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
.
68
~
72
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i1
.
p
p
68
-
72
68
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
Ana
ly
sis
of BBNs
O
v
er
Fault D
etec
t
io
n and
Diag
no
sis
in
Indu
stria
l
Ap
plic
a
tion
Upa
dh
y
a
y
Ana
nd
T
rilo
kin
a
t
h
1
,
Dr
Sa
ntho
s
h K
u
m
a
r
Si
ng
h
2
1
Re
se
a
rc
h
S
c
h
o
lar,
De
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
A
M
ET
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
2
A
s
sista
n
t
P
ro
f
e
ss
o
r,
De
p
a
rtm
e
n
t
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
T
a
g
o
re
Co
ll
e
g
e
o
f
S
c
ien
c
e
&
Co
m
m
e
r
c
e
,
M
u
m
b
a
i
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
9
,
2
0
1
6
R
ev
i
s
ed
No
v
2
0
,
2
0
1
6
A
cc
ep
ted
Dec
1
1
,
2
0
1
6
In
In
d
u
strial
p
r
o
c
e
d
u
re
s,
t
o
tru
st
th
e
a
c
h
iev
e
m
e
n
t
o
f
p
lan
n
e
d
o
p
e
ra
ti
o
n
,
a
c
tu
a
li
sin
g
n
e
w
a
n
d
e
x
a
c
t
stra
teg
y
f
o
r
p
e
rc
e
iv
in
g
irre
g
u
lar
w
o
rk
in
g
c
o
n
d
i
ti
o
n
s,
k
n
o
w
n
a
s
sh
o
rtco
m
in
g
s,
is
e
ss
e
n
ti
a
l.
A
p
o
w
e
r
f
u
l
tec
h
n
i
q
u
e
f
o
r
b
lam
e
lo
c
a
ti
o
n
a
n
d
a
n
a
ly
sis
h
e
lp
s
to
d
e
c
r
e
a
se
th
e
e
ff
e
c
t
o
f
th
e
se
d
e
f
icie
n
c
ies
,
p
ra
ise
s
th
e
w
e
ll
b
e
in
g
o
f
o
p
e
ra
ti
o
n
,
li
m
it
s
d
o
w
n
ti
m
e
a
n
d
les
s
e
n
s
fa
b
rica
ti
n
g
c
o
sts.
In
th
is
p
a
p
e
r,
u
ti
li
sa
ti
o
n
o
f
BBNs
e
x
a
m
in
e
d
f
o
r
a
b
e
n
c
h
m
a
r
k
s
y
n
th
e
ti
c
m
o
d
e
rn
p
ro
c
e
ss
,
k
n
o
w
n
a
s,
Ten
n
e
ss
e
e
Eas
t
m
a
n
k
e
e
p
in
g
in
m
in
d
th
e
e
n
d
g
o
a
l
to
a
c
c
o
m
p
li
sh
p
rime
b
la
m
e
lo
c
a
ti
o
n
a
n
d
sp
e
c
if
ic
li
k
e
l
y
f
in
d
in
g
o
f
th
e
ir
c
a
u
se
s.
Us
e
o
f
B
a
y
e
sia
n
c
o
n
v
ictio
n
sy
st
e
m
s
f
o
r
b
la
m
e
lo
c
a
ti
o
n
a
n
d
c
o
n
c
lu
si
o
n
o
f
T
e
n
n
e
ss
e
e
Eas
t
m
a
n
p
re
p
a
re
i
n
t
h
e
g
ra
p
h
ica
l
se
tt
in
g
d
e
p
ictio
n
h
a
s
n
o
t
b
e
e
n
tr
ied
y
e
t.
T
h
e
a
c
c
o
m
p
li
sh
m
e
n
t
o
f
th
is
c
o
m
p
o
n
e
n
t
a
f
f
ir
m
s
c
a
p
a
c
it
y
a
n
d
stra
ig
h
tf
o
r
w
a
rd
n
e
ss
u
ti
li
sa
ti
o
n
o
f
it
a
s
a
n
a
s
y
m
p
to
m
a
ti
c
f
ra
m
e
w
o
rk
in
sp
e
c
if
ic cu
rre
n
t
p
ro
c
e
d
u
re
s.
K
ey
w
o
r
d
s
:
B
B
Ns
Diag
n
o
s
is
Fau
lt De
tec
tio
n
Fau
lt Dia
g
n
o
s
i
s
T
E
P
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
:
Up
ad
h
y
a
y
An
a
n
d
T
r
ilo
k
in
ath
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
A
ME
T
Un
i
v
er
s
it
y
,
C
h
en
n
ai
.
1.
I
NT
RO
D
UCT
I
O
N
P
o
in
tin
g
o
f
p
r
ac
tical
p
r
o
d
u
ctiv
it
y
a
n
d
s
ec
u
r
it
y
ac
co
m
p
lis
h
m
en
ts
in
m
o
d
er
n
p
r
o
ce
d
u
r
es
is
a
d
o
w
n
an
d
o
u
t
e
x
p
lan
atio
n
b
eh
i
n
d
h
elp
o
f
a
s
u
b
s
ta
n
tia
l
an
d
u
s
e
f
u
l
d
e
m
o
n
s
tr
ati
v
e
f
r
a
m
e
w
o
r
k
.
L
atel
y
,
m
u
c
h
ex
a
m
in
at
io
n
s
a
n
d
r
esear
ch
w
o
r
k
s
h
a
v
e
b
ee
n
p
r
o
d
u
ce
d
to
ac
co
m
p
li
s
h
co
m
p
elli
n
g
p
r
o
ce
d
u
r
e
ch
ec
k
i
n
g
s
tr
ate
g
y
b
y
u
tili
s
atio
n
o
f
a
f
e
w
s
y
s
te
m
s
,
f
o
r
ex
a
m
p
le,
i
n
f
o
r
m
atio
n
d
r
o
v
e
b
ased
s
tr
ateg
ies,
s
h
o
w
b
ased
tech
n
iq
u
es,
a
n
d
ex
p
o
s
ito
r
y
tech
n
iq
u
e
s
.
E
ac
h
o
f
th
e
s
e
ap
p
r
o
ac
h
es
h
as
its
p
ar
ticu
lar
f
a
v
o
u
r
ab
le
p
o
s
itio
n
an
d
in
clin
at
io
n
.
I
n
an
y
ca
s
e,
th
er
e
ar
e
n
u
m
er
o
u
s
im
p
ed
i
m
e
n
ts
i
n
an
i
n
cr
ed
ib
le
n
u
m
b
er
o
f
cir
cu
m
s
ta
n
ce
s
,
w
h
ich
d
i
m
i
n
is
h
d
ep
en
d
ab
ilit
y
an
d
ex
ac
t
n
es
s
o
f
r
ec
o
m
m
e
n
d
ed
s
tr
ateg
y
.
A
s
i
n
d
icate
d
b
y
th
o
r
o
u
g
h
r
elatio
n
s
a
m
o
n
g
s
t
in
f
o
r
m
atio
n
a
n
d
y
ield
f
ac
to
r
s
in
co
n
v
o
l
u
ted
m
u
lt
iv
ar
iab
l
e
f
r
a
m
e
w
o
r
k
s
,
n
u
m
er
ical
m
o
d
el
d
ev
elo
p
m
e
n
t
i
s
ex
ce
p
tio
n
all
y
tr
o
u
b
leso
m
e
a
n
d
ev
en
o
u
tlan
d
i
s
h
i
n
a
f
e
w
ca
s
es.
Gr
ap
h
ical
j
o
in
t
ch
an
g
es
b
et
w
ee
n
p
r
o
ce
s
s
f
ac
to
r
s
a
n
d
p
r
o
b
ab
ilis
tic
i
n
v
esti
g
a
tio
n
s
i
n
s
tr
u
m
e
n
t
s
i
n
B
B
Ns
ar
e
ess
e
n
tia
l
i
n
te
n
d
s
to
m
a
n
ag
e
to
h
an
d
le
co
m
p
le
x
itie
s
a
n
d
v
u
l
n
er
ab
ilit
i
es.
T
h
ese
co
m
p
o
n
e
n
t
s
m
ak
e
B
B
Ns
an
i
n
cr
ed
ib
le
p
r
o
ce
d
u
r
e
ch
ec
k
in
g
ap
p
ar
atu
s
to
d
ea
l
w
it
h
co
m
p
lex
f
r
a
m
e
wo
r
k
s
.
E
ar
ly
co
m
p
r
eh
e
n
s
io
n
o
f
an
y
ab
n
o
r
m
alit
y
o
f
a
p
r
o
ce
s
s
f
r
o
m
an
o
r
d
in
ar
y
o
p
er
atio
n
an
d
r
ec
o
g
n
i
s
i
n
g
th
e
w
e
lls
p
r
in
g
o
f
it
is
a
n
e
x
p
r
ess
i
v
e
te
s
t
i
n
co
m
p
le
x
p
r
ese
n
t
-
d
a
y
s
tr
u
ct
u
r
es.
As
a
m
o
d
er
n
b
en
c
h
m
ar
k
p
r
o
ce
s
s
,
T
E
P
h
as
u
til
is
ed
f
o
r
ex
a
m
in
atio
n
o
f
t
h
ese
d
i
f
f
ic
u
lties
in
b
o
th
,
co
n
tr
o
l
an
d
o
p
er
atio
n
ch
ec
k
in
g
f
ield
s
[
1
]
.
Am
o
n
g
T
E
P
h
an
d
le
ch
ec
k
i
n
g
ap
p
r
o
ac
h
es,
w
e
ca
n
p
o
in
t
f
is
h
er
d
is
cr
i
m
in
a
n
t
ex
a
m
in
at
io
n
,
d
is
cr
i
m
in
a
n
t i
n
c
o
m
p
lete
s
li
g
h
test
s
q
u
ar
es,
an
o
f
f
icial
p
ar
t in
v
esti
g
atio
n
.
2.
B
AYES
I
AN
B
E
L
I
E
F
N
E
T
WO
RK
S:
A
RE
V
I
E
W
B
B
Ns
is
a
co
o
r
d
in
ated
n
o
n
-
c
y
clic
ch
ar
t
b
et
w
ee
n
f
r
a
m
e
w
o
r
k
's
f
ac
to
r
s
[
2
]
.
A
m
ix
o
f
a
p
ar
en
t,
k
id
,
an
d
r
o
o
t
h
u
b
s
w
i
th
ca
u
s
al
li
n
k
ag
e
m
a
k
e
a
s
y
s
te
m
f
o
r
r
estrictiv
e
an
d
p
r
o
b
ab
ilis
tic
in
v
es
tig
a
ti
o
n
s
.
E
v
er
y
k
id
h
u
b
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
2
0
1
8
:
68
–
72
69
h
as
a
p
ar
e
n
t
s
u
b
o
r
d
in
ate
li
k
eli
h
o
o
d
co
n
v
e
y
an
ce
o
r
co
n
d
itio
n
al
lik
el
ih
o
o
d
(
C
P
)
.
Ho
w
e
v
er
,
R
o
o
t
h
u
b
s
h
av
e
n
o
p
ar
en
t
an
d
th
e
ir
lik
e
lih
o
o
d
ap
p
r
o
p
r
iatio
n
.
Su
b
s
eq
u
en
t
l
y
,
a
B
B
N
co
m
p
r
is
es
o
f
ce
n
tr
es,
co
o
r
d
in
ated
lin
es,
a
n
d
h
u
b
s
'
li
k
eli
h
o
o
d
d
is
s
e
m
i
n
atio
n
s
.
An
y
m
o
m
e
n
tar
y
o
u
ts
id
e
d
ata
f
o
r
ev
er
y
h
u
b
ca
n
b
e
u
til
is
ed
to
in
s
ta
n
tiate
t
h
e
lik
eli
h
o
o
d
cir
cu
latio
n
o
f
t
h
at
h
u
b
.
B
y
u
tili
s
atio
n
o
f
th
e
s
e
c
o
n
f
ir
m
atio
n
s
a
n
d
f
r
a
m
e
w
o
r
k
's
i
n
f
o
r
m
atio
n
,
o
u
r
co
n
v
ictio
n
w
ill
r
ef
er
f
o
r
th
e
s
y
s
te
m
,
an
d
o
th
er
h
u
b
s
'
li
k
eli
h
o
o
d
d
is
s
e
m
i
n
atio
n
s
ca
n
b
e
f
i
g
u
r
ed
[
4
-
5
]
.
Pro
v
e
p
r
o
lif
er
atio
n
i
n
co
n
v
i
c
tio
n
r
ef
r
esh
i
n
g
w
ill
lead
t
h
e
B
B
N
co
u
n
t
to
p
r
o
b
ab
ilis
tic
o
b
s
tr
u
ctio
n
h
an
d
le
f
ig
u
r
i
n
g
,
w
h
ic
h
is
d
e
p
icted
b
y
B
a
y
e
s
'
r
u
n
th
e
s
h
o
w
:
(
|
)
=
(
|
)
(
)
(
)
A
a
n
d
E
ar
e
p
r
o
p
o
s
itio
n
al
v
a
r
iab
les.
Fig
u
r
e
1
r
ep
r
esen
t
s
t
h
e
co
n
s
tr
u
cted
B
B
Ns
s
tr
u
ct
u
r
e
f
o
r
f
a
u
lt
d
iag
n
o
s
i
s
p
u
r
p
o
s
e
co
n
s
i
s
ts
o
f
t
h
r
ee
la
y
er
s
:
f
a
u
lts
,
p
atter
n
a
n
d
p
r
o
ce
s
s
v
ar
iab
les.
Fig
u
r
e
1
.
B
B
Ns
Stru
ctu
r
e
f
o
r
Fau
lt Dia
g
n
o
s
i
s
P
er
f
o
r
m
a
n
ce
o
f
lea
f
s
p
r
in
g
s
m
ad
e
o
f
co
m
p
o
s
i
te
m
ater
ial
s
u
b
j
ec
ted
to
lo
w
-
f
r
eq
u
e
n
c
y
i
m
p
a
ct
lo
ad
in
g
w
a
s
p
r
o
p
o
s
ed
an
d
d
escr
ib
ed
in
[
6
]
.
A
r
ec
u
r
r
en
t
E
l
m
an
n
e
u
r
al
n
et
w
o
r
k
-
b
ased
ap
p
r
o
ac
h
to
d
etec
t
th
e
p
r
ese
n
ce
o
f
an
ep
ilep
tic
attac
k
in
E
lec
tr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
s
i
g
n
als
s
u
g
g
ested
i
n
w
h
ich
t
h
e
f
a
u
lts
o
r
an
y
s
e
v
er
e
attac
k
s
ar
e
d
etec
ted
u
s
in
g
n
e
u
r
al
n
et
w
o
r
k
[
7
]
.
A
s
o
f
t
co
m
p
u
tin
g
ap
p
r
o
ac
h
p
r
o
p
o
s
ed
[
8
]
w
h
ich
is
b
ased
o
n
s
h
ip
tr
aj
ec
to
r
y
co
n
tr
o
l
f
o
r
m
ar
in
e
ap
p
licatio
n
s
.
I
n
th
i
s
p
ap
er
[
9
]
,
a
s
o
lu
tio
n
b
ased
o
n
th
e
n
eu
r
al
f
u
zz
y
in
f
er
en
ce
s
y
s
te
m
(
A
NFI
S)
is
p
r
esen
ted
to
ac
h
iev
e
t
h
e
o
b
j
e
ctiv
es
o
f
f
a
u
lt
d
etec
tio
n
,
is
o
la
tio
n
in
a
s
atel
lite
's
AC
S
n
o
n
li
n
ea
r
s
y
s
te
m
w
it
h
th
e
m
ea
s
u
r
e
m
en
t
o
f
th
e
s
tate.
T
h
e
d
is
co
v
er
y
an
d
r
ep
lace
m
en
t
o
f
th
e
s
w
itc
h
e
s
d
is
cu
s
s
ed
i
n
t
h
i
s
p
ap
er
[
1
0
]
ar
e
d
o
n
e
b
y
m
ea
s
u
r
in
g
th
e
li
n
e
an
d
p
h
a
s
e
v
o
ltag
e
s
o
f
a
n
i
n
v
e
r
ter
an
d
co
m
p
ar
i
n
g
it
w
it
h
th
e
r
ef
er
e
n
ce
v
o
ltag
e
s
w
h
ic
h
ar
e
u
s
ed
to
i
n
te
r
r
u
p
t
th
e
p
r
o
ce
s
s
o
r
to
p
r
o
v
id
e
t
h
e
g
ati
n
g
p
u
ls
e
s
o
f
a
f
a
u
lt
y
s
w
itc
h
to
t
h
e
e
x
tr
a
ar
m
.
Fro
m
[
1
1
]
w
e
s
t
u
d
ied
a
k
i
n
d
o
f
ad
ap
tiv
e
v
ar
iab
le
s
tep
le
n
g
th
n
at
u
r
al
g
r
ad
ie
n
t
alg
o
r
ith
m
.
T
h
r
o
u
g
h
t
h
e
ex
p
er
i
m
en
tal
an
a
l
y
s
is
,
t
h
i
s
m
e
th
o
d
c
an
b
etter
s
ep
ar
ate
th
e
g
ea
r
b
o
x
el
ec
tr
ic
s
i
g
n
al,
b
y
r
esear
ch
in
g
t
h
e
s
ep
ar
atio
n
s
i
g
n
al
s
p
ec
tr
u
m
,
t
h
e
g
ea
r
b
o
x
f
au
lt
d
iag
n
o
s
is
r
ea
li
s
ed
.
I
n
th
e
f
u
r
t
h
er
,
th
e
m
o
r
e
ef
f
icien
t
p
r
o
ce
s
s
w
ill
b
e
p
r
esen
ted
to
co
m
p
lete
m
ec
h
a
n
ica
l
f
au
l
t
t
y
p
e
d
iag
n
o
s
is
.
T
h
e
s
u
b
m
itted
p
ap
er
[
1
2
]
ex
p
lain
ed
ab
o
u
t
t
h
e
s
p
ee
d
co
n
tr
o
l o
f
b
r
u
s
h
le
s
s
d
c
m
o
to
r
u
s
i
n
g
t
h
e
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
.
T
h
e
p
r
o
p
o
s
ed
cir
cu
it
h
as
a
co
n
ti
n
u
o
u
s
f
lo
w
o
f
cu
r
r
en
t
to
th
e
s
e
n
s
o
r
les
s
b
r
u
s
h
les
s
d
c
m
o
to
r
.
T
h
e
d
esig
n
an
d
u
s
e
o
f
s
o
lar
p
an
el
f
o
r
ex
tr
ac
ti
n
g
t
h
e
m
a
x
i
m
u
m
p
o
w
e
r
an
d
th
e
p
o
w
er
f
ed
i
n
to
th
e
B
L
D
C
m
o
to
r
.
3.
P
RO
P
O
SE
D
B
B
NS F
O
R
F
AULT
D
E
T
E
C
T
I
O
N
A
ND
DI
AG
NO
S
I
S
I
n
th
is
p
ap
er
,
B
B
Ns
b
ased
m
o
d
el
f
o
r
Fau
lt
Dete
ctio
n
an
d
Di
ag
n
o
s
is
(
FDD)
is
p
r
o
p
o
s
ed
,
ta
k
in
g
af
ter
s
u
p
p
o
s
itio
n
s
o
u
g
h
t to
co
n
s
id
er
:
No
s
en
s
o
r
,
co
n
tr
o
ller
,
o
r
ac
tu
ato
r
f
la
w
s
.
T
h
er
e
o
u
g
h
t
to
b
e
n
o
in
clin
at
io
n
,
f
lo
at,
an
d
cla
m
o
u
r
,
s
en
s
o
r
b
la
m
e
s
o
r
ts
,
co
n
tr
o
ller
d
is
ap
p
o
in
t
m
e
n
t o
r
ac
tu
ato
r
d
is
ap
p
o
in
t
m
e
n
t.
FDD
e
x
ec
u
tio
n
p
er
io
d
m
o
r
e
p
r
o
m
i
n
en
t
t
h
an
o
r
eq
u
i
v
ale
n
t
to
th
e
e
s
ti
m
atio
n
i
n
s
p
ec
ti
n
g
p
er
io
d
.
T
h
e
FDD
ex
ec
u
tio
n
p
er
io
d
h
as
ac
ce
p
ted
an
eq
u
iv
ale
n
t
o
r
m
o
r
e
p
r
o
m
i
n
en
t
th
a
n
t
h
e
test
in
g
ti
m
e
o
f
t
h
e
s
en
s
o
r
esti
m
at
io
n
s
[
3
]
.
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
n
a
lysi
s
o
f B
B
N
s
Ove
r
F
a
u
lt De
tectio
n
a
n
d
Dia
g
n
o
s
is
in
I
n
d
u
s
tr
ia
l
A
p
p
lica
tio
n
(
Up
a
d
h
ya
y
A
.
T
.
)
70
A
cc
e
s
s
ib
ilit
y
o
f
p
r
o
ce
s
s
m
o
d
e
l o
r
p
r
o
ce
s
s
i
n
f
o
r
m
atio
n
.
T
h
er
e
o
u
g
h
t
to
b
e
ad
eq
u
ate
an
d
e
x
ac
t p
r
o
ce
s
s
s
cien
t
if
ic
o
r
ex
p
lan
ato
r
y
m
o
d
el
o
r
p
r
o
ce
s
s
in
f
o
r
m
atio
n
to
p
o
r
tr
ay
th
e
r
elatio
n
s
h
ip
am
o
n
g
t
h
e
p
r
o
ce
d
u
r
e
f
ac
to
r
s
.
No
s
y
n
c
h
r
o
n
o
u
s
b
la
m
e
s
o
r
ts
.
Div
er
s
e
s
o
r
ts
o
f
p
r
o
ce
s
s
b
la
m
e
d
o
n
'
t
h
ap
p
en
s
i
m
u
ltan
eo
u
s
l
y
.
3
.
1
.
P
r
o
ce
du
re
Str
uct
ure
T
h
e
p
r
o
p
o
s
ed
s
y
m
p
to
m
atic
f
r
a
m
e
w
o
r
k
co
m
p
r
is
e
s
o
f
8
s
ta
g
es.
T
h
e
w
h
o
le
tec
h
n
iq
u
e
s
u
cc
ess
io
n
i
s
as
p
er
th
e
f
o
llo
w
in
g
:
A
t
t
h
e
in
itia
l
s
tep
,
p
r
im
ar
y
d
atab
ase
o
u
g
h
t
to
b
e
r
ea
d
y
.
R
ec
o
r
d
s
ca
n
ac
co
m
p
l
is
h
b
y
u
ti
lis
atio
n
o
f
p
r
o
ce
s
s
s
cien
ti
f
ic
m
o
d
el
o
r
p
r
o
ce
s
s
o
n
li
n
e
d
y
n
a
m
ic
i
n
f
o
r
m
a
tio
n
.
C
o
n
s
is
te
n
t
s
ta
te
v
al
u
es
a
n
d
th
e
len
ie
n
t
d
ev
iatio
n
f
r
o
m
u
n
f
al
ter
in
g
s
tate
q
u
al
ities
o
u
g
h
t
to
r
eso
lv
e
f
o
r
ea
ch
o
f
t
h
e
co
n
tr
o
lled
as
w
ell
as f
u
n
d
a
m
en
tal
ch
ec
k
ed
f
ac
to
r
s
.
(
±
_
f
r
o
m
s
e
t p
o
in
t)
Fo
r
ea
ch
o
f
th
e
m
o
n
ito
r
ed
o
r
p
r
im
ar
y
c
h
ec
k
ed
v
ar
iab
le,
u
p
p
er
an
d
lo
w
er
co
n
s
tr
ain
t
f
o
r
n
o
r
m
a
l
d
eleg
ate
s
tate
i
s
d
o
led
o
u
t.
T
y
p
ical
s
tate
u
p
p
er
an
d
l
o
w
er
li
m
it=
s
tead
y
-
s
tate
v
al
u
e±
∞
Fo
r
attr
ac
tiv
e
p
r
o
ce
s
s
o
p
er
atio
n
,
th
e
s
e
f
ac
to
r
s
o
u
g
h
t to
b
e
k
ep
t u
p
at
th
eir
s
ati
s
f
ac
to
r
y
r
a
n
g
e.
So
m
e
cr
itical
s
tate
s
(
n
)
f
o
r
ea
c
h
o
f
th
e
p
r
o
ce
d
u
r
e
f
ac
to
r
s
ch
o
s
en
i
n
t
h
e
w
a
y
t
h
at
co
v
er
s
t
h
e
ag
g
r
e
g
ate
ch
an
g
e
g
o
f
o
r
th
at
p
r
ed
ef
i
n
ed
f
ac
to
r
s
estee
m
.
I
n
t
h
is
w
a
y
,
i
n
li
g
h
t
o
f
t
y
p
ical
s
tate
u
p
p
er
an
d
lo
w
e
r
co
n
s
tr
ain
t,
n
-
1
s
ta
tes
ar
e
p
r
o
d
u
ce
d
b
y
a
s
i
m
ilar
co
n
tai
n
er
s
i
ze
an
d
eq
u
i
v
alen
t
s
tate
s
h
i
g
h
an
d
lo
w
e
r
th
e
o
r
d
in
ar
y
s
ta
te.
B
B
Ns
s
tr
u
ct
u
r
e
b
u
ilt
b
y
t
h
e
p
l
an
o
f
s
y
s
te
m
la
y
er
s
,
f
o
r
e
x
a
m
p
le,
f
la
w
s
,
d
esi
g
n
ac
k
n
o
w
led
g
e
m
en
t
an
d
m
ea
s
u
r
ed
f
ac
to
r
s
.
I
n
th
is
p
r
o
g
r
ess
io
n
,
u
tili
s
i
n
g
a
n
y
r
ig
h
t
h
an
d
,
f
o
r
ex
a
m
p
le,
Ma
tlab
o
r
s
o
m
e
o
th
er
p
r
o
g
r
am
m
i
n
g
ca
n
co
m
e
ab
o
u
t
b
etter
,
y
et
th
er
e
is
n
o
co
n
s
tr
ai
n
t.
No
t
w
it
h
s
ta
n
d
in
g
,
B
B
Ns
d
iag
r
a
m
ca
n
b
e
led
b
y
u
tili
s
in
g
m
aster
lear
n
in
g
,
a
n
d
p
r
o
ce
s
s
in
f
o
r
m
atio
n
co
n
tex
t
u
al
i
n
v
esti
g
atio
n
f
o
r
t
h
e
m
ea
n
in
g
o
f
f
ac
to
r
s
co
o
r
d
in
ated
co
n
n
ec
t
io
n
s
.
C
P
in
f
o
r
m
atio
n
o
u
g
h
t
to
b
e
f
ig
u
r
ed
b
y
an
aid
e
o
f
Mo
n
t
C
ar
lo
r
e
-
en
ac
t
m
e
n
t
a
n
d
th
e
d
et
er
m
in
is
tic
co
n
n
ec
tio
n
b
et
w
ee
n
f
ac
to
r
s
o
r
b
y
u
tili
s
i
n
g
n
o
r
m
al
s
tate
s
v
ar
iab
le
in
f
o
r
m
atio
n
an
d
B
B
N
s
lear
n
in
g
ab
ilit
y
.
I
n
t
h
is
p
ap
er
,
ass
u
r
a
n
c
e
o
f
C
P
in
f
o
r
m
atio
n
d
ep
en
d
s
o
n
th
e
s
ec
o
n
d
s
tr
ate
g
y
.
Fo
r
r
ec
r
ea
tio
n
o
f
ea
ch
p
r
o
ce
d
u
r
e,
ev
er
y
s
i
n
g
le
ab
o
v
e
s
tr
id
e
p
r
o
d
u
ce
d
.
4.
RE
SU
L
T
T
h
e
p
r
o
p
o
s
ed
p
r
o
ce
d
u
r
e
a
p
p
li
ed
o
n
T
E
P
.
T
h
er
e
a
r
e
th
r
ee
p
h
ases
f
o
r
FDD
p
u
r
p
o
s
e:
P
h
a
s
e1
.
Gen
er
atio
n
o
f
th
e
r
eq
u
ir
ed
d
ata
s
et.
Usi
n
g
F
OR
T
R
A
N
co
d
e,
tr
ain
in
g
an
d
test
i
n
g
d
atase
t
co
n
s
tr
u
cted
f
o
r
all
m
a
n
ip
u
lat
ed
an
d
m
ea
s
u
r
ed
v
ar
iab
les,
e
x
ce
p
t
r
ea
cto
r
ag
itatio
n
s
p
ee
d
v
ar
iab
le,
d
ef
in
ed
as
b
elo
w
v
ec
to
r
:
X=
[
XM
E
AS(
1
)
,
…,
XM
AS(
4
1
)
,
XM
V(
1
)
,
…,
XM
V(
1
1
)
]
T
T
h
e
d
ata
in
th
e
tr
ain
in
g
s
et
g
e
n
er
ated
f
r
o
m
f
o
u
r
s
i
m
u
latio
n
r
u
n
s
,
o
n
e
f
o
r
n
o
r
m
al
o
p
er
atio
n
(
f
au
lt=0
)
an
d
th
e
r
est
f
o
r
s
p
ec
if
ied
t
y
p
e
s
o
f
f
a
u
lt (
f
a
u
lt=4
,
9
,
1
1
; sep
ar
a
tel
y
)
.
Fo
r
ea
ch
r
u
n
,
t
h
e
s
i
m
u
latio
n
ti
m
e
is
2
5
h
o
u
r
s
.
A
to
tal
n
u
m
b
er
o
f
g
e
n
er
ated
tr
ain
i
n
g
d
ata
is
4
8
0
o
b
s
er
v
atio
n
s
.
T
h
e
d
ata
in
th
e
t
esti
n
g
s
et
p
r
o
d
u
ce
d
in
th
e
s
a
m
e
o
r
d
er
o
f
th
e
tr
ain
in
g
s
et.
T
h
e
o
n
l
y
d
if
f
er
en
ce
i
s
s
i
m
u
lat
io
n
r
u
n
ti
m
e
t
h
at
is
4
8
h
o
u
r
s
.
T
o
tal
test
in
g
d
ata
is
9
6
0
o
b
s
er
v
atio
n
s
.
P
h
a
s
e
I
I
.
Fau
lt
d
etec
tio
n
p
r
o
ce
d
u
r
e
.
Af
ter
r
eq
u
ir
ed
d
atab
ase
g
en
er
atio
n
,
d
ir
ec
ted
lin
k
s
b
et
w
ee
n
f
au
lt
n
o
d
es
an
d
co
n
tr
o
lled
v
ar
iab
le
s
o
f
T
E
P
s
h
o
u
ld
d
eter
m
in
e.
T
h
e
co
n
s
tr
u
cted
B
B
Ns
m
o
d
el
f
o
r
f
a
u
lt
d
etec
tio
n
r
ep
r
esen
ted
.
B
y
u
til
is
atio
n
o
f
t
r
ain
ed
d
ata
s
et
a
n
d
g
e
n
er
atio
n
o
f
r
eq
u
ir
ed
s
tates
(
s
tep
2
-
4
o
f
s
ec
tio
n
I
I
I
)
,
B
B
Ns
m
o
d
el
te
s
ted
f
o
r
ex
p
o
s
u
r
e
o
f
p
r
o
b
a
b
le
d
ev
ian
ce
f
r
o
m
n
o
r
m
al
o
p
er
atio
n
.
T
h
e
p
r
o
p
o
s
ed
r
esu
lt
e
n
s
u
r
es
t
h
at
B
B
Ns
ar
e
ca
p
ab
le
o
f
ac
cu
r
ate
f
au
lt
id
en
ti
f
icatio
n
i
n
p
r
o
ce
s
s
.
T
h
e
in
ter
esti
n
g
p
o
in
t
o
f
th
e
r
es
u
lt
is
th
a
t
d
etec
tio
n
ti
m
e
w
a
s
les
s
th
a
n
1
8
0
s
ec
.
P
h
a
s
e
I
I
I
.
Fau
lt
d
iag
n
o
s
is
p
r
o
ce
d
u
r
e.
Fo
r
th
is
task
,
B
B
Ns
s
h
o
u
ld
r
ec
o
g
n
i
s
e
th
e
t
y
p
e
o
f
f
a
u
lt,
w
h
ich
o
cc
u
r
r
ed
in
t
h
e
s
y
s
te
m
.
Fo
r
t
h
is
p
u
r
p
o
s
e,
B
B
Ns
d
ir
ec
ted
lin
k
s
b
et
w
ee
n
f
au
l
t
n
o
d
es
(
n
o
r
m
al=
0
,
f
a
u
lt=1
)
a
n
d
r
elate
d
x
v
ar
iab
les
s
h
o
u
ld
b
e
d
eter
m
in
ed
.
T
h
e
v
ital
p
ar
t
o
f
B
B
Ns
m
o
d
el
is
p
atter
n
la
y
er
.
I
n
th
is
p
ap
er
,
th
is
s
eg
m
e
n
t
estab
li
s
h
ed
b
y
u
s
in
g
d
ata
an
al
y
s
is
o
f
ea
ch
f
a
u
lt.
Fo
r
m
ak
i
n
g
it
m
o
r
e
tr
a
n
s
p
ar
en
t,
f
au
lt
4
an
d
1
1
ca
s
e
s
tu
d
y
c
u
r
v
e
s
s
h
o
w
n
i
n
f
i
g
u
r
es
2
.
A
cc
o
r
d
in
g
to
th
ese
s
tatis
tic
s
,
at
th
e
ti
m
e
o
f
f
ail
u
r
e
f
o
u
r
o
cc
u
r
r
en
ce
,
x
m
v
(
1
0
)
r
ea
ch
es
n
e
w
s
tead
y
-
s
tate
v
a
lu
e.
X
m
ea
s
(
9
)
m
o
v
es
ab
r
u
p
tl
y
a
t
f
a
u
lt
t
i
m
e
an
d
r
et
u
r
n
s
to
it
s
i
n
itial
v
al
u
e.
U
s
in
g
th
ese
ca
s
e
s
tu
d
ie
s
,
T
E
P
B
ay
esian
n
et
w
o
r
k
m
o
d
el.
Af
ter
tr
ain
i
n
g
t
h
e
s
y
s
te
m
s
g
e
n
er
ated
B
B
Ns
s
tu
d
ied
f
o
r
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
2
0
1
8
:
68
–
72
71
s
ev
er
al
s
i
m
u
latio
n
s
r
u
n
s
.
T
est
r
esu
lt
s
s
h
o
w
a
n
ac
c
u
r
ac
y
o
f
d
iag
n
o
s
i
s
i
n
m
o
r
e
th
a
n
al
m
o
s
t
9
0
%
o
f
s
eq
u
en
ce
s
.
Up
o
n
th
is
,
B
a
y
e
s
ia
n
n
et
w
o
r
k
p
r
o
v
es to
b
e
a
ca
p
a
b
le
d
iag
n
o
s
tic
s
y
s
te
m
.
Fig
u
r
e
2
.
C
ase
St
u
d
y
o
f
Fau
l
t
5.
CO
NCLU
SI
O
N
I
n
th
i
s
ar
ticle,
w
e
co
n
ce
n
tr
ate
o
n
B
a
y
esia
n
co
n
v
ict
io
n
s
y
s
te
m
s
e
x
ec
u
tio
n
a
s
a
co
m
p
ete
n
t
d
ev
ice
f
o
r
m
ec
h
a
n
ical
p
r
o
ce
d
u
r
es
b
la
m
e
s
lo
ca
tio
n
an
d
d
eter
m
i
n
atio
n
.
T
h
is
s
y
s
te
m
d
ep
en
d
s
o
n
ca
u
s
e
i
m
p
ac
t
co
n
n
ec
tio
n
b
et
w
ee
n
f
ac
to
r
s
.
A
d
ef
icie
n
ci
es
d
atab
ase
is
f
u
n
d
a
m
en
tal
f
o
r
b
u
ild
in
g
p
r
o
ce
s
s
b
la
m
e
d
is
c
o
v
er
y
a
n
d
an
al
y
s
i
s
B
B
Ns
s
h
o
w
.
E
x
ec
u
tio
n
o
f
B
B
Ns
o
n
T
E
P
ca
n
af
f
ir
m
t
h
e
ad
eq
u
ac
y
o
f
t
h
i
s
d
e
m
o
n
s
tr
a
tiv
e
f
r
a
m
e
w
o
r
k
i
n
s
p
ec
if
ic
m
ec
h
a
n
ical
p
r
o
ce
d
u
r
es.
As
p
er
th
e
test
o
u
tco
m
es,
lo
ca
tio
n
an
d
an
al
y
s
is
w
er
e
q
u
ick
an
d
s
u
f
f
icie
n
tl
y
p
r
ec
is
e
to
av
o
id
th
e
o
cc
u
r
r
en
c
e
o
f
an
y
ca
tac
l
y
s
m
ic
o
cc
asio
n
s
in
t
h
e
f
r
a
m
e
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
M
a
jee
d
BA
,
Ru
c
k
N.
S
tatisti
c
a
l
c
o
n
tr
o
l
b
a
se
d
f
a
u
lt
d
e
tec
ti
o
n
o
f
c
h
i
p
u
n
it
s.
C
o
n
tr
o
l
E
n
g
in
e
e
rin
g
.
2
0
0
1
;
8
:
13
-
2
0
.
[2
]
Do
w
n
s J J,
V
o
g
e
l
E
F
.
A
p
lan
t
-
wid
e
in
d
u
strial
p
r
o
c
e
ss
c
o
n
tro
l
p
r
o
b
lem
.
Ch
e
mic
a
l
En
g
in
e
e
rin
g
.
1
9
9
3
;
1
7
(2
)
.
[3
]
Rick
e
r
N.
D
e
c
e
n
tralize
d
c
o
n
tro
l
o
f
th
e
T
e
n
n
e
ss
e
e
Eas
t
m
a
n
c
h
a
ll
e
n
g
e
.
J
o
u
rn
a
l
o
f
Pro
c
e
ss
Co
n
tr
o
l
.
1
9
9
7
;
7
(3
):
2
0
5
-
2
2
1
.
[4
]
Yo
o
C,
L
e
e
I
B.
M
o
n
it
o
rin
g
o
f
a
d
y
n
a
m
i
c
p
ro
c
e
ss
b
a
se
d
o
n
a
n
in
d
e
p
e
n
d
e
n
t
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis.
Ch
e
mic
a
l
En
g
i
n
e
e
rin
g
.
2
0
0
3
;
7
0
(
1
0
):
2
9
9
5
-
3
0
0
6
.
[5
]
Ch
ian
g
L
,
Ru
ss
e
ll
E
L
,
Bra
a
t
z
R
D.
F
a
u
lt
d
iag
n
o
sis
in
th
e
c
h
e
m
ica
l
p
ro
c
e
ss
u
sin
g
f
ish
e
r
d
isc
ri
m
in
a
n
t
a
n
d
p
rin
c
i
p
le
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
.
Ch
e
mo
me
trics
a
n
d
In
telli
g
e
n
t
L
a
b
o
r
a
to
ry
.
2
0
0
2
;
5
1
(
3
):
2
4
3
-
3
5
2
.
[6
]
Ra
jes
h
S
,
B
h
a
sk
a
r
G
B,
V
e
n
k
a
tac
h
a
la
m
J,
P
a
z
h
a
n
iv
e
l
K,
S
a
g
a
d
e
v
a
n
S
.
P
e
rf
o
rm
a
n
c
e
o
f
lea
f
s
p
rin
g
s
m
a
d
e
o
f
c
o
m
p
o
site
m
a
teria
l
su
b
jec
ted
to
l
o
w
-
f
r
e
q
u
e
n
c
y
i
m
p
a
c
t
l
o
a
d
in
g
.
J
o
u
rn
a
l
o
f
M
e
c
h
a
n
ica
l
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
1
6
;
3
0
(9
)
:
4
2
9
1
-
4
2
9
8
.
[7
]
S
u
n
d
a
ra
m
S
,
A
ri
v
a
z
h
a
g
a
n
D,
Ga
n
e
sh
k
u
m
a
r
K.
A
re
c
u
rre
n
t
El
m
a
n
n
e
u
ra
l
n
e
tw
o
rk
-
b
a
se
d
a
p
p
ro
a
c
h
to
d
e
tec
t
th
e
p
re
se
n
c
e
o
f
e
p
il
e
p
ti
c
a
tt
a
c
k
in
El
e
c
tro
e
n
c
e
p
h
a
lo
g
ra
m
(EE
G
)
sig
n
a
ls.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
.
6
(
5
),
2
3
8
8
-
2
3
9
1
.
[8
]
S
e
th
u
ra
m
a
li
n
g
a
m
T
K,
N
a
g
a
r
a
j
B.
A
so
f
t
c
o
m
p
u
ti
n
g
a
p
p
ro
a
c
h
o
n
sh
ip
traje
c
to
ry
c
o
n
tro
l
f
o
r
m
a
ri
n
e
a
p
p
li
c
a
ti
o
n
s.
AR
PN
J
o
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s
,
2
0
1
5
.
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
n
a
lysi
s
o
f B
B
N
s
Ove
r
F
a
u
lt De
tectio
n
a
n
d
Dia
g
n
o
s
is
in
I
n
d
u
s
tr
ia
l
A
p
p
lica
tio
n
(
Up
a
d
h
ya
y
A
.
T
.
)
72
[9
]
Be
ll
a
li
Ba
d
re
,
A
.
H
a
z
z
a
b
,
I.
K.
Bo
u
ss
e
rh
a
n
e
,
Dim
it
ri
L
e
fe
b
v
r
e
.
A
De
c
o
u
p
led
P
a
ra
m
e
ters
Est
im
a
to
rs
f
o
r
in
No
n
l
i
n
e
a
r
S
y
ste
m
s
F
a
u
lt
d
iag
n
o
sis
b
y
A
NFIS
,
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(IJECE)
,
V
o
l
2
,
N
o
2
,
A
p
ril
2
0
1
2
,
p
p
.
1
6
6
-
1
7
4
.
[1
0
]
B.
Ju
stu
s
Ra
b
i,
F
a
u
lt
T
o
lera
n
t
C
o
n
tr
o
l
i
n
Z
-
S
o
u
rc
e
In
v
e
rter
F
e
d
I
n
d
u
c
t
io
n
M
o
to
r
,
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
),
Vo
l
1
,
No
1
,
S
e
p
tem
b
e
r
2
0
1
1
,
p
p
.
29
-
3
5
.
[1
1
]
Yu
Ch
e
n
,
Jin
ta
o
M
e
n
g
.
S
tu
d
y
o
n
BS
S
A
lg
o
rit
h
m
u
se
d
o
n
F
a
u
lt
Dia
g
n
o
sis
o
f
Ge
a
rb
o
x
,
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
EE
C)
,
Vo
l
1
1
,
No
6
,
J
u
n
e
2
0
1
3
,
P
P
.
2
9
4
2
-
2
9
4
7
.
[1
2
]
A
.
S
u
n
d
a
ra
m
,
G
.
P
.
Ra
m
e
sh
.
S
e
n
so
rles
s
Co
n
tr
o
l
o
f
BL
DC
M
o
to
r
u
sin
g
a
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
,
J
o
u
rn
a
l
o
f
M
C
S
q
u
a
r
e
S
c
ien
ti
fi
c
Res
e
a
rc
h
(
IJ
M
S
R),
Vo
l.
9
,
No
.
2
,
2
0
1
7
,
p
p
.
70
-
7
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.