I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
5
3
5
~
5
4
7
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
1
.
pp
535
-
5
4
7
535
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Identifica
tion o
f
f
a
ults in r
o
tati
ng
ma
chines usin
g
hi
g
h precisio
n
FBG
vib
ra
tion se
nso
r:
a
cas
e stu
dy
on
PM
sch
emes
Dipa
k
Ra
nja
n Na
y
a
k
1
,3
,
Nila
m
N
.
G
hu
g
e
1,
2
,
A
m
ba
rish
G
.
M
o
ha
pa
t
ra
3
,
P
ra
mo
d Sha
rma
1
,
Na
ra
y
a
n Na
y
a
k
3
,
Sa
t
y
a
priy
a
Sa
t
a
pa
t
hy
3
,
Ash
is
h K
ha
nn
a
4
1
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
(
U
o
T)
,
J
a
i
p
u
r
,
I
n
d
i
a
2
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
JS
P
M
’
s B
S
I
O
TR
,
P
u
n
e
,
I
n
d
i
a
3
E
l
e
c
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
S
i
l
i
c
o
n
U
n
i
v
e
r
si
t
y
,
S
i
l
i
c
o
n
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
(
S
I
T)
,
B
h
u
b
a
n
e
sw
a
r
,
I
n
d
i
a
4
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
M
a
h
a
r
a
j
a
A
g
r
a
s
e
n
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
(
M
A
I
T)
,
D
e
l
h
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
ul
5
,
2
0
2
3
R
ev
is
ed
J
u
n
15
,
2
0
2
4
Acc
ep
ted
J
u
n
25
,
2
0
2
4
P
re
d
ictiv
e
m
a
in
ten
a
n
c
e
(P
M
)
i
s
a
d
a
ta
-
d
ri
v
e
n
a
p
p
r
o
a
c
h
to
p
e
rfo
rm
in
g
p
ro
a
c
ti
v
e
m
a
in
ten
a
n
c
e
b
y
a
n
a
l
y
z
in
g
t
h
e
c
o
n
d
it
i
o
n
o
f
t
h
e
e
q
u
i
p
m
e
n
t
in
a
n
y
in
d
u
strial
se
tt
in
g
.
T
h
e
h
ig
h
-
p
r
e
c
isio
n
se
n
so
rs
a
re
wid
e
ly
a
d
a
p
ted
t
o
m
e
ti
c
u
lo
u
sl
y
a
n
a
ly
z
e
c
rit
ica
l
m
a
in
ten
a
n
c
e
c
o
n
d
it
i
o
n
s
u
si
n
g
s
u
c
h
a
d
a
ta
-
d
riv
e
n
a
p
p
r
o
a
c
h
.
I
n
a
sim
il
a
r
c
o
n
tex
t,
a
fi
b
e
r
b
ra
g
g
ra
ti
n
g
(
F
BG
)
s
e
n
so
r
is
a
p
a
ss
iv
e
a
n
d
h
ig
h
-
p
re
c
isio
n
se
n
s
o
r
t
h
a
t
is
wid
e
ly
u
se
d
i
n
i
n
d
u
st
ries
wh
e
re
c
o
n
v
e
n
ti
o
n
a
l
se
n
so
rs
a
re
n
o
t
p
re
f
e
rre
d
.
Bro
a
d
l
y
,
th
is
a
rti
c
le
p
re
se
n
ts
fo
u
r
su
b
e
lem
e
n
ts
of
th
e
p
ro
p
o
se
d
i
n
teg
ra
t
e
d
sy
ste
m
s
u
c
h
a
s
th
e
d
e
si
g
n
o
f
t
h
e
se
n
so
r
e
lem
e
n
t,
sig
n
a
l
p
ro
c
e
ss
in
g
sc
h
e
m
e
(S
P
S
),
m
a
c
h
i
n
e
lea
rn
in
g
(
M
L)
m
o
d
e
l
fo
r
p
re
d
ictin
g
a
n
o
m
a
li
e
s,
a
n
d
d
e
c
i
sio
n
su
p
p
o
r
t
s
y
ste
m
(DSS
)
to
su
g
g
e
st
m
a
in
ten
a
n
c
e
a
c
ti
o
n
s.
Als
o
,
t
h
is
a
rti
c
le
h
ig
h
li
g
h
ts
a
n
e
x
p
e
rime
n
tal
c
a
se
stu
d
y
o
n
v
i
b
ra
ti
o
n
m
o
n
it
o
r
in
g
a
n
d
a
n
a
ly
sis
o
f
re
a
l
-
ti
m
e
sig
n
a
ls
fo
r
m
a
k
in
g
p
ro
a
c
ti
v
e
m
a
in
te
n
a
n
c
e
d
e
c
isio
n
s.
An
F
BG
v
ib
ra
ti
o
n
se
n
s
o
r
o
f
c
e
n
ter
wa
v
e
len
g
th
1
,
5
5
0
n
m
is
d
e
sig
n
e
d
a
n
d
u
ti
li
z
e
d
t
o
a
c
q
u
ire
re
a
l
-
ti
m
e
v
i
b
ra
ti
o
n
sig
n
a
tu
re
s
o
f
a
r
o
tati
n
g
m
a
c
h
i
n
e
u
n
d
e
r
tes
t.
A
p
iez
o
e
lec
tri
c
v
i
b
ra
ti
o
n
se
n
s
o
r
is
u
se
d
with
t
h
e
F
BG
se
n
so
r
t
o
c
o
m
p
a
re
t
h
e
v
ib
ra
ti
o
n
re
sp
o
n
se
o
b
tain
e
d
d
u
ri
n
g
th
e
tes
t.
P
re
-
p
r
o
c
e
ss
in
g
o
f
ra
w
sig
n
a
ls
is
p
e
rf
o
rm
e
d
u
sin
g
a
m
o
v
in
g
a
v
e
ra
g
e
fil
ter
(M
AV
)
fo
ll
o
we
d
b
y
a
lo
w
p
a
ss
fil
ter
to
n
u
ll
i
fy
th
e
e
ffe
c
t
o
f
n
o
ise
.
To
o
b
tai
n
p
r
o
a
c
ti
v
e
m
a
in
t
e
n
a
n
c
e
d
e
c
isio
n
s,
a
DSS
m
o
d
e
l
i
s
p
re
p
a
re
d
b
y
c
o
n
sid
e
ri
n
g
t
h
e
p
ro
c
e
ss
e
d
v
ib
ra
ti
o
n
sig
n
a
tu
re
s.
Va
rio
u
s
m
a
in
ten
a
n
c
e
c
o
n
d
i
ti
o
n
s
a
re
tes
ted
d
u
ri
n
g
th
e
e
x
p
e
rime
n
tal
a
n
a
ly
sis
a
n
d
d
e
tail
e
d
re
su
lt
s
a
n
a
ly
sis
a
re
p
re
se
n
ted
.
K
ey
w
o
r
d
s
:
DSS
Fau
lt d
iag
n
o
s
is
FB
G
s
en
s
o
r
Ma
ch
in
e
lear
n
in
g
Pre
d
ictiv
e
m
ain
ten
an
ce
Sig
n
al
p
r
o
ce
s
s
in
g
Vib
r
atio
n
s
en
s
o
r
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Am
b
ar
is
h
G.
Mo
h
a
p
atr
a
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
Sil
ic
o
n
Un
iv
er
s
ity
,
Sil
ico
n
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
(
SIT
)
B
h
u
b
an
eswar
,
Od
is
h
a,
I
n
d
ia
E
m
ail: a
m
b
ar
is
h
.
m
o
h
ap
atr
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
s
h
if
t
in
m
o
d
er
n
h
is
to
r
y
f
r
o
m
an
ag
r
ar
ia
n
an
d
h
a
n
d
icr
af
t
ec
o
n
o
m
y
to
o
n
e
d
o
m
in
ated
b
y
in
d
u
s
tr
y
an
d
m
ac
h
in
e
p
r
o
d
u
ctio
n
was
k
n
o
w
n
as
th
e
in
d
u
s
tr
ial
r
e
v
o
lu
tio
n
.
T
ec
h
n
o
lo
g
y
b
r
o
u
g
h
t
ab
o
u
t
n
ew
way
s
o
f
liv
in
g
an
d
w
o
r
k
in
g
th
at
ch
a
n
g
ed
s
o
ciety
as
a
wh
o
le.
W
ith
th
e
in
tr
o
d
u
ctio
n
o
f
m
ec
h
a
n
izatio
n
,
wate
r
p
o
wer
,
an
d
s
team
p
o
wer
,
th
e
f
ir
s
t
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
(
I
n
d
u
s
tr
y
1
.
0
)
b
eg
a
n
in
th
e
1
8
th
ce
n
tu
r
y
.
T
h
e
s
ec
o
n
d
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
(
I
n
d
u
s
tr
y
2
.
0
)
,
wh
i
ch
b
eg
a
n
in
th
e
19
th
ce
n
tu
r
y
a
n
d
ce
n
ter
ed
ar
o
u
n
d
m
ass
p
r
o
d
u
ctio
n
an
d
ass
em
b
ly
lin
es
em
p
lo
y
in
g
elec
tr
icity
,
f
o
llo
wed
.
B
eg
in
n
in
g
in
t
h
e
1
9
7
0
s
o
f
th
e
2
0
th
ce
n
tu
r
y
,
t
h
e
th
ir
d
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
(
I
n
d
u
s
tr
y
3
.
0
)
wa
s
ch
ar
ac
ter
is
ed
b
y
th
e
in
tr
o
d
u
ctio
n
o
f
elec
tr
o
n
ics,
in
f
o
r
m
atio
n
tech
n
o
l
o
g
y
s
y
s
te
m
s
,
a
n
d
a
u
t
o
m
a
ti
o
n
.
T
h
e
s
e
d
e
v
e
l
o
p
m
e
n
t
s
p
a
v
e
d
t
h
e
w
a
y
f
o
r
t
h
e
f
o
u
r
t
h
i
n
d
u
s
t
r
i
a
l
r
e
v
o
l
u
t
i
o
n
(
I
n
d
u
s
t
r
y
4
.
0
)
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
535
-
5
4
7
536
wh
ich
is
as
s
o
ciate
d
with
cy
b
e
r
-
p
h
y
s
ical
s
y
s
tem
s
.
Fig
u
r
e
1
h
ig
h
lig
h
ts
th
e
co
n
ce
p
t
o
f
th
e
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
f
r
o
m
th
e
er
a
o
f
th
e
1
8
th
C
en
tu
r
y
to
th
e
2
0
th
C
en
tu
r
y
.
Fig
u
r
e
1
.
I
n
d
u
s
tr
ial
r
e
v
o
lu
tio
n
f
r
o
m
I
n
d
u
s
tr
y
1
.
0
to
I
n
d
u
s
tr
y
4
.
0
Prim
ar
y
r
o
tatin
g
m
ac
h
i
n
er
y
s
u
ch
as m
o
to
r
s
,
co
m
p
r
ess
o
r
s
,
g
e
n
er
ato
r
s
,
s
team
tu
r
b
in
es,
an
d
h
ig
h
-
s
p
ee
d
en
g
in
es
ar
e
cr
u
cial
to
m
o
d
er
n
in
d
u
s
tr
ial
p
r
o
ce
s
s
es
u
n
d
er
I
n
d
u
s
tr
y
4
.
0
[
1
]
-
[
3
]
.
Pre
cise
o
p
er
atio
n
an
d
f
a
u
lt
d
etec
tio
n
o
f
th
ese
m
ac
h
in
es
en
s
u
r
e
s
tab
le
in
d
u
s
tr
ial
p
r
o
ce
s
s
es.
Me
ch
an
ical
f
ailu
r
es
o
f
ten
m
an
if
est
as
v
ib
r
atio
n
s
[
4
]
,
[
5
]
,
wh
ic
h
ar
e
k
ey
p
ar
am
eter
s
f
o
r
eq
u
ip
m
en
t
h
ea
lth
a
n
d
s
af
ety
e
v
alu
atio
n
[
6
]
,
[
7
]
.
T
h
e
r
ef
o
r
e,
m
ea
s
u
r
in
g
v
ib
r
atio
n
s
ig
n
als
f
o
r
co
n
d
itio
n
an
d
f
au
lt
d
iag
n
o
s
is
o
f
r
o
tatin
g
m
ac
h
in
er
y
is
ess
en
tial
[
8
]
.
T
h
is
ar
ticle
h
ig
h
lig
h
ts
th
e
ca
p
ab
ili
ty
o
f
f
ib
er
b
r
ag
g
r
atin
g
(
FB
G
)
s
en
s
o
r
s
f
o
r
v
ib
r
atio
n
m
o
n
ito
r
in
g
o
f
r
o
tatin
g
m
ac
h
in
es a
n
d
in
ter
p
r
etin
g
th
e
ac
q
u
ir
ed
v
ib
r
atio
n
s
ig
n
atu
r
e
in
to
u
s
ef
u
l m
ac
h
in
e
f
au
lt d
ia
g
n
o
s
tics
.
F
B
G
s
en
s
o
r
s
ar
e
lig
h
tweig
h
t,
co
r
r
o
s
io
n
-
r
esis
tan
t,
E
MI
-
f
r
ee
,
an
d
s
m
aller
th
an
tr
ad
itio
n
al
s
en
s
o
r
s
.
B
ein
g
p
ass
iv
e,
th
ey
ar
e
s
u
itab
le
f
o
r
d
y
n
am
ic
d
is
tr
ib
u
t
ed
m
ea
s
u
r
em
en
ts
[
9
]
,
[
1
0
]
.
T
h
u
s
,
th
ey
ar
e
wid
ely
u
s
ed
f
o
r
h
ea
lth
m
o
n
ito
r
in
g
an
d
v
ib
r
atio
n
m
e
asu
r
em
en
t.
R
esear
ch
er
s
h
av
e
d
e
v
elo
p
e
d
FB
G
-
b
ased
v
ib
r
atio
n
s
en
s
o
r
s
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
n
o
n
-
u
n
if
o
r
m
FB
G
s
u
n
d
er
s
tr
ain
,
tem
p
er
atu
r
e,
an
d
v
ib
r
atio
n
lo
ad
s
.
C
h
ilelli
et
a
l.
[
1
1
]
ex
p
lain
ed
a
m
o
d
el
o
f
cr
ac
k
i
n
itiatio
n
an
d
g
r
o
wth
in
em
b
e
d
d
ed
m
etal
s
tr
u
ctu
r
es.
Yao
et
a
l.
[
1
2
]
d
is
cu
s
s
ed
FB
G
v
ib
r
atio
n
tu
n
in
g
b
ased
o
n
eq
u
al
in
te
n
s
ity
b
ea
m
s
an
d
it
s
o
p
tim
izatio
n
d
esig
n
.
Mo
d
elin
g
an
d
s
im
u
latio
n
ar
e
cr
u
cial
in
s
en
s
o
r
d
esig
n
.
T
wo
FB
G
s
ar
e
u
s
ed
to
en
h
an
ce
v
ib
r
atio
n
s
en
s
itiv
ity
:
o
n
e
m
ea
s
u
r
es
s
tr
ain
,
an
d
th
e
o
t
h
er
m
ea
s
u
r
es
v
ib
r
atio
n
an
d
tem
p
er
atu
r
e,
as
m
en
tio
n
ed
b
y
Ko
u
h
r
an
g
ih
a
et
a
l.
[
1
3
]
.
T
o
r
r
e
et
a
l.
[
1
4
]
d
escr
ib
ed
u
n
d
er
wate
r
v
ib
r
atio
n
f
r
e
q
u
en
c
y
.
Sen
s
o
r
tech
n
o
lo
g
y
f
o
r
v
ib
r
atio
n
m
o
n
ito
r
in
g
h
as
b
ec
o
m
e
a
s
ig
n
if
ican
t
r
esear
ch
a
r
ea
.
T
h
e
b
r
o
ad
o
b
jectiv
es
o
f
th
is
ex
p
e
r
im
en
tal
an
aly
s
is
ar
e
lis
ted
b
elo
w
,
wh
ich
is
s
h
o
wn
in
Fig
u
r
e
2
.
−
Desig
n
an
d
test
an
FB
G
v
ib
r
atio
n
s
en
s
o
r
b
y
u
tili
zin
g
lo
w
-
c
o
s
t p
o
ly
m
er
s
r
ea
d
ily
a
v
ailab
le
−
Acq
u
ir
in
g
r
ea
l
-
tim
e
s
ig
n
als
f
r
o
m
th
e
d
ev
elo
p
e
d
FB
G
v
ib
r
at
io
n
s
en
s
o
r
b
y
in
s
tallin
g
it
o
n
an
ex
p
er
im
en
tal
s
etu
p
co
n
s
is
tin
g
o
f
a
r
o
tatin
g
m
o
to
r
−
Dev
elo
p
in
g
a
s
ig
n
al
p
r
o
ce
s
s
in
g
s
ch
em
e
(
SP
S)
f
o
r
n
u
llify
in
g
th
e
ef
f
ec
t o
f
n
o
is
e
in
th
e
s
en
s
o
r
s
ig
n
al
−
Dev
elo
p
in
g
a
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
m
o
d
el
f
o
r
u
n
d
er
s
tan
d
in
g
t
h
e
m
ac
h
i
n
e
an
o
m
alies
o
f
th
e
r
o
tatin
g
m
ac
h
in
e
u
n
d
er
lab
o
r
ato
r
y
test
−
Dev
elo
p
in
g
a
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
(
DSS)
s
ch
em
e
f
o
r
g
en
er
atin
g
ad
e
q
u
ate
s
u
g
g
esti
o
n
s
o
n
m
ac
h
in
e
m
ain
ten
an
ce
o
p
er
atio
n
T
h
e
s
ig
n
al
p
r
o
ce
s
s
in
g
a
n
d
an
aly
s
is
ar
e
p
er
f
o
r
m
e
d
to
u
n
d
er
s
tan
d
th
e
ac
cu
r
ate
v
ib
r
atio
n
i
n
f
o
r
m
atio
n
o
f
a
m
o
to
r
u
n
d
er
a
v
i
b
r
atio
n
t
est.
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
o
f
th
e
p
r
ed
ictiv
e
m
ain
ten
an
c
e
s
tr
ateg
y
with
t
h
e
m
o
d
el
is
d
escr
ib
ed
in
Fig
u
r
e
3
.
T
h
is
ar
ticle
i
s
co
m
p
o
s
ed
o
f
eig
h
t
s
ec
tio
n
s
in
clu
d
in
g
th
e
in
tr
o
d
u
ctio
n
.
T
h
e
s
ec
o
n
d
s
ec
tio
n
ex
p
lain
s
h
o
w
FB
G
f
u
n
ctio
n
s
an
d
h
o
w
tem
p
er
atu
r
e
af
f
ec
ts
wav
elen
g
th
s
en
s
itiv
ity
,
in
clu
d
in
g
a
th
o
r
o
u
g
h
n
u
m
er
i
ca
l
an
aly
s
is
.
SP
S
s
ar
e
d
is
cu
s
s
ed
in
th
e
th
ir
d
s
ec
tio
n
,
f
o
ll
o
wed
b
y
s
tatis
tical
p
ar
am
eter
ex
tr
ac
tio
n
in
th
e
f
o
u
r
th
s
ec
tio
n
.
T
h
e
f
if
th
s
ec
tio
n
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
ML
m
o
d
el
f
o
r
an
o
m
aly
d
etec
tio
n
.
T
h
e
s
ix
th
s
ec
tio
n
d
is
cu
s
s
e
s
a
p
r
o
p
o
s
ed
ML
m
o
d
el
an
d
DSS
m
o
d
el,
f
o
llo
we
d
b
y
a
n
ex
p
er
im
en
tal
s
etu
p
,
wh
er
e
th
e
in
teg
r
atio
n
o
f
FB
G
in
ter
r
o
g
ato
r
with
an
in
ter
n
et
-
b
ased
m
o
d
el
is
p
r
esen
ted
.
T
h
e
s
u
m
m
ar
y
o
f
th
e
r
esu
lts
is
in
s
ec
tio
n
eig
h
t a
n
d
is
p
o
r
tr
a
y
ed
in
th
e
co
n
clu
s
io
n
,
f
o
llo
wed
b
y
th
e
r
e
f
er
en
ce
s
ec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
d
en
tifi
ca
tio
n
o
f f
a
u
lts
in
r
o
ta
t
in
g
ma
ch
in
es u
s
in
g
h
ig
h
p
r
ec
is
io
n
F
B
G
…
(
Dip
a
k
R
a
n
ja
n
N
a
ya
k
)
537
Fig
u
r
e
2
.
Pro
p
o
s
ed
ar
c
h
itectu
r
e
Fig
u
r
e
3
.
Pro
p
o
s
ed
ar
c
h
itectu
r
e
o
f
th
e
p
r
ed
ictiv
e
m
ain
ten
an
ce
(
PM)
s
tr
ateg
y
2.
WO
RK
I
NG
P
RINC
I
P
L
E
O
F
F
I
B
E
R
B
RAG
G
G
RA
T
I
N
G
FB
G
tech
n
o
lo
g
y
is
h
ig
h
l
y
r
e
g
ar
d
ed
f
o
r
o
p
tical
f
ib
er
s
en
s
o
r
s
d
u
e
t
o
its
s
im
p
le
m
a
n
u
f
ac
t
u
r
in
g
an
d
s
tr
o
n
g
r
ef
lecte
d
s
ig
n
al.
T
h
e
“
g
r
atin
g
”
r
ef
er
s
to
th
e
p
e
r
io
d
ic
ch
an
g
e
in
th
e
co
r
e
’
s
r
ef
r
ac
tiv
e
in
d
ex
.
W
h
en
lig
h
t
p
ass
es
o
v
er
th
e
g
r
atin
g
,
s
o
m
e
is
r
ef
lecte
d
wh
ile
th
e
r
est
r
e
ac
h
es
th
e
f
ib
er
’
s
o
u
tp
u
t.
T
h
e
co
m
b
in
ed
r
ef
lecte
d
lig
h
t
f
o
r
m
s
a
s
in
g
le
b
ea
m
th
at
m
ee
ts
th
e
B
r
ag
g
co
n
d
itio
n
.
W
h
en
ex
p
o
s
ed
to
ex
ter
n
al
f
o
r
ce
s
lik
e
s
tr
ain
an
d
tem
p
er
atu
r
e,
th
e
FB
G
ch
an
g
es
in
its
g
r
atin
g
p
er
io
d
an
d
B
r
ag
g
r
ef
r
ac
tiv
e
in
d
e
x
.
I
n
(
1
)
ex
p
lain
s
h
o
w
th
e
ef
f
ec
tiv
e
in
d
e
x
o
f
r
ef
r
ac
tio
n
o
f
th
e
co
r
e
,
an
d
t
h
e
g
r
atin
g
p
er
i
o
d
d
eter
m
in
e
th
e
wav
ele
n
g
th
o
f
lig
h
t
.
=
2
(
1
)
W
h
er
e
d
en
o
tes
th
e
ef
f
ec
tiv
e
c
o
r
e
r
ef
r
ac
tiv
e
i
n
d
ex
,
is
th
e
g
r
atin
g
p
er
io
d
t
h
at
d
eter
m
in
es
t
h
e
s
ep
ar
atio
n
b
etwe
en
two
ad
jace
n
t
g
r
atin
g
p
lan
es,
an
d
d
en
o
tes
th
e
B
r
ag
g
w
av
elen
g
th
[
1
5
]
-
[
1
8
]
.
T
h
e
p
r
in
cip
le
o
f
FB
G
is
ex
p
lain
ed
b
r
ief
l
y
an
d
r
ep
r
es
en
ted
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
B
asic w
o
r
k
in
g
p
r
in
ci
p
le
o
f
FB
G
T
h
e
b
ac
k
war
d
r
ef
lecte
d
p
ea
k
[
1
9
]
,
[
2
0
]
,
wh
o
s
e
ce
n
tr
al
wav
elen
g
th
is
d
ef
in
ed
b
y
,
f
o
r
m
s
wh
en
th
e
B
r
ag
g
co
n
d
itio
n
is
m
et.
T
h
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
s
h
if
t
i
n
th
e
B
r
ag
g
wav
elen
g
t
h
an
d
t
h
e
v
ar
iatio
n
s
i
n
th
e
g
r
atin
g
p
er
io
d
(
)
an
d
r
ef
r
ac
tiv
e
in
d
ex
(
)
,
wh
ich
ar
e
b
o
th
s
tr
o
n
g
ly
co
r
r
elate
d
with
th
e
o
r
i
g
in
al
wav
elen
g
th
,
is
s
h
o
wn
in
(
2
)
.
=
2
Ʌ
+
2
Ʌ
(
2
)
T
h
e
ef
f
ec
tiv
e
c
h
an
g
e
in
B
ca
n
b
e
ca
lcu
lated
u
s
in
g
t
h
e
r
atio
o
f
(
2
)
with
(
1
)
.
Δλ
B
λ
B
=
2
Δ
N
ef
f
Ʌ
+
2
N
ef
f
Δ
Ʌ
2
N
ef
f
Ʌ
(
3
)
Δλ
B
λ
B
=
Δ
N
ef
f
N
ef
f
+
Δ
Ʌ
Ʌ
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
535
-
5
4
7
538
B
r
ag
g
wav
elen
g
th
s
h
if
tin
g
(
)
is
d
ep
en
d
en
t
o
n
th
e
FB
G
’
s
tem
p
er
atu
r
e
v
a
r
iatio
n
,
wh
e
r
e
Δ
Ʌ
Ʌ
≪
Δ
N
ef
f
N
ef
f
.
W
h
en
co
n
s
id
er
in
g
th
e
c
h
an
g
e
in
r
ef
r
ac
tiv
e
in
d
ex
(
)
with
a
tem
p
er
atu
r
e
v
ar
iatio
n
,
th
e
B
r
ag
g
p
er
io
d
is
m
u
ch
s
m
aller
.
C
o
n
s
i
d
er
in
g
th
e
r
ea
s
o
n
s
m
en
tio
n
ed
ab
o
v
e,
a
s
lab
-
ty
p
e
s
tr
u
ctu
r
e
w
as
em
p
lo
y
ed
in
th
e
d
esig
n
o
f
th
e
FB
G
s
en
s
o
r
to
ac
h
iev
e
lar
g
er
f
ib
e
r
elo
n
g
atio
n
.
T
h
is
r
esu
lted
in
a
h
ig
h
er
r
an
g
e
o
f
s
en
s
itiv
ity
f
o
r
th
e
s
en
s
o
r
.
I
n
(
5
)
an
d
(
6
)
ca
n
b
e
u
tili
ze
d
to
d
em
o
n
s
tr
ate
h
o
w
tem
p
er
atu
r
e
in
f
lu
e
n
ce
s
th
e
B
r
ag
g
wav
elen
g
th
s
h
if
t (
).
∆
λ
B
λ
B
=
(
1
−
)
Δε
+
[
1
Ʌ
∂
Λ
∂
T
+
1
N
ef
f
∂
N
ef
f
∂
T
]
Δ
T
(
5
)
∆
λ
B
λ
B
=
(
1
−
)
Δε
+
(
α
+
ξ
)
Δ
T
(
6
)
T
h
e
ch
an
g
e
in
s
tr
ain
is
r
ep
r
e
s
en
ted
b
y
,
an
d
th
e
s
tr
ain
co
ef
f
icien
t
is
in
d
icate
d
b
y
.
T
h
e
tem
p
er
atu
r
e
ch
an
g
e
is
r
ep
r
esen
ted
b
y
,
an
d
th
e
th
er
m
al
ex
p
an
s
io
n
c
o
ef
f
i
cien
t
an
d
th
er
m
o
-
o
p
tic
co
ef
f
ic
ien
t
o
f
th
e
f
ib
r
e
ar
e
in
d
icate
d
b
y
an
d
,
r
esp
ec
tiv
ely
.
3.
SI
G
NA
L
P
RO
CE
S
SI
NG
S
C
H
E
M
E
T
h
e
ac
q
u
ir
ed
FB
G
s
ig
n
al
is
af
f
ec
ted
b
y
n
o
is
e
d
u
e
to
ar
tifa
ct
s
an
d
s
u
r
r
o
u
n
d
in
g
v
ib
r
atio
n
s
.
T
h
is
n
o
is
e
is
m
itig
ated
b
y
u
s
in
g
a
m
o
v
i
n
g
av
er
ag
e
f
ilter
(
MA
V)
.
T
h
e
MA
V
s
m
o
o
th
s
tim
e
-
s
er
ies
d
ata
b
y
av
er
ag
in
g
N
in
p
u
t
s
am
p
les.
T
h
e
f
ilter
’
s
r
esp
o
n
s
e
d
ep
e
n
d
s
o
n
th
e
co
n
v
o
lu
tio
n
s
u
m
o
f
t
h
e
in
p
u
t
s
ig
n
al
[
]
an
d
th
e
f
ilter
’
s
im
p
u
ls
e
r
esp
o
n
s
e,
p
r
o
d
u
cin
g
t
h
e
o
u
tp
u
t
[
]
.
T
h
is
o
p
er
atio
n
is
e
x
p
r
ess
ed
in
(
7
)
.
[
]
=
1
∑
[
−
]
−
1
=
0
(
7
)
Her
e,
[
]
,
[
−
]
ar
e
r
e
p
r
esen
t
t
h
e
s
m
o
o
th
ed
o
u
tp
u
t
an
d
i
n
p
u
t
s
ig
n
al
r
esp
ec
tv
ely
.
T
h
e
f
ilter
co
ef
f
icien
ts
ar
e
u
n
if
o
r
m
an
d
eq
u
al
to
1
b
y
co
n
f
ir
m
in
g
ev
en
ly
d
is
tr
ib
u
tio
n
ac
r
o
s
s
th
e
s
am
p
les.
B
y
ad
ju
s
tm
en
t
o
f
win
d
o
w
s
ize,
th
e
n
o
is
e
ca
n
b
e
r
ed
u
ce
d
an
d
th
e
r
e
is
tr
ad
e
-
o
f
f
b
etwe
en
p
r
eser
v
in
g
f
in
er
d
etails
in
t
h
e
s
ig
n
al
an
d
r
ed
u
ce
d
n
o
is
e.
4.
ST
A
T
I
S
T
I
CAL P
A
RAM
E
T
E
R
E
X
T
RA
CT
I
O
N
T
h
e
s
ig
n
al
p
r
o
ce
s
s
in
g
m
eth
o
d
s
ar
e
u
s
ed
to
o
b
tain
s
tatis
tical
p
ar
am
eter
s
th
at
q
u
a
n
tify
t
h
e
s
tatis
t
ical
p
r
o
p
er
ties
o
f
r
aw
d
ata.
T
h
ese
p
ar
am
eter
s
ar
e
ess
en
tial
f
o
r
ex
tr
ac
tin
g
m
ea
n
in
g
f
u
l
in
f
o
r
m
atio
n
f
r
o
m
th
e
d
ata.
T
ab
le
1
h
ig
h
lig
h
ts
th
e
m
ac
h
in
e
f
au
lts
with
th
eir
ca
teg
o
r
ies
an
d
th
e
s
tatis
tical
p
ar
am
eter
s
co
n
s
id
er
ed
to
tr
ain
th
e
ML
m
o
d
el
f
o
r
a
n
o
m
aly
d
e
tectio
n
.
T
ab
le
1
.
Statis
tical
p
ar
am
eter
s
co
n
s
id
er
ed
t
o
tr
ain
ML
m
o
d
el
f
o
r
an
o
m
aly
d
etec
tio
n
M
a
c
h
i
n
e
f
a
u
l
t
s
C
a
t
e
g
o
r
y
S
t
a
t
i
st
i
c
a
l
p
a
r
a
me
t
e
r
s
Lo
o
se
mo
u
n
t
i
n
g
F1
M
a
x
i
m
u
m
S
h
a
f
t
a
l
i
g
n
m
e
n
t
F2
M
i
n
i
m
u
m
B
e
n
t
s
h
a
f
t
F3
M
e
a
n
D
a
mag
e
d
b
e
a
r
i
n
g
s
F4
M
e
d
i
a
n
R
o
t
o
r
r
u
b
F5
M
o
d
e
B
r
o
k
e
n
r
o
t
o
r
b
a
r
F6
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
S
t
a
t
o
r
d
a
m
a
g
e
F7
V
a
r
i
a
n
c
e
S
h
a
f
t
i
m
b
a
l
a
n
c
e
F8
D
e
v
i
a
t
i
o
n
f
r
o
m m
e
a
n
5.
P
RO
P
O
SE
D
M
A
CH
I
N
E
L
E
ARNING
M
O
DE
L
F
O
R
AN
O
M
AL
Y
D
E
T
E
C
T
I
O
N
ML
m
eth
o
d
s
ar
e
em
p
lo
y
ed
in
p
r
ed
ictiv
e
m
ain
ten
an
ce
f
o
r
in
d
u
s
tr
ial
m
ac
h
in
e
r
y
to
en
ab
le
p
r
o
ac
tiv
e,
d
ata
-
d
r
iv
e
n
p
r
ac
tices.
T
h
ese
alg
o
r
ith
m
s
an
aly
ze
r
ea
l
-
tim
e
an
d
h
is
to
r
ical
d
ata
f
r
o
m
m
ac
h
in
er
y
to
f
o
r
ec
ast
p
r
o
b
a
b
le
f
ailu
r
es
an
d
s
ch
ed
u
l
e
m
ain
ten
an
ce
task
s
b
ef
o
r
e
b
r
ea
k
d
o
wn
s
o
cc
u
r
[
2
1
]
.
B
y
u
s
in
g
h
is
to
r
ical
f
ailu
r
e
d
ata,
eq
u
ip
m
e
n
t
u
s
ag
e,
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
,
an
d
o
th
er
r
elev
an
t
in
f
o
r
m
atio
n
,
th
e
s
e
m
o
d
els
p
r
ed
ict
m
ain
ten
an
ce
n
ee
d
s
with
h
ig
h
ac
cu
r
ac
y
.
T
h
is
ap
p
r
o
ac
h
m
in
im
izes
d
o
wn
tim
e,
r
ed
u
ce
s
th
e
lik
elih
o
o
d
o
f
ca
tast
r
o
p
h
ic
f
ailu
r
es,
a
n
d
o
p
ti
m
izes
m
ain
ten
an
ce
co
s
ts
,
th
er
eb
y
en
h
an
cin
g
o
v
e
r
all
eq
u
i
p
m
en
t
r
eliab
ilit
y
an
d
o
p
er
atio
n
al
e
f
f
ec
tiv
en
ess
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
d
en
tifi
ca
tio
n
o
f f
a
u
lts
in
r
o
ta
t
in
g
ma
ch
in
es u
s
in
g
h
ig
h
p
r
ec
is
io
n
F
B
G
…
(
Dip
a
k
R
a
n
ja
n
N
a
ya
k
)
539
6.
P
RO
P
O
SE
D
M
A
CH
I
N
E
L
E
ARNING
M
O
DE
L
AND
D
E
CIS
I
O
N
SUPP
O
RT
S
YST
E
M
T
h
e
p
r
o
p
o
s
ed
p
r
ed
ictiv
e
m
ai
n
ten
an
ce
s
ch
em
e
aim
s
to
en
h
an
ce
th
e
r
eliab
ilit
y
an
d
p
er
f
o
r
m
an
ce
o
f
r
o
tatin
g
m
ac
h
i
n
er
y
b
y
c
o
m
b
i
n
in
g
f
ast
f
o
u
r
ier
tr
a
n
s
f
o
r
m
(
FFT
)
-
b
ased
f
r
eq
u
en
cy
an
aly
s
is
with
ad
v
an
ce
d
ML
m
o
d
els
s
u
ch
as
p
ar
tial
least
s
q
u
ar
es
r
eg
r
ess
io
n
(
PLSR
)
an
d
r
a
d
ial
b
asis
f
u
n
ctio
n
(
R
B
F).
L
ev
er
a
g
in
g
a
n
in
ter
n
et
o
f
th
in
g
(
I
o
T
)
-
b
ased
f
r
am
ewo
r
k
,
th
e
s
ch
e
m
e
en
a
b
les
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
a
n
d
an
aly
s
is
o
f
cr
itical
f
r
eq
u
e
n
cy
co
m
p
o
n
en
ts
ass
o
ci
ated
with
v
ar
io
u
s
f
au
lt
co
n
d
itio
n
s
[
2
0
]
-
[
2
2
]
.
T
h
e
in
teg
r
atio
n
o
f
DSS
f
u
r
th
e
r
en
h
an
ce
s
th
e
s
y
s
tem
’
s
in
tellig
en
ce
,
p
r
o
v
id
in
g
ac
tio
n
a
b
le
in
s
ig
h
ts
f
o
r
m
ain
ten
a
n
ce
p
er
s
o
n
n
el
[
2
3
]
-
[
2
6
]
.
T
h
e
PLSR
m
o
d
el
estab
lis
h
es
a
r
elatio
n
s
h
ip
b
etwe
en
a
d
ep
e
n
d
en
t
v
a
r
iab
le,
‘
Fau
lt
’,
a
n
d
in
d
ep
en
d
e
n
t
v
ar
iab
les
co
n
s
is
tin
g
o
f
s
tatis
tical
ch
ar
ac
ter
is
tics
an
d
f
r
eq
u
en
c
y
co
m
p
o
n
en
ts
,
m
ax
im
izin
g
co
v
ar
ia
n
ce
wh
ile
co
n
s
id
er
in
g
m
u
ltico
llin
ea
r
ity
[
1
5
]
.
Fo
r
in
s
tan
ce
,
a
n
eg
ativ
e
co
ef
f
icien
t
f
o
r
‘
Min
’
in
d
icate
s
a
n
eg
ativ
e
co
r
r
elatio
n
b
etwe
en
an
in
cr
ea
s
e
in
th
e
m
i
n
im
u
m
v
alu
e
an
d
a
d
ec
r
ea
s
e
in
th
e
p
r
o
jecte
d
f
au
lt,
wh
ile
a
p
o
s
itiv
e
co
ef
f
icien
t
f
o
r
‘
Mean
’
s
u
g
g
ests
a
h
ig
h
er
m
ea
n
v
alu
e
is
lin
k
ed
to
a
g
r
ea
ter
l
ik
elih
o
o
d
o
f
th
e
f
au
lt
o
cc
u
r
r
in
g
.
T
h
e
in
ter
ce
p
t
o
f
6
5
.
0
5
3
0
r
e
p
r
esen
ts
th
e
b
aselin
e
f
au
lt
v
alu
e
wh
en
all
in
p
u
t
v
a
r
iab
les
ar
e
ze
r
o
.
T
h
e
r
ad
ial
b
a
s
is
f
u
n
ctio
n
n
eu
r
al
n
etwo
r
k
(
R
B
FNN)
,
with
its
u
n
iq
u
e
th
r
ee
-
lay
e
r
co
n
f
ig
u
r
atio
n
,
u
s
es
a
R
B
F
in
th
e
h
id
d
en
lay
er
,
m
ak
in
g
it
ef
f
ec
tiv
e
f
o
r
d
ata
p
r
o
ce
s
s
in
g
,
lear
n
in
g
,
a
n
d
an
aly
s
is
in
p
r
ed
ictiv
e
m
ain
ten
an
ce
.
I
n
itially
,
a
g
au
s
s
ian
d
is
tr
ib
u
ted
f
u
n
ctio
n
d
eter
m
in
es
th
e
ce
n
ter
an
d
wid
th
o
f
RBF
s
,
f
o
llo
wed
b
y
g
r
ad
ie
n
t
d
e
s
ce
n
t
f
o
r
ad
ju
s
tin
g
o
u
tp
u
t w
eig
h
ts
.
R
B
FNN
s
ca
n
ap
p
r
o
x
im
ate
co
m
p
lex
n
o
n
lin
e
ar
f
u
n
ctio
n
s
,
m
ak
in
g
th
em
s
u
itab
le
f
o
r
tim
e
-
s
er
ies
f
au
lt
p
r
e
d
ictio
n
,
ac
cu
r
ately
f
o
r
ec
asti
n
g
p
o
te
n
tial
b
r
ea
k
d
o
w
n
s
b
y
p
r
o
ce
s
s
in
g
p
r
e
v
io
u
s
e
q
u
ip
m
en
t
d
ata.
T
h
is
ca
p
ab
ilit
y
r
ed
u
ce
s
m
ain
ten
an
c
e
co
s
ts
,
im
p
r
o
v
es
m
ac
h
i
n
er
y
ef
f
icien
cy
,
a
n
d
m
in
im
izes
d
o
wn
tim
e,
d
esp
ite
th
e
n
ec
ess
ity
f
o
r
p
r
o
p
e
r
ad
ju
s
tm
e
n
t
o
f
c
h
ar
ac
ter
is
tics
s
u
ch
as
n
u
m
b
er
,
wid
th
,
ce
n
ter
,
a
n
d
o
u
t
p
u
t
weig
h
ts
o
f
RBF
s
.
Ov
er
all,
th
e
s
ch
em
e
ef
f
ec
tiv
ely
h
an
d
les h
i
g
h
-
d
i
m
en
s
io
n
al
d
a
ta
an
d
o
f
f
er
s
co
m
p
u
tatio
n
al
ef
f
icien
cy
b
en
e
f
its
.
7.
E
XP
E
R
I
M
E
N
T
A
L
SE
T
UP
Ma
ch
in
e
v
ib
r
atio
n
ca
n
b
e
ca
u
s
ed
b
y
a
v
ar
iety
o
f
f
ac
to
r
s
,
in
cl
u
d
in
g
b
ea
r
in
g
s
,
g
ea
r
s
,
u
n
b
alan
ce
,
an
d
s
o
o
n
,
an
d
ev
e
n
s
m
all
am
p
litu
d
es
ca
n
h
av
e
a
s
ig
n
if
ican
t
im
p
ac
t
o
n
o
v
er
all
m
ac
h
in
e
v
i
b
r
atio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
th
e
v
ib
r
ati
o
n
m
ea
s
u
r
em
en
t a
n
d
a
n
aly
s
is
o
f
a
m
ac
h
in
e
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
I
b
s
en
I
-
MO
N
h
ig
h
-
s
p
ee
d
FB
G
I
n
ter
r
o
g
ato
r
ca
p
tu
r
es
th
e
co
n
tin
u
o
u
s
ly
ch
a
n
g
in
g
wav
elen
g
th
d
u
e
to
m
ac
h
in
e
v
ib
r
atio
n
s
.
R
ea
l
-
tim
e
s
ig
n
als
ar
e
ac
q
u
ir
ed
b
y
in
ter
f
ac
in
g
th
e
FB
G
I
n
ter
r
o
g
ato
r
with
th
e
Natio
n
al
I
n
s
tr
u
m
en
ts
L
ab
VI
E
W
en
v
ir
o
n
m
en
t.
Fig
u
r
e
6
s
h
o
ws
th
e
ex
p
er
im
en
tal
s
etu
p
f
o
r
th
e
p
r
o
p
o
s
ed
v
ib
r
atio
n
s
en
s
in
g
p
r
o
ce
d
u
r
e.
Sig
n
a
l
p
r
o
ce
s
s
in
g
is
th
en
u
s
ed
t
o
ac
h
iev
e
p
r
ec
is
e
r
esp
o
n
s
e
d
ata.
Vib
r
atio
n
s
o
u
r
ce
s
h
av
e
ch
ar
a
cter
is
tic
f
r
eq
u
en
cies,
wh
ich
ca
n
b
e
d
is
cr
ete
o
r
co
m
b
in
ed
f
r
e
q
u
en
cies.
Vib
r
atio
n
m
ea
s
u
r
em
en
t,
a
co
m
m
o
n
s
en
s
in
g
tech
n
iq
u
e,
d
etec
ts
,
d
iag
n
o
s
es,
an
d
p
r
o
g
n
o
s
es
b
y
m
ea
s
u
r
in
g
th
e
o
v
er
all
v
ib
r
atio
n
lev
el
ac
r
o
s
s
a
f
r
eq
u
en
c
y
r
an
g
e
(
1
0
-
1
,
0
0
0
Hz
o
r
1
0
-
10
,
0
0
0
Hz)
.
Min
im
al
v
ib
r
atio
n
m
ac
h
in
es,
ex
clu
d
in
g
b
ea
r
in
g
v
ib
r
atio
n
,
ex
h
ib
it
s
p
ik
es
in
th
e
v
ib
r
atio
n
s
ig
n
al,
in
d
icate
d
b
y
t
h
e
cr
est
f
ac
to
r
(
Peak
/R
MS)
,
s
ig
n
alin
g
in
ci
p
ien
t
f
ailu
r
e,
wh
ile
h
i
g
h
R
MS
lev
els
in
d
icate
cr
itical
f
ailu
r
e.
R
o
llin
g
b
ea
r
in
g
s
with
o
u
t
d
e
f
ec
ts
g
en
er
ate
m
in
im
al
v
ib
r
ati
o
n
,
wh
e
r
ea
s
d
ef
ec
ts
ca
u
s
e
h
ig
h
n
atu
r
al
f
r
eq
u
en
cies
.
Sin
g
le
d
ef
ec
ts
,
lik
e
r
ac
ewa
y
f
r
ac
tu
r
in
g
,
d
o
m
in
ate
th
e
f
r
e
q
u
en
cy
s
p
ec
tr
u
m
with
im
p
u
ls
iv
e
ev
en
ts
at
r
ac
ewa
y
p
ass
in
g
f
r
eq
u
en
cies.
C
h
ar
ac
ter
is
tic
d
ef
ec
t
f
r
eq
u
en
cies
an
d
s
id
eb
an
d
s
in
cr
ea
s
e
with
d
am
ag
e
b
u
t
ev
en
tu
ally
d
ec
r
ea
s
e
as
b
r
o
ad
b
an
d
n
o
i
s
e
an
d
s
ig
n
if
ican
t
o
s
cillatio
n
s
at
s
h
af
t
r
o
tatio
n
f
r
eq
u
e
n
cy
in
cr
ea
s
e.
B
ea
r
in
g
s
at
s
lo
w
m
ac
h
in
e
s
p
ee
d
s
p
r
o
d
u
ce
lo
w
-
en
er
g
y
s
ig
n
als
th
at
ar
e
h
ar
d
to
d
etec
t,
an
d
th
o
s
e
in
g
ea
r
b
o
x
es a
r
e
c
h
allen
g
in
g
to
m
o
n
ito
r
d
u
e
t
o
h
ig
h
en
er
g
y
.
Fig
u
r
e
5
.
Pro
p
o
s
ed
m
o
d
el
f
o
r
t
h
e
v
ib
r
atio
n
m
ea
s
u
r
em
e
n
t
an
d
an
aly
s
is
o
f
a
m
ac
h
in
e
Fig
u
r
e
6
.
E
x
p
er
im
e
n
tal
s
etu
p
o
f
th
e
FB
G
s
en
s
o
r
f
o
r
v
ib
r
atio
n
a
n
aly
s
is
8.
RE
SU
L
T
S AN
A
L
YS
I
S
A
N
D
DIS
CU
SS
I
O
N
T
h
is
s
ec
tio
n
d
etails
th
e
im
p
lem
en
tatio
n
o
f
a
FB
G
in
ter
r
o
g
a
to
r
with
a
p
er
s
o
n
al
co
m
p
u
ter
to
ac
q
u
ir
e
r
ea
l
-
tim
e
v
ib
r
atio
n
s
ig
n
atu
r
es
u
n
d
er
v
a
r
io
u
s
f
au
lt
co
n
d
itio
n
s
.
I
n
teg
r
atin
g
th
e
FB
G
in
ter
r
o
g
ato
r
with
a
PC
en
ab
les
r
o
b
u
s
t
d
ata
ac
q
u
is
itio
n
,
allo
win
g
f
o
r
p
r
ec
is
e
m
o
n
it
o
r
in
g
an
d
r
ec
o
r
d
in
g
o
f
v
ib
r
ati
o
n
p
atter
n
s
d
u
r
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
535
-
5
4
7
540
d
i
f
f
e
r
e
n
t
f
a
u
l
t
s
c
e
n
a
r
i
o
s
.
T
h
e
r
a
w
s
i
g
n
a
ls
r
e
c
o
r
d
e
d
u
s
i
n
g
a
n
F
B
G
s
e
n
s
o
r
i
n
s
t
a
l
le
d
o
n
t
h
e
v
i
b
r
a
t
i
n
g
m
a
c
h
i
n
e
u
n
d
e
r
c
o
n
d
i
t
i
o
n
s
s
u
c
h
as
l
o
o
s
e
m
o
u
n
t
i
n
g
(
F
a
u
l
t
:
F
1
)
,
b
r
o
k
e
n
r
o
t
o
r
b
a
r
(
F
a
u
lt
:
F
2
)
,
d
a
m
a
g
e
d
b
e
a
r
i
n
g
(
F
a
u
lt
:
F
3
)
,
an
d
b
en
t
s
h
af
t
(
Fau
lt:
F4
)
ar
e
s
h
o
wn
in
Fig
u
r
e
7
.
Simila
r
ly
,
Fig
u
r
e
8
d
is
p
lay
s
th
e
r
aw
s
ig
n
als
f
o
r
s
h
af
t
alig
n
m
en
t
(
Fau
lt:
F5
)
,
s
h
af
t
im
b
alan
ce
(
Fau
lt:
F6
)
,
s
tato
r
d
am
ag
e
(
Fau
lt:
F7
)
,
an
d
r
o
to
r
r
u
b
(
Fau
lt:
F8
)
.
T
h
e
ap
p
licatio
n
o
f
a
MA
V
is
a
k
ey
asp
ec
t
o
f
s
ig
n
al
p
r
o
ce
s
s
in
g
th
at
f
u
n
ctio
n
s
to
s
m
o
o
th
o
u
t
f
lu
ctu
atio
n
s
an
d
ir
r
eg
u
lar
ities
in
th
e
d
ata.
T
h
is
p
r
o
v
es
in
v
alu
ab
le
in
en
h
an
ci
n
g
th
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
th
e
in
f
o
r
m
atio
n
d
er
iv
ed
f
r
o
m
t
h
e
FB
G
s
en
s
o
r
,
as
it
ef
f
ec
tiv
ely
r
ed
u
ce
s
th
e
i
m
p
ac
t
o
f
r
an
d
o
m
n
o
is
e,
wh
ich
ca
n
o
f
ten
d
is
to
r
t
th
e
tr
u
e
u
n
d
e
r
ly
in
g
s
ig
n
al.
Fi
g
u
r
e
9
s
h
o
ws
th
e
s
m
o
o
th
ed
s
ig
n
al
d
u
r
in
g
r
em
o
v
al
o
f
r
an
d
o
m
n
o
is
e
f
r
o
m
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
in
g
lo
o
s
e
m
o
u
n
tin
g
co
n
d
itio
n
(
Fau
lt:
F1
)
,
b
r
o
k
en
r
o
to
r
b
ar
(
Fau
lt:
F2
)
,
d
am
ag
ed
b
ea
r
in
g
(
Fau
lt:
F
3
)
,
b
en
t
s
h
af
t
(
Fau
lt:
F4
)
.
Similar
ly
,
r
em
o
v
al
o
f
r
an
d
o
m
n
o
is
e
f
r
o
m
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
i
n
g
Sh
af
t
alig
n
m
en
t
(
Fau
lt:
F5
)
,
s
h
af
t
im
b
alan
ce
(
Fau
lt:
F6
)
,
s
h
af
t
d
am
ag
e
(
Fau
lt:
F7
)
,
an
d
s
tato
r
r
u
b
(
Fau
lt:
F
8
)
f
au
lts
ar
e
b
r
ief
ly
e
x
p
lain
e
d
in
Fig
u
r
e
10.
Fig
u
r
e
7
.
FB
G
v
ib
r
atio
n
s
ig
n
a
l d
u
r
in
g
lo
o
s
e
m
o
u
n
tin
g
(
Fau
lt: F1
)
,
b
r
o
k
e
n
r
o
to
r
b
a
r
(
Fau
lt: F2
)
,
d
am
ag
ed
b
ea
r
in
g
(
Fau
lt: F3
)
,
b
en
t
s
h
af
t (
Fau
lt: F4
)
Fig
u
r
e
8
.
FB
G
v
ib
r
atio
n
s
ig
n
a
l d
u
r
in
g
s
h
af
t a
lig
n
m
e
n
t
is
s
u
e
(
Fau
lt: F5
)
,
s
h
af
t im
b
alan
ce
(
Fau
lt: F6
)
,
s
tato
r
d
am
ag
e
(
Fau
lt: F7
)
,
r
o
to
r
r
u
b
(
Fau
lt: F8
)
Fig
u
r
e
9
.
R
em
o
v
al
o
f
r
an
d
o
m
n
o
is
e
f
r
o
m
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
in
g
lo
o
s
e
m
o
u
n
tin
g
co
n
d
itio
n
(
Fau
lt: F1
)
,
b
r
o
k
e
n
r
o
to
r
b
ar
(
Fau
lt: F2
)
,
d
am
ag
ed
b
ea
r
in
g
(
Fau
lt: F
3
)
,
a
n
d
b
en
t
s
h
af
t (
Fau
lt: F4
)
T
h
e
FF
T
o
n
th
e
r
ef
in
e
d
FB
G
s
en
s
o
r
s
ig
n
al
[
2
7
]
p
r
o
v
id
es
in
s
ig
h
ts
in
to
v
ib
r
atio
n
s
r
elate
d
t
o
d
if
f
er
en
t
f
au
lt
co
n
d
itio
n
s
[
2
8
]
.
T
h
is
ap
p
r
o
ac
h
tr
a
n
s
f
o
r
m
s
tim
e
-
d
o
m
ai
n
s
ig
n
als
in
to
f
r
eq
u
en
cy
-
d
o
m
ain
r
ep
r
esen
tatio
n
s
,
f
ac
ilit
atin
g
a
d
etailed
ex
p
lo
r
at
io
n
o
f
v
ib
r
atio
n
al
p
atter
n
s
lin
k
ed
to
s
p
ec
if
ic
f
au
lts
.
I
t
p
r
o
v
es
cr
u
cial
f
o
r
f
au
lt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
d
en
tifi
ca
tio
n
o
f f
a
u
lts
in
r
o
ta
t
in
g
ma
ch
in
es u
s
in
g
h
ig
h
p
r
ec
is
io
n
F
B
G
…
(
Dip
a
k
R
a
n
ja
n
N
a
ya
k
)
541
d
etec
tio
n
,
co
n
d
itio
n
m
o
n
ito
r
in
g
,
an
d
s
tr
u
ctu
r
al
in
teg
r
ity
an
al
y
s
is
[
2
7
]
,
[
2
8
]
.
Similar
ly
,
FF
T
is
u
s
ed
to
an
aly
ze
v
ib
r
atio
n
s
ig
n
atu
r
es
f
o
r
v
a
r
io
u
s
p
r
e
d
ef
in
e
d
f
a
u
lts
s
u
ch
a
s
lo
o
s
e
m
o
u
n
tin
g
(
F1
)
,
b
r
o
k
en
r
o
to
r
b
ar
(
F2
)
,
d
am
ag
ed
b
ea
r
in
g
(
F3
)
,
b
en
t
s
h
af
t
(
F4
)
,
s
h
af
t
alig
n
m
en
t
(
F5
)
,
s
h
af
t
im
b
alan
ce
(
F6
)
,
s
h
af
t
d
am
ag
e
(
F7
)
,
an
d
s
tato
r
r
u
b
(
F8
)
[
2
7
]
,
[
2
8
]
.
Ad
d
itio
n
ally
,
Fig
u
r
e
1
1
illu
s
tr
ates
th
e
f
r
eq
u
en
c
y
r
esp
o
n
s
e
o
f
th
e
tim
e
d
o
m
ain
s
ig
n
al
d
u
r
in
g
th
ese
f
au
lt c
o
n
d
itio
n
s
,
s
h
o
wca
s
in
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
FF
T
in
an
aly
zin
g
v
ib
r
atio
n
s
ig
n
atu
r
es.
Fig
u
r
e
10
.
R
em
o
v
al
o
f
r
an
d
o
m
n
o
is
e
f
r
o
m
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
in
g
s
h
af
t a
l
ig
n
m
en
t (
Fau
lt: F5
)
,
s
h
af
t im
b
alan
ce
(
Fau
lt: F6
)
,
s
h
af
t d
am
ag
e
(
Fau
lt: F7
)
,
an
d
s
tato
r
r
u
b
(
Fau
lt: F
8
)
Fig
u
r
e
11
.
FF
T
s
p
ec
tr
u
m
o
f
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
in
g
d
if
f
e
r
en
t f
au
lt c
o
n
d
itio
n
T
h
e
PLSR
m
o
d
el
is
u
tili
ze
d
to
p
r
ed
ict
f
au
lt ty
p
es b
y
co
n
s
id
er
in
g
s
tatis
tical
p
ar
am
eter
s
an
d
f
r
eq
u
e
n
cy
co
m
p
o
n
en
ts
[
2
7
]
.
PLSR
ef
f
ec
tiv
ely
h
an
d
les
m
u
ltico
llin
ea
r
ity
an
d
estab
lis
h
es
s
tr
o
n
g
co
r
r
elatio
n
s
b
etwe
en
v
ar
iab
les,
aid
in
g
r
ea
l
-
tim
e
f
au
lt
id
en
tific
atio
n
[
2
7
]
.
Ad
d
itio
n
ally
,
a
r
ad
ial
b
asis
ty
p
e
n
eu
r
al
n
etwo
r
k
is
em
p
lo
y
ed
f
o
r
f
au
lt
p
r
ed
icti
o
n
an
d
co
r
r
elatio
n
estab
lis
h
m
en
t
lik
e
PLSR
[
2
7
]
.
T
a
b
le
2
ca
teg
o
r
izes
m
ea
s
u
r
em
en
ts
an
d
p
ar
a
m
eter
s
u
n
d
e
r
d
i
f
f
er
en
t
f
au
lt
t
y
p
es
lik
e
d
am
ag
e
d
b
ea
r
in
g
s
,
b
r
o
k
en
r
o
to
r
b
ar
s
,
an
d
lo
o
s
e
m
o
u
n
tin
g
s
,
p
r
o
v
id
in
g
a
co
m
p
r
eh
en
s
iv
e
o
v
e
r
v
iew
o
f
t
h
e
d
ata
[
2
7
]
.
T
ab
le
2
.
Statis
tical
p
ar
am
eter
s
o
f
th
e
p
r
e
-
p
r
o
ce
s
s
ed
FB
G
v
ib
r
atio
n
s
ig
n
al
d
u
r
in
g
d
if
f
er
e
n
t f
au
lt c
o
n
d
itio
n
s
Lo
o
se
m
o
u
n
t
i
n
g
B
r
o
k
e
n
r
o
t
o
r
b
ar
D
a
mag
e
d
b
e
a
r
i
n
g
B
e
n
t
s
h
a
f
t
S
h
a
f
t
a
l
i
g
n
me
n
t
S
h
a
f
t
i
mb
a
l
a
n
c
e
S
t
a
t
o
r
d
a
m
a
g
e
R
o
t
o
r
r
ub
F
a
u
l
t
s
1
2
3
4
5
6
7
8
M
i
n
(
n
m)
1
5
5
2
.
0
9
1
5
5
2
.
1
4
1
5
5
2
.
1
6
1
5
5
2
.
1
6
1
1
5
5
2
.
1
6
0
9
1
5
5
2
.
1
6
1
2
1
5
5
2
.
1
6
2
1
5
5
2
.
1
6
1
4
M
a
x
(
n
m)
1
5
5
2
.
2
3
1
5
5
2
.
1
9
1
5
5
2
.
1
6
9
1
5
5
2
.
1
7
1
1
5
5
2
.
1
6
9
3
1
5
5
2
.
1
6
5
1
5
5
2
.
1
6
7
1
5
5
2
.
1
6
3
4
M
e
a
n
(
n
m)
1
5
5
2
.
2
1
5
5
2
.
1
6
1
5
5
2
.
1
6
4
1
5
5
2
.
1
6
6
1
5
5
2
.
1
6
2
7
1
5
5
2
.
1
6
3
1
5
5
2
.
1
6
4
5
1
5
5
2
.
1
6
2
2
M
e
d
i
a
n
(
n
m)
1
5
5
2
.
2
2
1
5
5
2
.
2
1
1
5
5
2
.
2
1
5
5
2
.
2
1
5
5
2
.
2
1
1
5
5
2
.
2
1
1
5
5
2
.
2
1
1
5
5
2
.
2
1
M
o
d
e
(
n
m)
1
5
5
2
.
1
1
5
5
2
.
2
0
1
1
5
5
2
.
2
0
8
1
5
5
2
,
2
0
5
1
5
5
2
.
2
2
0
7
1
5
5
2
.
2
3
1
5
5
2
.
2
0
2
1
5
5
2
.
2
0
3
SD
0
.
0
4
0
5
0
.
0
1
3
9
0
.
0
0
1
3
0
.
0
0
1
4
0
.
0
0
1
5
6
.
6
9
6
5
×
10
-
4
9
.
9
5
4
×
10
-
4
3
.
1
1
4
×
10
-
4
V
a
r
i
a
n
c
e
0
.
0
0
1
6
0
.
0
0
0
1
9
2
7
0
.
7
5
6
×
10
-
6
1
.
9
9
1
1
×
10
-
6
2
.
2
4
1
×
10
-
6
4
.
4
8
4
4
×
10
-
7
9
.
1
1
3
7
×
10
-
7
9
.
6
9
8
×
10
-
8
M
e
a
n
o
f
d
e
v
i
a
t
i
o
n
0
.
0
3
6
6
0
.
0
1
2
2
9
.
8
3
×
10
-
4
0
.
0
0
1
0
0
.
0
0
1
2
5
.
4
0
6
7
×
10
-
4
7
.
8
2
×
10
-
4
2
.
4
9
3
×
10
-
4
F
0
(
H
z
)
6
.
8
7
6
.
7
5
3
.
1
2
3
.
2
5
3
.
2
2
3
.
1
2
3
.
2
5
3
.
5
F
1
(
H
z
)
1
3
.
6
2
1
3
.
6
5
5
.
6
2
5
.
6
7
5
.
6
2
6
.
5
6
.
7
4
Nu
m
er
ical
p
ar
a
m
eter
s
lik
e
a
m
p
litu
d
es,
f
r
e
q
u
en
cies,
a
n
d
s
tatis
tical
v
alu
es
ar
e
in
clu
d
ed
f
o
r
ea
ch
f
au
lt
ty
p
e,
cr
ea
tin
g
a
c
o
m
p
r
e
h
en
s
iv
e
d
ataset
f
o
r
f
a
u
lt
an
aly
s
is
.
T
h
e
d
iv
er
s
e
n
atu
r
e
o
f
m
ea
s
u
r
em
en
ts
an
d
ch
ar
ac
ter
is
tics
as
s
o
ciate
d
with
d
if
f
er
en
t
ty
p
es
o
f
m
ac
h
i
n
er
y
f
au
lts
is
ev
id
en
t
f
r
o
m
th
e
n
u
m
er
ical
v
alu
es
u
n
d
er
ea
ch
f
au
lt
ty
p
e
.
Fig
u
r
e
1
2
d
ep
ict
th
e
co
m
p
ar
ativ
e
a
n
aly
s
is
b
etwe
en
p
r
ed
icted
f
a
u
lt
ty
p
es
u
s
in
g
tw
o
m
eth
o
d
o
l
o
g
ies:
PLSR
an
d
a
r
ad
ial
b
asis
ty
p
e
n
eu
r
al
n
etwo
r
k
.
T
h
ese
f
i
g
u
r
es
s
h
o
wca
s
e
t
h
e
o
u
tco
m
es
o
f
th
e
r
esear
ch
’
s
d
u
al
ap
p
r
o
ac
h
to
f
a
u
lt c
lass
if
icatio
n
b
ased
o
n
th
e
p
r
e
-
p
r
o
ce
s
s
ed
FB
G
s
en
s
o
r
s
ig
n
al.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
535
-
5
4
7
542
Fig
u
r
e
12
.
E
s
tim
ated
f
au
lt ty
p
es u
s
in
g
PLSR
m
o
d
el
an
d
R
B
F n
eu
r
al
n
etwo
r
k
Fig
u
r
e
1
2
g
r
ap
h
ically
d
e
p
icts
th
e
PLSR
m
o
d
el
’
s
p
r
ed
ictio
n
s
f
o
r
f
a
u
lt
ty
p
es,
with
ea
ch
f
a
u
l
t
ca
teg
o
r
y
r
ep
r
esen
ted
as
a
d
is
tin
ct
b
ar
o
r
d
ata
p
o
in
t
o
n
th
e
g
r
a
p
h
.
T
h
e
x
-
ax
is
c
o
r
r
esp
o
n
d
s
to
d
if
f
er
e
n
t
f
au
lt
ty
p
es,
wh
ile
th
e
y
-
ax
is
r
ep
r
esen
ts
p
r
ed
icte
d
f
au
lt
p
r
o
b
ab
ilit
ies
o
r
class
if
icatio
n
s
,
in
d
icatin
g
th
e
m
o
d
el
’
s
co
n
f
id
en
ce
in
p
r
ed
ictin
g
s
p
ec
if
ic
f
au
lt
ty
p
e
s
.
T
h
is
v
is
u
aliza
tio
n
aid
s
r
es
ea
r
ch
er
s
an
d
r
ea
d
er
s
i
n
u
n
d
e
r
s
tan
d
in
g
t
h
e
PLSR
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
i
n
f
au
lt
id
en
tific
atio
n
an
d
d
if
f
er
en
tiatio
n
am
o
n
g
f
a
u
lt
co
n
d
itio
n
s
.
An
aly
zin
g
th
e
b
ar
s
/d
ata
p
o
in
ts
in
Fig
u
r
e
1
2
p
r
o
v
id
es
in
s
ig
h
ts
in
to
th
e
n
eu
r
al
n
etwo
r
k
’
s
f
au
lt
class
if
icatio
n
p
er
f
o
r
m
an
ce
an
d
en
ab
les a
s
id
e
-
by
-
s
id
e
ev
alu
ati
o
n
with
th
e
PLSR
m
o
d
el.
In
(
7
)
p
r
esen
ts
th
e
m
ath
em
atica
l
m
o
d
el
in
co
r
p
o
r
atin
g
s
tatis
t
ical
p
ar
am
eter
s
an
d
f
r
e
q
u
en
cy
c
o
m
p
o
n
en
ts
.
F
a
ul
t
=
65
.
0530
−
(
0
.
0084
×
M
in
)
−
(
0
.
0898
×
M
a
x
)
+
(
0
.
3218
×
M
e
a
n
)
−
(
0
.
2502
×
M
e
dia
n
)
−
(
0
.
0084
×
M
ode
)
+
(
0
.
0426
×
SD
)
−
(
0
.
0001
×
Va
r
ia
n
c
e
)
−
(
0
.
0384
×
M
e
a
n
va
r
ia
n
c
e
)
−
(
0
.
0522
×
F1
)
−
(
0
.
4258
×
F2
)
(
7
)
T
ab
le
3
co
m
p
ar
es
er
r
o
r
p
ar
a
m
eter
s
b
etwe
en
two
f
au
lt
p
r
ed
ictio
n
m
o
d
els:
PLSR
an
d
R
B
F
n
eu
r
al
n
etwo
r
k
,
cr
u
cial
f
o
r
ac
cu
r
ac
y
ass
ess
m
en
t.
T
h
e
m
etr
ics
i
n
c
lu
d
e
r
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
MSE
)
,
r
esid
u
al
s
tan
d
ar
d
er
r
o
r
(
R
SE)
,
an
d
MS
E
.
T
h
e
tab
le
h
ig
h
lig
h
ts
R
B
F
’
s
s
u
p
er
io
r
p
r
ed
ictiv
e
ac
cu
r
ac
y
o
v
er
PLSR
.
T
h
ese
m
etr
ics
aid
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
in
s
elec
tin
g
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el
f
o
r
f
au
lt
p
r
ed
ictio
n
b
ased
o
n
th
eir
n
ee
d
s
an
d
d
ata
ch
a
r
ac
ter
i
s
tics
.
T
ab
le
3
.
E
r
r
o
r
p
ar
am
eter
s
o
f
f
au
lt p
r
ed
ictio
n
m
o
d
els
R
M
S
E
R
S
E
M
S
E
P
LSR
0
.
0
7
9
9
6
6
0
.
9
9
8
7
8
1
0
.
0
0
6
3
9
5
RBF
0
.
0
0
0
0
2
5
1
.
0
0
0
0
0
0
0
.
0
0
0
4
3
7
T
ab
le
4
o
u
tlin
es
a
DSS
em
p
lo
y
in
g
f
u
zz
y
lo
g
ic
to
lin
k
m
ac
h
in
e
f
au
lts
with
f
au
lt
ca
te
g
o
r
ies
an
d
s
u
g
g
est
r
ep
air
a
n
d
m
ain
ten
a
n
ce
ac
tio
n
s
[
2
5
]
.
T
h
is
in
teg
r
atio
n
en
h
a
n
ce
s
ad
ap
ta
b
ilit
y
a
n
d
in
ter
p
r
etab
ilit
y
,
ad
d
r
ess
in
g
u
n
ce
r
tain
ties
in
in
d
u
s
tr
ial
ap
p
licatio
n
s
.
T
h
e
ar
ticl
e
p
r
o
m
o
tes p
r
o
ac
tiv
e
m
ain
ten
an
ce
s
tr
ateg
ies wi
th
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
a
n
d
d
ec
i
s
io
n
s
u
p
p
o
r
t i
n
in
d
u
s
tr
ial
s
etti
n
g
s
.
T
ab
le
4
.
I
n
p
u
t a
n
d
o
u
tp
u
t
p
ar
a
m
eter
s
o
f
f
u
zz
y
lo
g
ic
DSS m
o
d
el
f
o
r
d
if
f
er
e
n
t f
au
lt c
o
n
d
itio
n
s
M
a
c
h
i
n
e
f
a
u
l
t
s
F
a
u
l
t
c
a
t
e
g
o
r
y
S
u
g
g
e
s
t
i
o
n
f
o
r
r
e
p
a
i
r
a
n
d
ma
i
n
t
e
n
a
n
c
e
S
u
g
g
e
s
t
i
o
n
t
y
p
e
Lo
o
se
mo
u
n
t
i
n
g
1
Ti
g
h
t
e
n
b
o
l
t
s
,
e
n
s
u
r
e
a
l
i
g
n
m
e
n
t
1
1
,
1
2
S
h
a
f
t
a
l
i
g
n
m
e
n
t
2
P
r
e
c
i
s
i
o
n
a
l
i
g
n
me
n
t
,
r
e
g
u
l
a
r
c
h
e
c
k
s
2
1
,
2
2
B
e
n
t
s
h
a
f
t
3
R
e
p
l
a
c
e
o
r
r
e
p
a
i
r
,
i
n
v
e
st
i
g
a
t
e
c
a
u
se
3
1
,
3
2
D
a
mag
e
d
b
e
a
r
i
n
g
s
4
P
r
o
mp
t
r
e
p
l
a
c
e
me
n
t
,
p
r
o
a
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
4
1
,
4
2
R
o
t
o
r
r
u
b
5
I
n
v
e
st
i
g
a
t
e
c
a
u
s
e
,
e
n
su
r
e
c
l
e
a
r
a
n
c
e
5
1
,
5
2
B
r
o
k
e
n
r
o
t
o
r
b
a
r
6
M
o
t
o
r
a
n
a
l
y
s
i
s,
r
e
p
l
a
c
e
b
a
r
s
6
1
,
6
2
S
t
a
t
o
r
d
a
m
a
g
e
7
I
n
sp
e
c
t
a
n
d
r
e
p
l
a
c
e
st
a
t
o
r
w
i
n
d
i
n
g
s
7
1
,
7
2
S
h
a
f
t
i
m
b
a
l
a
n
c
e
8
D
y
n
a
mi
c
b
a
l
a
n
c
i
n
g
,
r
e
g
u
l
a
r
m
o
n
i
t
o
r
i
n
g
8
1
,
8
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
d
en
tifi
ca
tio
n
o
f f
a
u
lts
in
r
o
ta
t
in
g
ma
ch
in
es u
s
in
g
h
ig
h
p
r
ec
is
io
n
F
B
G
…
(
Dip
a
k
R
a
n
ja
n
N
a
ya
k
)
543
Fig
u
r
e
1
3
illu
s
tr
ates
in
p
u
t
an
d
o
u
tp
u
t
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
co
r
r
esp
o
n
d
i
n
g
to
m
a
in
ten
an
ce
s
u
g
g
esti
o
n
s
(
Su
g
g
1
an
d
Su
g
g
2
)
o
f
th
e
f
u
zz
y
DSS
m
o
d
el
,
s
h
o
win
g
h
o
w
f
au
lt
ca
teg
o
r
i
es
(
F1
to
F8
)
ar
e
lin
g
u
is
tically
ch
ar
ac
ter
ized
w
ith
in
th
e
f
u
zz
y
lo
g
ic
f
r
am
ewo
r
k
.
T
ab
le
5
p
r
esen
ts
th
e
f
u
zz
y
DSS
r
u
leb
ase,
d
etailin
g
lo
g
ical
r
elatio
n
s
h
ip
s
b
etwe
en
f
au
lts
an
d
m
ain
te
n
an
ce
s
u
g
g
esti
o
n
s
.
T
h
is
in
teg
r
atio
n
o
f
g
r
ap
h
ical
r
ep
r
esen
tatio
n
s
an
d
a
well
-
d
e
f
in
ed
r
u
leb
ase
alig
n
s
with
th
e
ar
ticle
’
s
o
b
jectiv
e
o
f
d
ev
elo
p
in
g
a
r
o
b
u
s
t
f
u
zz
y
lo
g
ic
-
b
ased
DSS
f
o
r
p
r
ed
ictiv
e
m
ain
ten
an
ce
as
s
h
o
wn
in
T
a
b
le
6
,
en
h
a
n
cin
g
p
r
o
ac
tiv
e
m
a
in
ten
an
ce
d
ec
is
io
n
s
u
p
p
o
r
t
in
in
d
u
s
tr
ial
p
r
ac
tices.
T
ab
le
6
p
r
o
v
i
d
es
a
co
n
cise
o
v
er
v
iew
o
f
th
e
test
in
g
p
h
ase
f
o
r
th
e
f
u
zz
y
DSS
m
o
d
el,
co
n
n
ec
tin
g
s
ea
m
less
l
y
with
th
e
p
r
e
v
io
u
s
ly
d
is
cu
s
s
ed
co
n
ce
p
ts
.
T
h
is
tab
le
o
u
tlin
es
s
p
ec
if
ic
f
u
zz
y
in
p
u
ts
an
d
th
eir
co
r
r
esp
o
n
d
in
g
f
u
zz
y
o
u
tp
u
ts
,
wh
ic
h
r
e
p
r
esen
t
th
e
s
y
s
tem
’
s
r
ec
o
m
m
en
d
a
tio
n
s
f
o
r
p
r
o
ac
tiv
e
m
ain
ten
an
ce
ac
tio
n
s
.
(
a
)
(
b
)
(
c
)
(
d
)
Fig
u
r
e
13
.
T
h
e
in
p
u
t a
n
d
o
u
tp
u
t m
em
b
er
s
h
ip
f
u
n
ctio
n
s
(
MF)
o
f
th
e
f
u
zz
y
in
f
er
e
n
ce
s
y
s
tem
(
FIS)
T
ab
le
5
.
Fu
zz
y
DSS
r
u
leb
ase
R
u
l
e
N
u
m
b
e
r
F
a
u
l
t
S
u
g
g
1
S
u
g
g
2
C
o
n
f
i
d
e
n
c
e
1
F1
11
12
1
2
F2
21
22
1
3
F3
31
32
1
4
F4
41
42
1
5
F5
51
52
1
6
F6
61
62
1
7
F7
71
72
1
8
F8
81
82
1
T
ab
le
6
.
T
esti
n
g
o
f
f
u
zz
y
DSS m
o
d
el
F
u
z
z
y
i
n
p
u
t
F
u
z
z
y
o
u
t
p
u
t
1
(
S
u
g
g
e
st
i
o
n
1
)
F
u
z
z
y
o
u
t
p
u
t
2
(
S
u
g
g
e
st
i
o
n
2
)
2
2
1
:
C
o
n
d
u
c
t
p
r
e
c
i
s
i
o
n
a
l
i
g
n
m
e
n
t
u
s
i
n
g
l
a
ser
a
l
i
g
n
me
n
t
t
o
o
l
s.
2
2
:
R
e
g
u
l
a
r
l
y
c
h
e
c
k
a
n
d
a
d
j
u
st
t
h
e
a
l
i
g
n
me
n
t
t
o
p
r
e
v
e
n
t
f
u
t
u
r
e
i
ssu
e
s.
4
4
1
:
R
e
p
l
a
c
e
d
a
ma
g
e
d
b
e
a
r
i
n
g
s
p
r
o
m
p
t
l
y
.
4
2
:
I
mp
l
e
me
n
t
a
p
r
o
a
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
s
c
h
e
d
u
l
e
f
o
r
b
e
a
r
i
n
g
l
u
b
r
i
c
a
t
i
o
n
a
n
d
i
n
sp
e
c
t
i
o
n
.
6
6
1
:
P
e
r
f
o
r
m
a
mo
t
o
r
c
u
r
r
e
n
t
s
i
g
n
a
t
u
r
e
a
n
a
l
y
si
s
t
o
i
d
e
n
t
i
f
y
b
r
o
k
e
n
r
o
t
o
r
b
a
r
s.
6
2
:
R
e
p
l
a
c
e
t
h
e
d
a
m
a
g
e
d
r
o
t
o
r
b
a
r
s a
n
d
i
n
s
p
e
c
t
t
h
e
r
o
t
o
r
f
o
r
o
t
h
e
r
i
ssu
e
s.
8
8
1
:
U
se
d
y
n
a
m
i
c
b
a
l
a
n
c
i
n
g
t
e
c
h
n
i
q
u
e
s
t
o
c
o
r
r
e
c
t
sh
a
f
t
i
m
b
a
l
a
n
c
e
.
8
2
:
R
e
g
u
l
a
r
l
y
mo
n
i
t
o
r
a
n
d
b
a
l
a
n
c
e
t
h
e
r
o
t
o
r
t
o
p
r
e
v
e
n
t
f
u
t
u
r
e
i
ssu
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
535
-
5
4
7
544
9.
P
RE
DIC
T
I
VE
M
AI
NT
E
NA
NCE SO
L
UT
I
O
N
ARCH
I
T
E
CT
URE
T
h
e
a
r
t
i
c
l
e
e
x
te
n
s
i
v
el
y
e
x
p
l
o
r
e
s
FF
T
-
b
a
s
e
d
f
r
e
q
u
e
n
c
y
a
n
a
l
y
s
is
[
2
9
]
,
a
w
e
l
l
-
es
t
a
b
li
s
h
e
d
t
ec
h
n
i
q
u
e
i
n
I
o
T
-
b
a
s
e
d
p
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
an
c
e
.
F
r
e
q
u
e
n
c
y
c
o
m
p
o
n
e
n
t
s
c
o
r
r
e
s
p
o
n
d
i
n
g
t
o
v
a
r
i
o
u
s
v
i
b
r
a
t
i
o
n
c
o
n
d
i
t
i
o
n
s
a
r
e
s
t
o
r
e
d
i
n
a
c
l
o
u
d
-
b
a
s
e
d
d
i
s
t
r
ib
u
t
e
d
p
l
a
t
f
o
r
m
,
f
a
c
i
l
i
t
a
ti
n
g
p
r
o
l
o
n
g
e
d
m
o
n
i
t
o
r
i
n
g
a
n
d
c
o
m
p
r
e
h
e
n
s
i
v
e
m
a
c
h
i
n
e
h
e
a
l
t
h
u
n
d
e
r
s
ta
n
d
i
n
g
o
v
e
r
t
i
m
e
.
T
o
a
d
d
r
e
s
s
d
a
ta
t
r
a
n
s
m
is
s
i
o
n
l
a
t
e
n
c
y
,
a
p
r
e
-
p
r
o
c
e
s
s
i
n
g
s
ch
e
m
e
i
s
i
n
t
r
o
d
u
c
e
d
[
3
0
]
.
T
h
i
s
s
c
h
e
m
e
e
f
f
e
ct
i
v
e
l
y
m
i
t
i
g
a
t
es
l
a
t
e
n
c
y
i
s
s
u
e
s
,
a
n
d
p
r
o
c
e
s
s
e
d
i
n
f
o
r
m
a
t
i
o
n
is
s
y
s
tem
a
t
i
c
a
ll
y
t
r
a
n
s
m
i
tt
e
d
t
o
t
h
e
c
l
o
u
d
p
l
a
t
f
o
r
m
a
t
p
e
r
i
o
d
ic
i
n
t
e
r
v
a
l
s
[
3
1
]
.
F
i
g
u
r
e
1
4
i
ll
u
s
t
r
a
t
e
s
t
h
e
p
r
o
p
o
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
i
n
t
e
g
r
a
t
i
n
g
a
D
SS
w
i
t
h
t
h
e
e
x
is
ti
n
g
F
B
G
i
n
t
e
r
r
o
g
a
t
i
o
n
s
y
s
te
m
[
3
2
]
.
T
h
e
a
r
c
h
i
t
e
c
t
u
r
e
,
d
es
i
g
n
e
d
f
o
r
p
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
o
f
r
o
t
a
t
i
n
g
m
a
c
h
i
n
es
u
s
i
n
g
I
o
T
,
d
e
l
i
n
e
a
t
es
t
e
c
h
n
o
l
o
g
i
e
s
i
n
v
o
l
v
e
d
i
n
t
h
is
i
n
te
g
r
a
t
e
d
d
is
t
r
i
b
u
te
d
FB
G
s
e
n
s
i
n
g
s
y
s
t
e
m
,
e
m
p
h
a
s
i
z
i
n
g
i
n
t
e
r
c
o
n
n
e
c
t
e
d
e
le
m
e
n
t
s
f
o
r
e
f
f
i
ci
e
n
t
a
n
d
p
r
o
a
c
t
iv
e
m
a
c
h
i
n
e
h
e
a
l
t
h
m
o
n
i
t
o
r
i
n
g
.
Fig
u
r
e
14
.
I
o
T
-
b
ased
s
o
lu
tio
n
ar
ch
itectu
r
e
f
o
r
p
r
e
d
ictiv
e
m
ai
n
ten
an
ce
o
f
r
o
tatin
g
m
ac
h
in
es
T
h
e
tab
le
p
r
o
v
id
es in
s
ig
h
ts
in
to
p
o
ten
tial f
au
lts
an
d
th
eir
p
r
i
m
ar
y
lo
ca
tio
n
s
with
in
a
r
o
tatin
g
m
ac
h
in
e
[
3
2
]
-
[
3
5
]
.
On
e
id
e
n
tifie
d
f
a
u
lt
is
“
im
p
eller
im
b
alan
ce
”
lo
ca
ted
in
th
e
im
p
eller
,
lik
e
ly
ca
u
s
ed
b
y
h
ig
h
v
ib
r
atio
n
,
in
d
icatin
g
ir
r
eg
u
lar
ities
in
weig
h
t
d
is
tr
ib
u
tio
n
a
n
d
n
ec
ess
itatin
g
clo
s
e
m
o
n
ito
r
in
g
an
d
co
r
r
ec
tiv
e
ac
tio
n
.
Po
ten
tial
f
au
lts
ass
o
ci
ated
with
th
e
b
ea
r
in
g
h
o
u
s
in
g
,
s
u
ch
as
“
b
ea
r
in
g
d
am
ag
e
”
l
ea
d
in
g
to
a
PA
f
a
n
tr
ip
,
ca
n
r
esu
lt
f
r
o
m
wea
r
o
r
lu
b
r
icatio
n
is
s
u
es,
p
o
s
in
g
c
r
itical
o
p
er
atio
n
al
r
is
k
s
.
T
h
e
t
ab
le
also
id
en
tifie
s
p
o
ten
tial
s
h
af
t
-
r
elate
d
f
a
u
lts
lik
e
“
s
h
af
t
r
u
n
o
u
t
”
lin
k
ed
to
h
i
g
h
v
ib
r
atio
n
o
r
wo
b
b
lin
g
,
wh
i
ch
ca
n
s
ig
n
if
ican
tly
im
p
ac
t
m
ac
h
in
e
p
er
f
o
r
m
an
ce
[
3
2
]
-
[
3
5
]
.
I
n
in
d
u
s
tr
ial
s
ce
n
ar
i
o
s
,
f
au
lt
id
en
tific
atio
n
in
r
o
tat
in
g
m
ac
h
in
es
u
s
in
g
PLCs
an
d
ad
v
an
ce
d
co
n
tr
o
l
s
y
s
tem
s
,
co
u
p
led
with
tem
p
er
atu
r
e
an
d
v
ib
r
atio
n
d
ata
co
llectio
n
,
en
ab
les
h
is
to
r
ical
p
er
f
o
r
m
an
ce
tr
ac
k
i
n
g
a
n
d
p
r
o
ac
tiv
e
is
s
u
e
s
p
o
tti
n
g
[
3
6
]
-
[
3
8
]
.
T
ab
le
7
o
u
tlin
es
p
o
ten
tial
f
ailu
r
e
s
ce
n
ar
io
s
,
th
eir
p
r
im
ar
y
l
o
ca
tio
n
s
,
an
d
ass
o
ciate
d
ca
u
s
es
in
a
r
o
tatin
g
m
ac
h
in
e
[
3
2
]
-
[
3
5
]
.
I
d
en
tifie
d
f
a
u
lts
in
clu
d
e
im
p
eller
im
b
alan
ce
,
b
ea
r
in
g
d
am
ag
e,
s
h
af
t
d
am
a
g
e,
h
o
u
s
in
g
d
am
a
g
e,
an
d
s
h
af
t
r
u
n
o
u
t
,
ea
ch
with
d
is
tin
ct
ca
u
s
es
an
d
im
p
licatio
n
s
f
o
r
m
ac
h
in
e
r
eliab
ilit
y
.
T
h
is
co
m
p
r
eh
e
n
s
iv
e
m
atr
i
x
s
u
p
p
o
r
ts
tar
g
eted
p
r
ed
ictiv
e
m
ain
te
n
an
ce
s
tr
ateg
ies,
aid
in
g
in
o
p
tim
al
m
ac
h
in
e
p
er
f
o
r
m
an
ce
a
n
d
p
r
ev
en
tin
g
s
ev
er
e
d
is
r
u
p
tio
n
s
.
T
ab
le
7
.
Fau
lt
id
en
tific
atio
n
m
atr
ix
f
o
r
r
o
tatin
g
m
ac
h
in
e
c
o
m
p
o
n
en
ts
P
r
i
mary
l
o
c
a
t
i
o
n
P
o
t
e
n
t
i
a
l
f
a
i
l
u
r
e
C
a
u
ses
I
mp
e
l
l
e
r
I
mp
e
l
l
e
r
i
m
b
a
l
a
n
c
e
H
i
g
h
v
i
b
r
a
t
i
o
n
B
e
a
r
i
n
g
h
o
u
s
i
n
g
B
e
a
r
i
n
g
d
a
m
a
g
e
P
A
f
a
n
t
r
i
p
S
h
a
f
t
d
a
ma
g
e
H
o
u
s
i
n
g
d
a
ma
g
e
S
h
a
f
t
S
h
a
f
t
r
u
n
o
u
t
H
i
g
h
v
i
b
r
a
t
i
o
n
o
r
W
o
b
b
l
i
n
g
o
f
t
h
e
sh
a
f
t
10.
CO
NCLU
SI
O
N
T
h
e
s
tu
d
y
em
p
lo
y
s
p
ass
iv
e,
n
o
n
-
c
o
n
tact
s
en
s
o
r
s
to
an
aly
ze
elec
tr
ic
m
o
to
r
v
i
b
r
atio
n
,
s
h
o
wca
s
in
g
ac
cu
r
ate
f
au
lt
d
etec
tio
n
.
I
t
o
p
er
ates
ef
f
ec
tiv
ely
ac
r
o
s
s
d
iv
er
s
e
co
n
d
itio
n
s
an
d
ca
p
t
u
r
es
in
ten
tio
n
al
f
au
lts
’
v
ib
r
atio
n
p
atter
n
s
with
r
em
ar
k
ab
le
s
en
s
itiv
ity
.
T
h
e
FB
G
s
en
s
o
r
-
b
ased
p
r
ed
ictiv
e
m
ain
ten
an
ce
s
ch
e
m
e
in
teg
r
ates
FF
T
an
aly
s
is
an
d
ML
,
o
f
f
er
in
g
r
o
b
u
s
t
f
a
u
lt
d
e
tectio
n
.
Statis
tical
p
ar
am
eter
s
an
d
f
u
n
d
am
e
n
tal
f
r
eq
u
e
n
cy
co
m
p
o
n
en
ts
ar
e
lev
er
ag
ed
in
co
n
s
tr
u
ctin
g
m
ath
e
m
atica
l m
o
d
els u
s
in
g
PLSR
a
n
d
a
r
ad
ial
b
asis
ty
p
e
n
eu
r
al
n
etwo
r
k
,
p
r
o
v
i
d
in
g
a
s
o
p
h
is
ticated
ap
p
r
o
ac
h
to
f
a
u
lt
class
if
icatio
n
.
C
o
m
p
ar
is
o
n
s
b
etwe
en
m
o
d
els
alo
n
g
with
er
r
o
r
m
etr
ics,
h
ig
h
lig
h
t
th
e
s
u
p
er
io
r
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
th
e
R
B
F
m
o
d
el.
I
o
T
an
d
DSS
en
h
an
ce
r
ea
l
-
tim
e
d
ec
is
io
n
-
m
ak
in
g
,
aid
in
g
tar
g
eted
m
ain
ten
a
n
ce
s
tr
ateg
ies.
Ov
er
all,
th
e
r
esear
ch
ad
v
an
ce
s
p
r
ed
ictiv
e
m
ain
ten
an
ce
,
p
r
o
v
id
in
g
a
co
m
p
r
eh
en
s
iv
e
m
eth
o
d
o
lo
g
y
f
o
r
in
d
u
s
tr
ial
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
a
n
d
d
ec
is
io
n
s
u
p
p
o
r
t.
F
B
G
V
i
b
r
a
t
i
o
n
S
e
n
s
o
r
F
B
G
I
n
t
e
r
r
o
g
a
t
o
r
P
C
I
n
t
e
r
n
e
t
C
o
n
n
e
c
t
i
v
i
t
y
C
l
o
u
d
C
o
m
p
u
t
i
n
g
I
o
T
F
r
a
m
e
w
o
r
k
P
r
e
-
p
r
o
c
e
s
s
i
n
g
M
o
d
e
l
P
r
o
c
e
s
s
e
d
I
n
f
o
r
m
a
t
i
o
n
M
a
c
h
i
n
e
O
p
e
r
a
t
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.