I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
,
p
p
.
1
~1
2
I
SS
N:
2252
-
8938
1
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
AI
Cla
ss
ificatio
n of
Po
w
er Q
ua
lity Ev
ents Using
Wa
v
elet
a
na
ly
sis
a
nd P
ro
ba
bilistic
neura
l Ne
tw
o
rk
P
a
m
pa
Si
nh
a
*
,
S
ud
ipta
Deb
a
t
h
**
,
Sw
a
pa
n
K
u
m
a
r
G
o
s
w
a
m
i
**
*
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Ne
taji
S
u
b
h
a
sh
E
n
g
in
e
e
rin
g
Co
ll
e
g
e
,
T
e
c
h
n
o
c
it
y
,
G
a
ria
**
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Ja
d
a
v
p
u
r
Un
iv
rsity
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
4
,
2
0
1
5
R
ev
i
s
ed
Feb
7
,
2
0
1
6
A
cc
ep
ted
Feb
2
5
,
2
0
1
6
P
o
w
e
r
q
u
a
li
ty
stu
d
ies
h
a
v
e
b
e
c
o
m
e
a
n
im
p
o
rtan
t
issu
e
d
u
e
t
o
w
id
e
sp
re
a
d
u
se
o
f
se
n
siti
v
e
e
le
c
tro
n
ic
e
q
u
i
p
m
e
n
t
in
p
o
w
e
r
s
y
ste
m
.
T
h
e
so
u
rc
e
s
o
f
p
o
w
e
r
q
u
a
li
ty
d
e
g
ra
d
a
ti
o
n
m
u
st
b
e
in
v
e
stig
a
t
e
d
in
o
rd
e
r
to
im
p
ro
v
e
th
e
p
o
w
e
r
q
u
a
li
ty
.
S
w
it
c
h
in
g
tran
sie
n
ts
in
p
o
w
e
r
s
y
ste
m
s
is
a
c
o
n
c
e
rn
in
stu
d
ies
o
f
e
q
u
ip
m
e
n
t
in
su
latio
n
c
o
o
r
d
i
n
a
ti
o
n
.
I
n
t
h
is
p
a
p
e
r
a
w
a
v
e
l
e
t
b
a
se
d
n
e
u
ra
l
n
e
tw
o
rk
h
a
s
b
e
e
n
i
m
p
le
m
e
n
ted
to
c
las
sify
th
e
tran
sie
n
ts
d
u
e
to
c
a
p
a
c
it
o
r
sw
it
c
h
in
g
,
m
o
to
r
sw
it
c
h
in
g
,
f
a
u
lt
s,
c
o
n
v
e
rter
a
n
d
tran
sf
o
r
m
e
r
s
w
it
c
h
in
g
.
T
h
e
d
e
tail
re
a
c
ti
v
e
p
o
w
e
rs
f
o
r
th
e
se
f
iv
e
tran
sie
n
ts
a
re
d
e
ter
m
in
e
d
a
n
d
a
m
o
d
e
l
w
h
ich
u
se
s
th
e
d
e
tail
re
a
c
ti
v
e
p
o
w
e
r
a
s
th
e
in
p
u
t
to
t
h
e
P
ro
b
a
b
il
i
stic
n
e
u
ra
l
n
e
tw
o
rk
(P
NN
)
is
se
t
u
p
t
o
c
la
ss
ify
th
e
a
b
o
v
e
m
e
n
ti
o
n
e
d
tran
s
ien
ts.
T
h
e
sim
u
latio
n
h
a
s
b
e
e
n
e
x
e
c
u
ted
f
o
r
a
n
1
1
k
v
d
istri
b
u
ti
o
n
sy
ste
m
.
W
it
h
th
e
h
e
lp
o
f
n
e
u
ra
l
n
e
tw
o
rk
c
las
si
f
ier,
th
e
tr
a
n
sie
n
t
sig
n
a
ls
a
re
e
ff
e
c
ti
v
e
l
y
c
la
ss
if
ied
.
K
ey
w
o
r
d
:
Deta
il R
ea
cti
v
e
P
o
w
er
s
,
P
o
w
er
S
y
s
te
m
,
P
r
o
b
ab
ilis
tic
Neu
r
al
Net
w
o
r
k
.
S
w
itc
h
in
g
-
T
r
an
s
ien
t
s
,
W
av
elet
Dec
o
m
p
o
s
itio
n
Co
p
y
rig
h
t
©
2
0
1
6
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
am
p
a
Si
n
h
a
,
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t
,
Ne
taji
S
u
b
h
a
sh
E
n
g
in
e
e
rin
g
Co
ll
e
g
e
,
T
e
c
h
n
o
c
it
y
,
Ga
ria.
Ko
lk
a
ta
-
7
0
0
1
5
2
,
E
m
ail:
p
a
m
p
a.
s
in
h
a.
ee
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Dete
ctio
n
an
d
clas
s
if
icatio
n
o
f
tr
an
s
ien
t
s
ig
n
al
s
h
a
v
e
r
ec
en
tl
y
b
ec
o
m
e
a
n
ac
tiv
e
r
esear
ch
t
o
p
ic
in
th
e
ar
ea
o
f
p
o
w
er
q
u
alit
y
a
n
al
y
s
is
[
1
-
5
]
.
I
n
[
6
-
7
]
th
e
a
u
t
h
o
r
s
h
av
e
p
r
o
p
o
s
ed
a
m
et
h
o
d
to
class
i
f
y
th
e
p
o
w
er
s
y
s
te
m
tr
an
s
ien
ts
b
ased
o
n
d
u
al
tr
ee
co
m
p
lex
w
a
v
e
let
tr
a
n
s
f
o
r
m
(
DT
C
W
T
)
.
B
u
t in
t
h
i
s
m
e
th
o
d
co
m
p
u
tatio
n
a
l
co
m
p
le
x
it
y
is
v
er
y
h
ig
h
.
P
o
w
er
tr
an
s
ien
t
s
o
cc
u
r
f
r
o
m
v
a
r
iet
y
o
f
d
is
t
u
r
b
an
ce
s
o
n
t
h
e
p
o
w
er
s
y
s
te
m
li
k
e,
ca
p
ac
ito
r
b
an
k
s
w
itc
h
in
g
,
d
i
f
f
er
en
t
t
y
p
e
s
o
f
f
au
lts
,
co
n
v
er
te
r
s
an
d
d
i
f
f
er
en
t
ap
p
ar
atu
s
s
w
i
tch
i
n
g
.
I
n
o
r
d
er
to
i
m
p
r
o
v
e
t
h
e
p
o
w
er
q
u
alit
y
,
t
h
e
lo
ca
tio
n
o
f
s
u
c
h
d
is
t
u
r
b
an
ce
s
m
u
s
t
b
e
id
en
ti
f
ied
.
T
ec
h
n
iq
u
e
s
li
k
e
w
a
v
elet
tr
an
s
f
o
r
m
s
,
m
at
h
e
m
a
tical
m
o
r
p
h
o
lo
g
y
etc
h
a
v
e
b
ee
n
u
s
ed
to
id
en
tify
t
h
e
m
[
5
-
7
]
.
W
a
v
elet
an
al
y
s
is
,
ca
n
ex
tr
ac
t
t
h
e
ess
e
n
tial
f
ea
t
u
r
es
o
f
tr
an
s
ie
n
t
s
i
g
n
al
ef
f
ec
t
iv
el
y
f
o
r
its
class
i
f
icatio
n
.
W
ith
t
h
e
s
e
f
ea
t
u
r
es
as
i
n
p
u
t
s
to
th
e
n
eu
r
al
n
et
w
o
r
k
,
cla
s
s
i
f
icatio
n
o
f
th
e
s
w
itc
h
i
n
g
tr
an
s
ien
ts
,
s
h
o
r
t
cir
c
u
it
f
a
u
lt,
p
r
im
ar
y
ar
c,
li
g
h
tn
in
g
d
is
tu
r
b
an
ce
a
n
d
li
g
h
t
n
i
n
g
s
tr
i
k
e
f
au
lt
is
p
o
s
s
ib
le
[
8
]
.
A
u
th
o
r
s
o
f
p
ap
er
[
9
]
h
av
e
p
r
o
p
o
s
ed
a
d
is
cr
ete
w
av
ele
t
tr
an
s
f
o
r
m
(
DW
T
)
b
ased
o
n
m
u
ltire
s
o
l
u
tio
n
a
n
al
y
s
i
s
tech
n
iq
u
e
an
d
p
ar
s
ev
al
’
s
t
h
eo
r
e
m
w
h
ich
is
e
m
p
lo
y
ed
to
ex
tr
ac
t
t
h
e
en
er
g
y
d
is
tr
ib
u
tio
n
f
ea
tu
r
es
o
f
tr
a
n
s
ie
n
t
s
ig
n
al
at
d
if
f
er
en
t
r
eso
l
u
tio
n
lev
e
ls
.
P
r
o
b
ab
ilis
tic
n
e
u
r
al
n
et
w
o
r
k
(
P
NN)
clas
s
if
ies
t
h
e
ex
tr
ac
ted
f
ea
t
u
r
es
to
id
en
ti
f
y
t
h
e
d
is
t
u
r
b
an
ce
t
y
p
e.
I
n
p
a
p
er
[
1
0
]
a
d
is
cr
ete
w
a
v
elet
tr
a
n
s
f
o
r
m
an
d
m
u
lti
f
r
ac
tal
an
al
y
s
is
b
ased
o
n
a
v
ar
ian
ce
d
i
m
e
n
s
io
n
tr
aj
ec
to
r
y
te
ch
n
iq
u
e
h
a
v
e
b
ee
n
u
s
ed
as
to
o
ls
to
a
n
al
y
ze
th
e
tr
an
s
i
e
n
ts
f
o
r
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
.
A
p
r
o
b
ab
ilis
tic
n
e
u
r
al
n
e
t
w
o
r
k
is
u
s
ed
as
a
class
i
f
ier
f
o
r
clas
s
i
f
icatio
n
o
f
tr
an
s
ie
n
t
s
as
s
o
ciate
d
w
it
h
p
o
w
er
s
y
s
te
m
f
au
lts
an
d
s
w
itc
h
i
n
g
.
T
h
e
a
u
t
h
o
r
s
o
f
p
ap
er
[
1
1
]
p
r
esen
ted
DW
T
-
FF
T
b
ased
in
teg
r
ated
ap
p
r
o
ac
h
f
o
r
d
etec
tio
n
a
n
d
clas
s
i
f
ica
tio
n
o
f
v
ar
io
u
s
P
Q
d
is
tu
r
b
an
ce
s
w
i
th
a
n
d
w
it
h
o
u
t
n
o
is
y
en
v
ir
o
n
m
e
n
t.
I
b
r
ah
i
m
a
n
d
Mo
r
co
s
[
1
2
]
h
av
e
g
iv
e
n
a
s
u
r
v
e
y
o
f
ar
ti
f
icial
in
telli
g
e
n
ce
tec
h
n
iq
u
e
f
o
r
p
o
w
er
q
u
a
lit
y
,
w
h
ic
h
i
n
cl
u
d
es
f
u
zz
y
lo
g
ic,
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
ANN)
an
d
g
en
et
ic
al
g
o
r
i
th
m
.
W
av
elet
b
ased
o
n
li
n
e
d
is
t
u
r
b
an
ce
d
ete
ctio
n
f
o
r
p
o
w
er
q
u
alit
y
ap
p
li
ca
tio
n
s
h
a
v
e
b
ee
n
d
is
cu
s
s
ed
in
[
1
3
]
.
P
er
u
n
icic
et
al.
[
1
4
]
u
s
ed
w
a
v
elet
co
ef
f
icien
t
s
o
f
d
is
cr
ete
w
a
v
elet
tr
a
n
s
f
o
r
m
(
DW
T
)
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
–
12
2
in
p
u
t
s
o
f
a
s
el
f
o
r
g
an
izi
n
g
m
ap
p
in
g
n
e
u
r
al
n
et
w
o
r
k
to
id
en
t
i
f
y
D
C
b
ias,
h
ar
m
o
n
ics,
v
o
ltag
e
s
a
g
s
an
d
o
th
e
r
tr
an
s
ie
n
t
d
i
s
tu
r
b
a
n
ce
s
.
E
l
m
it
wall
y
e
t
al.
[
1
5
]
h
a
v
e
p
r
o
p
o
s
ed
a
m
et
h
o
d
i
n
w
h
ic
h
w
a
v
elet
co
ef
f
icien
ts
ar
e
u
s
ed
as
in
p
u
t
s
to
th
e
n
e
u
r
o
-
f
u
zz
y
s
y
s
te
m
s
f
o
r
class
i
f
y
i
n
g
v
o
ltag
e
s
ag
,
s
w
ell,
i
n
ter
r
u
p
tio
n
,
i
m
p
u
ls
e,
v
o
l
tag
e
f
lic
k
er
,
h
ar
m
o
n
ic
an
d
f
lat
-
to
p
p
ed
w
a
v
es.
C
h
an
g
a
n
d
W
en
q
u
a
n
g
[
1
6
]
an
al
y
ze
d
t
h
e
e
f
f
ec
t
o
f
tr
a
n
s
i
en
ts
ar
i
s
in
g
d
u
e
to
u
tili
t
y
ca
p
ac
ito
r
s
w
itc
h
in
g
o
n
m
a
s
s
r
ap
id
tr
an
s
ie
n
t.
L
i
u
et
al
.
[
1
7
]
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
t
h
e
DW
T
co
ef
f
icie
n
t
s
o
f
s
o
m
e
t
y
p
ical
p
o
w
er
t
r
an
s
ie
n
ts
u
s
i
n
g
s
ca
lo
g
r
a
m
.
I
n
[
1
8
]
th
e
au
th
o
r
s
h
av
e
p
r
o
p
o
s
ed
a
n
o
v
el
m
et
h
o
d
f
o
r
id
en
ti
f
y
in
g
,
ch
a
r
ac
ter
izin
g
a
n
d
tr
ac
k
i
n
g
g
r
o
u
n
d
ed
ca
p
ac
ito
r
b
an
k
s
co
n
n
ec
ted
to
a
p
o
w
er
d
is
tr
ib
u
tio
n
li
n
e
in
a
co
s
t
ef
f
e
ctiv
e
m
a
n
n
er
.
B
eg
et
al
.
[
1
9
]
p
r
o
p
o
s
ed
a
s
im
p
le
m
et
h
o
d
b
a
s
ed
o
n
DW
T
an
d
a
m
u
lti
-
la
y
er
f
ee
d
f
o
r
w
ar
d
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
f
o
r
cla
s
s
if
icatio
n
o
f
ca
p
ac
ito
r
,
lo
ad
s
witch
i
n
g
a
n
d
li
n
e
to
g
r
o
u
n
d
f
au
lt.
I
n
th
is
m
eth
o
d
s
u
cc
es
s
r
ate
is
9
7
.
4
7
%.
T
o
id
en
tify
t
h
e
t
y
p
e
o
f
tr
a
n
s
ie
n
t
th
e
f
ir
s
t
s
tep
is
to
ex
tr
ac
t
th
e
f
ea
t
u
r
e
o
f
th
e
tr
a
n
s
ie
n
t
s
i
g
n
al.
T
h
ese
f
ea
t
u
r
es
ar
e
u
s
ed
as
i
n
p
u
t
to
a
class
i
f
ier
f
o
r
class
if
ica
tio
n
.
T
h
e
P
r
o
b
ab
ilis
tic
n
e
u
r
al
n
et
w
o
r
k
(
P
NN)
is
u
s
ed
as
a
class
i
f
ier
i
n
[
2
0
-
2
9
]
.
Pro
b
a
b
ilis
tic
n
eu
r
al
n
et
w
o
r
k
co
m
b
in
es
s
o
m
e
o
f
th
e
b
e
s
t
attr
ib
u
te
s
o
f
s
tati
s
tical
p
at
ter
n
r
ec
o
g
n
itio
n
a
n
d
f
ee
d
-
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
s
.
T
h
er
ef
o
r
e,
th
e
P
NN
is
ch
o
s
e
n
as
a
p
r
o
p
er
class
if
ier
o
f
tr
an
s
ie
n
ts
s
i
g
n
als.
I
n
[
3
0
]
h
av
e
s
h
o
w
n
w
a
v
elet
b
a
s
ed
r
ea
cti
v
e
p
o
w
er
co
m
p
u
ta
tio
n
r
es
u
lt
i
n
g
f
r
o
m
9
0
°
p
h
a
s
e
s
h
i
f
t
n
et
w
o
r
k
s
w
h
ich
g
iv
e
s
th
e
r
ea
ctiv
e
p
o
w
er
is
s
h
o
w
n
.
W
av
elet
tr
an
s
f
o
r
m
h
as
b
ee
n
u
s
e
d
to
r
ef
o
r
m
u
late
t
h
e
n
e
w
l
y
d
ef
in
ed
p
o
w
er
co
m
p
o
n
en
ts
[
3
1
]
.
W
av
elet
an
a
l
y
s
is
is
ab
le
to
ex
tr
ac
t
t
h
e
f
ea
t
u
r
es
o
f
d
ata,
b
r
ea
k
d
o
wn
p
o
in
ts
an
d
d
is
co
n
t
in
u
itie
s
v
er
y
ef
f
ec
t
iv
el
y
.
T
h
e
p
r
esen
t
p
ap
er
atte
m
p
ts
to
class
i
f
y
t
h
e
d
if
f
er
en
t
t
y
p
es
o
f
tr
an
s
ie
n
ts
s
u
c
h
a
s
ca
p
ac
ito
r
s
w
itc
h
in
g
,
m
o
to
r
s
w
i
tch
i
n
g
,
d
if
f
er
e
n
t
f
a
u
lt
in
d
u
ce
d
tr
an
s
ie
n
ts
,
co
n
v
er
ter
an
d
tr
an
s
f
o
r
m
er
in
r
u
s
h
u
s
in
g
a
s
i
m
p
le
P
NN
b
ased
tech
n
iq
u
e.
T
o
ex
tr
ac
t u
n
iq
u
e
f
ea
tu
r
e
o
f
ea
c
h
tr
an
s
ie
n
ts
f
ir
s
t d
i
s
cr
ete
w
a
v
elet
tr
a
n
s
f
o
r
m
(
DW
T
)
h
as b
ee
n
p
er
f
o
r
m
ed
to
ca
lc
u
late
t
h
e
d
etail
r
ea
ctiv
e
p
o
w
er
at
lev
el
1
an
d
3
.
A
s
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
h
as
t
h
e
ca
p
ab
ilit
y
to
s
i
m
u
late
t
h
e
lea
r
n
in
g
p
r
o
ce
s
s
an
d
w
o
r
k
as
a
class
i
f
ier
,
p
r
o
b
ab
ilis
tic
n
eu
r
al
n
et
w
o
r
k
h
a
s
b
ee
n
u
s
ed
to
clas
s
i
f
y
th
e
m
e
n
t
io
n
e
d
tr
an
s
ie
n
t
d
is
t
u
r
b
an
ce
s
an
d
i
t
h
as
b
ee
n
s
h
o
w
n
t
h
at
t
h
is
s
i
n
g
le
p
o
in
t
s
tr
ate
g
y
is
v
er
y
e
f
f
ec
tiv
e
i
n
clas
s
i
f
y
in
g
t
h
e
d
if
f
er
e
n
t tr
an
s
ien
t si
g
n
al
s
.
2.
WAVE
L
E
T
T
RANSF
O
RM
B
ASE
D
D
E
T
A
I
L
R
E
AC
T
I
V
E
P
O
WE
R
T
h
is
s
ec
tio
n
r
ed
ef
i
n
es
p
o
w
er
co
m
p
o
n
e
n
t
s
d
ef
i
n
it
io
n
s
co
n
ta
in
ed
in
I
E
E
E
Stan
d
ar
d
1
4
5
9
-
2
0
0
0
[
3
1
]
f
o
r
s
i
n
g
le
p
h
a
s
e
s
y
s
te
m
u
n
d
er
n
o
n
s
i
n
u
s
o
id
al
s
it
u
atio
n
s
.
C
o
n
s
id
er
th
e
f
o
llo
w
i
n
g
s
i
n
u
s
o
id
al
an
d
n
o
n
s
i
n
u
s
o
id
al
v
o
ltag
e
a
n
d
cu
r
r
en
t
w
av
e
f
o
r
m
s
:
T
ab
les
an
d
Fig
u
r
es
ar
e
p
r
esen
ted
ce
n
ter
,
as
s
h
o
w
n
b
el
o
w
an
d
cited
in
th
e
m
an
u
s
cr
ip
t.
v
1
=
√
s
in
(
ω
t
-
α
1
)
,
i
1
=
√
s
in
(
ω
t
-
α
1
)
,
(
1
)
v
H=
)
s
i
n
(
1
2
h
t
h
h
V
h
(
2
)
i
H=
)
s
i
n
(
1
2
h
t
h
h
I
h
(
3
)
W
h
er
e,
v
1
,
i
1
r
ep
r
esen
t
p
o
w
e
r
s
y
s
te
m
f
r
eq
u
e
n
c
y
co
m
p
o
n
e
n
ts
(
ω
=2
π
f
=1
0
0
π
r
ad
/s
ec
)
w
h
ile
v
H
,
i
H
r
ep
r
esen
t
th
e
to
tal
h
ar
m
o
n
ic
v
o
ltag
e
an
d
cu
r
r
en
t
co
m
p
o
n
e
n
t
s
,
α
1
a
n
d
β
1
r
ep
r
esen
t
th
e
f
u
n
d
a
m
en
tal
v
o
lta
g
e
an
d
cu
r
r
en
t
p
h
ase
a
n
g
le,
r
esp
ec
ti
v
el
y
,
w
h
ile
an
d
r
ep
r
esen
t
in
d
iv
id
u
al
h
ar
m
o
n
ic
v
o
lta
g
e
a
n
d
cu
r
r
en
t
p
h
ase
an
g
le
r
esp
ec
ti
v
el
y
.
T
h
e
R
MS
v
al
u
es o
f
v
o
lta
g
e
an
d
cu
r
r
en
t a
r
e
dt
v
t
V
t
T
0
2
V
H
V
V
t
2
2
1
2
1
2
2
h
V
h
V
H
(
4
)
dt
i
t
I
t
T
0
2
I
H
I
I
t
2
2
1
2
1
2
2
h
I
h
I
H
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
la
s
s
i
fica
tio
n
o
f P
o
w
er Qu
a
lity E
ve
n
ts
Usi
n
g
W
a
ve
let
a
n
a
lysi
s
a
n
d
P
r
o
b
a
b
ilis
tic
….
(
P
a
mp
a
S
in
h
a
)
3
W
h
er
e
T
i
s
t
h
e
ti
m
e
p
er
io
d
.
T
h
e
r
ea
cti
v
e
p
o
w
er
a
s
p
r
o
p
o
s
ed
in
[
3
0
]
is
m
ea
s
u
r
ed
w
h
er
e
v
t
-
90°
an
d
i
t
ar
e
th
e
v
o
ltag
e
an
d
cu
r
r
en
t
s
i
g
n
als.
v
t
-
90°
is
o
b
tain
ed
b
y
in
tr
o
d
u
cin
g
a
9
0
°
p
h
ase
lag
at
ea
ch
f
r
eq
u
en
c
y
o
v
er
its
r
an
g
e.
I
f
v
t
-
90°
an
d
i
t
ar
e
p
er
io
d
ic
s
ig
n
als
w
ith
t
i
m
e
p
er
io
d
T
,
t
h
en
r
ea
cti
v
e
p
o
w
er
Q
is
g
i
v
en
as
T
t
t
dt
v
i
T
Q
o
0
90
1
(
6
)
I
n
w
a
v
elet
d
o
m
a
in
t
h
e
to
tal
r
ea
ctiv
e
p
o
w
er
(
Q)
is
d
ef
i
n
ed
as
Q
=
Q
app
+
Q
det
[
2
4
]
(
7
)
W
h
er
e
Q
app
is
th
e
ap
p
r
o
x
i
m
ati
o
n
r
ea
ctiv
e
p
o
w
er
an
d
Q
det
i
s
t
h
e
d
etails r
ea
cti
v
e
p
o
w
er
.
Q
det
is
d
ef
i
n
ed
as
Q
det
=
∑
∑
[
2
3
]
(
8
)
W
h
er
e,
j
0
is
s
ca
li
n
g
lev
e
l,
th
e
v
o
lta
g
e
an
d
c
u
r
r
en
t
s
i
g
n
al
s
a
r
e
d
ig
itized
w
it
h
n
=0
,
1
,
-
-
-
2
P
-
1
,
d
j,
k
i
s
w
a
v
elet
co
ef
f
icie
n
t
o
f
c
u
r
r
en
t
an
d
d
"
j
,
k
is
t
h
e
co
ef
f
icien
t
o
f
v
o
ltag
e
w
it
h
9
0
°
p
h
ase
s
h
i
f
t
at
w
a
v
elet
le
v
el
j
an
d
ti
m
e
k
.
3.
CALCU
L
A
T
I
O
N
O
F
DE
T
A
I
L
R
E
AC
T
I
V
E
P
O
WE
R
I
N
A
RADIA
L
DI
ST
R
I
B
UT
I
O
N
SYST
E
M
A
r
ad
ial
d
is
tr
ib
u
tio
n
n
e
t
w
o
r
k
is
s
h
o
w
n
i
n
Fi
g
.
1
.
T
h
e
f
u
n
d
a
m
en
tal
f
r
eq
u
e
n
c
y
i
n
ter
n
a
l
i
m
p
ed
an
ce
o
f
th
e
v
o
lta
g
e
s
o
u
r
ce
Z
S
is
co
n
s
id
er
ed
to
b
e
(
0
.
5
+
j
0
.
5
)
Ω
an
d
th
e
li
n
e
i
m
p
ed
an
ce
is
(
1
+j
1
)
Ω
f
o
r
ea
c
h
s
ec
tio
n
.
T
h
e
f
u
n
d
a
m
en
tal
f
r
eq
u
e
n
c
y
i
m
p
ed
a
n
ce
o
f
ea
ch
lo
ad
v
iz.
Z
1
,
Z
2
,
Z
3
,
Z
4
an
d
Z
5
is
(
3
0
0
+
j
3
0
0
)
Ω
w
h
e
n
all
th
e
lo
ad
s
ar
e
lin
ea
r
.
T
r
an
s
f
o
r
m
er
,
ca
p
ac
ito
r
,
m
o
to
r
an
d
co
n
v
e
r
ter
h
av
e
b
ee
n
co
n
n
ec
ted
w
i
th
ti
m
e
co
n
tr
o
lled
s
w
itc
h
to
ea
ch
b
u
s
to
g
et
d
etail
r
ea
ctiv
e
p
o
w
er
u
n
d
er
d
if
f
er
en
t
t
r
an
s
ie
n
t
co
n
d
itio
n
s
.
E
M
T
P
s
i
m
u
latio
n
p
ac
k
ag
e
h
as
b
ee
n
u
s
ed
to
ca
p
tu
r
e
in
s
ta
n
tan
eo
u
s
v
o
lta
g
e
an
d
cu
r
r
en
t
s
i
g
n
als.
T
h
e
v
o
lta
g
e
an
d
cu
r
r
en
t
s
i
g
n
al
h
av
e
b
ee
n
p
r
o
ce
s
s
ed
an
d
a
n
al
y
ze
d
u
s
i
n
g
d
is
cr
ete
w
av
e
let
tr
an
s
f
o
r
m
(
DW
T
)
in
MA
T
L
A
B
.
An
1
1
k
v
d
is
tr
ib
u
tio
n
s
y
s
te
m
is
s
t
u
d
ied
i
n
t
h
is
p
ap
er
an
d
its
E
MT
P
m
o
d
el
is
s
et
u
p
as
s
h
o
w
n
i
n
Fig
.
1
.
A
ll
t
h
e
i
n
p
u
t
s
i
g
n
a
ls
ar
e
g
en
er
ated
w
i
th
1
2
8
s
a
m
p
le
s
p
er
cy
cle.
I
t
s
r
ec
o
r
d
in
g
ti
m
e
is
0
.
1
s
ec
o
n
d
an
d
h
en
ce
s
a
m
p
li
n
g
f
r
eq
u
e
n
c
y
o
f
t
h
e
s
i
g
n
al
i
s
6
.
4
k
Hz.
R
ef
er
en
c
e
f
r
eq
u
en
c
y
i
s
5
0
Hz.
T
h
er
e
a
r
e
v
ar
io
u
s
t
y
p
es
o
f
m
o
th
er
w
a
v
elet
s
f
o
r
s
ig
n
al
p
r
o
ce
s
s
in
g
b
u
t
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
m
o
t
h
er
w
a
v
elet
i
s
Da
u
b
ec
h
ie
s
[
3
6
]
w
h
ich
h
as
b
ee
n
u
s
ed
to
d
etec
t
an
d
c
h
ar
ac
ter
ize
p
o
w
er
tr
an
s
ien
ts
.
So
th
e
au
th
o
r
s
h
av
e
u
s
ed
d
au
b
ec
h
ies
w
a
v
elet
w
it
h
f
o
u
r
f
ilter
co
ef
f
ic
ien
t
s
(
d
b
4
)
f
o
r
tr
an
s
ien
t
an
al
y
s
is
.
S
i
m
u
lat
i
o
n
o
f
f
i
v
e
t
y
p
e
s
o
f
tr
an
s
ien
t
s
i
s
ca
r
r
ied
o
u
t
in
th
is
n
et
w
o
r
k
.
T
h
e
y
ar
e
ca
p
ac
ito
r
s
w
itc
h
i
n
g
,
co
n
v
er
ter
s
w
itc
h
in
g
,
m
o
to
r
s
w
itc
h
i
n
g
,
f
au
l
t
an
d
tr
an
s
f
o
r
m
er
s
w
itc
h
in
g
.
T
h
e
s
w
itc
h
in
g
tr
a
n
s
ien
t
s
ar
e
cla
s
s
i
f
ied
b
y
p
r
o
b
ab
ilis
tic
n
e
u
r
al
n
et
w
o
r
k
(
P
NN)
.
T
h
e
o
r
ig
in
al
s
i
g
n
al
is
d
ec
o
m
p
o
s
ed
u
p
to
le
v
el
5
u
s
in
g
DW
T
an
d
af
ter
co
n
s
id
er
in
g
all
th
e
p
ar
a
m
eter
th
e
au
th
o
r
s
o
f
th
is
p
ap
er
h
av
e
ch
o
s
en
t
h
e
d
etail
r
ea
cti
v
e
p
o
w
er
at
le
v
el
1
an
d
lev
e
l
3
i.e
.
Q
det1
an
d
Q
det3
as
in
p
u
ts
to
th
e
clas
s
i
f
ier
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
a
s
in
g
le
p
o
in
t
s
tr
ateg
y
b
ec
au
s
e
i
n
th
is
m
et
h
o
d
all
th
e
v
o
ltag
e
a
n
d
cu
r
r
en
t
s
ig
n
als
ar
e
ca
p
tu
r
ed
f
r
o
m
th
e
s
en
d
i
n
g
e
n
d
s
id
e
o
n
l
y
.
4.
WAVE
L
E
T
T
RANSF
O
RM
B
ASE
D
F
E
A
T
UR
E
E
XT
R
A
CT
I
O
N
a.
C
ap
ac
ito
r
s
w
itch
in
g
Fig
u
r
e
.
2
.
1
an
d
Fig
u
r
e
.
2
s
h
o
w
th
e
ca
p
ac
ito
r
s
w
itc
h
in
g
tr
an
s
ie
n
ts
i
n
th
e
ab
o
v
e
m
en
t
io
n
ed
r
ad
ial
n
et
w
o
r
k
.
I
n
th
i
s
p
ap
er
th
e
au
t
h
o
r
s
h
a
v
e
u
s
ed
ca
p
ac
ito
r
s
o
f
d
if
f
er
e
n
t
r
ati
n
g
s
(
5
0
µF
to
5
5
0
µF)
an
d
th
e
y
v
ar
ied
th
e
s
w
i
tch
in
g
ti
m
e
to
ca
p
t
u
r
e
th
e
d
etail
r
ea
cti
v
e
p
o
w
er
to
d
i
s
tin
g
u
is
h
t
h
e
ca
p
ac
ito
r
s
w
itc
h
in
g
tr
an
s
ien
ts
f
r
o
m
o
th
er
tr
an
s
ien
ts
.
T
ab
le
1
s
h
o
w
s
t
h
e
v
al
u
es
o
f
Q
det
f
r
o
m
l
ev
el
1
to
lev
el
5
at
d
i
f
f
er
en
t
b
u
s
e
s
w
h
en
1
5
0
µF
ca
p
ac
ito
r
is
s
w
i
tch
ed
o
n
.
b.
Mo
to
r
s
w
itc
h
i
n
g
Fig
u
r
e
.
3
s
h
o
w
s
t
h
e
m
o
to
r
s
w
itch
i
n
g
tr
an
s
ien
t
s
o
f
t
h
e
ab
o
v
e
m
en
tio
n
ed
r
ad
ial
n
et
w
o
r
k
.
T
o
p
er
f
o
r
m
th
e
s
i
m
u
latio
n
,
i
n
d
u
ctio
n
m
o
to
r
w
ith
d
i
f
f
er
e
n
t
r
atin
g
(
5
KW
to
1
0
KW
)
h
as
b
ee
n
co
n
s
id
er
ed
an
d
th
eir
s
w
itc
h
in
g
ti
m
e
is
al
s
o
v
ar
ied
t
o
co
llect
s
u
f
f
icie
n
t
n
u
m
b
er
o
f
d
ata.
T
ab
le
2
s
h
o
w
s
d
i
f
f
er
e
n
t
v
al
u
e
s
o
f
Q
det
f
r
o
m
le
v
el
1
to
le
v
e
l
5
at
d
if
f
er
en
t
b
u
s
es
w
h
e
n
a
9
KW
in
d
u
c
tio
n
m
o
to
r
is
s
w
itc
h
ed
o
n
w
h
en
v
o
ltag
e
w
a
s
at
its
p
ea
k
v
al
u
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
–
12
4
c.
Fau
lt i
n
d
u
ce
d
ev
e
n
t
s
I
n
Fig
u
r
e
.
4
th
e
f
a
u
lt
s
in
d
u
ce
d
tr
an
s
ie
n
ts
ar
e
s
h
o
w
n
a
n
d
T
ab
le
3
s
h
o
w
s
d
if
f
er
en
t
v
al
u
es
o
f
Q
det
f
r
o
m
lev
el
1
to
lev
el
5
w
h
e
n
u
n
s
y
m
m
etr
ical
f
au
l
t o
cc
u
r
s
at
d
if
f
er
e
n
t b
u
s
e
s
.
d.
C
o
n
v
er
ter
Fig
u
r
e
.
5
s
h
o
w
s
th
e
tr
a
n
s
ie
n
t
s
w
h
ic
h
ar
e
g
e
n
er
ated
b
y
th
e
c
o
n
v
er
ter
s
.
I
n
t
h
i
s
p
ap
er
th
e
au
th
o
r
s
h
a
v
e
u
s
ed
b
o
th
6
p
u
ls
e
a
n
d
1
2
p
u
ls
e
co
n
v
er
ter
s
w
it
h
v
ar
y
i
n
g
f
ir
i
n
g
a
n
g
les.
T
ab
le
4
s
h
o
w
s
th
e
d
if
f
er
e
n
t
v
a
lu
e
s
o
f
Q
det
f
r
o
m
le
v
el
1
to
lev
el
5
at
d
if
f
er
e
n
t b
u
s
e
s
.
e.
T
r
an
s
f
o
r
m
er
s
w
itc
h
i
n
g
Fig
u
r
e
.
6
s
h
o
w
s
tr
an
s
f
o
r
m
er
g
en
er
ated
tr
an
s
ien
t.
T
r
an
s
f
o
r
m
er
s
w
it
h
d
if
f
er
e
n
t
KV
A
r
at
in
g
s
h
a
v
e
b
ee
n
ch
o
s
e
n
to
d
i
s
ti
n
g
u
i
s
h
th
e
tr
an
s
f
o
r
m
er
i
n
r
u
s
h
w
it
h
th
e
o
th
er
tr
an
s
ie
n
ts
.
T
ab
le
5
s
h
o
w
s
t
h
e
d
i
f
f
er
e
n
t
v
al
u
e
s
o
f
Q
det
f
r
o
m
le
v
el
1
to
lev
el
5
w
h
e
n
a
1
0
0
KVA
tr
an
s
f
o
r
m
er
is
s
w
itc
h
ed
o
n
.
5.
P
RO
B
AB
I
L
I
S
T
I
C
N
E
URA
L
NE
T
WO
RK
(
P
NN)
Af
ter
ca
lc
u
lati
n
g
th
e
DW
T
b
ased
d
etail
r
ea
ctiv
e
p
o
w
er
at
le
v
el
1
an
d
3
,
th
e
a
u
t
h
o
r
s
h
a
v
e
class
i
f
ied
th
e
d
i
f
f
er
e
n
t tr
a
n
s
ie
n
t
s
i
g
n
al
s
i
n
t
h
e
n
et
w
o
r
k
.
T
h
e
p
r
o
b
lem
o
f
m
u
lti
-
clas
s
cla
s
s
i
f
icatio
n
h
as
b
ee
n
co
n
s
id
er
ed
i
n
th
is
p
ap
er
.
A
s
et
o
f
d
ata
p
o
in
t
s
ar
e
g
iv
e
n
f
r
o
m
ea
c
h
cla
s
s
a
n
d
o
b
j
ec
tiv
e
is
to
class
i
f
y
a
n
y
n
e
w
d
ata
s
a
m
p
le
i
n
to
o
n
e
o
f
t
h
e
cla
s
s
e
s
.
He
n
ce
t
h
e
au
th
o
r
s
u
s
ed
th
e
p
r
o
b
ab
ilis
tic
Neu
r
al
Net
w
o
r
k
(
P
NN)
as
a
c
lass
i
f
ier
b
ec
au
s
e
it
ca
n
lear
n
t
h
e
co
m
p
le
x
n
o
n
l
in
ea
r
m
ap
p
in
g
f
r
o
m
t
h
e
in
p
u
t
s
p
ac
e
to
o
u
tp
u
t
s
p
ac
e.
)
T
h
e
b
ase
o
f
P
NN
is
th
e
B
ay
e
s
clas
s
if
icatio
n
r
u
le
an
d
P
ar
ze
n
’
s
m
et
h
o
d
o
f
p
r
o
b
ab
ilit
y
d
en
s
it
y
f
u
n
ctio
n
(
P
DF)
est
i
m
a
tio
n
[
1
0
]
.
An
u
n
k
n
o
w
n
s
a
m
p
le
X=
(
x
1
,
…
.
x
p
)
.
is
class
i
f
ied
i
n
to
class
k
i
f
u
k
l
k
f
k
(
X)
>u
f
l
f
f
j
(
X)
f
o
r
all
clas
s
es j
n
o
t e
q
u
al
to
k
.
B
ay
e
s
cla
s
s
i
f
icatio
n
r
u
le
i
m
p
r
o
v
es
th
e
clas
s
if
icatio
n
r
at
e
b
y
m
i
n
i
m
izin
g
th
e
e
x
p
ec
t
ed
co
s
t
o
f
m
is
c
lass
if
ica
tio
n
.
I
n
t
h
i
s
r
u
le
f
ir
s
t P
DF h
as
to
b
e
esti
m
a
ted
b
ased
o
n
a
tr
ain
i
n
g
s
et.
A
m
et
h
o
d
o
f
d
eter
m
i
n
i
n
g
a
u
n
i
v
ar
iate
P
DF
f
r
o
m
r
an
d
o
m
s
a
m
p
le
s
h
a
s
b
ee
n
p
r
ese
n
ted
b
y
P
r
az
en
[
1
0
]
.
W
ith
t
h
e
i
n
c
r
ea
s
e
o
f
n
u
m
b
er
o
f
s
a
m
p
les
th
e
u
n
iv
ar
iate
P
DF
co
n
v
er
g
e
s
as
y
m
p
to
tica
ll
y
to
t
h
e
tr
u
e
P
DF.
A
s
s
u
m
i
n
g
th
er
e
ar
e
n
k
n
u
m
b
er
o
f
tr
ain
i
n
g
ca
s
e
s
f
o
r
a
g
i
v
e
n
clas
s
k
an
d
th
e
e
s
ti
m
ated
u
n
i
v
ar
iate
P
DF f
o
r
th
at
class
,
v
k
(
x
)
,
is
∑
W
h
er
e
W
(
x
)
is
a
w
ei
g
h
t
f
u
n
ct
io
n
(
k
er
n
el)
a
n
d
t
h
e
σ
is
s
ca
li
n
g
p
ar
a
m
eter
w
h
ic
h
d
e
f
i
n
es
th
e
w
id
th
o
f
th
e
k
er
n
el.
W
(
x
)
is
t
h
e
Ga
u
s
s
ian
F
u
n
c
tio
n
.
Si
n
ce
t
h
e
P
NN
p
r
o
ce
s
s
es
p
in
p
u
t
s
v
ar
iab
les,
th
e
P
DF
esti
m
ato
r
m
u
s
t
co
n
s
id
er
m
u
lti
v
a
r
iate
in
p
u
ts
[
1
0
]
.
Fig
.
7
s
h
o
w
s
th
e
P
NN
ar
ch
itectu
r
e
w
h
ic
h
co
n
s
is
ts
t
h
e
f
o
u
r
la
y
er
o
r
g
an
izatio
n
.
T
h
e
in
p
u
t
n
e
u
r
o
n
s
d
is
tr
ib
u
te
i
n
p
u
t
v
ar
iab
les
i
n
t
h
e
i
n
p
u
t
la
y
er
to
th
e
n
e
x
t
la
y
er
.
O
n
e
n
e
u
r
o
n
co
n
s
is
t
s
w
it
h
o
n
e
tr
ai
n
i
n
g
ca
s
e
an
d
i
t
co
m
p
u
tes
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
u
n
k
n
o
w
n
i
n
p
u
t
x
an
d
tr
ain
i
n
g
ca
s
e
r
ep
r
esen
ted
b
y
t
h
at
n
e
u
r
o
n
.
An
ac
ti
v
atio
n
f
u
n
ctio
n
,
k
n
o
w
n
as
th
e
P
ar
ze
n
esti
m
ato
r
,
is
ap
p
lied
to
th
e
d
is
tan
ce
m
ea
s
u
r
ed
.
I
n
th
e
s
u
m
m
atio
n
la
y
er
,
t
h
e
n
e
u
r
o
n
s
s
u
m
t
h
e
v
al
u
es
o
f
t
h
e
n
eu
r
o
n
s
co
r
r
esp
o
n
d
in
g
to
t
h
e
clas
s
w
h
o
’
s
esti
m
ate
d
P
DF
h
as
to
b
e
d
eter
m
i
n
ed
in
t
h
e
p
atter
n
la
y
er
b
y
t
h
e
B
a
y
es
d
is
cr
i
m
i
n
ate
cr
iter
io
n
.
I
n
t
h
e
o
u
tp
u
t
la
y
er
,
w
h
ich
is
s
i
m
p
le
th
r
e
s
h
o
ld
d
is
cr
i
m
in
ato
r
a
s
in
g
le
n
e
u
r
o
n
h
a
s
b
ee
n
ac
ti
v
ated
to
r
ep
r
esen
t
a
p
r
o
j
ec
ted
class
o
f
th
e
u
n
k
n
o
w
n
s
a
m
p
le.
6.
CL
AS
SI
F
I
CA
T
I
O
N
O
F
T
R
ANSI
E
N
T
S US
I
N
G
P
NN
T
o
ch
ec
k
th
e
v
alid
it
y
o
f
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
s
i
m
u
latio
n
w
o
r
k
h
as
b
ee
n
co
n
d
u
cted
to
class
i
f
y
t
h
e
d
if
f
er
e
n
t
tr
an
s
ie
n
ts
i
n
p
o
w
er
s
y
s
te
m
.
E
ac
h
t
y
p
e
o
f
tr
a
n
s
ie
n
t
is
tr
ea
ted
as
an
i
n
d
i
v
id
u
al
cla
s
s
an
d
as
s
ig
n
ed
th
e
class
i
f
icatio
n
n
u
m
b
er
f
r
o
m
1
t
o
5
.
MA
T
L
A
B
co
d
e
is
u
s
ed
to
ca
lcu
late
th
e
DW
T
b
ased
d
e
tail
r
ea
ctiv
e
p
o
w
er
i.e
.
Q
det1
an
d
Q
det3
.
T
h
ese
d
eta
il
r
ea
ctiv
e
p
o
w
er
s
ar
e
u
s
ed
as
in
p
u
t
to
th
e
A
N
N
m
o
d
el.
Fo
r
ea
ch
tr
an
s
ien
t
7
5
s
ets
o
f
f
ea
tu
r
es
ar
e
e
x
tr
ac
ted
,
in
w
h
ic
h
2
5
s
ets
ar
e
u
s
ed
a
s
tr
ain
i
n
g
p
u
r
p
o
s
e
i.e
.
1
2
5
f
e
atu
r
es
ar
e
ta
k
en
a
s
tr
ain
i
n
g
s
a
m
p
les
a
n
d
an
o
th
er
5
0
s
ets
i.e
.
2
5
0
f
ea
tu
r
es
ar
e
u
s
ed
f
o
r
test
in
g
p
u
r
p
o
s
e.
T
o
o
b
t
ain
th
e
tr
ain
in
g
an
d
test
i
n
g
d
ata
f
o
r
A
NN
m
o
d
el
f
o
r
ea
ch
tr
an
s
ien
t,
th
e
au
t
h
o
r
s
h
av
e
v
ar
ied
v
al
u
e
o
f
th
e
ca
p
ac
itan
ce
o
f
t
h
e
ca
p
ac
ito
r
,
KW
r
atin
g
o
f
t
h
e
in
d
u
ct
io
n
m
o
to
r
,
co
n
v
er
ter
f
ir
in
g
a
n
g
le,
KV
A
r
ati
n
g
o
f
tr
an
s
f
o
r
m
er
,
f
a
u
lt
r
esis
ta
n
ce
an
d
ti
m
e
o
f
o
cc
u
r
r
e
n
ce
o
f
f
a
u
lt.
T
h
e
s
i
m
u
la
tio
n
s
p
r
o
d
u
ce
d
3
7
5
s
ets
o
f
d
etail
r
ea
ctiv
e
p
o
w
e
r
(
Q
det
)
u
p
to
lev
el
5
in
d
iv
id
u
all
y
f
o
r
th
e
a
b
o
v
e
m
en
t
io
n
ed
f
i
v
e
tr
an
s
ie
n
ts
.
T
ab
le
6
s
h
o
w
s
th
e
a
s
s
i
g
n
ed
class
es o
f
tr
an
s
ien
t
s
a
m
p
le
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
la
s
s
i
fica
tio
n
o
f P
o
w
er Qu
a
lity E
ve
n
ts
Usi
n
g
W
a
ve
let
a
n
a
lysi
s
a
n
d
P
r
o
b
a
b
ilis
tic
….
(
P
a
mp
a
S
in
h
a
)
5
A
p
p
l
y
in
g
t
h
is
m
et
h
o
d
it
is
n
o
t
iced
th
at
s
u
cc
ess
r
ate
f
o
r
id
en
t
if
y
in
g
t
h
e
d
if
f
er
en
t
cla
s
s
e
s
o
f
tr
an
s
ie
n
ts
d
ep
en
d
s
o
n
th
e
d
ec
o
m
p
o
s
iti
o
n
lev
el
also
.
T
ab
le
7
s
h
o
w
s
th
e
v
a
r
iatio
n
o
f
s
u
cc
es
s
r
ate
b
y
v
ar
y
in
g
d
ec
o
m
p
o
s
itio
n
le
v
el.
Fro
m
t
h
is
tab
le
it
is
o
b
s
er
v
ed
th
a
t
i
f
th
e
o
r
ig
i
n
al
s
i
g
n
a
l
is
d
ec
o
m
p
o
s
ed
u
p
to
le
v
el
5
in
s
tead
o
f
lev
e
l
3
,
th
e
s
u
cc
es
s
r
ate
r
em
ain
s
s
a
m
e.
I
t
is
also
o
b
s
er
v
ed
th
at
th
e
s
u
cc
es
s
r
ate
at
1
st
,
3
rd
an
d
6
th
r
o
w
is
s
a
m
e.
B
u
t
i
n
r
e
m
ai
n
i
n
g
r
o
w
s
th
e
s
u
cc
es
s
r
ate
is
q
u
i
te
lo
w
.
So
co
n
s
id
er
i
n
g
all
t
h
e
r
esu
lts
t
h
e
au
th
o
r
s
h
av
e
c
h
o
s
e
n
o
n
l
y
lev
el
1
an
d
3
i.e
.
r
o
w
6
th
to
r
ed
u
ce
th
e
co
m
p
u
tat
io
n
al
b
u
r
d
en
.
T
h
e
class
i
f
icatio
n
r
es
u
lt
s
ca
n
b
e
d
escr
ib
ed
in
ter
m
s
o
f
co
n
f
u
s
i
o
n
m
atr
i
x
w
h
ic
h
i
s
a
s
ta
n
d
ar
d
to
o
l
f
o
r
test
i
n
g
c
lass
if
ier
.
Fro
m
T
ab
le
8
o
n
e
ca
n
s
ee
t
h
at
a
co
n
f
u
s
i
o
n
m
atr
i
x
h
as
o
n
e
r
o
w
an
d
o
n
e
co
lu
m
n
f
o
r
ea
ch
class
.
T
h
e
r
o
w
r
ep
r
esen
t
s
t
h
e
o
r
ig
in
al
cla
s
s
a
n
d
th
e
co
l
u
m
n
r
ep
r
ese
n
ts
t
h
e
p
r
ed
icted
class
b
y
t
h
e
P
NN
class
i
f
ica
tio
n
.
T
h
e
n
u
m
b
er
in
th
e
m
a
tr
ix
s
h
o
w
s
t
h
e
v
ar
io
u
s
p
atter
n
o
f
m
i
s
clas
s
i
f
icatio
n
th
at
is
o
b
tain
ed
f
r
o
m
th
e
test
i
n
g
s
et.
Fo
r
in
s
tan
ce
,
i
n
T
ab
le
8
,
w
e
ca
n
o
b
s
er
v
e
th
a
t
o
u
t
o
f
5
0
ca
s
es
o
f
m
o
to
r
s
w
i
tch
i
n
g
o
n
l
y
o
n
e
h
as
b
ee
n
m
i
s
clas
s
i
f
ied
as
f
a
u
lt.
I
n
th
is
tab
le
n
e
t
w
o
r
k
cla
s
s
i
f
ic
atio
n
er
r
o
r
r
ate
f
o
r
ea
ch
t
y
p
e
o
f
tr
an
s
ie
n
t
s
ar
e
m
en
tio
n
ed
.
Fro
m
th
e
ab
o
v
e
r
e
s
u
lt
it
ca
n
b
e
co
n
cl
u
d
ed
th
at
u
s
in
g
t
h
i
s
m
eth
o
d
t
h
e
n
et
w
o
r
k
class
i
f
ies
co
r
r
ec
tl
y
2
4
9
d
ata
o
u
t
o
f
2
5
0
.
T
h
at
m
ea
n
s
t
h
e
co
r
r
ec
t
class
if
icatio
n
r
ate
is
9
9
.
6
%.
I
n
T
ab
le
3
it
ca
n
b
e
s
ee
n
th
at
m
o
s
t
o
f
th
e
cla
s
s
i
f
icat
io
n
er
r
o
r
o
cc
u
r
s
i
n
b
et
w
ee
n
cla
s
s
2
an
d
3
,
b
ec
au
s
e
ch
ar
ac
ter
is
tic
h
ar
m
o
n
ics
o
f
t
h
ese
t
w
o
s
w
itc
h
in
g
ar
e
n
ea
r
l
y
s
i
m
ilar
.
7.
CO
M
P
ARATI
VE
S
T
UDY
WI
T
H
O
T
H
E
R
M
E
T
H
O
DS
I
n
T
ab
le
9
a
co
m
p
ar
ativ
e
s
tu
d
y
w
it
h
th
e
o
th
er
ex
i
s
ti
n
g
m
eth
o
d
is
p
r
esen
ted
.
T
h
ese
m
e
th
o
d
s
ar
e
s
o
m
e
w
h
at
s
i
m
i
lar
w
it
h
th
e
m
eth
o
d
o
lo
g
y
p
r
o
p
o
s
ed
in
th
i
s
p
ap
er
i.e
.
th
ey
e
x
tr
ac
ted
th
e
f
ea
tu
r
es
o
f
d
i
s
to
r
ted
s
ig
n
al
u
s
i
n
g
w
a
v
elet
tr
an
s
f
o
r
m
a
n
d
th
e
n
clas
s
i
f
ied
th
o
s
e
s
i
g
n
al
b
y
u
s
i
n
g
ar
t
if
ic
ial
i
n
telli
g
en
ce
tech
n
iq
u
e.
T
h
e
r
esu
lt
s
p
r
esen
ted
in
T
ab
le
9
h
av
e
s
h
o
w
n
t
h
at
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
g
i
v
es
b
etter
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
t
h
e
ex
is
t
in
g
m
et
h
o
d
s
b
ec
au
s
e
i
n
t
h
is
m
e
th
o
d
s
u
cc
es
s
r
ate
is
9
9
.
6
%
an
d
co
m
p
u
tatio
n
al
co
m
p
l
ex
it
y
i
s
lo
w
er
t
h
an
th
e
m
e
th
o
d
p
r
o
p
o
s
ed
in
[
6
]
.
8.
CO
NCLU
SI
O
NS
I
n
a
m
o
n
ito
r
in
g
s
y
s
te
m
th
e
i
n
d
icato
r
s
th
at
co
n
tai
n
t
h
e
u
n
iq
u
e
f
ea
t
u
r
es
o
f
p
o
w
er
s
y
s
te
m
s
ar
e
ac
q
u
ir
ed
f
o
r
d
is
tin
g
u
i
s
h
in
g
d
is
t
u
r
b
an
ce
s
.
B
u
t
f
o
r
ef
f
ec
ti
v
e
class
if
ica
ti
o
n
o
f
th
e
d
is
tu
r
b
an
ce
s
,
s
to
r
ag
e
o
f
a
lar
g
e
n
u
m
b
er
o
f
d
ata
s
h
o
u
ld
b
e
av
o
id
ed
.
I
n
th
i
s
p
ap
er
a
n
o
v
el
a
n
d
s
i
m
p
le
m
et
h
o
d
h
as
b
ee
n
p
r
o
p
o
s
ed
b
ased
o
n
DW
T
an
d
P
NN
f
o
r
class
i
f
icatio
n
o
f
ca
p
ac
ito
r
s
w
i
tch
i
n
g
,
co
n
v
er
ter
s
w
i
tch
i
n
g
,
m
o
to
r
s
w
itc
h
i
n
g
,
tr
an
s
f
o
r
m
er
s
w
itc
h
in
g
an
d
f
a
u
lt
in
d
u
ce
d
ev
e
n
t
s
.
A
n
ac
c
u
r
ate
an
d
r
eliab
le
p
o
w
er
tr
an
s
ien
t
c
lass
i
f
ier
h
a
s
b
ee
n
d
e
v
elo
p
ed
to
d
is
tin
g
u
i
s
h
th
e
s
e
tr
an
s
ie
n
t
s
ig
n
al
s
.
DW
T
h
as
b
ee
n
u
s
ed
to
ca
lc
u
late
t
h
e
d
et
ail
r
ea
ctiv
e
p
o
w
er
at
lev
el
1
(
Q
det1
)
an
d
3
(
Q
det3
)
w
h
ic
h
ar
e
u
s
ed
as
t
h
e
i
n
p
u
t
to
t
h
e
A
N
N
m
o
d
el.
Her
e
P
r
o
b
ab
ilis
tic
Neu
r
al
n
et
w
o
r
k
h
as
b
ee
n
u
s
ed
as
a
class
i
f
ier
.
T
o
ch
ec
k
it
s
v
al
id
it
y
a
n
d
r
eliab
ilit
y
d
i
f
f
er
en
t
ca
s
e
s
t
u
d
ies
ar
e
co
n
s
id
er
ed
w
h
ich
s
h
o
w
t
h
at
t
h
i
s
tech
n
iq
u
e
is
w
e
ll s
u
ited
f
o
r
cla
s
s
i
f
icatio
n
o
f
tr
an
s
i
en
ts
i
n
p
o
w
er
s
y
s
te
m
n
et
w
o
r
k
.
T
ab
le
1
.
C
ap
acito
r
Sw
i
tch
i
n
g
Data A
t
Diff
er
e
n
t B
u
s
B
U
S
Q
de
t
1
Q
de
t
2
Q
de
t
3
Q
de
t
4
Q
de
t
5
C
l
a
ss
A
1
.
6
4
×
1
0
8
1
.
6
7
×
1
0
6
3
.
8
7
×
1
0
7
2
.
2
×
1
0
6
4
.
3
×
1
0
7
1
(
C
=
1
5
0
µ
F
S
w
i
t
c
h
i
n
g
a
n
g
l
e
6
0
°
)
B
1
.
0
7
×
1
0
7
1
.
8
7
×
1
0
6
2
.
7
8
×
1
0
7
2
.
4
×
1
0
6
3
.
2
4
.
3
×
1
0
7
C
4
.
0
7
×
1
0
6
1
.
9
×
1
0
6
2
.
7
8
×
1
0
7
2
.
0
1
×
1
0
6
3
.
3
4
.
3
×
1
0
7
D
1
.
9
8
×
1
0
6
2
.
1
×
1
0
6
2
.
7
8
×
1
0
7
1
.
9
7
×
1
0
6
3
.
3
4
.
3
×
1
0
7
Y
1
.
0
5
×
1
0
6
2
.
4
4
×
1
0
6
2
.
7
8
×
1
0
7
2
.
3
×
1
0
6
3
.
3
4
.
3
×
1
0
7
T
ab
le
2
.
Mo
t
o
r
S
w
itc
h
in
g
Dat
a
B
U
S
Q
de
t
1
Q
de
t
2
Q
de
t
3
Q
de
t
4
Q
de
t
5
C
l
a
ss
A
2
.
1
×
1
0
8
6
.
1
×
1
0
8
2
.
9
×
1
0
7
5
.
5
×
1
0
8
2
.
4
×
1
0
7
2
(
9
k
w
S
w
i
t
c
h
i
n
g
a
n
g
l
e
9
0
°
)
B
6
.
1
×
1
0
7
4
.
2
1
×
1
0
8
6
.
7
6
×
1
0
6
3
.
7
5
×
1
0
8
6
.
2
×
1
0
6
C
4
.
6
×
1
0
7
3
.
3
×
1
0
8
4
.
0
5
×
1
0
6
2
.
5
6
×
1
0
8
3
.
6
7
×
1
0
6
D
3
.
3
×
1
0
7
2
.
4
×
1
0
8
3
.
4
5
×
1
0
6
1
.
8
7
×
1
0
8
2
.
7
8
×
1
0
6
Y
2
.
7
×
1
0
7
9
.
7
×
1
0
7
2
.
5
6
×
1
0
6
9
.
1
×
1
0
7
1
.
9
7
×
1
0
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
–
12
6
T
ab
le
4.
C
o
n
v
er
ter
S
w
itch
in
g
Data
A
t
Dif
f
er
e
n
t B
u
s
B
U
S
Q
de
t
1
Q
de
t
2
Q
de
t
3
Q
de
t
4
Q
de
t
5
C
l
a
ss
A
5
.
2
1
×
1
0
3
4
.
9
×
1
0
4
1
.
6
8
×
1
0
6
4
.
4
9
×
1
0
4
5
.
4
5
×
1
0
7
4
(
α=6
0
°
f
i
r
i
n
g
a
n
g
l
e
)
B
3
.
6
1
×
1
0
3
4
.
7
7
×
1
0
4
1
.
6
8
×
1
0
6
4
.
5
1
×
1
0
4
4
.
5
6
×
1
0
7
C
1
.
5
3
×
1
0
3
4
.
5
8
×
1
0
4
1
.
6
8
×
1
0
6
4
.
7
4
×
1
0
4
3
.
4
5
×
1
0
7
D
1
.
2
5
×
1
0
3
4
.
5
5
×
1
0
4
1
.
6
8
×
1
0
6
4
.
7
7
×
1
0
4
2
.
3
4
×
1
0
7
Y
1
.
2
×
1
0
3
4
.
5
4
×
1
0
4
1
.
6
9
×
1
0
6
4
.
6
1
×
1
0
4
1
.
1
2
×
1
0
7
T
ab
le
5
.
T
r
an
s
f
o
r
m
er
S
w
itc
h
i
n
g
Da
ta
A
t
Di
f
f
er
e
n
t B
u
s
B
U
S
Q
de
t
1
Q
de
t
2
Q
de
t
3
Q
de
t
4
Q
de
t
5
C
l
a
ss
A
1
.
0
5
×
1
0
5
5
.
9
8
×
1
0
5
1
.
8
3
×
1
0
7
6
.
0
7
×
1
0
7
6
.
2
×
1
0
5
5
(
1
0
K
V
A
S
w
i
t
c
h
i
n
g
a
n
g
l
e
6
0
°
)
B
1
.
0
4
×
1
0
5
5
.
9
7
×
1
0
5
1
.
7
8
×
1
0
7
5
.
9
9
×
1
0
7
6
.
0
1
×
1
0
5
C
8
.
9
×
1
0
4
5
.
8
5
×
1
0
5
1
.
7
8
×
1
0
7
5
.
2
×
1
0
7
5
.
9
×
1
0
5
D
1
.
0
9
×
1
0
5
5
.
2
×
1
0
5
1
.
7
9
×
1
0
7
3
.
4
5
×
1
0
7
5
.
2
8
×
1
0
5
Y
1
.
1
7
×
1
0
5
5
.
1
5
×
1
0
5
1
.
7
8
×
1
0
7
2
.
3
×
1
0
7
5
.
6
×
1
0
5
T
ab
le
6
.
C
lass
es o
f
tr
a
n
s
ie
n
t s
a
m
p
les a
n
d
s
i
m
u
lated
d
ata
s
et
f
o
r
tr
ain
i
n
g
a
n
d
test
i
n
g
o
f
P
NN
n
et
w
o
r
k
Ty
p
e
o
f
t
r
a
n
si
e
n
t
A
ssi
g
n
e
d
C
l
a
ss
T
r
a
i
n
i
n
g
d
a
t
a
(
S
e
t
)
T
e
st
i
n
g
d
a
t
a
(
S
e
t
)
C
a
p
a
c
i
t
o
r
sw
i
t
c
h
i
n
g
1
25
50
M
o
t
o
r
sw
i
t
c
h
i
n
g
2
25
50
F
a
u
l
t
3
25
50
C
o
n
v
e
r
t
e
r
4
25
50
T
r
a
n
sf
o
r
me
r
s
w
i
t
c
h
i
n
g
5
25
50
T
ab
le
7
.
Dec
o
m
p
o
s
itio
n
L
e
v
el
An
d
% Of
Su
cc
e
s
s
R
ate
S
L
.
N
o
D
e
c
o
mp
o
si
t
i
o
n
l
e
v
e
l
F
e
a
t
u
r
e
s
se
l
e
c
t
e
d
%
o
f
su
c
c
e
ss
r
a
t
e
1
D
e
c
o
mp
o
se
d
u
p
t
o
L
e
v
e
l
5
Q
de
t
1
t
o
Q
de
t
5
9
9
.
6
2
D
e
c
o
mp
o
se
d
u
p
t
o
L
e
v
e
l
4
Q
de
t
1
t
o
Q
de
t
4
9
9
.
6
3
D
e
c
o
mp
o
se
d
u
p
t
o
L
e
v
e
l
3
Q
de
t
1
t
o
Q
de
t
3
9
9
.
6
4
D
e
c
o
mp
o
se
d
u
p
t
o
L
e
v
e
l
2
Q
de
t
1
t
o
Q
de
t
2
9
2
.
1
5
D
e
c
o
mp
o
se
d
a
t
L
e
v
e
l
1
Q
de
t
1
o
n
l
y
2
1
.
4
6
D
e
c
o
mp
o
se
d
a
t
l
e
v
e
l
1
a
n
d
3
Q
de
t
1
a
n
d
Q
d
e
t
3
o
n
l
y
9
9
.
6
7
D
e
c
o
mp
o
se
d
a
t
l
e
v
e
l
1
a
n
d
2
Q
de
t
1
a
n
d
Q
d
e
t
2
o
n
l
y
9
7
.
6
T
ab
le
3
.
Fau
lt I
n
d
u
ce
d
T
r
an
s
ien
t D
ata
A
t D
i
f
f
er
en
t B
u
s
B
U
S
Q
de
t
1
Q
de
t
2
Q
de
t
3
Q
de
t
4
Q
de
t
5
C
l
a
ss
A
2
.
5
×
1
0
5
1
.
2
×
1
0
6
2
.
3
×
1
0
6
1
.
1
×
1
0
6
6
.
8
×
1
0
5
3
(R
f
=
2
0
Ω
S
w
i
t
c
h
i
n
g
a
n
g
l
e
9
0
°
)
B
1
.
1
×
1
0
5
1
.
2
×
1
0
6
7
.
2
×
1
0
6
4
.
2
×
1
0
5
3
.
2
×
1
0
5
C
4
.
2
×
1
0
4
5
.
6
7
×
1
0
5
4
.
2
×
1
0
6
2
.
1
×
1
0
5
2
.
1
×
1
0
5
D
3
.
9
8
×
1
0
4
2
.
9
5
×
1
0
5
3
.
1
×
1
0
6
1
.
1
×
1
0
5
1
.
0
6
×
1
0
5
Y
2
.
4
4
×
1
0
4
1
.
4
8
×
1
0
5
2
.
1
×
1
0
6
6
.
7
×
1
0
4
2
.
0
8
×
1
0
4
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
la
s
s
i
fica
tio
n
o
f P
o
w
er Qu
a
lity E
ve
n
ts
Usi
n
g
W
a
ve
let
a
n
a
lysi
s
a
n
d
P
r
o
b
a
b
ilis
tic
….
(
P
a
mp
a
S
in
h
a
)
7
T
ab
le
8
.
C
o
n
f
u
s
io
n
Ma
tr
i
x
C
l
a
ss
1
2
3
4
5
1
50
2
49
1
3
50
4
50
5
50
Fig
u
r
e
1
.
T
h
e
E
x
a
m
p
le
Net
w
o
r
k
Fig
u
r
e
2
.
1
.
(
a)
s
im
u
lated
cu
r
r
e
n
t tr
an
s
ien
t d
u
r
in
g
ca
p
ac
ito
r
s
w
itc
h
i
n
g
,
(
b
)
cu
r
r
en
t sig
n
al
d
e
co
m
p
o
s
ed
at
lev
el
1
,
(
c)
cu
r
r
en
t sig
n
al
d
ec
o
m
p
o
s
ed
at
le
v
el
3
.
S
l
.
N
o
.
M
e
t
h
o
d
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
P
o
w
e
r
s
y
st
e
m t
r
a
n
si
e
n
t
s
%
o
f
su
c
c
e
ss rat
e
O
t
h
e
r
d
i
sa
d
v
a
n
t
a
g
e
1
W
a
v
e
l
e
t
-
t
r
a
n
sf
o
r
m+A
N
N
b
a
se
d
c
l
a
ssi
f
i
e
r
[
3
3
]
95
2
W
a
v
e
l
e
t
-
t
r
a
n
sf
o
r
m
b
a
se
d
c
l
a
ss
i
f
i
e
r
[
3
4
]
95
3
S
-
t
r
a
n
sf
o
r
m
+
c
o
m
p
e
t
i
t
i
v
e
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
c
l
a
ssi
f
i
e
r
[
3
5
]
9
7
.
5
4
D
T
C
W
T
+
A
N
N
b
a
se
d
c
l
a
ssi
f
i
e
r
[
6
]
1
0
0
C
o
mp
u
t
a
t
i
o
n
a
l
C
o
mp
l
e
x
i
t
y
h
i
g
h
[
3
2
]
5
P
r
o
p
o
se
d
me
t
h
o
d
9
9
.
6
C
o
mp
u
t
a
t
i
o
n
a
l
C
o
mp
l
e
x
i
t
y
l
e
ss [
3
2
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
–
12
8
Fig
u
r
e
2
.
2
.
(
a)
V
o
ltag
e
p
r
o
f
ile
d
u
r
in
g
C
ap
ac
ito
r
s
w
itc
h
in
g
tr
an
s
ie
n
t,
(
b
)
C
u
r
r
en
t p
r
o
f
ile
d
u
r
in
g
C
ap
ac
ito
r
s
w
itch
in
g
tr
an
s
ie
n
t
(
c)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
il
e
at
lev
el
1
,
(
d
)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
lev
el
3
.
Fig
u
r
e
3
.
(
a)
Vo
ltag
e
p
r
o
f
ile
d
u
r
in
g
Mo
to
r
s
w
itc
h
in
g
tr
an
s
ie
n
t,
(
b
)
C
u
r
r
en
t p
r
o
f
ile
d
u
r
i
n
g
Mo
to
r
s
w
itc
h
in
g
tr
an
s
ie
n
t (
c)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
le
v
el
1
,
(
d
)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
lev
el
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
la
s
s
i
fica
tio
n
o
f P
o
w
er Qu
a
lity E
ve
n
ts
Usi
n
g
W
a
ve
let
a
n
a
lysi
s
a
n
d
P
r
o
b
a
b
ilis
tic
….
(
P
a
mp
a
S
in
h
a
)
9
Fig
u
r
e
4
.
(
a)
Vo
ltag
e
p
r
o
f
ile
d
u
r
in
g
Fa
u
lt i
n
d
u
ce
d
tr
an
s
ien
t,
(
b
)
C
u
r
r
en
t p
r
o
f
ile
d
u
r
in
g
Fa
u
l
t in
d
u
ce
d
tr
an
s
ie
n
t (
c)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
le
v
el
1
,
(
d
)
d
etai
l r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
lev
e
l 3
.
Fig
u
r
e
5
.
(
a)
Vo
ltag
e
p
r
o
f
ile
d
u
r
in
g
C
o
n
v
er
ter
S
w
i
tch
i
n
g
,
(
b
)
C
u
r
r
en
t p
r
o
f
ile
d
u
r
i
n
g
C
o
n
v
e
r
ter
S
w
itc
h
in
g
tr
an
s
iet
,
(
c)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
le
v
el
1
,
(
d
)
Deta
il r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
lev
el
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
–
12
10
Fig
u
r
e
6
.
(
a)
v
o
ltag
e
p
r
o
f
ile
d
u
r
in
g
T
r
an
s
f
o
r
m
er
s
w
itc
h
in
g
t
r
an
s
ie
n
t,
(
b
)
C
u
r
r
en
t p
r
o
f
ile
d
u
r
in
g
T
r
an
s
f
o
r
m
er
s
w
itc
h
in
g
tr
an
s
ie
n
t (
c)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
le
v
el
1
,
(
d
)
d
etail
r
ea
ctiv
e
p
o
w
er
p
r
o
f
ile
at
lev
el
3
.
Fig
u
r
e
7
.
P
NN
A
r
ch
itect
u
r
e
RE
F
E
R
E
NC
E
S
[1
]
Re
d
d
y
,
M
.
J.B,
a
n
d
M
o
h
a
n
ta
,
D.K
,
De
tec
ti
o
n
,
c
las
sif
ica
ti
o
n
a
n
d
lo
c
a
li
z
a
ti
o
n
o
f
p
o
w
e
r
s
y
st
e
m
i
m
p
u
lsiv
e
tran
sie
n
ts
u
sin
g
S
-
tran
sf
o
rm
.
In
:
En
v
iro
n
m
e
n
t
a
n
d
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
(EE
EIC),
9
th
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
,
P
ra
g
u
e
,
Cz
e
c
h
Re
p
u
b
li
c
M
a
y
1
6
-
1
9
,
2
0
1
0
.
[2
]
S
ty
v
a
k
ta
k
is,
E.
,
Bo
ll
e
n
,
M
.
H.J.;
G
u
,
I.
Y.
H.,
Clas
sif
ica
ti
o
n
o
f
p
o
w
e
r
s
y
st
e
m
tran
sie
n
ts:
sy
c
h
ro
n
ise
d
sw
it
c
h
in
g
.
P
o
w
e
r
En
g
in
e
e
rin
g
S
o
c
iety
W
in
te
r
M
e
e
ti
n
g
,
2
0
0
0
.
I
EE
E.
2
6
8
1
-
2
6
8
6
v
o
l.
4
.
[3
]
G
a
o
u
d
a
,
A
.
M
.
,
S
a
la
m
a
,
M
.
M
.
A
.
;
S
u
lt
a
n
,
M
.
R.
a
n
d
Ch
ik
h
a
n
i,
A
.
Y.
P
o
w
e
r
Qu
a
li
ty
d
e
tec
ti
o
n
a
n
d
c
las
si
f
ica
ti
o
n
u
sin
g
w
a
v
e
let
-
m
u
lt
ires
o
lu
ti
o
n
sig
n
a
l
d
e
c
o
m
p
o
siti
o
n
.
I
EE
E
T
ra
n
s
P
o
w
e
r
De
li
v
.
2
0
0
0
;
1
4
(4
):
1
4
6
9
-
1
4
7
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.