onc
e
pt
s
in
la
te
1960
s
.
R
e
c
e
nt
ly
,
S
V
M
ha
s
e
m
e
r
ge
d
a
s
a
popula
r
to
ol
f
or
s
ol
vi
ng
th
e
r
e
gr
e
s
s
io
n
a
nd
c
la
s
s
if
ic
a
ti
on
pr
obl
e
m
s
.
I
t
de
a
ls
pr
im
a
r
il
y
w
it
h
two
c
la
s
s
c
la
s
s
if
ic
a
ti
on
is
s
ue
s
.
A
hype
r
pl
a
ne
or
li
ne
a
r
li
ne
is
bui
lt
a
s
de
c
is
io
n
bounda
r
y
be
twe
e
n
f
e
a
tu
r
e
da
ta
s
e
ts
of
two
-
c
la
s
s
e
s
f
or
c
la
s
s
if
ic
a
ti
on.
T
he
ne
a
r
e
s
t
f
e
a
tu
r
e
da
t
a
poi
nt
s
to
th
e
hype
r
pl
a
ne
a
r
e
known
a
s
s
uppor
t
ve
c
to
r
s
.
T
he
two
c
la
s
s
da
ta
poi
nt
w
it
h
th
e
s
e
pa
r
a
ti
ng
li
ne
a
r
li
ne
is
de
pi
c
te
d
in
F
ig
ur
e
6.
M
e
a
nw
hi
le
,
s
uppor
t
ve
c
to
r
r
e
gr
e
s
s
io
n
c
a
n
be
e
m
pl
oye
d
to
d
e
te
r
m
in
e
a
f
unc
ti
on
w
hi
c
h
a
ppr
oxi
m
a
te
s
th
e
m
a
ppi
ng
f
unc
ti
on
f
r
om
a
n
in
put
dom
a
in
to
a
not
he
r
dom
a
in
of
r
e
a
l
va
lu
e
s
ba
s
e
d
on
tr
a
in
in
g
da
ta
s
e
t
w
hi
le
m
a
in
ta
in
in
g
a
ll
m
a
in
f
e
a
tu
r
e
s
th
a
t
e
xe
m
pl
if
y
t
he
m
a
xi
m
um
m
a
r
gi
n
m
e
th
od.
I
n
th
is
s
e
c
ti
on,
li
ne
a
r
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
ba
s
e
d t
e
c
hni
que
f
or
c
la
s
s
if
ic
a
ti
on of
s
hunt
f
a
ul
ts
i
n a
S
P
T
S
i
s
di
s
c
us
s
e
d.
F
ig
ur
e
6. L
in
e
a
r
S
V
M
F
or
th
e
pr
ot
e
c
ti
on
two
S
V
M
ha
ve
be
e
n
de
s
ig
ne
d
na
m
e
ly
S
V
M
-
D
a
nd
S
V
M
-
C
to
id
e
nt
if
y
th
e
f
a
ul
t
s
e
c
ti
on i
de
nt
if
ic
a
ti
on a
nd f
a
ul
t
c
la
s
s
if
ic
a
ti
on, r
e
s
pe
c
ti
ve
ly
. T
he
pos
it
iv
e
-
s
e
que
nc
e
c
om
pone
nt
pha
s
e
a
ngl
e
a
nd
H
a
a
r
w
a
ve
le
t
c
ur
r
e
nt
s
is
u
s
e
d
to
s
tu
dy
th
e
f
a
ul
ts
in
a
S
P
T
S
.
T
he
obt
a
in
e
d
s
a
m
pl
e
s
of
th
e
c
ur
r
e
nt
s
a
nd
pos
it
iv
e
-
s
e
que
nc
e
c
om
pone
nt
pha
s
e
a
ngl
e
a
r
e
c
la
s
s
if
ie
d
in
to
la
r
ge
r
a
nge
of
f
r
e
que
nc
ie
s
u
s
in
g
H
a
a
r
w
a
ve
le
t
s
.
A
f
te
r
th
a
t,
f
r
om
th
e
3
rd
le
ve
l
c
o
e
f
f
ic
ie
nt
s
a
r
e
e
xt
r
a
c
t
e
d.
T
h
e
to
ta
l
num
be
r
f
e
a
tu
r
e
s
e
t
s
a
r
e
1
84
f
e
a
t
ur
e
s
.
A
dd
it
i
on
a
ll
y,
to
s
c
a
le
f
e
a
t
ur
e
s
e
t
s
,
nor
m
a
l
iz
a
t
io
n
i
s
c
o
m
pl
e
t
e
d
b
e
tw
e
e
n
-
1
a
n
d
+
1
th
e
r
e
f
or
e
it
c
a
n
a
p
pr
o
pr
i
a
t
e
ly
be
c
om
p
a
r
e
d.
T
h
e
f
e
a
tu
r
e
d
a
ta
i
s
th
e
n
c
r
e
a
t
e
d
f
or
tr
a
in
i
ng
a
s
w
e
l
l
a
s
t
e
s
ti
ng
pr
oc
e
s
s
c
on
s
i
d
e
r
in
g
di
f
f
e
r
e
nt
of
s
im
ul
a
t
e
d
c
ond
it
i
on
s
vi
z
.
f
a
u
lt
ty
pe
s
,
f
a
ul
t
s
e
c
t
io
n
,
th
e
f
a
ul
t
r
e
s
i
s
t
a
n
c
e
, f
a
u
lt
in
s
t
a
nt
,
a
nd f
a
ul
t
di
s
ta
nc
e
.
F
e
w
f
e
a
tu
r
e
s
c
a
nnot
pr
e
di
c
t
th
e
out
put
p
e
r
f
e
c
tl
y
f
r
om
th
e
to
ta
l
f
e
a
tu
r
e
da
ta
s
e
t.
C
ons
e
qu
e
nt
ly
th
e
pr
e
di
c
ti
on
a
c
c
ur
a
c
y
de
c
r
e
a
s
e
s
.
T
hu
s
to
e
nha
nc
e
th
e
a
c
c
ur
a
c
y,
r
e
dunda
nt
f
e
a
tu
r
e
da
ta
a
r
e
r
e
m
ove
d
f
r
om
to
ta
l
f
e
a
tu
r
e
s
e
ts
by
e
m
pl
oyi
ng
f
or
w
a
r
d
f
e
a
tu
r
e
s
e
le
c
ti
on
m
e
th
od
dur
in
g
tr
a
in
in
g.
E
m
pl
oyi
ng
f
e
a
tu
r
e
s
e
le
c
ti
on
te
c
hni
que
,
th
e
to
ta
l
f
e
a
tu
r
e
s
e
ts
to
be
gi
ve
n
to
th
e
S
V
M
is
de
c
r
e
a
s
e
d,
w
hi
c
h
in
tu
r
n
m
a
ke
s
it
f
a
s
t
a
nd
s
im
pl
if
ie
s
th
e
pr
oc
e
s
s
. T
he
opt
im
a
l
f
e
a
tu
r
e
da
ta
s
e
t
w
it
h
th
e
te
s
ti
ng
da
ta
a
r
e
th
e
n
gi
ve
n
to
th
e
tr
a
in
e
d
S
V
M
-
D
a
nd
S
V
M
-
C
te
c
hni
que
f
or
p
r
e
di
c
ti
on
pur
pos
e
.
T
he
out
put
o
f
S
V
M
is
e
it
he
r
‘
0’
or
‘
1’
de
not
in
g
he
a
lt
hy
pha
s
e
or
f
a
ul
te
d
pha
s
e
.
F
or
e
a
c
h
of
th
e
s
e
f
a
ul
ts
,
s
a
m
pl
e
s
of
th
e
pos
it
iv
e
-
s
e
que
nc
e
c
om
pone
nt
pha
s
e
a
ngl
e
f
or
f
ul
l
c
yc
le
dur
a
ti
on
ha
ve
be
e
n
gi
ve
n
a
t
th
e
in
put
s
id
e
of
S
V
M
.
T
he
S
V
M
-
D
r
e
s
ul
ta
nt
out
put
in
di
c
a
te
s
w
he
th
e
r
th
e
c
or
r
e
s
ponding
s
e
c
ti
on
is
in
vol
ve
d
w
it
h
f
a
ul
t
or
not
.
T
he
S
V
M
-
C
r
e
s
ul
ta
nt
out
put
in
di
c
a
te
s
w
he
t
he
r
th
e
c
or
r
e
s
ponding phas
e
i
s
i
nvol
ve
d
w
it
h f
a
ul
t
or
not
.
4.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
T
he
de
v
e
lo
pe
d
s
uppor
t
v
e
c
to
r
m
a
c
hi
ne
(
S
V
M
)
s
ol
ut
io
ns
h
a
ve
be
e
n
te
s
te
d
th
or
oughly
w
it
h
th
e
he
lp
of
M
A
T
L
A
B
pr
ogr
a
m
.
W
he
n
th
e
r
e
is
he
a
lt
hy,
th
e
out
put
of
bot
h
S
V
M
-
D
a
nd
S
V
M
-
C
w
il
l
be
0
va
lu
e
s
.
I
f
f
a
ul
ts
oc
c
ur
,
th
e
S
V
M
-
D
r
e
s
pons
e
s
ta
r
ts
a
dj
us
ti
ng
to
1,
2,
a
nd
3
de
pe
ndi
ng
on
th
e
s
e
c
ti
on
1,
s
e
c
ti
on
2
a
nd
s
e
c
ti
on
3
f
a
ul
ts
,
r
e
s
pe
c
ti
ve
ly
a
nd
S
V
M
-
C
r
e
s
pon
s
e
s
ta
r
ts
a
dj
u
s
t
in
g
to
1
dur
in
g
S
P
T
S
f
a
ul
ts
. T
he
e
n
a
c
tm
e
nt
of
S
V
M
-
D
a
nd
S
V
M
-
C
f
or
s
hunt
f
a
ul
ts
w
it
h
c
ha
ngi
ng
num
e
r
ous
f
a
ul
t
lo
c
a
ti
ons
,
num
e
r
ous
f
a
ul
t
r
e
s
is
ta
nc
e
s
a
nd
num
e
r
ous
f
a
ul
t
ty
pe
s
is
s
um
m
a
r
iz
e
d.
T
he
S
V
M
-
D
a
nd
S
V
M
-
C
r
e
s
pons
e
s
f
or
a
ll
c
a
s
e
s
in
T
a
bl
e
2
a
nd
th
e
r
e
a
c
h
s
e
tt
in
g
a
nd
a
c
c
ur
a
c
y
of
th
e
s
e
c
a
s
e
s
a
r
e
a
bove
99.986
%
.
I
t
is
e
vi
de
nt
th
a
t
th
e
S
V
M
m
e
th
od
pr
ovi
de
s
s
a
ti
s
f
a
c
to
r
y e
na
c
tm
e
nt
of
f
a
ul
te
d l
in
e
di
s
c
r
im
in
a
ti
on, a
nd f
a
ul
ty
pha
s
e
i
de
nt
if
ic
a
ti
on f
or
a
ll
t
he
s
a
m
pl
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Suppor
t
v
e
c
to
r
m
a
c
hi
ne
bas
e
d f
aul
t
s
e
c
ti
on i
de
nt
if
ic
at
io
n and faul
t
c
la
s
s
if
ic
at
io
n …
(
A
. N
ar
e
s
h k
um
ar
)
1023
T
a
bl
e
2 S
V
M
-
D
a
nd S
V
M
-
C
r
e
s
ul
ts
f
or
a
ll
c
a
s
e
s
P
a
r
a
m
e
t
e
r
V
a
r
i
e
d
T
ype
L
(
km
)
F
I
A
(
o
)
R
(
Ω
)
S
e
c
t
i
on
S
V
M
-
D
S
V
M
-
C
A
B
C
D
E
F
G
F
a
ul
t
t
ype
i
s
c
ha
ngi
ng
a
nd
L
, F
I
A
, R
a
nd
S
e
c
t
i
on a
r
e
f
i
xe
d
Ag
21
45
10
1
1
1
0
0
0
0
0
1
Eg
21
45
10
1
1
0
0
0
0
1
0
1
D
F
g
21
45
10
1
1
0
0
0
1
0
1
1
A
B
g
21
45
10
1
1
1
1
0
0
0
0
1
A
B
C
g
21
45
10
1
1
1
1
1
0
0
0
1
A
B
C
D
g
21
45
10
1
1
1
1
1
1
0
0
1
A
B
C
D
E
g
21
45
10
1
1
1
1
1
1
1
0
1
A
B
C
D
E
F
g
21
45
10
1
1
1
1
1
1
1
1
1
L
i
s
c
ha
ngi
ng
a
nd
F
a
ul
t
t
ype
, F
I
A
, R
a
nd S
e
c
t
i
on a
r
e
f
i
xe
d
CD
12
90
30
2
2
0
0
1
1
0
0
0
CD
26
90
30
2
2
0
0
1
1
0
0
0
CD
34
90
30
2
2
0
0
1
1
0
0
0
CD
56
90
30
2
2
0
0
1
1
0
0
0
CD
61
90
30
2
2
0
0
1
1
0
0
0
CD
75
90
30
2
2
0
0
1
1
0
0
0
CD
86
90
30
2
2
0
0
1
1
0
0
0
CD
93
90
30
2
2
0
0
1
1
0
0
0
F
I
A
i
s
c
ha
ngi
ng
a
nd
F
a
ul
t
t
ype
, L
, R
a
nd S
e
c
t
i
on a
r
e
f
i
xe
d
B
F
g
74
5
40
3
3
0
1
0
0
0
1
1
B
F
g
74
50
40
3
3
0
1
0
0
0
1
1
B
F
g
74
120
40
3
3
0
1
0
0
0
1
1
B
F
g
74
160
40
3
3
0
1
0
0
0
1
1
B
F
g
74
200
40
3
3
0
1
0
0
0
1
1
B
F
g
74
240
40
3
3
0
1
0
0
0
1
1
B
F
g
74
290
40
3
3
0
1
0
0
0
1
1
B
F
g
74
330
40
3
3
0
1
0
0
0
1
1
R
i
s
c
ha
ngi
ng
a
nd
L
, F
a
ul
t
t
ype
, F
I
A
a
nd S
e
c
t
i
on a
r
e
f
i
xe
d
D
E
F
92
135
15
1
1
0
0
0
1
1
1
0
D
E
F
92
135
30
1
1
0
0
0
1
1
1
0
D
E
F
92
135
45
1
1
0
0
0
1
1
1
0
D
E
F
92
135
60
1
1
0
0
0
1
1
1
0
D
E
F
92
135
80
1
1
0
0
0
1
1
1
0
D
E
F
92
135
100
1
1
0
0
0
1
1
1
0
D
E
F
92
135
120
1
1
0
0
0
1
1
1
0
D
E
F
92
135
140
1
1
0
0
0
1
1
1
0
S
e
c
t
i
on i
s
c
ha
ngi
ng
a
nd
L
, F
a
ul
t
t
ype
, F
I
A
,
R
a
r
e
f
i
xe
d
A
B
D
E
F
g
68
315
50
1
1
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
2
2
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
3
3
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
1
1
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
2
2
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
3
3
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
2
2
1
1
0
1
1
1
0
A
B
D
E
F
g
68
315
50
3
3
1
1
0
1
1
1
0
5.
C
O
N
C
L
U
S
I
O
N
F
a
ul
t
pr
ot
e
c
ti
on
in
S
P
T
S
is
a
ve
r
y
im
por
ta
nt
is
s
ue
in
no
w
a
d
a
ys
.
A
pr
ot
e
c
ti
v
e
r
e
la
yi
ng
te
c
hni
qu
e
ba
s
e
d
on
S
V
M
is
pr
opos
e
d
in
th
is
pa
p
e
r
w
it
h
r
e
a
c
h
s
e
tt
in
g
up
t
o
99.986
%
in
bot
h
r
e
ve
r
s
e
&
f
or
w
a
r
d
pa
th
s
of
S
P
T
S
.
T
w
o
di
f
f
e
r
e
nt
S
V
M
ha
ve
be
e
n
de
ve
lo
pe
d
f
a
ul
te
d
l
in
e
di
s
c
r
im
in
a
ti
on
a
nd
f
a
ul
ty
pha
s
e
id
e
nt
if
ic
a
ti
on
in
ti
m
e
dom
a
in
.
T
he
po
s
it
iv
e
-
s
e
que
n
c
e
c
om
pone
nt
ph
a
s
e
a
ngl
e
a
nd
H
a
a
r
w
a
ve
le
t
c
ur
r
e
nt
s
a
r
e
pr
e
r
e
qui
s
it
e
f
or
S
V
M
.
I
t
is
w
or
th
y
to
m
e
nt
io
n
he
r
e
th
a
t
th
e
s
ugg
e
s
te
d
S
V
M
of
f
e
r
s
e
xc
e
ll
e
nt
a
c
c
ur
a
c
y
f
or
bot
h
r
e
ve
r
s
e
&
f
or
w
a
r
d
pa
th
s
a
ls
o
us
in
g
onl
y
m
id
dl
e
two
bus
e
s
da
ta
.
F
ur
th
e
r
m
or
e
,
it
s
r
obus
tn
e
s
s
a
ga
in
s
t
num
e
r
ous
f
a
ul
t
lo
c
a
ti
ons
,
num
e
r
ous
f
a
ul
t
r
e
s
is
ta
nc
e
s
a
nd
num
e
r
ous
f
a
ul
t
ty
pe
s
is
a
ls
o
s
tu
di
e
d.
I
t
w
a
s
c
onf
ir
m
e
d
th
a
t
f
or
a
ll
c
a
s
e
s
, t
he
r
e
a
c
h
s
e
tt
in
g of
f
a
ul
t
r
e
la
yi
ng i
s
m
uc
h s
upe
r
io
r
t
o ot
he
r
m
e
th
ods
.
R
E
F
E
R
E
N
C
E
S
[1]
S.
S.
Venkata,
W.
C.
Guyter,
J.
Kondragunta,
and
N.
B.
Butt,
“
EPPC
-
A
computer
program
for
six
-
phas
e
transmission
line
design,”
IEEE
Transactions
on
Power
Apparatus
and
Systems
,
vol.
101,
no.
7
,
pp.
1859
-
1869,
1982
, doi:
10.1109/TPAS.1982.317457.
[2]
J.
R.
Stewar
t,
L.
J.
Oppel,
G.
C.
Thomas,
T.
F.
Dorazio,
and
M.
T.
Br
own,
“
Insulatio
n
coordinatio
n,
environment
al
and
system
analysis
of
existing
double
circuit
line
reco
nfigured
to
six
-
phase
operation,”
IEEE
Transact
ions
on
Power Delivery
, vol. 7, no. 3
,
pp. 1628
-
1633, 1992
, doi:
10.1109/61.141883
.
[3]
L.
Oppel,
and
E.
Krizauskas,
“
Evaluation
of
the
performance
of
line
protection
schemes
on
the
NYS
E
G
six
phase
transmission
system,”
IEEE
Transact
ions
on
Power
Delive
ry
,
vol.
14,
no.
1
,
pp.
110
-
115,
1990
,
doi:
10.1109/61.736697
.
[4]
A.
Apostolov,
and
W.
George,
“
Protec
ting
NYSE
G’s
six
-
phase
trans
mission
line,”
IEEE
computer
applicatio
ns
in
power
,
vol. 5, no. 4
,
pp.
33
-
36, 1992
, doi:
10.1109/67.160044
.
[5]
K.
Ebha,
J.
Anamika,
A.
S.
Thoke,
J.
Abhinav,
and
G.
Subho
jit,
“
Dete
ction
and
classification
of
faults
on
six
ph
ase
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
4
,
D
e
c
e
m
be
r
2021:
1019
-
10
24
1024
transmission
line
using
ANN,”
2011
2nd
International
Conferen
ce
o
n
Computer
and
Communica
tion
Technolog
y
(ICCCT
-
2011)
,
2011, pp.
100
-
103, doi:
10.1109/ICCCT.2011.6075177.
[6]
K.
Ravi,
K.
Ebha,
Y.
Anamika,
and
A.
S.
Thoke,
“
Fault
classific
ation
of
phase
to
phase
fault
in
six
phase
transmission
line
using
haar
wavelet
and
ANN
,”
2014
In
ternatio
nal
Conference
on
Signal
Processing
and
Integrated N
etworks (SP
IN)
,
India,
2014, pp. 5
-
8
, doi:
10.1109/SPIN.2014.6776911
.
[7]
A.
N.
kumar,
and
M.
Chakravarthy,
“
Simultane
ous
fault
classif
ic
ation
and
localiz
ation
scheme
in
six
phas
e
transmission
line
u
sing
artificial
neural
networks,”
Journal
of
Advanced
Research
in
Dynamical
&
Control
Systems,
vol. 10, no. 3
,
pp.
342
-
349, 2018
.
[
8]
A.
Naresh,
and
M.
Chakravarthy,
“
Fuzzy
inference
system
based
dis
tance
estimation
approach
for
multi
lo
catio
n
and
transforming
phase
to
ground
faults
in
six
phase
transmission
li
ne,”
Internati
onal
Journal
of
Computat
ional
Intelligen
ce
Systems
, vol. 11, no. 1, pp. 757
-
769, 2018
, doi:
10.2991/ijcis.11.1.58
.
[9]
G.
Kapoor
and
A.
Yadav,
“
A
Single
-
Terminal
Hybri
d
Scheme
for
Six
-
Pha
se
Transmission
Line
Protection,”
2020
IEEE
International
Conference
on
Power
Electronics,
Drives
and
Energy
Systems
(PEDES)
,
2020,
pp.
1
-
6
,
doi:
10.1109/PEDES49360.2020.9379377
.
[10]
K.
S.
Sunil,
K.
Ebha,
and
G.
Subhojit,
“
A
hybrid
wa
velet
-
APSO
-
ANN
-
based
protection
scheme
for
six
-
phase
transmission
line
with
real
-
time
validation,
”
Neural
Computing
and
Applications
,
vol.
31,
pp.
5751
-
5765
,
2018,
doi:
1
0.1007/s00521
-
018
-
3400
-
x.
[11]
K.
S.
Sunil,
K.
Ebha,
G.
Subhojit,
and
K.
M.
Dusmanta,
“
Enhancing
the
reliability
of
six
phase
transmission
line
protection
using
power
quality
inform
atics
with
real
time
validatio
n,”
Internati
onal
Transact
io
ns
on
Electrical
Energy Systems
,
vol. 29, no. 9,
2019,
Art. no. e12048,
doi:
10.1002/2050
-
703
8.12048.
[12]
K. Ebha, Y. Anamika,
and
S. T. A
niruddh
a,
“
A new single
-
ended arti
f
icial neu
ral networ
k
-
based protection schem
e
for
shunt
faults
in
six
-
phase
transmission
line,”
Internati
onal
Transa
ctions
on
Electrical
Energy
S
ystems,
vol.
25,
no. 7, pp. 12
57
-
1280, 2015
, doi:
10.1002/etep.1901
.
[13]
K.
Ebha,
V.
Khushaboo,
and
G.
Subhojit,
“
An
improved
fault
detec
tion
classification
and
fault
location
scheme
based
on
wavelet
transform
and
artificial
neural
networks
for
six
p
hase
transmission
line
using
single
end
data
only,”
Springer Plus,
vol. 4,
2015
,
Art.
No
. 551,
doi:
10.1186/s40064
-
015
-
1342
-
7
.
[14]
K.
Mishra,
and
A.
Yadav,
“
A
single
ended
fuzzy
based
directi
onal
relaying
scheme
for
transmission
line
compen
sated
by
fixed
series
capacitor,”
Internati
onal
Conference
on
Intelligen
t
Systems
Design
and
Applicati
ons
,
vol. 941,
2020, pp. 749
-
759
, doi:
10.1007/978
-
3
-
030
-
16660
-
1_73
.
[15]
A.
N.
kumar,
Ch
Sanjay,
and
M.
Chakravarthy,
“
A
single
-
end
directional
relaying
scheme
for
double
-
circuit
transmis
sion
line
using
fuzzy
expert
system,”
Complex
and
Intell
igent
Systems
,
vol.
6,
pp.
335
-
346
,
2020
,
doi:
10.1007/s40747
-
020
-
00131
-
w.
[16]
S.
R.
Samantaray,
“
Decision
tree
-
based
fault
zone
identificatio
n
and
fault
classification
in
flexible
AC
transm
issions
-
based
transmission
line,”
IET
Generation,
Transmission
and
Distributi
on
,
vol.
3,
no.
5
,
pp.
425
-
436
,
2009
, doi:
10.1049/iet
-
gtd.2008.0316.
[17]
Y.
Anamika,
D.
Yajnaseni,
and
V.
Ashok,
“
ANN
based
directional
r
elaying
scheme
for
protection
of
korba
-
bhila
i
transmis
sion
line
of
chhattisgarh
state,”
Protection
and
Control
of
M
odern
Power
Systems
,
vol.
1,
no.
1,
pp.
1
-
17,
2016
, doi:
10.1186/s41601
-
016
-
0029
-
6
.
[18]
K.
Ebha,
V.
Khushaboo,
and
G.
Subhojit,
“
A
modular
neuro
-
wavelet
based
non
-
unit
protection
scheme
for
zone
identifica
tion
and
fault
location
in
six
phase
transmission
line,”
Neura
l
Computing
and
A
pplications
,
vol.
28,
no.
6,
pp. 1369
-
1385, 2017
, doi:
10.1007/s00521
-
016
-
2566
-
3.
[19]
A
. N.
kumar
, Ch. Sanjay,
and
M. Chakravarthy
,
“
Mamdani fuzzy
expert system ba
sed directional r
elaying approa
ch
for
six
phase
transmission
line,”
Internati
onal
Journal
of
Interactive
Multimedia
and
Artifici
al
Intelligence
,
vol.
6,
no. 1, pp. 41
-
50,
2020
, doi:
10.9781/ijimai.2019.06.002.
[20]
P.
K.
Dash,
S.
R.
Samant
aray,
and
G.
Panda,
“
Fault
classification
an
d
section
identification
of
an
advanced
series
compensat
ed
transmi
ssion
li
ne
using
support
vector
machine,”
IEE
E
Transactions
on
Power
Delivery
,
vol.
22,
pp. 67
-
73, 2007
, doi:
10.1109/TPWRD.2006.876695.
[21]
S.
Aleena,
and
Y.
Anamika,
“
Directional
relaying
using
support
vector
machine
for
double
circuit
transmission
lines
including
cross
-
c
ountry
and
inter
-
circuit
faults,”
Internati
ona
l
Journal
of
Electrical
Power
and
En
ergy
Systems,
vol.
81, pp. 254
-
264, 2016
, doi:
10.1016/j.ijepes.2016.02.034.
[22]
P.
Ray,
S.
R.
Arya,
and
D.
P.
Mishra,
“
Intelligen
ce
Scheme
for
fault
l
ocation
in
a
combined
overhead
trans
mission
line
&underground
cable,”
Internati
onal
Journal
of
Emerging
Electric
Power
Systems
,
vol.
19,
no.
5
,
pp.
1
-
18,
2018
, doi: 10.1515/ijeeps
-
2017
-
0277.
[23]
D.
P.
Mishra,
and
P.
Ray,
“
Fault
detection,
location
and
classi
ficatio
n
of
a
transmission
line,”
Neural
Computing
and Applic
ations
,
vol. 30, no. 5, 1377
-
1424, 2018
, doi:
10.1007/s00521
-
017
-
3295
-
y
.
[24]
P.
Ray,
and
D.
P.
Mishra,
“
Support
vector
machine
-
based
fault
class
ification
and
location
of
a
long
transmissio
n
lin
e,”
Engineering
Science
and
Technology,
an
Internation
al
Journa
l,
vol.
19,
no.
3,
pp.
1368
-
1380,
2016
,
doi:
10.1016/j.jestch.2016.04.001
.
[25]
P.
Ray,
and
D.
P.
Mishra,
“
Application
of
extreme
learning
mac
hine
for
u
nderground
cable
fault
location,”
Internati
onal
Transact
ions
on
Electrical
Energy
Systems
,
vol.
25,
no.
12
,
pp.
3227
-
3247,
2015
,
doi:
10.1002/etep.2032
.
Evaluation Warning : The document was created with Spire.PDF for Python.