I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
,
p
p
.
187
~
205
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
1
.
pp
1
8
7
-
2
0
5
187
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
a
chine learning
-
ba
sed pred
ictive
ma
intenance
framewo
rk f
o
r
seis
mo
meters:
is
i
t
po
ss
ible?
Arif
ra
hm
a
n Yus
t
ik
a
P
utr
a
1
,
T
it
ik
L
esta
ri
2
,
Adhi
H
a
rm
o
ko
Sa
pu
t
ro
1
1
D
e
p
a
r
t
me
n
t
o
f
P
h
y
si
c
s,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
m
a
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s
,
U
n
i
v
e
r
si
t
a
s
I
n
d
o
n
e
si
a
,
D
e
p
o
k
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
st
r
u
m
e
n
t
a
t
i
o
n
a
n
d
C
a
l
i
b
r
a
t
i
o
n
,
I
n
d
o
n
e
s
i
a
n
M
e
t
e
o
r
o
l
o
g
i
c
a
l
,
C
l
i
ma
t
o
l
o
g
i
c
a
l
,
a
n
d
G
e
o
p
h
y
si
c
a
l
A
g
e
n
c
y
,
Jak
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
4
,
2
0
2
5
R
ev
is
ed
Oct
6
,
2
0
2
5
Acc
ep
ted
No
v
2
3
,
2
0
2
5
S
e
ism
o
m
e
ters
a
re
c
ru
c
ial
in
e
a
rth
q
u
a
k
e
a
n
d
tsu
n
a
m
i
e
a
rly
wa
rn
in
g
sy
ste
m
s,
sin
c
e
th
e
y
re
c
o
rd
g
ro
u
n
d
v
ib
ra
ti
o
n
s
d
u
e
to
sig
n
ifi
c
a
n
t
se
ism
ic
e
v
e
n
ts.
Th
e
h
e
a
lt
h
c
o
n
d
it
io
n
o
f
a
se
ism
o
m
e
ter
is
stro
n
g
ly
re
late
d
to
t
h
e
m
e
a
su
re
m
e
n
t
o
f
se
ism
ic
d
a
ta
q
u
a
li
t
y
,
m
a
k
in
g
s
e
ism
o
m
e
ter
h
e
a
lt
h
c
o
n
d
i
ti
o
n
m
a
in
ten
a
n
c
e
c
rit
ica
l.
P
re
d
ictiv
e
m
a
in
ten
a
n
c
e
is
th
e
m
o
st
a
d
v
a
n
c
e
d
c
o
n
tr
o
l
o
r
m
e
a
su
re
m
e
n
t
sy
ste
m
m
a
in
ten
a
n
c
e
m
e
th
o
d
,
sin
c
e
it
i
n
fo
rm
s
a
b
o
u
t
th
e
fa
u
lt
s
th
a
t
h
a
v
e
o
c
c
u
rre
d
in
th
e
sy
ste
m
a
n
d
th
e
re
m
a
in
i
n
g
l
ifetime
o
f
th
e
sy
ste
m
.
Ho
we
v
e
r,
n
o
re
se
a
rc
h
h
a
s
p
r
o
p
o
se
d
a
se
ism
o
m
e
ter
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
fra
m
e
wo
rk
.
Th
u
s,
th
is
a
rti
c
le
re
v
iew
s
g
e
n
e
ra
l
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
m
e
th
o
d
s
a
n
d
se
ism
ic
d
a
ta
q
u
a
li
ty
a
n
a
ly
sis
m
e
th
o
d
s
to
fi
n
d
th
e
fe
a
sib
il
it
y
o
f
d
e
v
e
lo
p
in
g
a
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
fra
m
e
wo
rk
f
o
r
se
ism
o
m
e
ters
in
se
ism
ic
sta
ti
o
n
s.
Ba
se
d
o
n
th
e
re
v
iew
,
it
i
s
fo
u
n
d
th
a
t
su
c
h
a
fra
m
e
wo
rk
c
a
n
b
e
b
u
i
lt
u
n
d
e
r
p
a
rt
icu
lar
c
h
a
ll
e
n
g
e
s
a
n
d
re
q
u
irem
e
n
ts.
F
in
a
ll
y
,
m
a
c
h
in
e
l
e
a
rn
in
g
is
th
e
b
e
st
a
p
p
r
o
a
c
h
t
o
b
u
il
d
t
h
e
c
las
sifica
ti
o
n
a
n
d
re
g
re
ss
io
n
m
o
d
e
ls
in
t
h
e
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
fra
m
e
wo
r
k
d
u
e
t
o
it
s
ro
b
u
stn
e
ss
a
n
d
h
ig
h
p
re
d
ictio
n
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
Fau
lt d
iag
n
o
s
is
Fau
lt p
r
o
g
n
o
s
is
Ma
ch
in
e
lear
n
in
g
Pre
d
ictiv
e
m
ain
ten
an
ce
Seis
m
ic
d
ata
q
u
ality
Seis
m
o
m
eter
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
:
Ad
h
i H
ar
m
o
k
o
Sap
u
tr
o
Dep
ar
tm
en
t o
f
Ph
y
s
ics,
Facu
lty
o
f
Ma
th
e
m
atics a
n
d
Natu
r
al
Scien
ce
s
,
Un
iv
er
s
ity
o
f
I
n
d
o
n
esia
Dep
o
k
,
W
est J
av
a,
I
n
d
o
n
esia
E
m
ail: a
d
h
i@
s
ci.
u
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
Seis
m
o
m
eter
s
s
er
v
e
as
th
e
p
r
im
ar
y
m
ea
s
u
r
em
en
t
in
s
tr
u
m
en
t
o
f
g
l
o
b
al
ea
r
th
q
u
ak
e
m
o
n
ito
r
in
g
s
y
s
tem
s
,
r
ec
o
r
d
in
g
g
r
o
u
n
d
v
ib
r
atio
n
s
th
at
en
ab
le
ea
r
ly
war
n
in
g
s
y
s
tem
s
an
d
s
cie
n
tific
an
aly
s
is
f
o
r
ea
r
th
q
u
ak
es,
ts
u
n
am
is
,
o
r
o
t
h
er
m
ajo
r
s
eismic
ev
en
ts
[
1
]
–
[
3
]
.
T
h
e
f
o
r
ce
-
f
ee
d
b
ac
k
s
eismo
m
eter
,
f
ea
tu
r
in
g
a
s
u
s
p
en
d
ed
r
ef
er
e
n
ce
m
ass
an
d
s
o
p
h
is
ticated
f
ee
d
b
ac
k
m
ec
h
a
n
is
m
,
r
ep
r
esen
ts
m
o
d
er
n
s
eismic
n
etwo
r
k
s
'
m
o
s
t
wid
ely
d
ep
lo
y
ed
s
en
s
o
r
tech
n
o
lo
g
y
[
4
]
.
Ho
wev
er
,
th
e
r
elia
b
ilit
y
o
f
s
eismic
d
ata
f
u
n
d
am
en
tally
d
ep
en
d
s
o
n
th
e
h
ea
lth
co
n
d
itio
n
o
f
th
ese
s
en
s
itiv
e
in
s
tr
u
m
en
ts
,
as
f
au
lty
s
en
s
o
r
s
ca
n
g
en
er
ate
s
p
u
r
io
u
s
s
ig
n
als,
lead
in
g
to
f
alse e
ar
th
q
u
ak
e
d
etec
tio
n
s
o
r
m
is
s
ed
cr
itical
ev
en
ts
[
5
]
.
C
u
r
r
en
t
s
eismo
m
eter
m
ain
ten
an
ce
p
r
ac
tices
in
I
n
d
o
n
esia
e
x
em
p
lify
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
ap
p
r
o
ac
h
es.
T
h
e
I
n
d
o
n
esian
Me
teo
r
o
lo
g
ical,
C
lim
ato
lo
g
ical,
an
d
Geo
p
h
y
s
ical
Ag
en
c
y
(
B
MK
G)
,
wh
ich
m
an
ag
es
h
u
n
d
r
ed
s
o
f
s
eismic
o
b
s
er
v
atio
n
s
tatio
n
s
in
th
e
I
n
d
o
n
esian
-
T
s
u
n
am
i
E
ar
ly
W
a
r
n
in
g
Sy
s
tem
(
I
n
a
-
T
E
W
S)
s
ti
ll
em
p
lo
y
s
s
eismo
m
eter
m
ain
ten
an
ce
p
r
o
ce
d
u
r
e
s
th
at
r
ely
p
r
ed
o
m
in
a
n
tly
o
n
r
ea
ctiv
e
o
r
s
ch
ed
u
led
ap
p
r
o
ac
h
es,
wh
er
e
r
ep
air
s
o
c
cu
r
af
ter
eq
u
ip
m
en
t
f
ailu
r
e
o
r
at
p
r
e
d
eter
m
in
ed
in
ter
v
als
r
eg
ar
d
less
o
f
ac
tu
a
l
d
ev
ice
co
n
d
itio
n
[
6
]
.
Pre
v
io
u
s
s
tu
d
ies
in
in
d
u
s
tr
ial
m
ain
ten
a
n
ce
co
n
clu
d
ed
th
at
b
o
th
r
ea
ctiv
e
an
d
p
r
ev
e
n
tiv
e
r
ep
air
s
tr
ateg
ies
r
esu
lt
in
u
n
n
ec
ess
ar
y
d
o
wn
tim
e,
in
cr
ea
s
ed
o
p
er
atio
n
al
co
s
ts
,
an
d
p
o
ten
tial
d
ata
q
u
ality
d
eg
r
ad
atio
n
d
u
r
in
g
u
n
d
etec
te
d
f
au
lt
p
er
i
o
d
s
[
7
]
,
[
8
]
.
W
h
ile
th
ese
lim
itatio
n
s
h
av
e
e
n
co
u
r
a
g
ed
s
eismic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
1
8
7
-
205
188
n
etwo
r
k
tech
n
ician
s
to
d
ev
elo
p
ad
d
itio
n
al
m
ain
ten
an
ce
p
r
o
ce
d
u
r
es
f
o
r
ass
ess
in
g
s
eismo
m
eter
h
ea
lth
co
n
d
itio
n
s
,
in
clu
d
in
g
s
en
s
itiv
ity
s
h
if
t
m
ea
s
u
r
em
en
t
u
s
in
g
s
en
s
o
r
ca
lib
r
atio
n
an
d
p
er
f
o
r
m
an
ce
d
eg
r
ad
atio
n
d
etec
tio
n
u
s
in
g
s
eismic
tim
e
-
s
er
ies
o
r
f
r
eq
u
en
c
y
-
d
o
m
ain
d
at
a
co
m
p
ar
is
o
n
s
,
th
ese
ap
p
r
o
ac
h
es
r
em
ain
f
ar
f
r
o
m
id
ea
l a
s
th
ey
lack
in
a
u
to
m
atio
n
an
d
t
h
e
p
r
e
d
ictiv
e
ca
p
ab
ilit
i
es o
f
m
o
d
e
r
n
m
ain
te
n
an
ce
p
a
r
ad
ig
m
s
[
9
]
,
[
1
0
]
.
Pre
d
ictiv
e
m
ain
ten
a
n
ce
h
as
e
m
er
g
ed
as
th
e
m
o
s
t
ad
v
an
ce
d
m
ain
ten
a
n
ce
p
ar
ad
i
g
m
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ial
s
ec
to
r
s
,
lev
er
ag
in
g
r
ea
l
-
tim
e
co
n
d
itio
n
m
o
n
ito
r
i
n
g
an
d
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
to
f
o
r
ec
ast
eq
u
ip
m
en
t
f
ailu
r
es
b
ef
o
r
e
th
e
y
o
cc
u
r
[
1
1
]
,
[
1
2
]
.
Mo
d
e
r
n
p
r
ed
ictiv
e
m
ain
ten
an
ce
f
r
am
ew
o
r
k
s
in
teg
r
ate
f
au
lt
d
iag
n
o
s
is
ca
p
ab
ilit
ies,
wh
ich
en
co
m
p
ass
d
etec
tio
n
,
is
o
latio
n
,
an
d
id
en
tific
atio
n
,
alo
n
g
with
p
r
o
g
n
o
s
tic
m
o
d
els
th
at
esti
m
ate
r
em
ain
in
g
u
s
ef
u
l
life
(
R
UL
)
[
1
3
]
,
[
1
4
]
.
Ma
ch
i
n
e
lear
n
in
g
tec
h
n
iq
u
es,
p
ar
ticu
lar
ly
class
if
icatio
n
an
d
r
eg
r
ess
io
n
m
o
d
els,
h
av
e
d
em
o
n
s
tr
ated
s
u
p
e
r
io
r
p
e
r
f
o
r
m
an
ce
t
o
tr
ad
itio
n
al
s
tatis
tical
ap
p
r
o
ac
h
es,
ac
h
iev
in
g
lo
wer
d
o
wn
tim
e
a
n
d
s
ig
n
if
ican
tly
h
ig
h
er
p
r
e
d
ictio
n
ac
cu
r
ac
ies
in
v
ar
io
u
s
ap
p
licatio
n
s
[
1
5
]
.
Ho
wev
er
,
d
esp
ite
th
e
p
r
o
v
en
ef
f
ec
tiv
en
ess
o
f
p
r
ed
ictiv
e
m
ain
ten
an
ce
in
in
d
u
s
tr
ial
au
to
m
atio
n
an
d
c
o
n
tr
o
l
s
y
s
tem
s
,
n
o
co
m
p
r
eh
en
s
iv
e
f
r
am
ewo
r
k
h
as
b
ee
n
d
ev
elo
p
ed
s
p
ec
if
ically
f
o
r
s
eismo
m
eter
h
ea
lth
m
o
n
ito
r
in
g
i
n
s
eismic
n
etwo
r
k
s
.
Desp
ite
th
e
m
is
s
io
n
-
cr
itical
n
atu
r
e
o
f
co
n
tin
u
o
u
s
s
eis
m
ic
m
o
n
ito
r
in
g
f
o
r
s
eismo
lo
g
ical
ea
r
ly
war
n
in
g
s
y
s
tem
s
,
th
e
ap
p
li
ca
tio
n
o
f
m
o
d
er
n
p
r
ed
ictiv
e
m
ain
ten
an
ce
m
eth
o
d
o
lo
g
ies
to
s
eismo
lo
g
ical
in
s
tr
u
m
en
tatio
n
r
em
ain
s
lar
g
ely
u
n
e
x
p
lo
r
e
d
.
W
h
ile
ex
ten
s
iv
e
r
esear
ch
h
as
ad
d
r
ess
ed
s
eismic
d
ata
q
u
ality
an
aly
s
is
m
eth
o
d
s
,
th
ese
ap
p
r
o
ac
h
es
r
e
m
ain
d
is
co
n
n
ec
t
ed
m
ain
ly
f
r
o
m
s
y
s
tem
atic
eq
u
ip
m
e
n
t
h
ea
lth
ass
es
s
m
en
t
an
d
f
ailu
r
e
p
r
ed
ictio
n
ca
p
ab
ilit
ies.
T
h
is
s
tu
d
y
ex
p
lo
r
es
th
is
in
ter
s
ec
tio
n
b
y
p
r
o
v
id
in
g
a
co
m
p
r
eh
e
n
s
iv
e
r
ev
iew
o
f
r
el
ev
an
t
m
eth
o
d
o
lo
g
ies
to
in
v
e
s
tig
ate
th
e
f
ea
s
ib
ilit
y
o
f
d
ev
elo
p
in
g
a
m
ac
h
in
e
lear
n
in
g
-
b
ased
p
r
ed
ictiv
e
m
ain
ten
an
ce
f
r
a
m
ewo
r
k
d
esig
n
ed
ex
p
licitly
f
o
r
s
eismo
m
eter
s
in
s
eismic
m
o
n
ito
r
in
g
n
etwo
r
k
s
,
th
er
e
b
y
b
r
id
g
in
g
th
e
d
o
m
ain
s
o
f
a
d
v
a
n
ce
d
m
ain
te
n
an
ce
e
n
g
in
ee
r
i
n
g
an
d
s
eismo
lo
g
ical
in
s
tr
u
m
en
tatio
n
.
Fo
u
r
f
u
n
d
am
e
n
tal
r
esear
ch
q
u
esti
o
n
s
co
llectiv
ely
b
r
id
g
e
th
e
g
a
p
b
etwe
en
ad
v
a
n
ce
d
p
r
ed
ictiv
e
m
ain
ten
an
ce
m
eth
o
d
o
lo
g
ies
an
d
s
eismo
lo
g
ical
i
n
s
tr
u
m
en
tatio
n
.
First,
we
in
v
esti
g
ate
wh
at
estab
lis
h
ed
m
eth
o
d
s
ex
is
t
f
o
r
p
r
ed
ictiv
e
m
ain
ten
an
ce
ac
r
o
s
s
in
d
u
s
tr
ial
ap
p
licatio
n
s
an
d
h
o
w
th
ese
ap
p
r
o
ac
h
es
ca
n
b
e
ad
ap
ted
f
o
r
s
en
s
o
r
-
b
ased
m
o
n
ito
r
in
g
s
y
s
tem
s
.
Seco
n
d
,
we
e
x
am
in
e
th
e
c
r
iter
ia
m
o
s
t
ap
p
r
o
p
r
iate
f
o
r
s
eismic
d
ata
q
u
ality
ass
ess
m
en
t
th
at
ca
n
s
er
v
e
as
r
eliab
le
h
ea
lth
in
d
i
ca
to
r
s
f
o
r
m
ac
h
in
e
lear
n
i
n
g
-
b
ased
f
au
lt
d
ia
g
n
o
s
is
alg
o
r
ith
m
s
.
T
h
ir
d
,
we
s
y
n
t
h
e
s
ize
f
in
d
in
g
s
f
r
o
m
b
o
th
i
n
d
u
s
tr
ial
h
ea
lth
m
o
n
ito
r
i
n
g
a
n
d
s
eismic
d
ata
q
u
ality
cr
iter
ia
d
o
m
ain
s
to
ex
p
lo
r
e
wh
at
co
n
s
titu
tes
a
f
ea
s
ib
le
m
ac
h
in
e
lear
n
in
g
-
b
ased
p
r
e
d
ictiv
e
m
ain
ten
an
ce
f
r
am
ewo
r
k
f
o
r
s
eismo
m
eter
s
in
s
eismic
m
o
n
ito
r
in
g
s
tatio
n
s
.
Fin
ally
,
we
ass
ess
wh
at
p
r
ac
t
ical
r
eq
u
ir
em
en
ts
,
im
p
lem
en
tatio
n
ch
allen
g
es,
an
d
o
p
e
r
atio
n
al
co
n
s
tr
ain
ts
m
u
s
t
b
e
ad
d
r
ess
ed
to
d
ep
l
o
y
s
u
ch
a
f
r
am
ew
o
r
k
i
n
r
ea
l
-
wo
r
ld
s
eismo
lo
g
ical
n
et
wo
r
k
s
s
u
cc
ess
f
u
lly
.
T
h
ese
r
e
s
ea
r
ch
q
u
esti
o
n
s
p
r
o
v
id
e
th
e
f
o
u
n
d
atio
n
f
o
r
o
u
r
s
y
s
tem
atic
li
ter
atu
r
e
an
aly
s
is
an
d
g
u
id
e
th
e
d
ev
elo
p
m
en
t
o
f
o
u
r
p
r
o
p
o
s
ed
p
r
ed
i
ctiv
e
m
ain
ten
an
ce
ar
ch
itectu
r
e.
T
o
ad
d
r
ess
th
ese
r
esear
ch
q
u
esti
o
n
s
s
y
s
tem
atica
lly
an
d
p
r
o
v
id
e
co
m
p
r
e
h
en
s
iv
e
g
u
i
d
an
ce
f
o
r
s
eismo
m
eter
p
r
ed
ictiv
e
m
ain
ten
an
ce
d
ev
el
o
p
m
en
t,
t
h
is
r
ev
iew
is
s
tr
u
ctu
r
ed
to
f
ac
ilit
ate
th
eo
r
etica
l
u
n
d
er
s
tan
d
i
n
g
a
n
d
p
r
ac
tical
im
p
lem
en
tatio
n
c
o
n
s
id
er
atio
n
s
ac
r
o
s
s
d
iv
er
s
e
s
eismic
o
b
s
er
v
atio
n
n
etwo
r
k
s
.
Sectio
n
1
estab
lis
h
es
th
e
r
esear
ch
b
ac
k
g
r
o
u
n
d
b
y
ex
am
in
in
g
th
e
c
r
itical
r
o
le
o
f
s
eismo
m
eter
r
eliab
ilit
y
,
id
en
tify
in
g
cu
r
r
en
t
m
ain
te
n
an
ce
lim
itatio
n
s
,
an
d
p
o
s
itio
n
in
g
p
r
ed
ictiv
e
m
ain
ten
an
c
e
as
an
ess
en
tial
to
o
l
in
th
e
s
eismic
s
en
s
o
r
m
ain
ten
an
ce
s
y
s
tem
.
Sectio
n
2
p
r
o
v
id
es
th
e
th
eo
r
etica
l
f
o
u
n
d
atio
n
b
y
r
e
v
iewin
g
f
u
n
d
a
m
en
tal
co
n
ce
p
ts
o
f
s
eismic
d
ata
a
n
aly
s
is
,
s
eismo
m
eter
f
au
lt
s
ch
em
es,
an
d
g
en
e
r
al
p
r
e
d
ictiv
e
m
ain
ten
an
ce
ar
ch
itectu
r
e.
Sectio
n
3
p
r
es
en
ts
th
e
r
e
v
iew
m
eth
o
d
s
f
o
r
co
m
p
r
eh
e
n
s
iv
e
liter
atu
r
e
c
o
v
er
ag
e,
in
clu
d
in
g
d
atab
ase
s
elec
tio
n
cr
iter
ia,
s
ea
r
ch
s
tr
ateg
ies,
an
d
an
aly
tica
l
f
r
am
ewo
r
k
s
u
s
ed
to
s
y
n
th
e
s
ize
f
in
d
in
g
s
f
r
o
m
d
iv
er
s
e
en
g
in
ee
r
i
n
g
an
d
s
eismo
lo
g
ical
d
o
m
ain
s
.
Sectio
n
4
d
eliv
er
s
co
m
p
r
eh
en
s
iv
e
r
esu
lts
an
d
cr
itical
d
is
cu
s
s
io
n
b
y
an
aly
zin
g
f
au
lt
d
etec
tio
n
,
is
o
latio
n
,
an
d
id
en
t
if
icatio
n
m
eth
o
d
s
,
ass
ess
in
g
s
eismic
d
ata
q
u
ality
cr
iter
ia
as
h
ea
lth
in
d
icato
r
s
,
an
d
s
y
n
th
esizin
g
th
ese
f
in
d
i
n
g
s
in
to
a
u
n
if
ied
p
r
ed
ictiv
e
m
ain
ten
an
ce
f
r
am
ewo
r
k
ar
ch
itectu
r
e.
Fin
ally
,
s
ec
tio
n
5
c
o
n
clu
d
es
with
im
p
licatio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
d
i
r
ec
tio
n
s
,
p
r
ac
tical
im
p
lem
en
tatio
n
s
tr
ateg
ies,
an
d
p
o
ten
tial c
h
allen
g
es.
2.
B
ACK
G
RO
UND
AN
D
T
H
E
O
RE
T
I
CA
L
F
O
UNDA
T
I
O
N
2
.
1
.
Seis
m
ic
s
ig
na
l a
na
ly
s
is
E
f
f
ec
tiv
e
s
eismo
m
eter
h
ea
lth
m
o
n
ito
r
in
g
r
eq
u
i
r
es
a
co
m
p
r
e
h
en
s
iv
e
u
n
d
e
r
s
tan
d
in
g
o
f
s
eismic
s
ig
n
al
ch
ar
ac
ter
is
tics
th
at
r
ef
lect
in
s
t
r
u
m
en
t
c
o
n
d
itio
n
[
1
6
]
.
T
h
u
s
,
s
eismic
s
ig
n
al
an
aly
s
is
f
o
r
m
s
th
e
f
o
u
n
d
atio
n
f
o
r
ex
tr
ac
tin
g
m
ea
n
in
g
f
u
l
h
ea
lth
in
d
icato
r
s
f
r
o
m
s
eismo
m
eter
m
ea
s
u
r
em
en
ts
,
as
in
s
tr
u
m
en
t
co
n
d
itio
n
d
ir
ec
tly
in
f
lu
en
ce
s
th
e
ch
ar
ac
te
r
is
tics
o
f
r
ec
o
r
d
e
d
g
r
o
u
n
d
m
o
tio
n
d
ata
[
1
7
]
.
M
o
d
er
n
s
eismo
lo
g
ic
al
p
r
ac
tice
em
p
lo
y
s
two
co
m
p
lem
en
tar
y
an
aly
ti
ca
l
d
o
m
ain
s
to
ch
ar
ac
te
r
ize
s
eismic
s
ig
n
als
an
d
ass
ess
d
ata
q
u
ality
co
m
p
r
eh
e
n
s
iv
ely
.
Un
d
er
s
tan
d
in
g
th
ese
an
aly
tical
ap
p
r
o
ac
h
es
is
e
s
s
en
tial
f
o
r
d
ev
elo
p
in
g
p
r
ac
tical
p
r
ed
ictiv
e
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
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
r
ed
ictive
ma
in
ten
a
n
ce
fr
a
mewo
r
k
fo
r
…
(
A
r
ifr
a
h
ma
n
Yu
s
tika
P
u
tr
a
)
189
m
ain
ten
an
ce
al
g
o
r
ith
m
s
,
d
is
tin
g
u
is
h
in
g
b
etwe
en
g
en
u
in
e
s
eismic
p
h
en
o
m
e
n
a
a
n
d
in
s
tr
u
m
en
t
-
r
elate
d
an
o
m
alies.
T
im
e
-
d
o
m
ain
a
n
aly
s
is
p
r
o
v
id
es
es
s
en
tial
d
iag
n
o
s
tic
ca
p
ab
ilit
ies
f
o
r
d
etec
tin
g
tem
p
o
r
al
an
o
m
alies
in
s
eismo
m
eter
p
er
f
o
r
m
a
n
ce
.
I
t
f
o
cu
s
es
o
n
th
e
tem
p
o
r
al
ch
a
r
ac
ter
is
tics
o
f
s
ei
s
m
ic
wav
ef
o
r
m
s
an
d
ex
am
in
es
th
e
p
h
y
s
ical
p
ar
am
eter
s
o
f
ea
r
t
h
m
o
tio
n
,
in
clu
d
in
g
d
is
p
lace
m
en
t,
v
elo
city
,
an
d
ac
ce
ler
a
tio
n
am
p
litu
d
es
as
f
u
n
ctio
n
s
o
f
tim
e
[
1
8
]
,
[
1
9
]
.
T
h
is
an
aly
tical
ap
p
r
o
ac
h
en
a
b
les
ex
tr
ac
tin
g
cr
itical
tem
p
o
r
al
f
ea
tu
r
es
s
u
c
h
a
s
s
ig
n
al
o
f
f
s
ets,
p
ea
k
am
p
litu
d
e
s
,
an
d
wav
ef
o
r
m
p
atter
n
s
,
m
a
k
in
g
it
id
ea
l
to
d
etec
t
s
ig
n
als
f
r
o
m
ea
r
th
q
u
ak
es
o
r
o
th
er
m
ajo
r
s
eismic
ev
en
ts
.
T
h
e
s
ec
o
n
d
an
aly
tical
ty
p
e
is
th
e
f
r
e
q
u
en
c
y
-
d
o
m
ain
an
aly
s
is
,
wh
ich
tr
an
s
f
o
r
m
s
tem
p
o
r
al
s
eismic
d
ata
in
to
s
p
ec
tr
al
r
ep
r
esen
tati
o
n
s
,
m
o
s
t
co
m
m
o
n
ly
ex
p
r
ess
ed
as
p
o
wer
s
p
ec
tr
al
d
e
n
s
ity
(
P
SD)
[
2
0
]
,
[
2
1
]
.
T
h
e
s
p
ec
tr
al
an
aly
s
is
o
f
s
ei
s
m
ic
d
ata
ca
n
b
e
u
s
ed
to
ch
ar
ac
ter
i
ze
s
ig
n
als
b
ased
o
n
th
eir
p
o
wer
lev
els
an
d
also
co
m
p
ar
e
th
em
with
th
e
well
-
k
n
o
wn
a
m
b
ien
t
s
p
ec
tr
al
n
o
is
e
m
o
d
els
(
e.
g
.
,
n
ew
lo
w
n
o
is
e
m
o
d
el
a
n
d
n
ew
h
i
g
h
n
o
is
e
m
o
d
el)
[
2
2
]
,
[
2
3
]
.
I
n
o
r
d
er
to
o
b
tain
s
eismic
s
ig
n
al
P
SD
r
ep
r
esen
tatio
n
,
a
Fo
u
r
ier
T
r
an
s
f
o
r
m
m
u
s
t
b
e
ap
p
lied
to
th
e
au
to
co
r
r
elatio
n
s
eq
u
en
ce
o
f
th
e
tim
e
-
s
er
ies s
ig
n
al
[
2
4
]
,
[
2
5
]
.
2
.
2
.
P
o
s
s
ibl
e
s
ei
s
m
o
m
et
er
f
a
ult
s
chem
es
Pre
d
ictiv
e
m
ain
ten
an
ce
s
y
s
tem
s
r
eq
u
ir
e
a
co
m
p
r
eh
e
n
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
p
o
te
n
tial
f
ailu
r
e
m
o
d
es
to
ef
f
ec
tiv
ely
d
iag
n
o
s
e
s
y
s
tem
f
au
lts
an
d
p
r
e
d
ict
r
em
ain
in
g
u
s
ef
u
l
life
b
ased
o
n
f
a
u
lt
ty
p
e
an
d
s
ev
er
ity
[
2
6
]
.
T
h
er
ef
o
r
e,
s
y
s
tem
atic
class
if
icatio
n
o
f
p
o
s
s
ib
le
f
au
lt
s
ch
em
es
is
cr
u
cial
b
ef
o
r
e
d
esig
n
in
g
a
p
r
e
d
ictiv
e
m
ain
ten
an
ce
ar
c
h
itectu
r
e
f
o
r
s
eismo
m
eter
s
in
s
eismic
m
o
n
ito
r
in
g
n
etwo
r
k
s
.
T
ab
le
1
s
h
o
ws
1
6
p
o
s
s
ib
le
g
r
o
u
n
d
s
eismo
m
eter
f
a
u
lt
s
ce
n
ar
io
s
th
at
ca
n
b
e
in
d
icate
d
b
y
th
e
s
eismic
s
ig
n
al
p
atter
n
s
[
1
0
]
.
T
h
ese
f
au
lt
ca
teg
o
r
ies
en
c
o
m
p
ass
a
b
r
o
a
d
s
p
ec
tr
u
m
o
f
f
ailu
r
e
m
ec
h
an
is
m
s
b
ased
o
n
th
eir
u
n
d
e
r
ly
in
g
r
o
o
t
ca
u
s
es,
r
an
g
in
g
f
r
o
m
co
m
p
lete
s
en
s
o
r
f
ailu
r
e
s
ce
n
ar
io
s
s
u
ch
as
"d
ea
d
s
e
n
s
o
r
s
"
with
n
o
r
esp
o
n
s
e
to
g
r
o
u
n
d
m
o
tio
n
s
,
to
co
m
p
lex
in
te
r
n
al
m
ec
h
a
n
ical
i
s
s
u
es
in
clu
d
in
g
f
o
r
ce
-
f
ee
d
b
ac
k
m
ec
h
an
is
m
f
ailu
r
es
lead
in
g
to
"m
ass
-
lo
ck
"
an
d
"f
r
ee
o
s
cillatio
n
"
co
n
d
itio
n
s
,
a
s
well
as e
lectr
ical
cir
cu
itry
d
ef
ec
ts
th
at
m
an
if
est as "
ea
r
ly
f
a
ilu
r
e
s
ig
n
s
".
T
ab
le
1
.
Seis
m
o
m
eter
f
a
u
lt sch
em
es a
n
d
in
d
icato
r
s
F
a
u
l
t
s
c
h
e
me
C
a
u
se
I
n
d
i
c
a
t
o
r
D
e
a
d
se
n
s
o
r
-
N
o
r
e
s
p
o
n
s
e
t
o
g
r
o
u
n
d
m
o
t
i
o
n
s
-
D
e
c
r
e
a
s
i
n
g
se
n
si
t
i
v
i
t
y
-
P
S
D
<
N
LN
M
-
S
e
i
sm
o
g
r
a
m
c
o
u
n
t
s
>
0
H
a
l
f
a
d
o
u
b
l
e
-
e
n
d
e
d
o
u
t
p
u
t
D
a
mag
e
d
d
i
f
f
e
r
e
n
t
i
a
l
o
u
t
p
u
t
s
y
st
e
m
c
o
n
d
u
c
t
o
r
-
P
S
D
d
r
o
p
s
6
d
B
-
H
a
l
v
e
d
se
i
sm
o
g
r
a
m a
mp
l
i
t
u
d
e
U
n
i
n
t
e
n
d
e
d
p
u
l
s
e
r
e
c
o
r
d
s
S
e
i
sm
o
me
t
e
r
t
r
a
n
si
e
n
t
p
u
l
ses
H
i
g
h
-
a
m
p
l
i
t
u
d
e
l
o
n
g
-
p
e
r
i
o
d
s
e
i
s
mo
g
r
a
m w
a
v
e
f
o
r
ms
S
h
o
r
t
-
p
e
r
i
o
d
m
o
d
e
l
o
c
k
S
i
mu
l
t
a
n
e
o
u
s
u
se
o
f
c
o
n
t
r
o
l
l
i
n
e
s
P
S
D
<
N
LN
M
(
p
e
r
i
o
d
>
1
s)
Ea
r
l
y
f
a
i
l
u
r
e
s
i
g
n
S
e
n
s
o
r
m
o
i
s
t
u
r
e
a
n
d
c
o
r
r
o
s
i
o
n
H
i
g
h
-
a
m
p
l
i
t
u
d
e
,
u
n
st
a
b
l
e
se
i
smo
g
r
a
m
si
g
n
a
l
s
U
V
W
mo
d
e
l
o
c
k
-
M
i
x
e
r
f
a
u
l
t
s
-
B
a
d
c
o
n
f
i
g
u
r
a
t
i
o
n
l
o
g
i
c
R
e
l
a
t
i
v
e
l
y
l
o
w
v
e
r
t
i
c
a
l
P
S
D
c
o
m
p
o
n
e
n
t
Te
l
e
me
t
r
y
d
r
o
p
o
u
t
s
Ti
me
-
s
e
r
i
e
s
me
a
n
a
n
d
t
r
e
n
d
r
e
m
o
v
a
l
S
t
r
a
i
g
h
t
P
S
D
l
i
n
e
s
F
r
e
e
o
sci
l
l
a
t
i
o
n
F
o
r
c
e
-
f
e
e
d
b
a
c
k
me
c
h
a
n
i
sm f
a
i
l
u
r
e
-
S
e
i
sm
o
g
r
a
m
o
sc
i
l
l
a
t
o
r
y
p
u
l
ses
-
P
S
D
>
N
H
N
M
(
w
i
t
h
p
e
r
i
o
d
i
c
n
o
i
se)
A
n
a
l
o
g
t
e
l
e
me
t
r
y
o
v
e
r
l
o
a
d
o
r
sh
o
r
t
-
p
e
r
i
o
d
mass
l
o
c
k
-
Te
l
e
me
t
r
y
i
ss
u
e
s
-
S
e
n
s
o
r
m
a
ss l
o
c
k
e
d
t
o
o
n
e
s
i
d
e
-
P
S
D
<
N
LN
M
-
P
S
D
si
mi
l
a
r
t
o
d
i
g
i
t
i
z
e
r
n
o
i
ses
c
o
n
v
o
l
v
e
d
w
i
t
h
sh
o
r
t
-
p
e
r
i
o
d
r
e
sp
o
n
se
D
e
g
r
a
d
e
d
r
e
s
p
o
n
se
C
o
r
r
o
si
o
n
i
n
f
e
e
d
b
a
c
k
b
o
x
e
s
H
i
g
h
-
a
m
p
l
i
t
u
d
e
s
e
i
sm
o
g
r
a
m s
i
g
n
a
l
s
P
o
o
r
l
y
c
h
a
r
a
c
t
e
r
i
z
e
d
r
e
s
p
o
n
se
M
o
d
i
f
i
e
d
f
e
e
d
b
a
c
k
e
l
e
c
t
r
o
n
i
c
s
U
n
ma
t
c
h
e
d
se
i
sm
o
me
t
e
r
r
e
sp
o
n
se
V
a
c
u
u
m
l
o
ss
P
r
e
ssu
r
e
v
e
ssel
l
e
a
k
a
g
e
-
S
e
i
sm
o
g
r
a
m
d
i
s
t
u
r
b
a
n
c
e
s
-
El
e
v
a
t
e
d
v
e
r
t
i
c
a
l
n
o
i
se
l
e
v
e
l
a
f
t
e
r
d
i
st
u
r
b
a
n
c
e
S
p
u
r
i
o
u
s
h
i
g
h
-
f
r
e
q
u
e
n
c
y
s
i
g
n
a
l
s
P
r
o
b
l
e
ma
t
i
c
g
a
i
n
r
a
n
g
i
n
g
S
e
i
sm
o
g
r
a
m s
p
i
k
e
s
C
l
i
p
p
e
d
s
i
g
n
a
l
s
-
P
r
o
b
l
e
m
a
t
i
c
g
a
i
n
r
a
n
g
i
n
g
-
G
a
i
n
r
a
n
g
i
n
g
d
e
c
o
d
i
n
g
f
a
u
l
t
s
F
l
a
t
se
i
smo
g
r
a
m
a
m
p
l
i
t
u
d
e
s
C
a
l
i
b
r
a
t
i
o
n
d
u
r
i
n
g
a
n
e
a
r
t
h
q
u
a
k
e
D
i
sr
u
p
t
i
o
n
s
d
u
e
t
o
c
a
l
i
b
r
a
t
i
o
n
p
u
l
ses
U
n
ma
t
c
h
e
d
e
a
r
t
h
q
u
a
k
e
se
i
sm
o
g
r
a
m
Ti
mi
n
g
e
r
r
o
r
Ti
mi
n
g
c
o
m
p
o
n
e
n
t
f
a
u
l
t
s
S
i
g
n
i
f
i
c
a
n
t
t
i
me
d
i
f
f
e
r
e
n
c
e
s
Sy
s
tem
atic
f
au
lt
p
atter
n
an
a
ly
s
is
d
em
o
n
s
tr
ates
th
at
s
eismo
m
eter
m
alf
u
n
ctio
n
s
p
r
o
d
u
ce
d
is
tin
ct
d
iag
n
o
s
tic
s
ig
n
atu
r
es
ac
r
o
s
s
m
u
ltip
le
s
ig
n
al
d
o
m
ain
s
.
T
a
b
le
1
r
ev
ea
ls
th
at
s
eismo
m
eter
m
alf
u
n
ctio
n
s
ca
n
b
e
r
eliab
ly
id
en
tifie
d
th
r
o
u
g
h
s
y
s
tem
atic
ex
am
in
atio
n
o
f
b
o
th
tim
e
d
o
m
ain
a
n
d
f
r
eq
u
en
cy
d
o
m
ain
s
ig
n
al
ch
ar
ac
ter
is
tics
,
with
m
an
y
f
au
lt
ty
p
es
p
r
o
d
u
cin
g
u
n
iq
u
e
c
o
m
b
in
atio
n
s
o
f
tem
p
o
r
al
an
d
s
p
ec
tr
al
an
o
m
alies.
T
im
e
d
o
m
ain
in
d
icato
r
s
in
clu
d
e
ab
r
u
p
t
am
p
litu
d
e
c
h
an
g
es,
wav
ef
o
r
m
d
is
to
r
tio
n
s
,
tim
in
g
i
n
co
n
s
is
ten
cies,
an
d
s
p
u
r
io
u
s
tr
an
s
ien
t
s
ig
n
als.
Fre
q
u
en
cy
d
o
m
ain
i
n
d
icato
r
s
en
c
o
m
p
ass
s
y
s
tem
atic
s
h
if
ts
in
n
o
is
e
p
o
wer
lev
els,
ap
p
ea
r
an
ce
o
f
p
er
io
d
ic
n
o
is
e
co
m
p
o
n
e
n
ts
,
an
d
d
ev
iatio
n
s
f
r
o
m
estab
lis
h
ed
n
o
is
e
m
o
d
el
p
r
ed
ictio
n
s
.
T
h
e
m
u
lti
-
m
o
d
al
n
at
u
r
e
o
f
t
h
ese
d
iag
n
o
s
tic
in
d
icato
r
s
n
ec
ess
itates
ex
tr
ac
tin
g
co
m
p
r
e
h
en
s
iv
e
f
ea
tu
r
e
s
ets
th
at
ca
p
tu
r
e
b
o
th
tem
p
o
r
al
a
n
d
s
p
ec
tr
al
ch
a
r
ac
ter
is
tics
,
p
r
o
v
i
d
in
g
t
h
e
r
ich
i
n
p
u
t
d
ata
r
eq
u
ir
ed
f
o
r
ef
f
ec
tiv
e
m
ac
h
in
e
lear
n
in
g
-
b
ased
f
au
lt
class
if
icatio
n
alg
o
r
ith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
1
8
7
-
205
190
2
.
3
.
G
ener
a
l da
t
a
-
driv
en
pr
edict
iv
e
m
a
inte
na
nce
a
rc
hite
ct
ure
T
h
is
s
ec
tio
n
th
o
r
o
u
g
h
ly
ex
p
l
ain
s
th
e
g
en
er
al
ar
ch
itectu
r
e
o
f
d
ata
-
d
r
i
v
en
p
r
e
d
ictiv
e
m
ain
ten
an
ce
f
r
am
ewo
r
k
s
estab
lis
h
ed
f
o
r
i
n
d
u
s
tr
ial
s
y
s
tem
s
an
d
elec
tr
o
n
ic
in
s
tr
u
m
en
ts
in
p
r
ev
io
u
s
s
tu
d
ies.
Gen
er
ally
,
p
r
ed
ictiv
e
m
ain
ten
an
ce
co
n
s
is
ts
o
f
f
o
u
r
f
u
n
d
am
en
tal
s
tag
es: d
ata
ac
q
u
is
itio
n
,
d
ata
p
r
o
ce
s
s
in
g
,
f
a
u
lt
d
iag
n
o
s
is
,
an
d
f
au
lt
p
r
o
g
n
o
s
is
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
[
2
7
]
,
[
2
8
]
.
Fir
s
t,
th
e
d
ata
ac
q
u
is
itio
n
p
r
o
ce
s
s
o
b
tain
s
co
n
d
itio
n
m
o
n
ito
r
in
g
d
ata
f
r
o
m
s
en
s
o
r
s
an
d
s
y
s
tem
s
,
h
is
to
r
ical
m
ai
n
ten
an
ce
r
ec
o
r
d
s
,
an
d
ev
en
t
lo
g
s
.
T
h
en
,
th
e
a
cq
u
ir
e
d
d
ata
u
n
d
er
g
o
es
clea
n
in
g
a
n
d
an
aly
s
is
d
u
r
in
g
th
e
p
r
o
ce
s
s
in
g
s
tag
e.
Data
clea
n
i
n
g
r
e
m
o
v
es
er
r
o
r
s
,
n
o
is
e
ar
tifa
cts,
an
d
ir
r
elev
an
t
d
ata
s
eg
m
en
ts
,
wh
ile
d
ata
a
n
aly
s
is
ex
tr
ac
ts
m
ea
n
in
g
f
u
l
h
ea
lth
f
ea
tu
r
es
f
r
o
m
th
e
co
n
d
itio
n
m
o
n
ito
r
i
n
g
d
ata
an
d
id
en
tifie
s
p
o
s
s
ib
le
s
y
s
tem
f
au
lt m
o
d
es f
r
o
m
h
is
to
r
ical
ev
en
t
r
ec
o
r
d
s
.
Fig
u
r
e
1
.
Gen
e
r
al
d
ata
-
d
r
iv
en
p
r
ed
ictiv
e
m
ain
te
n
an
ce
ar
c
h
itectu
r
e
Nex
t,
th
e
ex
tr
ac
ted
f
ea
tu
r
es
a
r
e
f
ed
in
to
th
e
f
a
u
lt
d
iag
n
o
s
is
m
o
d
el,
wh
ich
g
en
e
r
ates
co
m
p
r
eh
en
s
iv
e
ass
es
s
m
en
ts
in
clu
d
in
g
th
e
cu
r
r
en
t
h
ea
lth
s
tate,
s
p
ec
if
ic
f
au
lt
ty
p
e,
an
d
s
ev
er
ity
g
r
ad
e
o
f
th
e
f
au
lty
in
s
tr
u
m
en
ts
.
C
o
m
b
in
ed
with
th
e
o
r
ig
in
al
e
x
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
th
e
c
o
n
d
itio
n
m
o
n
ito
r
in
g
d
ata,
th
ese
d
iag
n
o
s
tic
o
u
tp
u
ts
ar
e
th
en
an
aly
ze
d
b
y
th
e
f
au
lt
p
r
o
g
n
o
s
is
m
o
d
el
to
esti
m
ate
t
h
e
s
y
s
tem
is
R
UL
.
Ma
in
ten
an
ce
tech
n
ician
s
ca
n
u
s
e
th
e
in
teg
r
ated
r
esu
lts
f
r
o
m
f
au
lt d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
to
d
ev
elo
p
ac
cu
r
ate
an
d
p
r
ec
is
e
m
ain
ten
an
ce
s
tr
ateg
ies
f
o
r
p
r
o
b
lem
atic
in
s
tr
u
m
en
ts
,
o
p
tim
izin
g
tim
in
g
an
d
r
eso
u
r
ce
allo
ca
tio
n
[
2
9
]
.
Fu
r
th
er
m
o
r
e,
m
o
r
e
ad
v
an
ce
d
p
r
ed
ictiv
e
m
ain
te
n
an
ce
s
y
s
tem
s
in
co
r
p
o
r
ate
au
to
m
ated
m
ain
ten
an
ce
s
tr
ateg
y
d
ec
is
io
n
-
m
ak
i
n
g
s
tag
es
th
at
g
en
er
ate
s
p
ec
if
ic
r
ec
o
m
m
en
d
atio
n
s
b
ased
o
n
t
h
e
d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
r
esu
lts
[
3
0
]
,
[
3
1
]
.
T
h
e
s
p
ec
if
ic
f
a
u
lt
d
ia
g
n
o
s
is
an
d
p
r
o
g
n
o
s
is
m
eth
o
d
s
p
r
o
p
o
s
ed
in
p
r
e
v
io
u
s
s
tu
d
ies
will b
e
r
ev
iewe
d
in
d
etail
in
s
ec
tio
n
4
.
3.
M
E
T
H
O
DS
3
.
1
.
Rev
iew
pro
t
o
co
l
T
h
e
r
ev
iew
p
r
o
t
o
co
l
was
d
esi
g
n
ed
t
o
ad
d
r
ess
th
e
in
ter
d
is
cip
lin
ar
y
n
atu
r
e
o
f
p
r
ed
ictiv
e
m
ain
ten
an
ce
an
d
s
eismo
lo
g
ical
in
s
tr
u
m
en
tatio
n
,
r
eq
u
ir
i
n
g
in
teg
r
atio
n
o
f
k
n
o
wled
g
e
f
r
o
m
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
en
g
in
ee
r
in
g
,
s
en
s
o
r
m
ea
s
u
r
e
m
en
ts
,
an
d
g
e
o
p
h
y
s
ics
d
o
m
a
in
s
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
e
m
p
lo
y
s
a
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew
m
eth
o
d
o
l
o
g
y
th
at
en
s
u
r
es
c
o
m
p
r
e
h
en
s
iv
e
co
v
er
a
g
e
o
f
th
ese
to
p
ics
wh
ile
m
ain
tain
in
g
r
ep
r
o
d
u
cib
ilit
y
a
n
d
m
in
im
izin
g
s
elec
tio
n
b
ias.
T
o
ac
h
iev
e
th
is
g
o
al,
th
e
s
ea
r
ch
s
tr
ateg
y
e
n
c
o
m
p
ass
ed
r
esear
ch
ar
ticles
f
r
o
m
r
ep
u
tab
le
d
ata
b
ases
,
in
clu
d
in
g
Go
o
g
le
Sc
h
o
lar
,
Sco
p
u
s
,
I
E
E
E
XPLO
R
E
,
Scien
ce
Dir
ec
t,
Sp
r
in
g
er
,
MD
PI,
I
AE
S,
an
d
s
p
ec
ialized
r
ep
o
s
ito
r
ies
f
r
o
m
t
h
e
Seis
m
o
lo
g
ical
So
ciety
o
f
Am
er
ica.
T
h
e
s
ea
r
c
h
was
lim
ited
to
p
u
b
licatio
n
s
f
r
o
m
2
0
0
5
to
2
0
2
5
,
em
p
h
asizin
g
th
e
m
o
s
t
r
ec
en
t
f
iv
e
y
ea
r
s
to
ca
p
tu
r
e
cu
r
r
en
t
ad
v
an
ce
s
in
m
a
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
an
d
p
r
ed
ictiv
e
m
a
in
ten
an
ce
f
r
a
m
ewo
r
k
s
.
Fig
u
r
e
2
d
em
o
n
s
tr
ates
an
ex
am
p
le
o
f
r
ef
e
r
en
ce
k
e
y
wo
r
d
an
d
d
ate
f
ilter
in
g
s
tr
ateg
y
in
th
e
I
n
ter
n
atio
n
al
J
o
u
r
n
a
l
o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
(
I
J
E
C
E
)
ar
ch
iv
e
with
in
th
e
I
AE
S
d
atab
ase,
lim
itin
g
r
esu
lts
to
p
u
b
licatio
n
s
f
r
o
m
J
an
u
ar
y
2
0
2
1
t
o
Au
g
u
s
t 2
0
2
5
.
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
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
r
ed
ictive
ma
in
ten
a
n
ce
fr
a
mewo
r
k
fo
r
…
(
A
r
ifr
a
h
ma
n
Yu
s
tika
P
u
tr
a
)
191
Fig
u
r
e
2
.
Sear
ch
p
ar
am
ete
r
s
s
etu
p
f
o
r
f
au
lt d
etec
tio
n
liter
atu
r
e
(
2
0
2
1
-
2
0
2
5
)
,
tak
e
n
f
r
o
m
[
3
2
]
T
h
e
s
ea
r
ch
em
p
lo
y
ed
ap
p
r
o
p
r
iate
k
ey
wo
r
d
co
m
b
in
atio
n
s
to
ca
p
tu
r
e
r
elev
a
n
t
s
tu
d
ies
ac
r
o
s
s
m
u
ltip
le
d
o
m
ain
s
.
Prim
ar
y
s
ea
r
ch
ter
m
s
in
clu
d
ed
co
m
b
in
atio
n
s
o
f
:
“seis
m
o
m
eter
f
au
lts
,
”
“sen
s
o
r
f
au
lts
,
”
“p
r
ed
ictiv
e
m
ain
ten
an
ce
,
”
“f
a
u
lt
d
etec
tio
n
,
”
“f
au
lt
is
o
latio
n
,
”
“f
a
u
lt
id
en
tific
atio
n
,
”
“RUL
esti
m
atio
n
,
”
“seis
m
ic
d
ata
q
u
ality
,
”
“m
ac
h
in
e
lea
r
n
in
g
class
if
icatio
n
,
”
an
d
“m
ac
h
in
e
lear
n
in
g
r
e
g
r
ess
io
n
.
”
A
d
d
itio
n
al
s
ea
r
ch
es
in
co
r
p
o
r
ated
s
p
ec
if
ic
alg
o
r
ith
m
n
am
es
(
SVM,
ANN,
R
an
d
o
m
Fo
r
est,
an
d
L
STM
)
a
n
d
a
p
p
licatio
n
d
o
m
ain
s
(
h
ea
lth
m
o
n
ito
r
i
n
g
,
s
y
s
tem
d
i
ag
n
o
s
is
)
.
E
ac
h
d
ata
b
ase
was
s
ea
r
ch
ed
u
s
in
g
its
n
ativ
e
s
ea
r
ch
in
ter
f
ac
e,
with
k
ey
wo
r
d
s
ad
a
p
ted
to
o
p
tim
ize
r
esu
lts
f
o
r
ea
ch
p
latf
o
r
m
’
s
s
ea
r
ch
alg
o
r
ith
m
.
3
.
2
.
L
it
er
a
t
ure
a
na
ly
s
is
a
nd
s
y
nthesi
s
f
ra
m
ewo
r
k
A
co
m
p
r
e
h
en
s
iv
e
liter
atu
r
e
an
aly
s
is
f
r
am
ewo
r
k
was
d
ev
elo
p
ed
to
s
y
s
tem
atica
lly
ca
p
t
u
r
e,
e
v
alu
ate,
an
d
s
y
n
th
esize
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
s
elec
ted
s
tu
d
ies
ac
r
o
s
s
p
r
ed
ictiv
e
m
ain
ten
a
n
ce
,
m
ac
h
in
e
lear
n
in
g
,
an
d
s
eismic
d
ata
q
u
ality
ass
ess
m
en
t
d
o
m
ain
s
.
Fig
u
r
e
3
p
r
esen
ts
th
e
f
o
u
r
ca
teg
o
r
ies
o
f
cr
iter
ia
u
s
ed
f
o
r
liter
atu
r
e
an
aly
s
is
in
th
is
s
tu
d
y
.
Fig
u
r
e
3
.
L
iter
atu
r
e
an
aly
s
is
f
r
am
ewo
r
k
T
h
e
f
ir
s
t
ca
teg
o
r
y
is
th
e
s
o
u
r
ce
m
etad
ata,
wh
ich
c
o
m
p
r
is
es
p
u
b
licatio
n
y
ea
r
(
as
ex
p
lain
ed
p
r
ev
io
u
s
ly
)
,
th
e
jo
u
r
n
al
d
at
ab
ase
th
at
p
u
b
lis
h
ed
th
e
s
t
u
d
ies
(
r
ep
u
tab
le
s
o
u
r
ce
s
ar
e
m
an
d
ato
r
y
)
,
an
d
g
eo
g
r
a
p
h
ic
o
r
i
g
in
,
wh
ich
is
n
o
t
d
ir
ec
tly
r
elev
a
n
t
p
r
o
v
id
ed
t
h
e
s
tu
d
y
is
wr
itten
in
E
n
g
lis
h
.
T
h
e
s
ec
o
n
d
asp
ec
t
,
co
v
er
s
tech
n
ical
s
p
ec
if
icatio
n
s
o
f
th
e
s
tu
d
ies,
i
n
clu
d
in
g
th
e
s
cien
tific
m
eth
o
d
o
lo
g
y
(
e.
g
.
,
s
tatis
tics
,
m
ac
h
in
e
lear
n
in
g
)
,
s
p
ec
if
ic
alg
o
r
ith
m
s
(
e.
g
.
,
lin
ea
r
r
eg
r
ess
io
n
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e)
,
d
ataset
ch
ar
ac
ter
is
tics
(
e.
g
.
s
im
u
latio
n
r
esu
lts
,
ex
p
er
im
en
t
d
ata)
,
an
d
m
o
d
el
p
er
f
o
r
m
a
n
ce
m
etr
ics
(
e.
g
.
,
ac
cu
r
ac
y
,
er
r
o
r
,
lo
s
s
)
.
T
h
e
th
ir
d
cr
iter
io
n
ex
am
i
n
es
im
p
lem
en
tatio
n
d
etails,
in
clu
d
i
n
g
co
m
p
u
tatio
n
al
r
eq
u
ir
em
en
ts
(
e.
g
.
,
h
a
r
d
war
e
s
p
ec
if
icatio
n
s
,
s
o
f
twar
e
p
ac
k
a
g
es),
co
m
p
u
tatio
n
al
tim
e
f
o
r
t
r
ain
in
g
an
d
in
f
e
r
en
ce
(
r
ar
ely
r
ep
o
r
ted
in
s
tu
d
ies),
an
d
f
ea
s
ib
ilit
y
f
o
r
r
ea
l
-
tim
e
i
m
p
lem
en
tatio
n
.
Stu
d
ies
r
eq
u
i
r
in
g
ex
ce
s
s
iv
e
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
o
r
b
ein
g
to
o
d
e
m
an
d
in
g
a
r
e
ex
cl
u
d
ed
.
Fin
ally
,
th
e
f
o
u
r
th
ca
teg
o
r
y
ad
d
r
ess
es
p
r
ac
tical
co
n
s
id
er
atio
n
s
,
in
clu
d
in
g
m
eth
o
d
co
m
p
lex
ity
(
e
.
g
.
,
m
o
d
el
ar
ch
itectu
r
e
,
h
y
p
er
p
a
r
am
eter
s
)
,
v
alid
atio
n
s
tr
ateg
ies
(
m
eth
o
d
o
lo
g
ical
ju
s
tific
atio
n
)
,
r
ep
r
o
d
u
cib
ilit
y
(
im
p
lem
en
tatio
n
f
ea
s
ib
ilit
y
)
,
an
d
s
tu
d
y
lim
itatio
n
s
(
e.
g
.
,
wea
k
n
ess
es
an
d
r
esear
ch
g
ap
s
)
.
Usi
n
g
th
is
co
m
p
r
eh
en
s
iv
e
an
aly
tical
f
r
am
ewo
r
k
,
ea
c
h
s
ele
cted
s
tu
d
y
u
n
d
er
wen
t
r
ig
o
r
o
u
s
q
u
ality
ass
es
s
m
en
t
b
ased
o
n
m
eth
o
d
o
lo
g
ical
r
ig
o
r
,
em
p
i
r
ical
v
alid
atio
n
q
u
ality
,
an
d
p
r
ac
ti
ca
l
ap
p
licab
ilit
y
to
s
eismo
m
eter
h
ea
lth
m
o
n
ito
r
i
n
g
ap
p
licatio
n
s
.
T
h
e
ass
ess
m
en
t
f
r
am
ew
o
r
k
e
m
p
lo
y
e
d
f
iv
e
p
r
im
ar
y
cr
iter
ia:
i)
clar
ity
an
d
co
m
p
leten
ess
o
f
m
eth
o
d
o
lo
g
y
d
escr
ip
tio
n
s
u
f
f
icien
t
f
o
r
r
ep
licatio
n
,
ii)
ap
p
r
o
p
r
iaten
ess
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
1
8
7
-
205
192
d
atasets
an
d
ex
p
er
im
en
tal
d
es
ig
n
f
o
r
th
e
s
tated
r
esear
ch
o
b
j
ec
tiv
es,
iii)
s
tati
s
tical
s
ig
n
if
ic
an
ce
an
d
r
eliab
ilit
y
o
f
r
e
p
o
r
ted
p
er
f
o
r
m
a
n
ce
r
es
u
lts
,
iv
)
co
m
p
ar
ativ
e
ev
alu
a
tio
n
ag
ain
s
t
co
n
v
en
tio
n
al
m
eth
o
d
s
o
r
b
aselin
e
ap
p
r
o
ac
h
es,
an
d
v
)
cr
itical
d
i
s
cu
s
s
io
n
o
f
lim
itatio
n
s
an
d
p
o
ten
tial
s
o
u
r
ce
s
o
f
b
ias
o
r
er
r
o
r
.
Stu
d
ies
lack
in
g
th
ese
f
u
n
d
am
e
n
tal
q
u
ality
in
d
icato
r
s
wer
e
ex
clu
d
e
d
f
r
o
m
p
r
im
ar
y
an
aly
s
is
b
u
t
r
etain
ed
f
o
r
co
n
tex
t
u
al
r
ef
er
en
ce
wh
e
r
e
th
ey
p
r
o
v
id
ed
r
elev
an
t b
ac
k
g
r
o
u
n
d
in
f
o
r
m
at
io
n
o
r
i
d
en
tifie
d
im
p
o
r
tan
t
r
esear
ch
g
ap
s
.
3
.
3
.
P
re
dict
iv
e
m
a
inte
na
nce
f
ra
m
ewo
r
k
pro
po
s
a
l
Pre
v
io
u
s
liter
atu
r
e
r
ev
iews
h
av
e
b
ee
n
p
u
b
lis
h
ed
to
ex
p
lo
r
e
cu
r
r
e
n
t
ad
v
a
n
ce
s
in
p
r
ed
ictiv
e
m
ain
ten
an
ce
f
o
r
m
a
n
u
f
ac
tu
r
in
g
an
d
in
d
u
s
tr
ial
s
y
s
tem
s
in
I
n
d
u
s
tr
y
4
.
0
,
with
o
u
t
ac
tu
al
ly
p
r
o
p
o
s
in
g
n
o
v
e
l
f
r
am
ewo
r
k
s
f
o
r
s
p
ec
if
ic
s
en
s
o
r
ap
p
licatio
n
s
[
3
3
]
–
[
3
5
]
.
W
h
il
e
th
ese
co
n
v
en
tio
n
al
r
e
v
iew
a
p
p
r
o
ac
h
es
p
r
o
v
id
e
v
alu
ab
le
o
v
er
v
iews
o
f
ex
is
tin
g
m
eth
o
d
o
lo
g
ies,
th
ey
t
y
p
ical
ly
f
o
cu
s
o
n
b
r
o
a
d
in
d
u
s
tr
ial
a
p
p
licatio
n
s
with
o
u
t
ad
d
r
ess
in
g
th
e
u
n
iq
u
e
r
eq
u
ir
em
en
ts
o
f
s
af
ety
-
cr
itical
s
ci
en
tific
in
s
tr
u
m
en
tatio
n
.
I
n
c
o
n
tr
ast,
th
is
s
tu
d
y
em
p
lo
y
s
a
n
o
v
el
m
eth
o
d
o
lo
g
y
th
at
co
m
b
in
es
s
y
s
tem
atic
liter
atu
r
e
an
aly
s
is
f
r
o
m
m
u
ltip
le
en
g
in
ee
r
in
g
d
o
m
ain
s
with
ap
p
licatio
n
-
s
p
e
cif
ic
f
r
am
ewo
r
k
d
ev
el
o
p
m
en
t.
Ou
r
ap
p
r
o
ac
h
d
if
f
er
s
f
r
o
m
co
n
v
en
tio
n
al
r
ev
iews
b
y
:
i)
in
teg
r
atin
g
k
n
o
wle
d
g
e
f
r
o
m
b
o
th
p
r
ed
ictiv
e
m
ain
ten
an
ce
en
g
in
ee
r
in
g
an
d
s
eismo
lo
g
ical
in
s
tr
u
m
en
tatio
n
d
o
m
ain
s
,
ii)
s
y
s
tem
atica
lly
ev
alu
atin
g
th
e
ap
p
licab
ilit
y
o
f
g
e
n
er
al
p
r
e
d
ictiv
e
m
ain
ten
an
ce
m
eth
o
d
s
to
s
eismo
m
eter
-
s
p
ec
if
ic
f
au
lt
s
ce
n
ar
io
s
,
an
d
iii)
s
y
n
th
esizin
g
f
in
d
in
g
s
in
to
a
co
m
p
r
eh
e
n
s
iv
e,
im
p
lem
en
tab
le
f
r
a
m
ewo
r
k
r
at
h
er
th
an
m
er
ely
ca
talo
g
in
g
e
x
is
tin
g
ap
p
r
o
ac
h
es.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
F
a
ult
dia
g
no
s
is
T
h
is
s
ec
tio
n
ex
p
lai
n
s
th
e
b
asic
co
n
ce
p
t
o
f
f
au
lt
d
iag
n
o
s
is
an
d
r
ev
iews
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
in
p
r
ev
io
u
s
r
ele
v
an
t
s
tu
d
ies.
T
o
b
eg
in
with
,
f
a
u
lt
d
iag
n
o
s
is
is
an
ess
en
tial
to
o
l
in
m
ea
s
u
r
em
en
t
an
d
c
o
n
tr
o
l
s
y
s
tem
m
ain
ten
an
ce
s
in
ce
it
in
f
o
r
m
s
th
e
m
ain
ten
a
n
ce
p
er
s
o
n
n
el
a
b
o
u
t
th
e
f
au
lt
th
a
t
o
cc
u
r
r
ed
in
t
h
e
s
y
s
tem
[
3
6
]
,
[
3
7
]
.
Diag
n
o
s
is
is
f
o
r
m
ed
b
y
f
au
lt
d
etec
tio
n
,
is
o
latio
n
,
a
n
d
id
e
n
tific
atio
n
[
3
8
]
,
[
3
9
]
.
Fau
lt
d
etec
tio
n
is
a
r
ep
o
r
tin
g
s
y
s
tem
o
f
an
o
m
aly
o
cc
u
r
r
en
ce
in
a
s
en
s
o
r
's
o
p
er
atin
g
co
n
d
iti
o
n
.
Fau
lt
is
o
latio
n
s
p
ec
if
ies
th
e
ty
p
e
o
f
f
au
lt
o
r
th
e
f
au
lty
co
m
p
o
n
en
t
o
f
th
e
s
y
s
tem
,
wh
ile
f
au
lt
id
en
tific
atio
n
q
u
an
tifie
s
th
e
s
ev
er
ity
o
f
th
e
f
au
lt
[
4
0
]
.
4
.
1
.
1
.
F
a
ult
det
ec
t
io
n
T
h
e
co
n
v
en
tio
n
al
d
ata
-
d
r
iv
e
n
f
au
lt
d
etec
tio
n
m
eth
o
d
c
o
m
p
r
is
es
a
co
n
d
itio
n
d
ata
m
o
n
ito
r
in
g
alg
o
r
ith
m
(
e.
g
.
,
th
r
esh
o
l
d
lim
i
ts
im
p
lem
en
tatio
n
)
a
n
d
a
n
o
m
aly
/f
au
lt
r
ep
o
r
tin
g
as
th
e
h
ea
l
th
-
s
tate
m
o
n
ito
r
in
g
p
r
o
to
co
l
[
4
1
]
,
[
4
2
]
.
Ho
wev
er
,
th
e
latest
s
tu
d
ies
o
f
ten
u
s
e
m
ac
h
in
e
lear
n
in
g
b
in
ar
y
class
if
ier
s
to
d
etec
t
f
au
lts
in
th
e
o
b
s
er
v
e
d
s
y
s
tem
,
d
u
e
t
o
th
eir
r
o
b
u
s
tn
ess
an
d
ad
a
p
tiv
e
lear
n
in
g
a
b
ilit
ies
[
4
3
]
,
[
4
4
]
.
Du
r
in
g
th
e
m
ak
in
g
o
f
th
is
s
tu
d
y
,
th
er
e
h
as
b
ee
n
n
o
s
p
ec
if
ic
r
esear
ch
o
n
s
eismo
m
eter
f
au
lt
d
etec
tio
n
,
alth
o
u
g
h
p
r
ed
ictiv
e
m
ain
ten
an
ce
h
as
b
ee
n
wid
ely
ap
p
lied
f
o
r
v
ar
io
u
s
in
d
u
s
tr
ial
s
y
s
tem
s
.
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
g
en
er
al
f
au
lt
d
etec
tio
n
s
ch
em
es p
r
o
p
o
s
ed
in
p
r
ev
io
u
s
s
tu
d
ies.
C
o
m
p
ar
ativ
e
an
aly
s
is
o
f
f
au
lt
d
etec
tio
n
m
eth
o
d
o
lo
g
ies
r
ev
ea
ls
s
ig
n
if
ican
t
p
er
f
o
r
m
a
n
ce
ad
v
an
tag
es
f
o
r
m
ac
h
in
e
lea
r
n
in
g
ap
p
r
o
a
ch
es
o
v
er
tr
ad
itio
n
al
s
tatis
tic
al
m
eth
o
d
s
.
T
ab
le
2
s
u
m
m
a
r
izes
f
au
lt
d
etec
tio
n
m
eth
o
d
s
ac
r
o
s
s
d
iv
er
s
e
s
en
s
o
r
ap
p
licatio
n
s
an
d
in
d
u
s
tr
ial
s
y
s
tem
s
.
Ma
ch
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
d
em
o
n
s
tr
ate
s
ig
n
if
ican
tly
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
to
tr
ad
itio
n
al
s
tatis
tic
al
m
eth
o
d
s
f
o
r
f
au
lt
d
etec
tio
n
ap
p
licatio
n
s
.
T
h
e
s
tatis
t
ical
ap
p
r
o
ac
h
es
s
h
o
w
co
n
s
id
er
ab
le
v
ar
ia
b
ilit
y
in
p
er
f
o
r
m
an
ce
,
with
s
o
m
e
m
eth
o
d
s
ac
h
iev
in
g
p
er
f
ec
t
d
etec
tio
n
f
o
r
s
p
ec
if
ic
f
au
lt
s
ce
n
ar
io
s
wh
ile
co
m
p
letely
f
aili
n
g
to
d
etec
t
o
th
e
r
s
in
d
i
f
f
er
en
t
n
o
is
e
co
n
d
itio
n
s
.
Fo
r
in
s
tan
ce
,
s
tatis
tical
f
au
lt
d
etec
tio
n
in
win
d
tu
r
b
in
e
s
y
s
tem
s
u
s
in
g
r
esid
u
al
m
o
n
ito
r
i
n
g
ag
ain
s
t
a
th
r
esh
o
ld
ac
h
iev
ed
s
u
cc
ess
f
u
l
d
etec
tio
n
in
o
n
ly
o
n
e
o
u
t
o
f
f
o
u
r
test
ed
s
ce
n
ar
io
s
u
n
d
er
v
ar
y
in
g
n
o
is
e
co
n
d
itio
n
s
,
wh
ile
f
au
lt
p
r
o
b
ab
ilit
y
m
o
n
ito
r
in
g
in
win
d
en
e
r
g
y
c
o
n
v
e
r
s
io
n
s
y
s
tem
s
s
h
o
wed
d
etec
tio
n
r
ates
r
an
g
in
g
f
r
o
m
9
5
.
1
%
to
1
0
0
% d
e
p
en
d
i
n
g
o
n
th
e
s
p
e
cif
ic
f
au
lt ty
p
e.
I
n
c
o
n
tr
ast,
m
ac
h
in
e
lear
n
in
g
m
o
d
els
d
em
o
n
s
tr
ate
c
o
n
s
is
ten
tly
h
ig
h
a
n
d
s
tab
le
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
en
t
ap
p
licatio
n
s
,
with
r
a
n
d
o
m
f
o
r
est
class
if
ier
s
ac
h
iev
in
g
9
9
.
4
%
ac
c
u
r
ac
y
f
o
r
p
h
o
t
o
v
o
ltaic
ar
r
a
y
f
au
lt
d
etec
tio
n
,
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
s
m
ain
tain
i
n
g
a
p
p
r
o
x
im
a
tely
9
7
%
ac
cu
r
ac
y
f
o
r
T
en
n
e
s
s
ee
E
astma
n
(
T
E
)
p
r
o
ce
s
s
m
o
n
it
o
r
in
g
,
an
d
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
-
b
ased
r
esi
d
u
al
m
o
n
ito
r
in
g
s
u
cc
ess
f
u
lly
d
etec
tin
g
f
a
u
lts
in
s
ix
o
u
t o
f
s
ev
en
test
s
ce
n
ar
io
s
f
o
r
wate
r
r
ea
cto
r
s
y
s
tem
s
.
Ho
wev
er
,
d
esp
ite
th
e
r
eliab
ilit
y
o
f
m
ac
h
in
e
lear
n
in
g
-
b
ased
f
au
lt
d
etec
tio
n
s
y
s
tem
s
,
th
er
e
ar
e
p
ar
ticu
lar
c
h
allen
g
e
s
in
im
p
lem
en
tin
g
th
em
f
o
r
s
eismo
m
eter
h
ea
lth
m
o
n
ito
r
in
g
,
s
u
ch
as
d
eter
m
in
i
n
g
th
e
s
u
itab
le
alg
o
r
ith
m
f
o
r
s
eismic
d
ata,
co
n
s
id
er
in
g
th
e
co
m
p
u
tatio
n
al
tim
e
d
u
e
to
th
e
d
ataset
s
ize
o
f
th
e
in
p
u
t
s
eismic
s
ig
n
als,
an
d
ch
o
o
s
in
g
th
e
ap
p
r
o
p
r
iate
m
eth
o
d
to
ex
tr
ac
t
s
eismo
m
eter
h
ea
lth
f
ea
tu
r
es f
r
o
m
s
eismic
s
ig
n
als.
Alth
o
u
g
h
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
d
o
m
in
ate
p
er
f
o
r
m
an
ce
ac
cu
r
ac
ies,
s
tatis
tical
ap
p
r
o
ac
h
es
o
f
f
er
ce
r
tain
ad
v
an
tag
es
th
at
m
er
it
co
n
s
id
er
atio
n
.
T
r
a
d
itio
n
al
th
r
esh
o
ld
-
b
ased
m
eth
o
d
s
p
r
o
v
id
e
in
ter
p
r
etab
l
e
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
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
r
ed
ictive
ma
in
ten
a
n
ce
fr
a
mewo
r
k
fo
r
…
(
A
r
ifr
a
h
ma
n
Yu
s
tika
P
u
tr
a
)
193
r
esu
lts
th
at
m
ain
ten
a
n
ce
p
er
s
o
n
n
el
ca
n
ea
s
ily
u
n
d
e
r
s
tan
d
,
wh
er
ea
s
m
ac
h
i
n
e
lear
n
in
g
m
o
d
e
ls
o
f
ten
f
u
n
ctio
n
as
“
b
lack
b
o
x
es.
”
Ad
d
itio
n
ally
,
s
tatis
t
ical
m
eth
o
d
s
r
e
q
u
ir
e
m
i
n
im
al
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
an
d
ca
n
o
p
er
at
e
r
eliab
ly
in
r
em
o
te
s
eismic
s
tatio
n
s
with
lim
ited
p
r
o
ce
s
s
in
g
p
o
wer
,
wh
er
ea
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
s
p
ec
if
ically
d
ee
p
lear
n
i
n
g
n
e
u
r
al
n
etwo
r
k
s
,
r
e
q
u
ir
e
r
eso
u
r
ce
-
in
ten
s
iv
e
co
m
p
u
tatio
n
al
p
o
we
r
.
T
ab
le
2
.
Su
m
m
a
r
y
o
f
f
a
u
lt d
et
ec
tio
n
m
eth
o
d
s
A
p
p
r
o
a
c
h
O
b
serv
e
d
sy
st
e
m
C
o
n
d
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
d
a
t
a
M
e
t
h
o
d
R
e
s
u
l
t
s
R
e
f
e
r
e
n
c
e
S
t
a
t
i
st
i
c
s
C
h
i
l
l
e
r
p
l
a
n
t
si
mu
l
a
t
i
o
n
t
e
m
p
e
r
a
t
u
r
e
,
w
a
t
e
r
f
l
o
w
c
o
n
f
i
d
e
n
c
e
d
e
g
r
e
e
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
a
t
h
r
e
sh
o
l
d
Th
e
sy
s
t
e
m
s
u
c
c
e
e
d
e
d
i
n
d
e
t
e
c
t
i
n
g
sy
st
e
ma
t
i
c
e
r
r
o
r
s.
H
o
w
e
v
e
r
,
w
h
e
n
t
h
e
r
e
a
r
e
n
o
me
a
su
r
e
me
n
t
e
r
r
o
r
s,
t
h
e
c
o
n
f
i
d
e
n
c
e
d
e
g
r
e
e
i
s
l
o
w
e
r
t
h
a
n
t
h
e
mi
n
i
m
u
m
t
h
r
e
s
h
o
l
d
,
l
e
a
d
i
n
g
t
o
f
a
l
se
f
a
u
l
t
n
o
t
i
f
i
c
a
t
i
o
n
s.
[
4
5
]
S
t
a
t
i
st
i
c
s
W
i
n
d
t
u
r
b
i
n
e
b
e
n
c
h
mar
k
p
i
t
c
h
a
n
g
l
e
,
t
o
r
q
u
e
,
a
n
d
a
n
g
u
l
a
r
s
p
e
e
d
t
e
st
st
a
t
i
st
i
c
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
a
t
h
e
o
r
e
t
i
c
a
l
t
h
r
e
s
h
o
l
d
Tw
o
f
a
u
l
t
s
c
e
n
a
r
i
o
s
r
e
su
l
t
e
d
i
n
si
g
n
i
f
i
c
a
n
t
t
e
st
st
a
t
i
st
i
c
l
e
a
p
s
o
v
e
r
t
h
e
c
o
n
st
a
n
t
t
h
r
e
sh
o
l
d
,
me
a
n
i
n
g
t
h
e
f
a
u
l
t
s
a
r
e
p
e
r
f
e
c
t
l
y
d
e
t
e
c
t
e
d
.
I
n
c
o
n
t
r
a
s
t
,
t
h
e
o
t
h
e
r
f
a
u
l
t
sc
h
e
m
e
f
a
i
l
e
d
t
o
b
e
d
e
t
e
c
t
e
d
,
si
n
c
e
t
h
e
t
e
st
st
a
t
i
s
t
i
c
v
a
l
u
e
st
a
y
e
d
u
n
d
e
r
t
h
e
t
h
r
e
sh
o
l
d
l
i
mi
t
.
[
4
6
]
S
t
a
t
i
st
i
c
s
W
i
n
d
t
u
r
b
i
n
e
b
e
n
c
h
mar
k
W
i
n
d
t
u
r
b
i
n
e
p
a
r
a
m
e
t
e
r
s
R
e
si
d
u
a
l
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
a
t
h
r
e
sh
o
l
d
O
f
a
l
l
t
h
e
f
o
u
r
d
e
t
e
c
t
i
o
n
sc
h
e
m
e
s r
u
n
,
o
n
l
y
o
n
e
s
u
c
c
e
e
d
e
d
i
n
d
e
t
e
c
t
i
n
g
a
l
l
t
h
e
f
a
u
l
t
s
i
n
o
n
e
n
o
i
s
e
s
c
e
n
a
r
i
o
.
N
o
n
e
o
f
t
h
e
f
o
u
r
d
e
t
e
c
t
i
o
n
sc
h
e
mes
c
a
n
c
o
r
r
e
c
t
l
y
d
e
t
e
c
t
a
l
l
f
a
u
l
t
s
i
n
t
h
e
o
t
h
e
r
t
w
o
n
o
i
s
e
sc
e
n
a
r
i
o
s.
[
4
7
]
S
t
a
t
i
st
i
c
s
W
i
n
d
En
e
r
g
y
C
o
n
v
e
r
si
o
n
S
y
st
e
m
t
e
m
p
e
r
a
t
u
r
e
,
sp
e
e
d
f
a
u
l
t
p
r
o
b
a
b
i
l
i
t
y
a
n
d
c
o
n
f
i
d
e
n
c
e
l
e
v
e
l
c
o
m
p
a
r
i
s
o
n
1
0
0
%
a
n
d
9
5
.
1
%
d
e
t
e
c
t
i
o
n
r
a
t
e
s f
o
r
g
e
a
r
b
o
x
a
i
r
c
o
o
l
e
r
a
n
d
s
e
n
so
r
f
a
u
l
t
s
,
r
e
sp
e
c
t
i
v
e
l
y
.
[
4
8
]
S
t
a
t
i
st
i
c
s
V
o
l
t
a
g
e
sen
s
o
r
si
mu
l
a
t
i
o
n
v
o
l
t
a
g
e
M
e
a
su
r
e
me
n
t
i
n
n
o
v
a
t
i
o
n
(
M
I
)
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
t
h
e
a
l
l
o
w
a
n
c
e
i
n
t
e
r
v
a
l
A
d
r
a
s
t
i
c
M
I
i
n
c
r
e
a
se
o
r
d
r
o
p
i
s
g
e
n
e
r
a
t
e
d
e
a
c
h
t
i
me
a
b
i
a
s
v
o
l
t
a
g
e
i
s
a
p
p
l
i
e
d
.
Th
e
r
e
l
a
t
i
v
e
e
r
r
o
r
b
e
t
w
e
e
n
t
h
e
e
s
t
i
m
a
t
e
d
a
n
d
r
e
a
l
M
I
i
s
2
.
6
3
%
u
n
d
e
r
f
o
u
r
c
o
n
d
i
t
i
o
n
s
c
e
n
a
r
i
o
s
.
[
4
9
]
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
P
h
o
t
o
v
o
l
t
a
i
c
(
P
V
)
a
r
r
a
y
si
mu
l
a
t
i
o
n
t
e
m
p
e
r
a
t
u
r
e
,
i
r
r
a
d
i
a
n
c
e
,
a
n
d
3
P
V
o
u
t
p
u
t
p
a
r
a
m
e
t
e
r
s
B
i
n
a
r
y
r
a
n
d
o
m
f
o
r
e
st
c
l
a
ssi
f
i
e
r
(
R
F
C
)
Th
e
R
F
C
m
a
i
n
t
a
i
n
e
d
a
n
a
c
c
u
r
a
c
y
o
f
9
9
.
4
%,
w
h
i
c
h
s
u
r
p
a
s
ses
o
t
h
e
r
t
e
st
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s s
u
c
h
a
s
S
V
M
,
K
N
N
,
mu
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
LP)
,
d
e
c
i
s
i
o
n
t
r
e
e
,
a
n
d
s
t
o
c
h
a
st
i
c
g
r
a
d
i
e
n
t
d
e
sc
e
n
t
(SGD).
[
5
0
]
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
Te
n
n
e
s
see
Ea
st
m
a
n
(
TE)
p
r
o
c
e
ss
5
2
TE
p
r
o
c
e
ss
mea
s
u
r
e
me
n
t
s
A
N
N
b
i
n
a
r
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
A
n
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
o
f
a
b
o
u
t
9
7
%
i
s
o
b
t
a
i
n
e
d
f
o
r
t
h
e
m
o
d
e
l
w
i
t
h
3
a
n
d
4
n
e
u
r
a
l
n
e
t
w
o
r
k
l
a
y
e
r
s.
[
5
1
]
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
W
a
t
e
r
r
e
a
c
t
o
r
si
mu
l
a
t
i
o
n
t
e
m
p
e
r
a
t
u
r
e
,
r
e
a
c
t
i
v
i
t
y
R
e
si
d
u
a
l
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
t
h
r
e
s
h
o
l
d
l
i
m
i
t
s
S
i
x
o
f
t
h
e
s
e
v
e
n
r
e
si
d
u
a
l
s
d
e
t
e
c
t
e
d
t
h
e
f
a
u
l
t
w
h
e
n
a
sc
h
e
m
e
w
a
s si
mu
l
a
t
e
d
.
[
5
2
]
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
N
u
c
l
e
a
r
P
o
w
e
r
P
l
a
n
t
S
i
mu
l
a
t
i
o
n
4
1
si
m
u
l
a
t
e
d
v
a
r
i
a
b
l
e
s
c
o
n
si
s
t
e
n
c
y
i
n
d
e
x
mo
n
i
t
o
r
i
n
g
a
g
a
i
n
st
t
h
e
e
r
r
o
r
a
l
l
o
w
a
n
c
e
1
0
0
%
se
n
si
t
i
v
i
t
y
i
s
o
b
t
a
i
n
e
d
w
i
t
h
a
1
0
%
e
r
r
o
r
a
l
l
o
w
a
n
c
e
a
n
d
a
0
.
5
c
o
n
si
s
t
e
n
c
y
t
h
r
e
sh
o
l
d
.
[
5
3
]
Desp
ite
th
e
p
r
o
v
e
n
ef
f
ec
tiv
e
n
ess
o
f
m
ac
h
in
e
lea
r
n
in
g
m
u
lti
-
class
cla
s
s
if
icatio
n
in
f
au
lt
is
o
latio
n
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ial
ap
p
licatio
n
s
,
s
ev
er
al
cr
itical
c
h
allen
g
es
m
u
s
t
b
e
ad
d
r
ess
ed
wh
en
d
ev
elo
p
i
n
g
s
eismo
m
eter
-
s
p
ec
if
ic
f
au
lt
is
o
latio
n
s
y
s
tem
s
.
T
h
e
p
r
im
ar
y
c
h
allen
g
e
lies
in
ac
q
u
ir
in
g
co
m
p
r
eh
en
s
iv
e
lab
eled
tr
ain
in
g
d
atasets
,
wh
ich
r
eq
u
ir
es
ex
ten
s
iv
e
c
o
r
r
elatio
n
a
n
aly
s
is
b
etwe
en
s
eismic
m
o
n
ito
r
in
g
d
ata
a
n
d
h
is
to
r
ical
m
ain
ten
an
ce
r
ec
o
r
d
s
to
estab
lis
h
g
r
o
u
n
d
t
r
u
th
f
a
u
lt
class
if
icatio
n
s
.
Un
lik
e
co
n
v
en
tio
n
al
in
d
u
s
tr
ial
s
en
s
o
r
s
,
wh
er
e
f
a
u
lt
co
n
d
itio
n
s
ca
n
b
e
ar
tific
ially
in
d
u
ce
d
f
o
r
d
ataset
g
e
n
er
atio
n
,
s
eismo
m
eter
s
o
p
e
r
ate
in
cr
itical
ea
r
th
q
u
a
k
e
m
o
n
ito
r
i
n
g
n
etwo
r
k
s
wh
er
e
d
elib
e
r
ate
f
au
lt
in
tr
o
d
u
ctio
n
is
im
p
r
ac
tical
an
d
p
o
te
n
tially
d
an
g
er
o
u
s
to
p
u
b
lic
s
af
ety
s
y
s
tem
s
.
Fu
r
th
er
m
o
r
e,
d
ev
el
o
p
in
g
an
a
p
p
r
o
p
r
iate
f
a
u
lt
is
o
latio
n
f
r
am
ewo
r
k
p
r
esen
ts
u
n
iq
u
e
c
o
m
p
lex
ities
,
as
th
e
1
6
id
en
tifie
d
s
eismo
m
eter
f
au
lt
ca
teg
o
r
ies
m
u
s
t
b
e
v
alid
ated
ag
ain
s
t
ac
tu
al
f
ield
f
ailu
r
e
e
v
en
ts
to
en
s
u
r
e
th
e
class
if
icatio
n
m
o
d
el
ac
cu
r
ately
r
ef
lects
r
e
al
-
wo
r
ld
o
p
e
r
atio
n
al
co
n
d
itio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
1
8
7
-
205
194
4
.
1
.
2
.
F
a
ult
is
o
la
t
io
n
Fau
lt
is
o
latio
n
s
p
ec
if
ies
th
e
ty
p
e
o
f
f
au
lt
o
r
d
ec
lar
es
a
f
au
lt
y
co
m
p
o
n
en
t
with
in
a
s
y
s
tem
[
5
4
]
,
[
5
5
]
.
Ma
ch
in
e
lear
n
in
g
m
u
lti
-
class
class
if
icatio
n
is
th
e
m
o
s
t
c
o
m
m
o
n
m
eth
o
d
f
o
r
b
u
ild
i
n
g
a
f
a
u
lt
is
o
latio
n
s
y
s
tem
.
T
ab
le
3
s
u
m
m
ar
izes
th
e
f
au
lt
is
o
latio
n
m
eth
o
d
s
,
d
em
o
n
s
tr
atin
g
ex
ce
p
tio
n
al
p
e
r
f
o
r
m
an
ce
co
n
s
is
ten
cy
ac
r
o
s
s
d
if
f
er
en
t
in
s
tr
u
m
e
n
tatio
n
s
y
s
tem
s
an
d
o
p
er
atio
n
al
co
n
d
itio
n
s
.
T
h
e
r
esu
lts
r
ev
ea
l
th
at
m
ac
h
in
e
lear
n
in
g
m
u
lti
-
class
cla
s
s
if
ier
s
ac
h
iev
e
o
u
ts
tan
d
in
g
ac
cu
r
ac
y
r
ates,
with
m
u
ltip
le
s
tu
d
ies
r
ep
o
r
tin
g
p
er
f
ec
t
1
0
0
%
class
if
icatio
n
p
er
f
o
r
m
an
ce
f
o
r
b
ea
r
in
g
c
o
n
d
itio
n
m
o
n
ito
r
in
g
u
s
in
g
On
e
-
vs
-
all
SVM
class
if
ier
s
,
tem
p
er
atu
r
e
s
en
s
o
r
f
au
lt
is
o
latio
n
u
s
in
g
p
o
ly
n
o
m
ial
an
d
R
B
F
k
er
n
el
f
u
n
ctio
n
s
,
r
an
d
o
m
f
o
r
est
class
if
ie
r
s
f
o
r
b
ea
r
in
g
s
tate
id
en
tific
atio
n
,
an
d
m
o
t
o
r
f
a
u
lt d
etec
tio
n
u
s
in
g
On
e
-
vs
-
o
n
e
SVM
ap
p
r
o
ac
h
es.
T
ab
le
3
.
Su
m
m
a
r
y
o
f
f
a
u
lt is
o
latio
n
m
eth
o
d
s
C
o
n
d
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
d
a
t
a
M
e
t
h
o
d
C
l
a
s
s l
a
b
e
l
s
P
e
r
f
o
r
ma
n
c
e
R
e
f
e
r
e
n
c
e
V
i
b
r
a
t
i
o
n
s
O
n
e
-
vs
-
a
l
l
S
V
M
M
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
F
i
v
e
b
e
a
r
i
n
g
c
o
n
d
i
t
i
o
n
s
1
0
0
%
c
l
a
ss
i
f
i
c
a
t
i
o
n
r
a
t
e
[
5
6
]
T
e
mp
e
r
a
t
u
r
e
O
n
e
-
vs
-
a
l
l
S
V
M
M
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
w
i
t
h
p
o
l
y
n
o
m
i
a
l
a
n
d
R
B
F
k
e
r
n
e
l
f
u
n
c
t
i
o
n
S
i
x
t
e
m
p
e
r
a
t
u
r
e
s
e
n
so
r
st
a
t
e
s
1
0
0
%
c
l
a
ss
i
f
i
c
a
t
i
o
n
r
a
t
e
[
5
7
]
V
i
b
r
a
t
i
o
n
s
R
F
a
n
d
R
N
N
c
l
a
ssi
f
i
e
r
s
F
o
u
r
b
e
a
r
i
n
g
st
a
t
e
s
1
0
0
%
R
F
c
l
a
ssi
f
i
c
a
t
i
o
n
r
a
t
e
[
5
8
]
S
o
u
n
d
s
O
n
e
-
vs
-
o
n
e
S
V
M
m
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
f
o
r
h
e
l
i
c
o
p
t
e
r
a
n
d
d
u
o
c
o
p
t
e
r
mo
t
o
r
s
F
i
v
e
m
o
t
o
r
c
o
n
d
i
t
i
o
n
s
1
0
0
%
a
c
c
u
r
a
c
y
[
5
9
]
F
l
o
w
r
a
t
e
,
w
a
t
e
r
l
e
v
e
l
K
G
K
N
N
mu
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
3
D
TS
2
0
0
t
h
r
e
e
-
t
a
n
k
sy
st
e
m
c
o
n
d
i
t
i
o
n
s
9
9
%
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
[
6
0
]
T
e
mp
e
r
a
t
u
r
e
,
i
r
r
a
d
i
a
n
c
e
,
3
P
V
o
u
t
p
u
t
p
a
r
a
m
e
t
e
r
s
R
F
m
u
l
t
i
-
c
l
a
ss
c
l
a
ssi
f
i
e
r
4
P
V
a
r
r
a
y
f
a
u
l
t
s
9
9
.
4
%
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
[
5
0
]
T
e
mp
e
r
a
t
u
r
e
,
sp
e
e
d
,
a
n
d
p
r
e
ss
u
r
e
A
N
N
,
K
N
N
,
a
n
d
D
T
M
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
s
1
2
g
a
s
t
u
r
b
i
n
e
d
e
g
r
a
d
a
t
i
o
n
c
o
n
d
i
t
i
o
n
s
9
9
%
a
c
c
u
r
a
c
y
[
6
1
]
T
e
mp
e
r
a
t
u
r
e
a
n
d
r
e
a
c
t
i
v
i
t
y
LSTM
mu
l
t
i
-
c
l
a
ss
c
l
a
ssi
f
i
e
r
S
i
x
w
a
t
e
r
r
e
a
c
t
o
r
c
o
n
d
i
t
i
o
n
s
1
0
0
%
c
l
a
ss
i
f
i
c
a
t
i
o
n
r
a
t
e
[
5
2
]
4
.
1
.
3
.
F
a
ult
identif
ica
t
io
n
Fau
lt
id
en
tific
atio
n
esti
m
ates
th
e
o
b
s
er
v
ed
s
y
s
tem
'
s
f
au
lt
s
ev
er
ity
[
6
2
]
,
[
6
3
]
I
t
is
also
th
e
f
i
n
al
s
tep
o
f
f
au
lt
d
iag
n
o
s
is
,
wh
ich
in
f
o
r
m
s
th
e
m
o
s
t
cr
itical
s
en
s
o
r
co
n
d
itio
n
p
ar
a
m
eter
.
T
h
e
m
o
d
el
b
u
ilt
f
o
r
f
au
lt
id
en
tific
atio
n
d
ec
lar
es
th
e
d
a
m
ag
e
to
th
e
s
y
s
tem
as
a
s
tate
in
a
d
ef
in
e
d
h
ier
ar
ch
ical
o
r
d
er
.
L
ik
e
s
tan
d
ar
d
f
a
u
lt
d
etec
tio
n
an
d
is
o
latio
n
m
eth
o
d
s
,
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
el
s
ar
e
also
im
p
lem
en
tab
le
f
o
r
f
au
lt
id
en
tific
atio
n
task
s
.
Ho
wev
er
,
in
s
tead
o
f
d
ec
lar
in
g
th
e
f
au
lt
ty
p
e,
ea
ch
la
b
el
in
th
e
tr
ain
in
g
d
ata
o
f
a
f
au
lt
id
en
tific
atio
n
m
o
d
el
in
f
o
r
m
s
h
o
w
d
am
ag
e
d
t
h
e
s
y
s
tem
is
.
Fau
lt
id
en
tific
atio
n
m
eth
o
d
o
l
o
g
ies
d
em
o
n
s
tr
ate
clea
r
alg
o
r
ith
m
ic
p
r
ef
e
r
en
ce
s
th
at
r
ev
ea
l
b
o
th
th
e
ad
v
an
tag
es
o
f
m
ac
h
in
e
lear
n
i
n
g
a
p
p
r
o
ac
h
es
an
d
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
s
tatis
tical
m
eth
o
d
s
f
o
r
s
ev
er
ity
ass
es
s
m
en
t
ap
p
licatio
n
s
.
T
ab
le
4
co
m
p
r
e
h
en
s
iv
ely
s
u
m
m
ar
izes
f
au
lt
id
en
tific
atio
n
m
eth
o
d
s
ac
r
o
s
s
d
iv
er
s
e
in
d
u
s
tr
ial
ap
p
licatio
n
s
.
T
h
e
c
o
m
p
ar
ativ
e
an
aly
s
is
d
em
o
n
s
tr
ates
th
at
f
au
lt
id
e
n
tific
atio
n
m
eth
o
d
o
l
o
g
ies
s
h
ar
e
s
u
b
s
tan
tial
s
im
ilar
itie
s
with
f
au
lt
is
o
latio
n
ap
p
r
o
ac
h
es,
as
b
o
th
p
r
o
ce
s
s
es
p
r
ed
o
m
in
an
tl
y
em
p
lo
y
m
ac
h
in
e
lear
n
in
g
-
b
ased
m
u
lti
-
class
class
if
ier
s
a
s
th
eir
co
r
e
d
ec
is
io
n
-
m
ak
in
g
alg
o
r
ith
m
s
.
H
o
wev
er
,
a
cr
itical
d
is
tin
ctio
n
em
er
g
es
wh
en
ex
am
in
in
g
t
h
e
s
in
g
le
s
tatis
tical
ap
p
r
o
ac
h
in
clu
d
e
d
i
n
th
e
r
e
v
iew:
th
e
g
as
r
atio
ev
alu
atio
n
tech
n
iq
u
e
f
o
r
ele
ctr
ical
in
s
u
latio
n
d
eter
i
o
r
atio
n
ass
ess
m
en
t.
T
h
is
s
tatis
tica
l
m
eth
o
d
ex
h
i
b
its
in
h
er
en
t
lim
itatio
n
s
,
as
it
r
e
q
u
ir
es
d
is
tin
ct
ev
alu
atio
n
tech
n
iq
u
es
tailo
r
ed
to
ea
c
h
s
p
ec
if
ic
d
eter
io
r
atio
n
ty
p
e,
m
ak
in
g
it
u
n
s
u
itab
le
f
o
r
g
e
n
e
r
alize
d
f
au
lt
id
en
tific
atio
n
f
r
a
m
ewo
r
k
s
wh
er
e
m
u
ltip
le
f
au
lt
s
ev
er
ities
m
u
s
t
b
e
ass
es
s
ed
u
s
in
g
a
u
n
if
ied
ap
p
r
o
ac
h
.
I
n
co
n
tr
ast,
m
ac
h
in
e
lea
r
n
i
n
g
ap
p
r
o
ac
h
es
d
em
o
n
s
tr
ate
s
u
p
er
io
r
v
er
s
atility
an
d
p
er
f
o
r
m
a
n
ce
co
n
s
is
ten
cy
ac
r
o
s
s
ap
p
licatio
n
s
.
Dec
is
io
n
tr
ee
class
if
ier
s
ac
h
iev
e
9
8
%
an
d
9
5
%
class
if
icatio
n
r
ates
f
o
r
tr
ain
in
g
a
n
d
test
in
g
d
atasets
f
o
r
v
a
r
iab
le
r
e
f
r
ig
er
a
n
t
f
lo
w
s
y
s
tem
s
,
wh
ile
On
e
-
vs
-
o
n
e
SVM
m
u
lti
-
class
class
if
ier
s
r
ea
ch
9
9
.
3
%
ac
cu
r
ac
y
f
o
r
m
icr
o
g
r
id
f
au
lt
lev
el
id
en
tific
atio
n
.
L
STM
class
if
ier
s
ex
ce
l
in
tem
p
o
r
al
s
ev
er
ity
p
atter
n
r
ec
o
g
n
itio
n
,
ac
h
iev
in
g
9
8
.
9
2
%
ac
c
u
r
ac
y
ac
r
o
s
s
1
2
d
if
f
er
e
n
t
s
ev
er
ity
l
ev
els
in
in
d
u
ctio
n
m
ac
h
in
e
s
y
s
tem
s
,
an
d
Mu
ltil
a
y
er
Per
ce
p
tr
o
n
class
if
ier
s
d
em
o
n
s
tr
ate
ex
ce
p
tio
n
al
p
r
ec
is
io
n
with
b
elo
w
0
.
3
%
class
if
icatio
n
er
r
o
r
s
f
o
r
L
i
-
i
o
n
b
atter
y
State
o
f
Hea
lth
ass
ess
m
en
t.
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
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
p
r
ed
ictive
ma
in
ten
a
n
ce
fr
a
mewo
r
k
fo
r
…
(
A
r
ifr
a
h
ma
n
Yu
s
tika
P
u
tr
a
)
195
T
ab
le
4
.
Su
m
m
a
r
y
o
f
f
a
u
lt id
e
n
tific
atio
n
m
eth
o
d
s
C
o
n
d
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
d
a
t
a
M
e
t
h
o
d
C
l
a
s
s l
a
b
e
l
s
P
e
r
f
o
r
ma
n
c
e
R
e
f
e
r
e
n
c
e
G
a
s rat
i
o
S
t
a
t
i
st
i
c
a
l
mea
n
,
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
,
a
n
d
r
a
n
g
e
a
n
a
l
y
si
s
u
si
n
g
R
o
g
e
r
s,
D
o
e
r
n
e
n
b
u
r
g
,
I
EC
,
a
n
d
C
I
G
R
E
g
a
s
r
a
t
i
o
e
v
a
l
u
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
Th
r
e
e
e
l
e
c
t
r
i
c
a
l
i
n
s
u
l
a
t
i
o
n
d
e
t
e
r
i
o
r
a
t
i
o
n
Ea
c
h
d
e
t
e
r
i
o
r
a
t
i
o
n
t
y
p
e
h
a
s
i
t
s
o
w
n
su
i
t
a
b
l
e
g
a
s ra
t
i
o
e
v
a
l
u
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
b
a
se
d
o
n
h
o
w
t
h
e
t
h
r
e
e
s
t
a
t
i
s
t
i
c
a
l
v
a
l
u
e
s
a
r
e
i
so
l
a
t
e
d
f
r
o
m
t
h
e
o
t
h
e
r
t
e
c
h
n
i
q
u
e
s.
[
6
4
]
Te
mp
e
r
a
t
u
r
e
D
e
c
i
s
i
o
n
t
r
e
e
c
l
a
ss
i
f
i
e
r
F
i
v
e
f
o
u
l
i
n
g
f
a
u
l
t
sev
e
r
i
t
i
e
s
o
f
t
h
e
V
a
r
i
a
b
l
e
R
e
f
r
i
g
e
r
a
n
t
F
l
o
w
(
V
R
F
)
o
u
t
d
o
o
r
u
n
i
t
9
8
%
a
n
d
9
5
%
c
l
a
ssi
f
i
c
a
t
i
o
n
r
a
t
e
s
f
o
r
t
r
a
i
n
i
n
g
a
n
d
t
e
st
i
n
g
d
a
t
a
s
e
t
s,
r
e
sp
e
c
t
i
v
e
l
y
[
6
5
]
C
u
r
r
e
n
t
,
v
o
l
t
a
g
e
,
a
n
d
p
o
w
e
r
O
n
e
-
vs
-
o
n
e
S
V
M
m
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
e
r
Th
r
e
e
m
i
c
r
o
g
r
i
d
f
a
u
l
t
l
e
v
e
l
s
9
9
.
3
%
a
c
c
u
r
a
c
y
[
6
6
]
M
o
t
o
r
c
u
r
r
e
n
t
LSTM
c
l
a
ssi
f
i
e
r
1
2
se
v
e
r
i
t
y
l
e
v
e
l
s
o
f
t
h
e
i
n
d
u
c
t
i
o
n
mac
h
i
n
e
sy
st
e
m
9
8
.
9
2
%
a
c
c
u
r
a
c
y
[
6
7
]
V
o
l
t
a
g
e
,
c
u
r
r
e
n
t
,
a
n
d
t
e
m
p
e
r
a
t
u
r
e
M
LP
c
l
a
ssi
f
i
e
r
F
i
v
e
L
i
-
i
o
n
b
a
t
t
e
r
y
S
t
a
t
e
o
f
H
e
a
l
t
h
(
S
O
H
)
B
e
l
o
w
0
.
3
%
o
f
c
l
a
ssi
f
i
c
a
t
i
o
n
e
r
r
o
r
s
[
6
8
]
P
r
e
ssu
r
e
P
h
y
s
i
c
s
i
n
f
o
r
m
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
(
P
I
N
N
)
F
o
u
r
a
x
i
a
l
p
i
s
t
o
n
p
u
m
p
c
o
n
d
i
t
i
o
n
s
1
0
0
%
a
c
c
u
r
a
c
y
[
6
9
]
T
h
ese
co
m
p
r
eh
e
n
s
iv
e
p
r
io
r
s
tu
d
ies
d
em
o
n
s
tr
ate
th
e
s
ig
n
if
ic
an
t
p
o
ten
tial
f
o
r
im
p
lem
en
tin
g
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
an
d
r
eg
r
ess
o
r
s
to
d
ev
elo
p
r
o
b
u
s
t
d
ata
-
d
r
iv
en
f
au
lt
s
ev
er
ity
id
en
tific
atio
n
s
y
s
tem
s
f
o
r
o
p
er
atio
n
al
s
eismo
m
eter
s
.
T
h
e
co
n
s
is
ten
tly
h
ig
h
p
er
f
o
r
m
a
n
ce
ac
h
iev
e
d
ac
r
o
s
s
d
iv
er
s
e
s
en
s
o
r
ap
p
licatio
n
s
s
u
g
g
ests
th
at
s
im
ilar
p
er
f
o
r
m
an
ce
lev
els
co
u
ld
b
e
attain
a
b
l
e
f
o
r
s
eismo
m
eter
ap
p
licatio
n
s
with
ap
p
r
o
p
r
iate
d
ataset
d
ev
elo
p
m
e
n
t
an
d
f
ea
tu
r
e
en
g
in
ee
r
in
g
.
Ho
wev
e
r
,
th
e
p
r
im
ar
y
im
p
lem
en
tatio
n
ch
allen
g
e
e
x
ten
d
s
b
ey
o
n
d
alg
o
r
ith
m
ic
s
elec
tio
n
to
th
e
f
u
n
d
am
en
tal
d
ef
in
itio
n
o
f
s
ev
er
ity
class
if
icatio
n
s
ch
em
es
th
at
ac
cu
r
ately
r
ef
lect
s
eismo
m
eter
h
ea
lth
d
eg
r
ad
atio
n
p
atter
n
s
.
Un
lik
e
in
d
u
s
tr
ial
ap
p
licatio
n
s
,
wh
er
e
s
ev
er
ity
lev
els
ca
n
b
e
d
ef
in
ed
th
r
o
u
g
h
co
n
t
r
o
lled
te
s
tin
g
o
r
s
tan
d
ar
d
ized
p
er
f
o
r
m
an
ce
m
etr
ics,
s
eismo
m
eter
s
ev
er
ity
class
if
icatio
n
r
eq
u
ir
es
ca
teg
o
r
ical
g
r
ad
es
r
e
p
r
esen
tin
g
t
h
e
o
p
er
atio
n
al
h
ea
lth
s
tate
b
ased
o
n
ex
ten
s
iv
e
a
n
aly
s
is
o
f
h
is
to
r
ical
m
ain
ten
an
ce
r
ec
o
r
d
s
s
p
an
n
in
g
d
ec
ad
es o
f
n
etwo
r
k
o
p
er
atio
n
.
4
.
2
.
F
a
ult
pro
g
no
s
is
Fau
lt
p
r
o
g
n
o
s
is
r
ep
r
esen
ts
th
e
m
o
s
t
ad
v
an
ce
d
s
tag
e
o
f
p
r
ed
i
ctiv
e
m
ain
ten
an
ce
,
f
o
c
u
s
in
g
o
n
th
e
ea
r
ly
p
r
ed
ictio
n
o
f
s
y
s
tem
p
o
ten
tia
l
f
ailu
r
e
a
n
d
t
h
e
q
u
an
titativ
e
esti
m
atio
n
o
f
R
UL
b
ef
o
r
e
cr
itical
b
r
ea
k
d
o
wn
o
cc
u
r
s
[
7
0
]
,
[
7
1
]
.
T
h
is
s
o
p
h
is
ticated
p
r
ed
ictiv
e
ca
p
ab
ilit
y
e
n
ab
les
m
ain
ten
an
ce
p
er
s
o
n
n
el
to
tr
an
s
itio
n
f
r
o
m
r
ea
ctiv
e
r
ep
air
s
tr
ateg
ies
to
p
r
o
ac
tiv
e
m
ain
ten
a
n
ce
s
ch
ed
u
lin
g
,
o
p
tim
izin
g
b
o
th
s
y
s
tem
av
ailab
ilit
y
an
d
r
eso
u
r
ce
allo
ca
tio
n
th
r
o
u
g
h
p
r
ec
is
e
tim
in
g
o
f
r
ep
air
o
r
c
o
m
p
o
n
en
t
r
ep
lace
m
en
t
in
ter
v
en
tio
n
s
[
7
2
]
,
[
7
3
]
.
Un
lik
e
f
au
lt
d
iag
n
o
s
is
,
wh
ich
ad
d
r
ess
es
cu
r
r
en
t
s
y
s
tem
h
ea
lth
s
tatu
s
,
f
au
lt
p
r
o
g
n
o
s
is
p
r
o
v
id
es
f
o
r
war
d
-
lo
o
k
in
g
in
s
ig
h
ts
f
o
r
s
tr
ateg
ic
m
ain
ten
an
ce
p
la
n
n
in
g
an
d
o
p
e
r
atio
n
al
r
is
k
m
an
a
g
em
en
t.
T
h
e
ev
o
lu
tio
n
o
f
f
a
u
lt
p
r
o
g
n
o
s
is
m
eth
o
d
o
lo
g
ies
d
em
o
n
s
tr
ates
a
clea
r
tech
n
o
lo
g
ical
p
r
o
g
r
es
s
io
n
f
r
o
m
b
asic
s
tatis
tical
ap
p
r
o
ac
h
es
to
ad
v
an
ce
d
m
ac
h
i
n
e
lear
n
in
g
f
r
am
ewo
r
k
s
,
co
r
r
esp
o
n
d
i
n
g
im
p
r
o
v
e
m
en
ts
in
p
r
ed
ictio
n
ac
c
u
r
ac
y
an
d
o
p
er
atio
n
al
ca
p
ab
ilit
y
.
T
ab
le
5
co
m
p
r
eh
en
s
iv
ely
s
u
m
m
ar
i
ze
s
f
au
lt
p
r
o
g
n
o
s
is
m
eth
o
d
s
ac
r
o
s
s
d
iv
e
r
s
e
in
d
u
s
t
r
ial
ap
p
licatio
n
s
.
T
h
e
p
r
o
g
r
es
s
io
n
d
em
o
n
s
tr
ates
m
ar
k
ed
im
p
r
o
v
em
e
n
ts
in
b
o
t
h
m
eth
o
d
o
l
o
g
ical
s
o
p
h
is
ticatio
n
an
d
p
er
f
o
r
m
a
n
ce
ca
p
a
b
ilit
ies.
T
h
e
th
eo
r
etica
l
lin
ea
r
r
eg
r
ess
io
n
ap
p
r
o
ac
h
r
ep
r
esen
ts
th
e
ea
r
lies
t
g
en
er
atio
n
o
f
R
UL
esti
m
at
io
n
,
r
ely
in
g
o
n
ex
p
er
ie
n
ce
-
b
ased
d
ete
r
m
in
atio
n
with
o
u
t
q
u
an
titativ
e
p
er
f
o
r
m
an
ce
m
et
r
ics.
I
n
co
n
tr
ast,
m
o
d
er
n
ap
p
r
o
ac
h
es
s
h
o
wca
s
e
s
u
b
s
tan
tial
ad
v
an
ce
m
e
n
t:
Dee
p
R
ein
f
o
r
ce
m
en
t
L
ea
r
n
in
g
ac
h
iev
es
R
MSE
v
alu
es
r
an
g
in
g
f
r
o
m
1
2
.
1
7
t
o
1
8
.
8
7
ac
r
o
s
s
d
i
f
f
er
en
t
o
p
er
atio
n
al
co
m
p
lex
ities
,
wh
ile
p
h
y
s
ics
g
u
id
ed
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
n
etwo
r
k
s
d
e
m
o
n
s
tr
ate
ex
ce
p
tio
n
al
ac
cu
r
ac
y
with
R
²
v
alu
es o
f
0
.
9
0
2
a
n
d
m
ea
n
a
b
s
o
lu
te
er
r
o
r
o
f
0
.
0
7
1
7
.
Fu
r
th
er
m
o
r
e
,
th
e
L
STM
-
b
ased
h
y
b
r
id
a
p
p
r
o
ac
h
r
ep
r
esen
ts
th
e
cu
r
r
en
t
s
tate
-
of
-
th
e
-
ar
t,
ac
h
iev
in
g
h
ig
h
class
if
icatio
n
ac
c
u
r
ac
y
(
0
.
9
6
an
d
0
.
8
6
)
f
o
r
d
e
g
r
ad
atio
n
s
tag
e
id
e
n
tific
atio
n
a
n
d
lo
w
r
eg
r
ess
io
n
e
r
r
o
r
s
(
4
.
2
1
a
n
d
5
.
2
1
R
MSE
)
f
o
r
co
n
tin
u
o
u
s
R
UL
p
r
ed
ictio
n
,
in
d
icatin
g
t
h
e
ef
f
ec
tiv
en
ess
o
f
co
m
b
in
in
g
class
if
icatio
n
an
d
r
eg
r
ess
io
n
m
eth
o
d
o
l
o
g
ies.
T
h
e
s
u
cc
ess
o
f
th
e
m
ac
h
in
e
lear
n
in
g
-
b
ase
d
R
UL
es
tim
atio
n
ap
p
r
o
ac
h
es
lies
in
r
o
b
u
s
t
q
u
a
n
tific
atio
n
m
eth
o
d
o
lo
g
ies
th
at
estab
lis
h
g
r
o
u
n
d
tr
u
th
f
o
r
alg
o
r
ith
m
tr
ain
i
n
g
a
n
d
v
alid
atio
n
,
w
h
ich
p
r
esen
ts
th
e
f
u
n
d
am
en
tal
ch
allen
g
e
f
o
r
p
r
ac
tical
ap
p
licatio
n
t
o
o
p
er
atio
n
al
s
eismo
m
eter
s
in
s
eismic
m
o
n
ito
r
in
g
n
etwo
r
k
s
.
T
h
e
d
ev
elo
p
m
en
t
o
f
r
o
b
u
s
t
m
ac
h
in
e
lear
n
in
g
r
eg
r
ess
io
n
m
o
d
els
f
o
r
s
eismo
m
eter
p
r
o
g
n
o
s
is
ap
p
licatio
n
s
f
ac
es
a
f
u
n
d
am
en
tal
an
d
cr
itical
ch
allen
g
e:
th
e
r
eq
u
ir
em
e
n
t
f
o
r
c
o
m
p
r
e
h
en
s
iv
e
tr
ain
in
g
d
atasets
th
at
ca
p
tu
r
e
co
m
p
lete
d
eg
r
ad
atio
n
tr
ajec
to
r
ies
ac
r
o
s
s
all
f
au
lt
ca
teg
o
r
ies
th
r
o
u
g
h
o
u
t
th
e
en
tire
o
p
er
atio
n
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
1
8
7
-
205
196
life
cy
cle
o
f
s
eismo
m
eter
s
y
s
tem
s
.
T
h
is
d
ata
s
ca
r
city
r
ep
r
esen
ts
th
e
m
o
s
t
s
ig
n
if
ican
t
b
ar
r
ier
to
p
r
ac
tical
im
p
lem
en
tatio
n
,
as
ef
f
ec
tiv
e
R
UL
esti
m
at
io
n
m
o
d
els
r
eq
u
ir
e
ex
ten
s
iv
e
h
is
to
r
ical
r
ec
o
r
d
s
t
h
at
co
r
r
elate
h
ea
lth
f
ea
tu
r
e
e
v
o
lu
tio
n
with
ac
tu
al
f
ailu
r
e
tim
elin
es,
d
o
cu
m
en
ti
n
g
th
e
p
r
o
g
r
ess
iv
e
d
eter
i
o
r
atio
n
p
atter
n
s
f
r
o
m
in
itial
h
ea
lth
y
o
p
er
atio
n
th
r
o
u
g
h
v
ar
io
u
s
d
eg
r
ad
atio
n
s
tag
es
to
u
ltima
te
co
m
p
o
n
en
t
f
ailu
r
e
.
Ho
w
ev
er
,
t
h
e
r
ea
lity
o
f
o
p
er
atio
n
al
s
eismic
n
etwo
r
k
s
o
f
ten
co
n
f
licts
with
th
ese
d
ata
r
eq
u
ir
em
e
n
ts
,
as
p
r
ev
en
tiv
e
m
ain
ten
an
ce
p
r
o
to
co
ls
m
a
y
lead
to
s
en
s
o
r
r
ep
lace
m
en
ts
b
ef
o
r
e
co
m
p
lete
d
eg
r
ad
atio
n
cy
cles c
an
b
e
ca
p
t
u
r
ed
.
T
ab
le
5
.
Su
m
m
a
r
y
o
f
f
a
u
lt p
r
o
g
n
o
s
is
m
eth
o
d
s
C
o
n
d
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
d
a
t
a
R
U
L
e
s
t
i
mat
i
o
n
me
t
h
o
d
R
U
L
q
u
a
n
t
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
P
e
r
f
o
r
ma
n
c
e
R
e
f
e
r
e
n
c
e
Th
e
o
r
e
t
i
c
a
l
c
o
n
d
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
d
a
t
a
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
b
e
t
w
e
e
n
d
a
t
a
d
e
v
i
a
t
i
o
n
a
n
d
h
i
s
t
o
r
i
c
a
l
R
U
L
e
x
p
e
r
i
e
n
c
e
-
b
a
s
e
d
d
e
t
e
r
mi
n
a
t
i
o
n
u
n
s
t
a
t
e
d
[
7
4
]
V
i
b
r
a
t
i
o
n
s
o
f
t
u
r
b
o
f
a
n
e
n
g
i
n
e
s
D
e
e
p
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
(
D
R
L)
C
-
M
A
P
S
S
t
u
r
b
o
f
a
n
e
n
g
i
n
e
h
e
a
l
t
h
d
i
v
i
si
o
n
i
n
t
o
t
w
o
st
a
g
e
s:
(
e
a
r
l
y
,
l
i
n
e
a
r
d
e
g
r
a
d
a
t
i
o
n
)
R
M
S
E
:
1
2
.
1
7
(
F
D
0
0
1
)
,
1
6
.
2
8
(
F
D
0
0
2
)
,
1
3
.
0
9
(
F
D
0
0
3
)
,
1
8
.
8
7
(
F
D
0
0
4
)
.
[
7
5
]
B
e
a
r
i
n
g
v
i
b
r
a
t
i
o
n
s
S
V
M
c
l
a
ss
i
f
i
e
r
A
n
a
l
y
s
i
s
o
f
h
i
st
o
r
i
c
a
l
f
a
i
l
u
r
e
p
a
t
t
e
r
n
s
9
4
.
4
%
o
f
a
v
e
r
a
g
e
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
[
7
6
]
B
e
a
r
i
n
g
v
i
b
r
a
t
i
o
n
s
P
h
y
s
i
c
s
g
u
i
d
e
d
l
o
n
g
sh
o
r
t
-
t
e
r
m
mem
o
r
y
(
P
G
LSTM
)
u
n
s
t
a
t
e
d
0
.
0
7
1
7
o
f
M
A
E,
0
.
0
8
6
6
o
f
R
M
S
E
,
0
.
9
0
2
o
f
2
a
n
d
5
6
o
f
c
o
n
si
s
t
e
n
c
y
a
c
c
u
r
a
c
y
[
7
7
]
V
o
l
t
a
g
e
,
t
e
m
p
e
r
a
t
u
r
e
LSTM
r
e
g
r
e
ssi
o
n
u
n
s
t
a
t
e
d
2
t
o
6
d
a
y
s
o
f
t
h
e
l
e
a
st
p
r
e
d
i
c
t
i
o
n
d
e
v
i
a
t
i
o
n
[
7
8
]
2
1
se
n
s
o
r
mea
s
u
r
e
me
n
t
s
LSTM
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
r
e
g
r
e
ss
i
o
n
Th
e
d
e
g
r
a
d
a
t
i
o
n
p
r
o
c
e
ss
i
s
d
i
v
i
d
e
d
i
n
t
o
t
h
r
e
e
s
t
a
g
e
s
0
.
9
6
&
0
.
8
6
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
i
e
s
a
n
d
4
.
2
1
a
n
d
5
.
2
1
r
e
g
r
e
ss
i
o
n
R
M
S
Es
[
7
9
]
4
.
3
.
Seis
m
ic
da
t
a
qu
a
lity
cr
i
t
er
ia
Seis
m
ic
d
ata
q
u
ality
cr
iter
ia
r
ep
r
esen
t
a
co
m
p
r
eh
en
s
iv
e
s
et
o
f
s
tatis
tical
an
d
s
ig
n
al
p
r
o
ce
s
s
in
g
p
ar
am
eter
s
s
p
ec
if
ically
d
esig
n
ed
to
d
eter
m
in
e
s
eismo
m
eter
s
’
o
p
er
atio
n
al
h
ea
lth
an
d
m
ea
s
u
r
em
e
n
t
p
er
f
o
r
m
an
ce
th
r
o
u
g
h
an
aly
s
is
o
f
r
ec
o
r
d
ed
s
eismic
s
ig
n
als
[
8
0
]
.
T
h
ese
cr
iter
ia
ar
e
f
u
n
d
am
e
n
tal
h
ea
lth
in
d
icato
r
s
b
ec
au
s
e
th
e
y
ca
p
tu
r
e
m
ea
s
u
r
ab
le
d
ev
iatio
n
s
f
r
o
m
ex
p
ec
ted
s
eismo
m
eter
b
eh
av
io
r
th
at
c
o
r
r
elate
d
ir
ec
tly
with
s
p
ec
if
ic
f
a
u
lt
c
o
n
d
itio
n
s
,
s
en
s
o
r
d
eg
r
a
d
atio
n
p
atter
n
s
,
an
d
en
v
ir
o
n
m
en
tal
in
ter
f
er
en
ce
ef
f
ec
ts
[
8
1
]
.
T
h
u
s
,
tr
an
s
f
o
r
m
in
g
r
a
w
s
eismic
r
ec
o
r
d
in
g
s
in
to
q
u
an
titativ
e
h
ea
lth
m
etr
ics
en
ab
les
s
y
s
tem
atic
in
s
tr
u
m
en
t
p
er
f
o
r
m
a
n
ce
m
o
n
i
to
r
in
g
a
n
d
p
r
o
v
id
es
th
e
ess
en
tial
f
ea
tu
r
e
s
p
ac
e
r
eq
u
ir
e
d
f
o
r
m
ac
h
in
e
lea
r
n
in
g
-
b
ased
f
au
lt d
iag
n
o
s
is
alg
o
r
ith
m
s
.
An
aly
zin
g
well
-
estab
lis
h
ed
s
eismic
d
ata
q
u
ality
cr
iter
ia
is
cr
itical,
s
in
ce
th
ese
cr
iter
ia
ca
n
b
e
ca
n
d
id
ates
f
o
r
r
elev
an
t
s
eismo
m
eter
h
ea
lth
f
ea
tu
r
es.
T
ab
le
6
s
h
o
ws
th
e
p
r
e
v
io
u
s
s
tu
d
ies
an
d
th
e
co
r
r
esp
o
n
d
in
g
s
eismic
d
ata
q
u
ality
cr
iter
ia,
r
ev
ea
lin
g
a
d
iv
er
s
e
lan
d
s
ca
p
e
o
f
m
eth
o
d
o
lo
g
ical
ap
p
r
o
ac
h
es
th
at
s
p
an
s
in
g
le
-
s
en
s
o
r
an
d
m
u
ltip
le
-
s
en
s
o
r
an
aly
s
is
tech
n
iq
u
es
with
v
ar
y
in
g
c
o
m
p
le
x
ity
an
d
p
r
ac
tical
ap
p
licab
ilit
y
.
Sin
g
le
-
s
en
s
o
r
c
r
iter
ia
an
aly
s
is
f
o
cu
s
es
ex
clu
s
iv
ely
o
n
d
ata
f
r
o
m
in
d
i
v
i
d
u
al
s
eismo
m
eter
s
,
em
p
lo
y
in
g
th
r
ee
p
r
im
ar
y
an
a
ly
tical
ap
p
r
o
ac
h
es:
tim
e
-
d
o
m
ain
s
eismo
g
r
am
co
m
p
ar
is
o
n
with
s
y
n
th
etica
lly
g
en
er
ated
id
ea
l
s
ig
n
als
to
d
e
tect
am
p
litu
d
e
an
d
wav
ef
o
r
m
d
is
to
r
tio
n
s
,
f
r
e
q
u
en
c
y
-
d
o
m
ain
p
o
wer
s
p
ec
tr
al
d
en
s
ity
co
m
p
ar
is
o
n
with
estab
lis
h
ed
n
o
is
e
m
o
d
els
to
id
en
tify
s
p
ec
tr
al
an
o
m
alies,
an
d
s
y
s
tem
atic
in
s
tr
u
m
en
t
ca
lib
r
atio
n
p
r
o
ce
d
u
r
es to
q
u
a
n
tify
s
en
s
o
r
p
er
f
o
r
m
a
n
ce
d
eg
r
a
d
atio
n
o
v
er
tim
e.
T
h
e
ca
lib
r
atio
n
m
eth
o
d
o
lo
g
i
es
en
co
m
p
ass
r
elativ
e
an
d
ab
s
o
lu
te
ap
p
r
o
ac
h
es,
wh
er
e
r
elativ
e
ca
lib
r
atio
n
u
tili
ze
s
th
e
s
eismo
m
eter
’
s
b
u
ilt
-
in
ca
lib
r
atio
n
co
il
to
s
im
u
late
g
r
o
u
n
d
m
o
tio
n
an
d
m
ea
s
u
r
e
s
en
s
itiv
ity
ch
an
g
es
r
e
m
o
tely
.
On
th
e
o
t
h
er
h
an
d
,
ab
s
o
l
u
te
ca
lib
r
atio
n
r
eq
u
ir
es
p
h
y
s
ical
r
em
o
v
al
o
f
th
e
s
eismo
m
eter
f
r
o
m
its
in
s
tallatio
n
p
latf
o
r
m
f
o
r
test
in
g
o
n
p
r
ec
is
io
n
v
ib
r
atin
g
tab
les
th
at
m
ec
h
an
ically
e
x
cite
th
e
s
en
s
o
r
ac
r
o
s
s
its
o
p
er
atio
n
al
f
r
eq
u
e
n
cy
r
an
g
e,
en
ab
lin
g
co
m
p
r
e
h
en
s
iv
e
tr
an
s
f
er
f
u
n
ctio
n
an
aly
s
is
an
d
co
m
p
ar
is
o
n
with
o
r
ig
i
n
al
m
an
u
f
ac
tu
r
er
s
p
ec
if
icatio
n
s
.
Ho
w
ev
er
,
b
o
th
ca
lib
r
atio
n
m
et
h
o
d
s
p
r
esen
t
s
ig
n
if
ican
t
o
p
er
atio
n
al
r
is
k
s
,
as
th
ey
tem
p
o
r
ar
ily
r
em
o
v
e
t
h
e
s
eismo
m
eter
'
s
ab
ili
ty
to
d
etec
t
g
en
u
i
n
e
g
r
o
u
n
d
m
o
tio
n
b
y
o
v
er
r
id
i
n
g
n
o
r
m
al
s
ig
n
al
ac
q
u
is
itio
n
with
ca
lib
r
atio
n
in
p
u
ts
,
r
esu
ltin
g
i
n
cr
itical
d
a
ta
lo
s
s
th
at
co
u
l
d
co
m
p
r
o
m
is
e
ea
r
th
q
u
a
k
e
d
etec
t
io
n
ca
p
ab
ilit
ies d
u
r
in
g
m
ajo
r
s
eismic
ev
en
ts
.
I
n
co
n
tr
ast,
m
u
ltip
le
-
s
en
s
o
r
a
n
aly
s
is
em
p
lo
y
s
co
m
p
ar
ativ
e
m
eth
o
d
o
l
o
g
ies
th
at
r
eq
u
ir
e
an
ad
d
itio
n
al
o
p
er
atio
n
al
s
eismo
m
eter
to
s
er
v
e
as
a
p
er
f
o
r
m
an
ce
r
ef
e
r
en
ce
b
en
ch
m
ar
k
,
with
th
e
r
e
f
er
en
ce
in
s
tr
u
m
e
n
t
ty
p
ically
b
ein
g
eith
er
a
c
o
-
l
o
ca
ted
s
en
s
o
r
with
in
th
e
s
am
e
s
eismic
s
tatio
n
o
r
a
s
en
s
o
r
f
r
o
m
th
e
n
ea
r
est
n
eig
h
b
o
r
in
g
s
tatio
n
e
x
p
er
ien
c
in
g
s
im
ilar
g
r
o
u
n
d
m
o
tio
n
co
n
d
itio
n
s
.
T
h
ese
co
m
p
ar
ativ
e
an
aly
s
is
tech
n
iq
u
es
o
p
er
ate
ac
r
o
s
s
b
o
t
h
f
r
eq
u
e
n
c
y
an
d
tim
e
d
o
m
ain
s
,
u
tili
zin
g
f
r
e
q
u
en
c
y
-
d
o
m
ain
ap
p
r
o
ac
h
es
s
u
ch
as
m
ed
ian
p
o
wer
-
lev
el
d
if
f
er
en
ce
ca
lcu
l
atio
n
s
an
d
tim
e
-
d
o
m
ain
m
et
h
o
d
s
in
clu
d
in
g
r
o
o
t
m
ea
n
s
q
u
a
r
e
(
R
MS)
am
p
litu
d
e
Evaluation Warning : The document was created with Spire.PDF for Python.