I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
5
2
8
8
~
5
2
9
5
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
5
.
pp
5
2
8
8
-
5
2
9
5
5288
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Fault
d
ia
g
no
sis
of
r
o
lling
e
le
m
en
t
b
ea
ring
s
using
artificial n
e
ura
l net
w
o
rk
Sa
a
di L
a
ribi So
ua
d
1
,
B
endia
bd
ella
h Az
ze
d
ine
2
,
Sa
m
ir
M
er
a
di
3
1
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
L
a
b
o
ra
to
ry
o
f
L
2
G
E
G
I,
Un
iv
e
rsit
y
Ib
n
Kh
a
ld
o
u
n
,
A
lg
e
ria
2
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
L
a
b
o
ra
to
ry
o
f
L
DEE,
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
s a
n
d
T
e
c
h
n
o
lo
g
y
M
o
h
a
m
e
d
Bo
u
d
iaf
,
A
lg
e
ri
a
3
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
N
a
ti
o
n
a
l
P
o
ly
tec
h
n
ic S
c
h
o
o
l,
A
lg
e
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
1
3
,
2
0
1
9
R
ev
i
s
ed
A
p
r
2
8
,
2
0
2
0
A
cc
ep
ted
Ma
y
9
,
2
0
2
0
Be
a
rin
g
s
a
re
e
s
se
n
ti
a
l
c
o
m
p
o
n
e
n
ts
in
th
e
m
o
st
e
lec
tri
c
a
l
e
q
u
ip
m
e
n
t.
P
r
o
c
e
d
u
re
s
f
o
r
m
o
n
it
o
ri
n
g
th
e
c
o
n
d
it
io
n
o
f
b
e
a
rin
g
s
m
u
st
b
e
d
e
v
e
lo
p
e
d
to
p
re
v
e
n
t
u
n
e
x
p
e
c
ted
f
a
il
u
re
o
f
th
e
se
c
o
m
p
o
n
e
n
ts
d
u
ri
n
g
o
p
e
ra
ti
o
n
to
a
v
o
i
d
c
o
stly
c
o
n
se
q
u
e
n
c
e
s.
In
t
h
is
p
a
p
e
r,
th
e
d
e
sig
n
o
f
a
m
o
n
it
o
rin
g
s
y
ste
m
f
o
r
th
e
d
e
tec
ti
o
n
o
f
ro
ll
in
g
e
lem
e
n
t
-
b
e
a
rin
g
s
fa
il
u
re
is
p
ro
p
o
se
d
.
T
h
e
m
e
th
o
d
f
o
r
d
e
tec
ti
n
g
a
n
d
lo
c
a
ti
n
g
t
h
is
ty
p
e
o
f
f
a
u
lt
is
c
a
rried
o
u
t
u
sin
g
a
d
v
a
n
c
e
d
in
telli
g
e
n
t
tec
h
n
iq
u
e
s
b
a
se
d
o
n
a
p
e
rc
e
p
tro
n
m
u
lt
il
a
y
e
r
a
rti
f
ic
ial
n
e
u
ra
l
n
e
tw
o
rk
(M
L
P
-
AN
N);
it
s
d
a
tab
a
se
u
se
s
sta
ti
stic
a
l
in
d
ica
to
rs
c
h
a
ra
c
teriz
in
g
v
ib
ra
ti
o
n
sig
n
a
ls.
T
h
e
e
ff
e
c
ti
v
e
n
e
ss
o
f
th
e
p
ro
p
o
se
d
m
e
th
o
d
is
il
lu
stra
ted
u
sin
g
e
x
p
e
rim
e
n
tall
y
o
b
tain
e
d
b
e
a
rin
g
v
ib
ra
ti
o
n
d
a
ta,
a
n
d
th
e
re
su
lt
s
h
a
v
e
sh
o
w
n
g
o
o
d
a
c
c
u
ra
c
y
in
d
e
tec
ti
n
g
a
n
d
l
o
c
a
ti
n
g
d
e
f
e
c
ts
.
K
ey
w
o
r
d
s
:
B
ea
r
in
g
Dete
ctio
n
Diag
n
o
s
is
ML
P
n
e
u
r
al
n
et
w
o
r
k
T
im
e
-
d
o
m
ai
n
an
al
y
s
is
Co
p
y
rig
h
t
©
2
0
2
0
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
:
Saad
i L
ar
ib
i So
u
ad
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
L
ab
o
r
ato
r
y
o
f
L
2
GE
GI
,
Un
i
v
er
s
it
y
I
b
n
Kh
a
ld
o
u
n
,
T
iar
et,
A
l
g
er
ia.
E
m
ail:
s
o
u
ad
.
lar
ib
i@
u
n
i
v
-
tiar
et.
d
z
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
o
b
j
ec
tiv
e
o
f
co
n
d
itio
n
-
b
ased
m
ai
n
te
n
an
ce
is
to
d
etec
t
f
ail
u
r
es
o
f
r
o
tati
n
g
m
ac
h
i
n
er
y
b
ef
o
r
e
a
cr
itical
f
ailu
r
e
o
cc
u
r
s
.
T
h
is
m
ai
n
ten
a
n
ce
ap
p
r
o
ac
h
h
as
m
a
n
y
ad
v
a
n
ta
g
es,
as
it
av
o
id
s
t
h
e
n
ee
d
to
d
is
m
a
n
tle
th
e
m
ac
h
i
n
e
to
ch
ec
k
t
h
e
co
n
d
itio
n
o
f
its
co
m
p
o
n
e
n
t
s
.
I
n
ad
d
itio
n
,
th
e
ch
a
n
ce
s
o
f
d
etec
ti
n
g
a
d
ef
ec
t
b
ef
o
r
e
it
b
ec
o
m
e
s
cr
itical
i
n
cr
ea
s
e,
t
h
u
s
av
o
id
in
g
a
m
a
x
i
m
u
m
o
f
lo
s
s
es
an
d
f
ail
u
r
es
o
f
t
h
e
m
ac
h
in
e
.
Fo
r
th
ese
r
ea
s
o
n
s
,
th
e
au
to
m
atio
n
o
f
f
au
l
t
d
iag
n
o
s
is
in
p
r
o
ce
s
s
e
s
is
i
n
d
is
p
en
s
a
b
le.
T
h
e
in
d
u
s
tr
ial
s
ec
to
r
h
a
s
ar
o
u
s
ed
th
e
i
n
ter
est
o
f
s
ev
er
al
r
esear
c
h
er
s
o
v
er
th
e
p
ast d
ec
ad
es.
B
e
a
r
i
n
g
s
i
n
r
o
t
a
t
i
n
g
m
a
c
h
i
n
e
r
y
a
r
e
v
u
l
n
e
r
a
b
l
e
c
o
m
p
o
n
e
n
t
s
a
n
d
t
h
e
p
r
e
s
e
n
c
e
o
f
d
e
f
e
c
t
s
i
n
t
h
e
b
e
a
r
i
n
g
s
ca
n
lead
to
th
e
f
ailu
r
e
o
f
th
ese
m
ac
h
in
e
s
.
T
h
e
b
ea
r
in
g
s
g
e
n
e
r
all
y
co
n
s
i
s
t
o
f
t
w
o
r
i
n
g
s
,
an
in
n
er
an
d
an
o
u
ter
,
b
e
t
w
e
e
n
w
h
i
c
h
t
h
e
r
e
i
s
a
s
e
t
o
f
b
a
l
l
s
o
r
r
o
t
a
t
i
n
g
r
o
l
l
e
r
s
.
B
a
l
l
b
e
a
r
i
n
g
d
e
f
e
c
t
s
a
r
e
g
e
n
e
r
a
l
l
y
c
l
a
s
s
i
f
i
e
d
i
n
t
h
e
c
a
t
e
g
o
r
y
o
f
ec
ce
n
tr
icit
y
d
ef
ec
t
s
a
n
d
ca
n
b
e
cla
s
s
i
f
ied
a
s
a
d
e
f
ec
t
o
f
t
h
e
o
u
ter
r
in
g
,
d
ef
ec
t
o
f
th
e
i
n
n
er
r
in
g
a
n
d
d
ef
ec
t
o
f
b
alls
[
1
]
.
T
h
er
ef
o
r
e,
ea
r
ly
id
en
ti
f
icatio
n
o
f
th
e
s
er
io
u
s
n
es
s
o
f
t
h
ese
b
ea
r
in
g
f
au
l
ts
d
u
r
i
n
g
o
p
er
atio
n
ca
n
p
r
ev
en
t
m
ac
h
in
er
y
m
al
f
u
n
c
tio
n
an
d
f
a
ilu
r
e.
Def
ec
ti
v
e
b
ea
r
in
g
s
ca
u
s
e
v
ib
r
atio
n
s
,
th
er
e
f
o
r
e
th
ese
v
i
b
r
atio
n
s
ig
n
als
ca
n
b
e
u
s
ed
to
ev
al
u
ate
t
h
e
m
.
T
h
e
f
ir
s
t
d
e
f
ec
t
d
etec
tio
n
ap
p
r
o
ac
h
es
co
n
s
i
s
ted
o
f
t
h
e
an
a
l
y
s
is
o
f
v
ib
r
atio
n
s
i
g
n
a
l
s
ex
tr
ac
ted
f
r
o
m
t
h
e
m
ac
h
i
n
e
[
2
-
5
]
.
Diag
n
o
s
tic
tec
h
n
iq
u
es
f
o
r
b
ea
r
in
g
f
ail
u
r
es
ca
n
b
e
clas
s
if
i
ed
in
to
th
r
ee
ap
p
r
o
ac
h
es:
ti
m
e
an
a
l
y
s
i
s
b
a
s
e
d
o
n
s
t
a
t
i
s
t
i
c
a
l
p
a
r
a
m
e
t
e
r
s
[
5
,
6
]
,
f
r
e
q
u
e
n
c
y
a
n
a
l
y
s
i
s
[
7
,
8
]
,
a
n
d
t
i
m
e
-
f
r
e
q
u
e
n
c
y
a
n
a
l
y
s
i
s
,
s
u
c
h
a
s
t
h
e
w
a
v
e
l
e
t
tr
an
s
f
o
r
m
(
W
T
)
[
9
-
1
1
]
an
d
t
h
e
Hi
lb
er
t
-
H
u
an
g
tr
an
s
f
o
r
m
(
HHT
)
[
1
2
]
.
T
im
e
-
b
ased
d
ia
g
n
o
s
tic
s
i
s
n
o
t
v
er
y
ef
f
ec
tiv
e
w
h
e
n
ap
p
lied
to
in
cip
ien
t f
a
u
lt
s
,
o
r
w
h
e
n
t
h
e
s
y
s
te
m
is
e
x
p
o
s
ed
to
lo
w
lo
ad
s
,
as d
escr
ib
ed
in
[
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
a
u
lt d
ia
g
n
o
s
is
o
f
r
o
llin
g
ele
men
t b
ea
r
in
g
s
u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
S
a
a
d
i La
r
ib
i
S
o
u
a
d
)
5289
Sp
ec
tr
al
an
al
y
s
is
is
t
h
e
m
o
s
t
class
ic
ap
p
r
o
ac
h
to
d
etec
ti
n
g
f
ail
u
r
es
in
r
o
tatin
g
m
ac
h
in
er
y
,
an
d
en
v
elo
p
e
an
a
l
y
s
is
i
s
t
h
e
m
o
s
t
p
o
p
u
lar
m
et
h
o
d
o
f
d
iag
n
o
s
i
n
g
b
ea
r
in
g
f
ai
lu
r
es.
I
n
a
co
m
p
l
ex
v
ib
r
atio
n
s
i
g
n
a
l
f
r
o
m
a
n
i
n
d
u
s
tr
ia
l
m
ac
h
in
e,
e
n
v
elo
p
e
a
n
al
y
s
is
ca
n
b
e
u
s
ed
t
o
ex
tr
ac
t
p
er
io
d
ic
i
m
p
ac
ts
s
u
c
h
as
th
o
s
e
p
r
o
d
u
ce
d
d
u
r
in
g
b
ea
r
in
g
d
eter
io
r
atio
n
[
6
]
.
Ho
w
e
v
er
,
t
h
is
c
lass
ic
to
o
l
is
s
er
io
u
s
l
y
a
f
f
ec
ted
b
y
n
o
is
e,
esp
ec
iall
y
i
n
th
e
ea
r
l
y
s
tag
e
s
o
f
d
e
f
ec
ts
.
An
o
th
er
to
o
l u
s
u
all
y
u
s
ed
to
e
x
a
m
i
n
e
t
h
e
f
r
eq
u
e
n
c
y
d
o
m
ai
n
o
f
s
i
g
n
al
s
is
e
m
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
itio
n
(
E
MD
)
,
w
h
ich
allo
w
s
to
d
ec
o
m
p
o
s
e
a
s
ig
n
al
in
to
d
if
f
er
en
t
m
o
d
e
s
o
r
I
MFs
(
in
tr
in
s
ic
m
o
d
e
f
u
n
ctio
n
)
[
1
3
,
1
4
]
.
Du
e
to
th
e
d
r
a
w
b
ac
k
s
o
f
f
r
eq
u
en
c
y
a
n
al
y
s
i
s
,
it
is
n
ec
ess
ar
y
to
f
in
d
ad
d
itio
n
a
l
m
et
h
o
d
s
f
o
r
an
al
y
zin
g
th
e
n
o
n
-
s
tatio
n
ar
y
o
f
t
h
e
s
i
g
n
al.
T
i
m
e
-
f
r
eq
u
e
n
c
y
d
o
m
ai
n
a
n
al
y
s
i
s
i
s
t
h
e
m
o
s
t
p
o
p
u
lar
ap
p
r
o
ac
h
f
o
r
th
e
a
n
al
y
s
i
s
o
f
s
u
ch
s
i
g
n
als;
s
o
m
e
ca
n
b
e
cited
s
u
c
h
as
th
e
W
ig
n
er
-
f
ile
d
is
tr
ib
u
tio
n
(
W
VD)
an
d
t
h
e
s
h
o
r
t
-
ter
m
f
o
u
r
i
e
r
t
r
a
n
s
f
o
r
m
(
S
T
F
T
)
.
T
h
e
s
e
m
e
t
h
o
d
s
p
e
r
f
o
r
m
a
o
n
e
-
d
i
m
en
s
i
o
n
a
l
s
i
g
n
a
l
t
r
a
n
s
f
o
r
m
a
t
i
o
n
t
o
a
t
w
o
-
d
i
m
e
n
s
i
o
n
a
l
f
u
n
ctio
n
;
a
n
d
ca
n
t
h
er
ef
o
r
e
p
r
o
v
id
e
tr
u
e
t
i
m
e
-
f
r
eq
u
e
n
c
y
r
ep
r
esen
ta
t
io
n
s
o
f
t
h
e
s
i
g
n
al,
b
u
t
ea
ch
o
f
th
e
f
r
eq
u
en
c
y
-
ti
m
e
a
n
al
y
s
i
s
m
et
h
o
d
s
s
u
f
f
er
f
r
o
m
s
o
m
e
p
r
o
b
lem
s
.
Ho
w
ev
er
,
t
h
e
u
s
e
o
f
th
ese
m
et
h
o
d
s
f
o
r
id
en
ti
f
y
i
n
g
t
h
e
n
at
u
r
e
o
f
t
h
e
d
ef
ec
t
an
d
th
e
esti
m
atio
n
o
f
i
ts
s
e
v
er
it
y
r
eq
u
ir
es
th
e
k
n
o
w
l
ed
g
e
o
f
t
h
e
e
x
p
er
t
w
h
o
is
n
o
t
a
l
w
a
y
s
a
v
ailab
le
[
1
5
,
1
6
]
.
T
o
d
ay
,
t
h
an
k
s
to
th
e
d
ev
elo
p
m
en
t
o
f
ar
ti
f
ic
ial
i
n
tel
lig
e
n
ce
tec
h
n
iq
u
es,
th
is
o
b
s
tacle
is
o
v
er
co
m
e.
T
h
ese
tec
h
n
iq
u
es
ar
e
ca
p
ab
le
o
f
m
an
a
g
i
n
g
a
m
o
n
ito
r
in
g
p
r
o
ce
d
u
r
e
o
f
w
h
ic
h
th
e
y
r
ep
r
esen
t
th
e
e
x
p
er
tis
e
s
id
e
an
d
th
u
s
ta
k
e
t
h
e
r
o
le
d
esig
n
ed
f
o
r
th
e
ex
p
er
t.
I
n
a
d
iag
n
o
s
t
ic
p
r
o
ce
d
u
r
e,
af
ter
th
e
ex
tr
ac
tio
n
o
f
c
h
ar
ac
ter
i
s
tics
,
an
i
n
tell
ig
e
n
t
clas
s
i
f
icati
o
n
s
y
s
te
m
is
r
eq
u
ir
ed
.
Se
v
er
al
i
n
telli
g
e
n
t
cla
s
s
i
f
icat
io
n
s
y
s
te
m
s
h
a
v
e
b
ee
n
d
ev
elo
p
ed
an
d
u
s
ed
f
o
r
m
o
n
ito
r
in
g
a
n
d
d
iag
n
o
s
i
s
,
s
u
c
h
a
s
f
u
zz
y
clas
s
if
ier
s
,
g
e
n
etic
alg
o
r
it
h
m
s
,
a
n
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
es
(
S
VM
s
)
a
n
d
ar
tific
ial
n
eu
r
al
n
e
t
w
o
r
k
(
A
N
N
)
[
1
7
-
1
9
]
.
N.
T
alb
i,
et
al.
,
[
1
9
]
p
r
o
p
o
s
ed
a
r
o
b
u
s
t
b
ea
r
in
g
d
ef
ec
t
class
i
f
icatio
n
tech
n
iq
u
e,
w
h
ich
w
a
s
u
s
ed
b
y
t
h
e
ad
ap
tiv
e
n
et
w
o
r
k
r
ef
e
r
en
ce
in
f
o
r
m
atio
n
s
y
s
te
m
(
ANFI
S).
T
h
e
r
esu
lts
o
b
tain
ed
b
y
t
h
is
tec
h
n
iq
u
e
g
a
v
e
a
b
etter
ac
cu
r
ac
y
o
f
d
ef
ec
t
class
i
f
icatio
n
.
I
n
t
h
i
s
co
n
tex
t
,
w
e
h
a
v
e
tr
ied
to
d
ev
elo
p
an
o
th
er
ap
p
r
o
ac
h
f
o
r
th
e
d
etec
tio
n
an
d
clas
s
i
f
icati
o
n
o
f
b
ea
r
in
g
d
e
f
ec
ts
u
s
i
n
g
ag
ain
t
h
e
ad
v
a
n
ce
d
in
telli
g
e
n
t
tec
h
n
iq
u
e,
b
u
t
t
h
i
s
ti
m
e
th
e
tech
n
iq
u
e
i
s
b
ased
o
n
a
p
er
ce
p
tr
o
n
m
u
ltil
a
y
er
ar
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
(
ML
P
-
A
NN)
.
T
h
e
m
et
h
o
d
is
p
r
o
p
o
s
ed
to
co
m
b
in
e
v
ib
r
atio
n
s
ig
n
al
a
n
al
y
s
is
a
n
d
(
ML
P
-
AN
N)
.
S
e
v
e
r
a
l
s
t
a
t
i
s
t
i
c
a
l
i
n
d
i
c
a
t
o
r
s
e
x
i
s
t
i
n
t
h
e
l
i
t
e
r
a
t
u
r
e
,
m
o
r
e
o
r
l
e
s
s
e
f
f
i
c
i
e
n
t
a
n
d
a
d
e
q
u
a
t
e
t
o
c
h
a
r
a
c
t
e
r
i
z
e
a
g
i
v
e
n
s
i
g
n
a
l
.
T
h
e
i
n
d
i
c
a
t
o
r
s
m
o
s
t
s
e
n
s
i
t
i
v
e
t
o
d
e
f
e
c
t
s
h
a
v
e
b
e
e
n
s
e
l
e
c
t
e
d
a
n
d
u
s
e
d
a
s
i
n
p
u
t
s
f
o
r
(
M
L
P
-
A
N
N
)
.
T
h
is
tech
n
iq
u
e
is
u
s
ed
f
o
r
th
e
d
etec
tio
n
an
d
lo
ca
lizatio
n
o
f
b
ea
r
in
g
f
au
lts
u
n
d
er
d
if
f
er
en
t
lo
ad
co
n
d
itio
n
s
.
T
h
e
ef
f
ec
ti
v
e
n
ess
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
test
s
w
ith
e
x
p
er
im
en
tal
r
esu
lts
.
2.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
T
h
e
d
atab
ase
u
s
ed
is
a
s
et
o
f
r
o
llin
g
v
ib
r
atio
n
s
i
g
n
als
f
r
o
m
"
C
ase
W
es
ter
n
R
eser
v
e
Un
i
v
er
s
it
y
B
ea
r
in
g
Data
C
en
ter
,
[
2
0
]
.
T
h
e
d
atab
ase
o
f
n
o
r
m
al
o
r
d
ef
ec
tiv
e
b
all
b
ea
r
in
g
s
i
s
co
llect
ed
o
n
a
test
b
en
c
h
co
n
s
is
tin
g
o
f
a
m
o
to
r
,
a
co
u
p
lin
g
an
d
a
g
en
er
ato
r
.
De
f
ec
t
s
i
n
t
h
e
f
o
r
m
o
f
d
o
ts
o
f
d
i
f
f
e
r
en
t
d
ia
m
eter
s
a
n
d
d
ep
th
s
h
av
e
b
ee
n
cr
ea
ted
o
n
t
h
e
d
i
f
f
er
e
n
t
p
ar
ts
o
f
t
h
e
b
ea
r
in
g
s
.
As
s
h
o
w
n
i
n
Fi
g
u
r
e
1
,
t
h
e
test
b
en
c
h
co
n
s
is
t
s
m
ai
n
l
y
o
f
a
m
o
to
r
o
n
t
h
e
le
f
t
s
id
e,
a
co
u
p
lin
g
"
tr
an
s
d
u
ce
r
/
e
n
co
d
er
"
at
th
e
ce
n
ter
,
a
d
y
n
a
m
o
m
e
ter
at
t
h
e
r
ig
h
t
s
id
e
an
d
th
e
co
n
tr
o
l c
ir
cu
its
n
o
t v
is
ib
le
i
n
th
e
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
E
x
p
er
i
m
en
tal
test
-
b
e
d
(
Data
b
ea
r
in
g
ce
n
ter
)
2
.
1
.
I
dentif
ica
t
io
n o
f
t
he
bea
ring
s
us
ed
T
h
e
t
e
s
t
e
d
b
e
a
r
in
g
s
s
u
p
p
o
r
t
th
e
m
o
t
o
r
s
h
af
t
o
n
b
o
t
h
s
i
d
e
s
(
d
r
i
v
e
s
i
d
e
a
n
d
f
an
s
i
d
e
)
.
S
im
p
le
d
o
t
-
s
h
a
p
e
d
f
au
lt
s
a
r
e
c
r
e
a
t
e
d
o
n
th
e
t
es
t
b
e
a
r
i
n
g
s
,
u
s
in
g
e
l
e
c
t
r
o
-
d
is
ch
a
r
g
e
m
a
ch
in
in
g
.
F
au
lt
s
r
an
g
in
g
f
r
o
m
0
.
0
0
7
i
n
c
h
e
s
t
o
0
.
0
2
8
i
n
c
h
e
s
i
n
d
i
am
e
t
e
r
a
r
e
in
t
r
o
d
u
c
e
d
s
e
p
a
r
a
t
ely
in
:
T
h
e
b
ea
r
in
g
in
n
er
r
in
g
;
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
8
8
-
5295
5290
T
h
e
r
o
llin
g
ele
m
e
n
t (
t
h
e
b
all)
;
T
h
e
b
ea
r
in
g
o
u
ter
r
in
g
.
A
ll
d
ata
f
ile
s
ar
e
in
Ma
t
lab
f
o
r
m
at
(
*
.
m
at)
.
E
ac
h
f
ile
co
n
ta
in
s
t
h
r
ee
d
ata:
v
ib
r
atio
n
s
i
g
n
a
ls
o
n
b
o
t
h
co
u
p
lin
g
a
n
d
f
an
s
id
e
s
as
w
e
ll
as
t
h
e
s
p
ee
d
o
f
r
o
tatio
n
o
f
th
e
m
o
to
r
.
Th
e
b
ea
r
in
g
s
u
s
e
d
in
o
u
r
w
o
r
k
ar
e
th
e
s
id
e
co
u
p
li
n
g
b
ea
r
i
n
g
s
.
2
.
2
.
Repre
s
ent
a
t
io
n o
f
t
i
m
e
s
ig
na
ls
Fo
r
th
e
v
alid
atio
n
o
f
th
e
d
i
ag
n
o
s
tic
p
r
o
ce
d
u
r
e
u
s
ed
,
th
e
ac
q
u
is
itio
n
s
o
f
ti
m
e
-
d
o
m
ai
n
v
ib
r
atio
n
s
ig
n
al
s
r
ec
o
r
d
ed
o
n
th
e
co
u
p
lin
g
s
id
e
f
o
r
f
o
u
r
lo
ad
lev
e
ls
(
0
,
1
,
2
,
3
HP
)
an
d
1
2
,
0
0
0
p
o
in
ts
/
s
ec
o
n
d
ar
e
f
o
r
th
e
f
o
llo
w
i
n
g
o
p
er
atin
g
m
o
d
e
s
,
s
ee
Fi
g
u
r
e
s
2
a
n
d
3
:
1
m
il
=
0
.
0
0
1
in
ch
es,
1
in
c
h
=
2
5
.
4
m
m
,
1
HP
=
1
Ho
r
s
e
P
o
w
er
=
7
4
5
.
6
9
W
att
Fig
u
r
e
2
.
Vib
r
atio
n
ti
m
e
s
ig
n
a
ls
f
o
r
h
ea
lt
h
y
an
d
f
a
u
lt
y
o
p
er
atio
n
f
o
r
d
if
f
er
en
t r
es
is
ti
v
e
to
r
q
u
es
an
d
d
ef
ec
t d
ia
m
eter
s
(
0
.
0
0
7
"
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
a
u
lt d
ia
g
n
o
s
is
o
f
r
o
llin
g
ele
men
t b
ea
r
in
g
s
u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
S
a
a
d
i La
r
ib
i
S
o
u
a
d
)
5291
Fig
u
r
e
3
.
Vib
r
atio
n
ti
m
e
s
ig
n
a
ls
f
o
r
f
a
u
lt
y
o
p
er
atio
n
f
o
r
d
if
f
e
r
en
t r
esis
ti
v
e
to
r
q
u
es
an
d
d
ef
ec
t d
ia
m
eter
s
(
0
.
0
0
7
"
)
3.
AP
P
L
I
CA
T
I
O
N
O
F
ANN
F
O
R
DE
T
E
C
T
I
O
N
O
F
B
E
A
RIN
G
DE
F
E
C
T
S
T
h
e
am
p
lit
u
d
e
o
f
th
e
s
h
o
ck
s
ap
p
lied
to
th
e
b
ea
r
in
g
d
ep
en
d
s
d
ir
ec
tl
y
o
n
th
e
d
ia
m
et
er
o
f
t
h
e
d
ef
ec
t.
T
h
e
lar
g
er
th
e
d
ef
ec
t,
th
e
g
r
ea
ter
th
e
s
h
o
ck
.
T
h
e
v
ib
r
atio
n
s
i
g
n
al,
w
h
ic
h
is
th
e
r
esp
o
n
s
e
to
th
e
s
h
o
ck
,
i
s
also
d
ir
ec
tl
y
r
elate
d
to
th
e
s
ize
o
f
th
e
d
ef
ec
t.
T
o
ch
ar
ac
ter
ize
a
v
ib
r
atio
n
s
i
g
n
al,
s
e
v
er
al
ti
m
e
d
escr
ip
to
r
s
ex
is
t,
allo
w
i
n
g
h
a
v
i
n
g
i
n
f
o
r
m
atio
n
b
y
m
ea
n
s
o
f
a
u
n
iq
u
e
v
al
u
e.
T
h
e
b
est
k
n
o
w
n
ar
e
th
e
P
E
AK
(
m
ax
i
m
u
m
v
al
u
e)
,
th
e
R
M
S
(
r
o
o
t
m
ea
n
s
q
u
ar
e)
w
h
ic
h
r
ep
r
esen
ts
t
h
e
R
M
S
v
al
u
e
o
f
th
e
s
ig
n
al,
t
h
e
cr
est
f
ac
t
o
r
an
d
th
e
k
u
r
to
s
i
s
.
T
ab
le
1
s
u
m
m
ar
izes t
h
e
m
a
in
co
n
v
e
n
tio
n
al
d
escr
ip
to
r
s
t
h
at
w
e
ar
e
g
o
i
n
g
to
u
s
e
i
n
o
u
r
w
o
r
k
.
T
ab
le
1
.
T
em
p
o
r
al
d
escr
ip
to
r
s
[
2
1
]
T
e
mp
o
r
a
l
i
n
d
i
c
a
t
o
r
s
Ex
p
r
e
ssi
o
n
Pe
a
k
p
e
a
k
=
su
p
1
≤
K
≤
N
|
a
k
|
R
o
o
t
M
e
a
n
S
q
u
a
r
e
RMS
=
√
1
=
∑
2
=
1
Kurt
o
si
s
Kurt
o
si
s
=
1
=
∑
(
−
̅
)
4
=
1
4
I
mp
u
l
se
F
a
c
t
o
r
I
M
F
=
p
e
a
k
1
=
∑
|
|
=
1
C
r
e
st
F
a
c
t
o
r
CF
=
p
e
a
k
RMS
TA
L
A
F
T
A
LA
F
=
lo
g
[
+
0
]
T
H
I
K
A
T
T
HI
KA
T
=
lo
g
[
(
)
+
(
0
)
]
I
n
o
r
d
er
to
d
eter
m
i
n
e
t
h
e
t
y
p
e
o
f
ex
i
s
ti
n
g
b
ea
r
in
g
d
ef
ec
t,
a
f
a
u
lt
d
etec
tio
n
an
d
d
iag
n
o
s
i
s
p
r
o
ce
d
u
r
e
ar
e
p
r
o
p
o
s
ed
u
s
in
g
a
co
m
b
in
a
tio
n
o
f
a
s
tatis
tical
an
al
y
s
is
te
ch
n
iq
u
e
b
ased
o
n
v
ib
r
atio
n
s
i
g
n
al
i
n
d
icato
r
s
an
d
an
i
n
telli
g
e
n
t
tec
h
n
iq
u
e
b
ased
o
n
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
A
NN)
[
2
1
-
2
6
]
.
Fi
g
u
r
e
4
s
h
o
w
s
a
s
i
m
p
lifie
d
f
lo
w
ch
ar
t o
f
th
e
p
r
o
p
o
s
ed
p
r
o
ce
s
s
.
T
h
e
s
tep
s
o
f
co
n
s
tr
u
ctio
n
a
n
d
v
alid
atio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
s
ar
e
d
iv
in
g
in
to
t
h
r
ee
p
h
ases
:
-
C
h
o
ice
o
f
n
et
w
o
r
k
in
p
u
ts
T
h
e
lear
n
in
g
b
ase
o
f
th
e
A
N
N
is
p
r
esen
ted
in
th
e
f
o
r
m
o
f
a
f
ile
o
r
a
tab
le
(
m
atr
ix
)
.
I
t
is
r
ep
r
esen
ted
b
y
clas
s
es
o
f
v
ec
to
r
s
,
w
h
er
e
ea
ch
class
r
ep
r
esen
t
s
a
t
y
p
e
o
f
o
p
er
atio
n
,
an
d
ea
ch
v
ec
to
r
is
r
ep
r
esen
ted
b
y
th
e
s
a
m
p
led
v
al
u
es.
I
n
o
u
r
ca
s
e
s
t
u
d
y
,
th
er
e
ar
e
s
e
v
er
al
v
ec
to
r
s
,
w
h
ic
h
r
ep
r
esen
t
t
h
e
f
o
u
r
t
y
p
es
o
f
o
p
er
atio
n
m
o
d
e
s
,
a
n
d
t
h
ese
r
ep
r
ese
n
t
f
o
u
r
v
ec
to
r
s
f
o
r
th
e
d
if
f
er
en
t
lo
ad
s
(
0
,
1
,
2
,
3
HP
)
an
d
1
2
,
0
0
0
p
o
in
ts
/s
ec
o
n
d
co
n
ce
r
n
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
8
8
-
5295
5292
T
h
e
s
a
m
p
led
v
al
u
es
c
h
o
s
e
n
as
in
p
u
ts
o
f
t
h
e
n
e
u
r
al
n
e
t
w
o
r
k
ar
e
t
h
e
s
tatis
ti
c
al
i
n
d
icato
r
s
o
f
th
e
v
ib
r
atio
n
s
i
g
n
als,
t
h
eir
m
at
h
e
m
a
tical
e
x
p
r
ess
io
n
s
ar
e
g
i
v
e
n
in
T
ab
le
1
.
H
en
ce
th
e
n
u
m
b
er
o
f
in
p
u
ts
o
n
th
i
s
n
et
w
o
r
k
i
s
eq
u
al
to
7
:
[
Pe
a
k
R
M
S
Ku
IM
F
CF
TAL
A
F
THIK
A
T
]
-
C
h
o
ice
o
f
n
et
w
o
r
k
o
u
tp
u
t
s
W
h
en
a
f
a
u
lt
i
s
d
etec
ted
,
t
h
e
n
et
w
o
r
k
m
u
s
t
i
n
d
icate
a
b
i
n
ar
y
n
u
m
b
er
t
h
r
o
u
g
h
its
o
u
t
p
u
t,
w
h
ich
co
r
r
esp
o
n
d
s
to
a
ty
p
e
o
f
f
au
l
t;
th
i
s
is
ca
lled
t
h
e
clas
s
if
ica
tio
n
s
tep
.
I
n
t
h
is
w
o
r
k
,
f
o
u
r
t
y
p
es
o
f
f
a
u
lts
ar
e
co
n
s
id
er
ed
an
d
ar
e
b
in
ar
y
co
d
ed
as sh
o
w
n
i
n
T
ab
le
2
.
T
ab
le
2
.
C
lass
if
icatio
n
o
f
t
y
p
e
s
o
f
r
o
llin
g
d
ef
ec
t
s
B
e
a
r
i
n
g
c
o
n
d
i
t
i
o
n
C
o
d
i
f
i
c
a
t
i
o
n
/
d
e
si
r
e
d
o
u
t
p
u
t
H
e
a
l
t
h
y
st
a
t
e
1
0
0
0
F
a
u
l
t
i
n
t
h
e
i
n
n
e
r
r
i
n
g
0
1
0
0
F
a
u
l
t
i
n
t
h
e
o
u
t
e
r
r
i
n
g
0
0
1
0
F
a
u
l
t
i
n
t
h
e
b
a
l
l
0
0
0
1
-
C
h
o
ice
o
f
ac
ti
v
atio
n
f
u
n
ctio
n
Sin
ce
th
e
o
u
tp
u
ts
ar
e
b
i
n
ar
y
a
n
d
th
e
i
n
p
u
ts
ar
e
r
ea
l,
t
h
e
ac
ti
v
atio
n
f
u
n
ctio
n
is
a
s
i
g
m
o
id
f
u
n
ct
io
n
a
s
d
ep
icted
in
Fig
u
r
e
5
.
T
h
is
f
i
g
u
r
e
illu
s
tr
ate
s
th
e
s
tr
u
ct
u
r
e
o
f
t
h
e
ML
P
-
A
NN
n
e
u
r
o
n
n
et
w
o
r
k
u
s
ed
in
o
u
r
w
o
r
k
.
Fig
u
r
e
4
.
C
lass
if
ica
tio
n
s
c
h
e
m
e
b
y
R
N
A
-
b
ased
o
n
v
al
u
es o
f
th
e
te
m
p
o
r
al
i
n
d
icato
r
s
Fig
u
r
e
5
.
Neu
r
al
n
et
w
o
r
k
d
es
i
g
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
a
u
lt d
ia
g
n
o
s
is
o
f
r
o
llin
g
ele
men
t b
ea
r
in
g
s
u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
S
a
a
d
i La
r
ib
i
S
o
u
a
d
)
5293
3
.
1
.
Resul
t
s
o
f
lea
rning
T
h
e
b
est
lear
n
i
n
g
p
er
f
o
r
m
an
ce
s
o
b
tain
ed
t
h
r
o
u
g
h
a
g
o
o
d
ch
o
ice
o
f
th
e
ANN
s
tr
u
ct
u
r
e
an
d
af
ter
s
ev
er
al
lear
n
i
n
g
test
s
.
T
h
e
r
e
s
u
lt
in
g
n
et
w
o
r
k
is
ch
ar
ac
ter
iz
ed
b
y
a
s
i
m
p
le
ar
ch
i
tectu
r
e
c
o
m
p
r
i
s
in
g
an
i
n
p
u
t
la
y
er
(
r
etin
a)
,
an
o
u
tp
u
t
la
y
er
f
o
r
th
e
d
ec
is
io
n
an
d
a
h
id
d
en
la
y
er
co
m
p
o
s
ed
o
f
ten
n
e
u
r
o
n
s
w
h
o
s
e
tr
an
s
f
er
f
u
n
ctio
n
is
o
f
s
i
g
m
o
id
t
y
p
e
an
d
o
f
lin
ea
r
t
y
p
e
f
o
r
th
e
n
e
u
r
o
n
o
f
th
e
o
u
tp
u
t
la
y
er
as
s
h
o
w
n
i
n
Fig
u
r
e
6
.
T
h
e
lear
n
in
g
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
u
s
ed
A
NN
i
s
ev
al
u
ated
t
h
r
o
u
g
h
t
h
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
.
Fo
r
o
u
r
ca
s
e,
th
e
A
NN
r
ea
c
h
es
a
v
alu
e
o
f
7
.
1
1
9
2
e
-
1
1
af
ter
1
8
iter
atio
n
s
as
s
h
o
w
n
in
Fig
u
r
e
7
.
Fro
m
t
h
e
r
esu
lt
s
o
b
tain
ed
i
n
th
e
test
p
h
a
s
e,
ca
n
b
e
s
ee
n
th
a
t
th
e
o
u
tp
u
ts
o
f
t
h
e
A
NN
f
o
ll
o
w
al
m
o
s
t
ex
ac
t
l
y
(
w
it
h
an
er
r
o
r
o
f
7
.
1
1
9
2
e
-
1
1
)
th
e
d
esire
d
p
r
e
-
estab
lis
h
ed
o
u
t
p
u
ts
.
Fig
u
r
e
6
.
B
u
ild
in
g
t
h
e
A
N
N
b
lo
ck
F
ig
u
r
e
7
.
P
er
f
o
r
m
a
n
ce
o
f
th
e
n
eu
r
o
n
n
et
w
o
r
k
3
.
2
.
T
ests o
f
t
he
ANN
f
o
r
f
a
ult
det
ec
t
io
n
On
ce
t
h
e
ANN
h
as
b
u
ilt
a
n
d
its
lear
n
in
g
h
as
ac
h
ie
v
ed
s
atis
f
ac
to
r
y
p
er
f
o
r
m
an
ce
,
w
e
m
o
v
e
to
th
e
co
m
p
ar
i
s
o
n
s
ta
g
e
b
et
w
ee
n
ex
a
m
p
les
at
t
h
e
e
n
tr
an
ce
o
f
t
h
e
n
et
w
o
r
k
.
I
n
f
ac
t,
t
h
e
s
e
e
x
a
m
p
les
b
elo
n
g
to
t
w
o
d
atab
ases
,
th
e
f
ir
s
t
b
ein
g
t
h
e
l
ea
r
n
in
g
b
ase
an
d
th
e
s
ec
o
n
d
b
ein
g
t
h
e
test
b
ase
o
n
w
h
ic
h
o
n
e
test
s
th
e
ab
ilit
y
o
f
th
e
n
et
w
o
r
k
to
r
ec
o
g
n
ize
n
o
r
m
al
e
x
a
m
p
les
(
n
o
t
lear
n
ed
)
.
T
h
e
last
o
p
er
atio
n
m
ak
e
s
it
p
o
s
s
ib
le
to
es
ti
m
a
te
th
e
g
e
n
er
aliza
tio
n
ca
p
ac
it
y
o
f
th
e
A
NN
n
et
w
o
r
k
.
As
f
o
r
th
e
n
et
w
o
r
k
test
o
n
t
h
e
ex
a
m
p
les
th
at
ar
e
n
o
t
lear
n
ed
in
t
h
e
lear
n
i
n
g
p
h
ase
(
n
e
w
e
x
a
m
p
les),
th
e
ir
r
esu
l
ts
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
8
.
Fro
m
th
e
r
es
u
lt
s
o
b
tain
ed
in
t
h
e
test
p
h
ase,
it
ca
n
b
e
s
ee
n
t
h
at
t
h
e
o
u
tp
u
ts
o
f
t
h
e
A
NN
ev
o
l
v
e
ac
co
r
d
in
g
to
th
e
p
r
e
-
estab
li
s
h
ed
d
esire
d
o
u
tp
u
ts
f
o
r
th
e
d
if
f
er
en
t t
y
p
es o
f
o
p
er
atio
n
(
h
ea
lt
h
y
s
tate
a
n
d
f
a
u
lt
y
s
tat
e
w
it
h
b
ea
r
in
g
d
ef
ec
t
s
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
8
8
-
5295
5294
(
a)
(
b
)
(
c)
(
d
)
F
ig
u
r
e
8
.
Ou
tp
u
t
s
an
d
er
r
o
r
s
o
f
A
NN
lear
n
in
g
,
(
a)
Hea
lth
y
m
ac
h
in
e:
d
es
ir
ed
o
u
tp
u
t 1
0
0
0
,
(
b
)
Ma
ch
in
e
w
ith
Fau
lt i
n
t
h
e
in
n
er
r
in
g
: d
esire
d
o
u
tp
u
t 0
1
0
0
,
(
c)
Ma
ch
in
e
w
it
h
Fa
u
lt in
t
h
e
o
u
ter
r
i
n
g
: d
es
ir
ed
o
u
tp
u
t 0
0
1
0
an
d
(
d
)
Ma
ch
in
e
w
it
h
Fa
u
lt i
n
th
e
b
all: d
esire
d
o
u
tp
u
t 0
0
0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
a
u
lt d
ia
g
n
o
s
is
o
f
r
o
llin
g
ele
men
t b
ea
r
in
g
s
u
s
in
g
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
(
S
a
a
d
i La
r
ib
i
S
o
u
a
d
)
5295
4
.
CONC
L
U
S
I
O
N
T
h
is
w
o
r
k
is
d
e
v
o
ted
to
t
h
e
p
r
o
p
o
s
al
o
f
t
h
e
b
ea
r
in
g
d
e
f
ec
t
clas
s
i
f
icatio
n
u
s
i
n
g
ar
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
s
(
A
NN)
.
T
h
e
r
esu
lti
n
g
n
et
w
o
r
k
i
s
ch
ar
ac
ter
ized
b
y
a
s
i
m
p
le
ar
ch
itect
u
r
e
w
ith
a
n
in
p
u
t
la
y
er
(
r
etin
a)
,
an
o
u
tp
u
t
la
y
er
f
o
r
th
e
d
ec
is
io
n
an
d
a
h
id
d
en
la
y
er
o
f
1
0
n
eu
r
o
n
s
,
an
d
g
r
ap
h
ical
r
es
u
lts
t
h
at
s
h
o
w
th
e
r
es
u
lt
s
o
f
t
h
e
tr
ai
n
in
g
.
I
t
ca
n
b
e
co
n
clu
d
ed
th
at
b
etter
lear
n
in
g
p
e
r
f
o
r
m
an
ce
ac
h
iev
e
s
t
h
r
o
u
g
h
a
g
o
o
d
ch
o
ice
o
f
a
n
A
N
N
s
tr
u
c
tu
r
e
a
f
ter
s
ev
er
al
le
ar
n
in
g
test
s
.
RE
F
E
R
E
NC
E
S
[1
]
B.
M
u
r
u
g
a
n
a
th
a
m
,
e
t
a
l.
,
“
Ro
ll
e
r
El
e
m
e
n
t
Be
a
rin
g
F
a
u
lt
Di
a
g
n
o
sis
Us
in
g
S
i
n
g
u
lar
S
p
e
c
tru
m
A
n
a
l
y
sis,”
M
e
c
h
a
n
ica
l
S
y
ste
ms
a
n
d
S
i
g
n
a
l
P
ro
c
e
ss
in
g
,
v
o
l.
3
5
,
n
o
.
1
-
2
,
p
p
.
1
5
0
-
1
6
6
,
2
0
1
3
.
[2
]
S.
Ku
lk
a
rn
i
a
n
d
S
.
W
a
d
k
a
r
.
,
“
Ex
p
e
rim
e
n
tal
In
v
e
stig
a
ti
o
n
f
o
r
Distr
ib
u
te
d
De
f
e
c
ts
in
Ba
ll
Be
a
rin
g
U
sin
g
V
i
b
ra
ti
o
n
S
ig
n
a
tu
re
A
n
a
l
y
sis,”
Pro
c
e
d
ia
En
g
in
e
e
rin
g
,
v
o
l.
1
4
4
,
n
o
.
2
0
1
6
,
p
p
.
7
8
1
-
7
8
9
,
2
0
1
6
.
[3
]
A
.
P
a
v
a
n
a
n
d
P
.
Ja
y
a
s
w
a
l,
“
S
e
l
e
c
ti
o
n
o
f
Be
st
Cla
ss
i
f
ica
ti
o
n
A
l
g
o
rit
h
m
f
o
r
F
a
u
lt
Dia
g
n
o
sis
o
f
Be
a
rin
g
Us
in
g
V
ib
ra
ti
o
n
S
ig
n
a
tu
re
A
n
a
l
y
sis,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Exp
l
o
rin
g
En
g
i
n
e
e
rin
g
,
v
o
l.
8
,
n
o
.
5
,
p
p
.
5
3
8
-
5
4
6
,
2
0
1
9
.
[4
]
A
.
Bo
u
g
u
e
r
n
e
,
e
t
a
l.
,
"
Op
ti
m
isa
ti
o
n
o
f
Vib
ra
ti
o
n
Da
ta
Us
i
n
g
P
a
r
ti
c
le
S
w
a
r
m
Op
ti
m
i
z
a
ti
o
n
A
p
p
li
e
d
to
In
d
u
c
ti
o
n
M
a
c
h
in
e
F
a
u
l
ts,”
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ren
e
wa
b
le E
n
e
rg
ies
,
2
0
1
3
.
[5
]
B.
M
u
r
u
g
a
n
a
th
a
m
.
e
t
a
l.
,
“
Be
a
rin
g
F
a
u
lt
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
Us
in
g
A
NC
-
Ba
se
d
F
il
tere
d
V
i
b
ra
ti
o
n
S
ig
n
a
l,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ica
t
io
n
s a
n
d
Cy
b
e
r P
h
y
sic
a
l
En
g
i
n
e
e
rin
g
,
p
p
.
3
2
5
-
3
3
4
,
2
0
1
8
.
[6
]
D.
Did
ik
,
e
t
a
l
.
,
“
F
a
u
lt
Dia
g
n
o
s
is
o
f
Ro
ll
e
r
Be
a
rin
g
Us
in
g
P
a
ra
m
e
ter
Ev
a
lu
a
ti
o
n
T
e
c
h
n
iq
u
e
s
a
n
d
M
u
lt
i
-
Clas
s
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
,
”
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
En
g
in
e
e
rin
g
,
S
c
ie
n
c
e
a
n
d
Na
n
o
tec
h
n
o
lo
g
y
,
2
0
1
6
.
[7
]
A
.
Bo
u
d
in
a
r,
e
t
a
l.
,
“
Im
p
ro
v
e
d
S
tato
r
C
u
rre
n
t
S
p
e
c
tral
A
n
a
ly
sis
Tch
n
iq
u
e
f
o
r
Be
a
rin
g
F
a
u
lt
Dia
g
n
o
sis,”
1
6
t
h
In
ter
n
a
ti
o
n
a
l
Po
we
r E
lec
tro
n
ics
a
n
d
M
o
t
io
n
Co
n
tro
l
Co
n
fer
e
n
c
e
a
n
d
Exp
o
siti
o
n
,
p
p
.
1
2
2
8
-
1
2
3
3
,
2
0
1
4
.
[8
]
S
.
Dja
b
a
ll
a
h
a
n
d
M
.
Ka
m
e
l,
“
D
e
tec
ti
o
n
a
n
d
Dia
g
n
o
sis
o
f
F
a
u
lt
Be
a
rin
g
Us
in
g
Wav
e
let
P
a
c
k
e
t
T
ra
n
s
f
o
r
m
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
,
”
Arti
c
le i
n
Fra
tt
u
ra
E
d
I
n
teg
rità
S
tr
u
tt
u
ra
le,
v
o
l
.
1
3
,
n
o
.
4
9
,
p
p
.
2
9
1
-
3
0
1
,
2
0
1
9
.
[
9
]
L
.
C
.
J
o
s
é
.
e
t
a
l
.
,
“
B
e
a
r
i
n
g
F
a
u
l
t
D
i
a
g
n
o
s
i
s
B
a
s
e
d
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
C
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
W
a
v
e
l
e
t
T
r
a
n
s
f
o
r
m
,
”
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
W
S
E
A
S
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
W
a
v
e
l
e
t
A
n
a
l
y
s
i
s
&
M
u
l
t
i
r
a
t
e
S
y
s
t
e
m
s
,
p
p
.
16
-
1
8
,
2
0
0
6
.
[1
0
]
T
.
Na
re
n
d
iran
a
th
Ba
b
u
,
e
t
a
l
.
,
“
Jo
u
rn
a
l
Be
a
rin
g
F
a
u
lt
De
tec
ti
o
n
Ba
se
d
o
n
Da
u
b
e
c
h
ies
W
a
v
e
l
e
t,
”
Arc
h
ive
s
o
f
Aco
u
stics
,
v
o
l.
4
2
,
n
o
.
3
,
p
p
.
4
0
1
-
414
,
2
0
1
7
.
[1
1
]
A
.
Ka
b
la
a
n
d
K.
M
o
k
ra
n
i,
“
Be
a
r
in
g
F
a
u
lt
Dia
g
n
o
sis
Us
i
n
g
Hilb
e
rt
-
Hu
a
n
g
T
ra
n
sf
o
r
m
(HH
T
)
a
n
d
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
in
e
(S
V
M
)
,
”
M
e
c
h
a
n
ics
&
I
n
d
u
stry
,
v
o
l.
1
7
,
n
o
.
3
,
2
0
1
6
.
[1
2
]
W
.
T
s
a
o
,
e
t
a
l.
,
“
Re
so
n
a
n
t
-
F
re
q
u
e
n
c
y
Ba
n
d
Ch
o
ice
f
o
r
Be
a
rin
g
F
a
u
lt
Dia
g
n
o
sis
Ba
se
d
o
n
EM
D
a
n
d
En
v
e
lo
p
e
A
n
a
l
y
si
s,
In
I
n
telli
g
e
n
t
C
o
n
tr
o
l
a
n
d
A
u
to
m
a
ti
o
n
(W
CICA
),
”
8
th
W
o
rl
d
Co
n
g
re
ss
o
n
I
n
telli
g
e
n
t
C
o
n
tr
o
l
a
n
d
Au
to
m
a
ti
o
n
,
p
p
.
1
2
8
9
-
1
2
9
4
,
2
0
1
0
.
[1
3
]
J.
Be
n
A
li
,
e
t
a
l.
,
“
A
p
p
li
c
a
ti
o
n
o
f
E
m
p
iri
c
a
l
M
o
d
e
De
c
o
m
p
o
siti
o
n
a
n
d
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
f
o
r
A
u
to
m
a
ti
c
Be
a
rin
g
F
a
u
l
t
Dia
g
n
o
sis Ba
se
d
o
n
V
ib
ra
ti
o
n
S
ig
n
a
ls,”
A
p
p
li
e
d
Aco
u
stics
,
v
o
l.
8
9
,
p
p
.
1
6
-
2
7
,
2
0
1
5
.
[1
4
]
L
.
Ho
n
g
m
e
i,
e
t
a
l.
,
“
Ro
ll
i
n
g
Be
a
rin
g
F
a
u
lt
Dia
g
n
o
sis
Ba
se
d
o
n
S
T
F
T
-
D
e
e
p
L
e
a
rn
in
g
a
n
d
S
o
u
n
d
S
ig
n
a
ls,”
S
h
o
c
k
a
n
d
Vi
b
ra
ti
o
n
,
v
o
l.
2
0
1
6
,
n
o
.
2
,
p
p
.
1
-
1
2
,
2
0
1
6
.
[1
5
]
R.
R.
S
h
a
rm
a
,
e
t
a
l.
,
“
A
n
E
m
p
iri
c
a
l
W
a
v
e
let
T
ra
n
s
f
o
r
m
-
Ba
s
e
d
A
p
p
ro
a
c
h
f
o
r
Cro
ss
-
T
e
r
m
s
-
F
re
e
W
ig
n
e
r
–
V
il
le
Distrib
u
ti
o
n
,
”
S
i
g
n
a
l,
Im
a
g
e
a
n
d
Vi
d
e
o
Pr
o
c
e
ss
in
g
,
v
o
l.
14,
n
o
.
2
,
p
p
.
2
4
9
-
2
5
6
,
2
0
2
0
.
[1
6
]
S.
Ja
g
a
th
,
e
t
a
l.
,
“
Early
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
f
Be
a
rin
g
F
a
u
lt
s
u
si
n
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
A
lg
o
rit
h
m
,
”
IEE
E
W
o
rk
sh
o
p
o
n
El
e
c
trica
l
M
a
c
h
in
e
s De
sig
n
,
Co
n
tro
l
a
n
d
Di
a
g
n
o
sis,
p
p
.
2
5
0
-
2
5
5
,
2
0
1
7
.
[1
7
]
A
.
Ch
o
u
g
,
e
t
a
l.
,
“
De
te
c
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
f
Be
a
rin
g
F
a
u
lt
s
in
In
d
u
strial
G
e
a
r
e
d
M
o
to
rs
Us
in
g
Te
m
p
o
ra
l
F
e
a
tu
re
s a
n
d
A
d
a
p
ti
v
e
Ne
u
ro
-
F
u
z
z
y
In
f
e
r
e
n
c
e
S
y
ste
m
,
”
H
e
li
y
o
n
,
v
o
l.
5
,
n
o
.
8
,
p
p
.
1
-
1
1
,
2
0
1
9
.
[1
8
]
J.
L
e
e
,
e
t
a
l.
,
“
F
a
u
lt
Dia
g
n
o
sis
o
f
In
d
u
c
ti
o
n
M
o
t
o
r
Us
in
g
Co
n
v
o
lu
t
i
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
,
”
Ap
p
li
e
d
S
c
ien
c
e
s,
v
o
l.
9
,
n
o
.
1
5
,
p
p
.
1
-
1
0
,
2
0
1
9
.
[1
9
]
N.
T
a
lb
i,
e
t
a
l.
,
“
Dia
g
n
o
sis
o
f
Be
a
rin
g
De
f
e
c
ts
b
y
A
n
f
i
s
in
T
h
e
In
d
u
c
ti
o
n
M
o
to
r
,
”
Ca
r
p
a
t
h
ia
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
1
3
,
n
o
.
1
,
p
p
.
3
0
-
4
4
,
2
0
1
9
.
[2
0
]
Un
iv
e
rsit
y
C
W
R.
“
Be
a
rin
g
Da
ta
Ce
n
ter,”
e
d
S
e
c
o
n
d
a
ry
,
Un
iv
e
rs
it
y
C
W
R
(Un
it
e
d
S
tate
:
Ca
se
W
e
ste
rn
Re
v
e
rse
Un
iv
e
sit
y
),
2
0
1
6
.
[2
1
]
P
.
P
r
o
f
,
e
t
a
l.
,
“
F
a
u
lt
De
tec
ti
o
n
in
Ro
ll
i
n
g
El
e
m
e
n
t
Be
a
rin
g
Us
in
g
V
ib
ra
ti
o
n
Ba
se
d
A
n
,
a
l
y
si
s,”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Id
e
a
s
,
Imp
a
c
t
a
n
d
In
n
o
v
a
ti
o
n
i
n
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
6
6
6
-
1
6
7
4
,
2
0
1
7
.
[2
2
]
B.
Na
re
n
d
iran
a
th
Ba
b
u
,
e
t
a
l.
,
“
A
p
p
li
c
a
ti
o
n
o
f
EM
D
A
NN
a
n
d
DN
N
f
o
r
S
e
lf
-
A
li
g
n
in
g
Be
a
rin
g
F
a
u
lt
Dia
g
n
o
sis,”
Arc
h
ive
s o
f
a
c
o
u
stics
,
v
o
l.
4
3
,
n
o
.
2
,
p
p
.
1
6
3
-
1
7
5
,
2
0
1
8
.
[
2
3
]
M
.
T
a
l
h
a
,
e
t
a
l
.
,
“
A
M
a
t
l
a
b
a
n
d
S
i
m
u
l
i
n
k
B
a
s
e
d
T
h
r
e
e
-
P
h
a
s
e
I
n
v
e
r
t
e
r
F
a
u
l
t
D
i
a
g
n
o
s
i
s
M
e
t
h
o
d
U
s
i
n
g
T
h
r
e
e
-
D
i
m
e
n
s
i
o
n
a
l
F
e
a
t
u
r
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
u
z
z
y
L
o
g
i
c
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
1
7
3
-
1
8
0
,
2
0
1
6
.
[2
4
]
E.
L
e
v
e
n
t,
“
Be
a
rin
g
F
a
u
lt
De
t
e
c
ti
o
n
b
y
On
e
-
Di
m
e
n
sio
n
a
l
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
M
a
th
e
ma
ti
c
a
l
Pro
b
lem
s in
En
g
in
e
e
rin
g
,
v
o
l.
2
0
1
7
,
p
p
.
1
-
9
,
2
0
1
7
.
[2
5
]
C.
Zh
iq
ia
n
g
,
a
t
a
l.
,
”
V
ib
ra
ti
o
n
-
Ba
se
d
G
e
a
rb
o
x
F
a
u
lt
Dia
g
n
o
sis
Us
in
g
De
e
p
Ne
u
ra
l
Ne
t
w
o
rk
s,”
J
o
u
rn
a
l
o
f
Vi
b
ro
e
n
g
i
n
e
e
rin
g
,
v
o
l.
1
9
,
n
o
.
4
,
p
p
.
2
4
7
5
-
2
4
9
6
,
2
0
1
7
.
[2
6
]
B.
Be
ss
a
m
.
e
t
a
l.
,
“
De
tec
ti
o
n
o
f
Bro
k
e
n
Ro
t
o
r
Ba
r
F
a
u
lt
s
in
I
n
d
u
c
ti
o
n
M
o
to
r
a
t
L
o
w
L
o
a
d
Us
in
g
Ne
u
r
a
l
Ne
tw
o
rk
,
”
IS
A
tra
n
sa
c
ti
o
n
s,
v
o
l.
6
4
,
p
p
.
2
4
1
-
2
4
6
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.