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.
8
,
No
.
4
,
A
u
g
u
s
t
201
8
,
p
p
.
2
4
8
6
~
2
4
9
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
4
.
p
p
2
4
8
6
-
2493
2486
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Co
a
l
-
Fired
Bo
ile
r
F
a
ult
Predi
ction
u
sing
Artif
i
cia
l Neural
Netw
o
rk
s
No
ng
Nurnie
M
o
hd
Nis
t
a
h
1
,
K
ing
H
a
nn
L
i
m
2
,
L
e
nin
G
o
p
a
l
3
,
F
ira
s
B
a
s
i
m
I
s
m
a
il Alna
i
m
i
4
1
De
p
a
rt
m
e
n
t
o
f
F
o
u
n
d
a
ti
o
n
o
f
S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
Cu
rt
in
U
n
iv
e
rsit
y
M
a
la
y
sia
,
M
a
l
a
y
s
i
a
2
,3
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
&
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
Cu
rt
in
U
n
iv
e
rsit
y
M
a
la
y
sia
,
M
a
l
a
y
s
i
a
4
De
p
a
rt
m
e
n
t
o
f
M
e
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
,
Un
iv
e
rsity
T
e
n
a
g
a
M
a
lay
sia
(UN
I
T
EN)
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
3
1
,
2
0
1
8
R
ev
i
s
ed
A
p
r
2
,
2
0
1
8
A
cc
ep
ted
A
p
r
2
0
,
2
0
1
8
Bo
il
e
r
f
a
u
lt
is
a
c
rit
ica
l
issu
e
i
n
a
c
o
a
l
-
f
ired
p
o
w
e
r
p
lan
t
d
u
e
to
it
s
h
ig
h
tem
p
e
r
a
tu
re
a
n
d
h
ig
h
p
re
ss
u
re
c
h
a
ra
c
teristics
.
T
h
e
c
o
m
p
lex
it
y
o
f
b
o
il
e
r
d
e
sig
n
in
c
re
a
se
s
th
e
d
iff
icu
lt
y
o
f
f
a
u
lt
in
v
e
stig
a
ti
o
n
in
a
q
u
ick
m
o
m
e
n
t
to
a
v
o
id
lo
n
g
d
u
ra
ti
o
n
sh
u
t
-
d
o
w
n
.
I
n
th
is
p
a
p
e
r,
a
b
o
il
e
r
f
a
u
lt
p
re
d
ict
io
n
m
o
d
e
l
is
p
ro
p
o
se
d
u
si
n
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
.
T
h
e
k
e
y
in
f
lu
e
n
ti
a
l
p
a
ra
m
e
ters
a
n
a
ly
sis
is
c
a
rried
o
u
t
to
id
e
n
ti
f
y
it
s
c
o
rre
latio
n
w
it
h
th
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
b
o
il
e
r.
T
h
e
p
re
d
ictio
n
m
o
d
e
l
is
d
e
v
e
lo
p
e
d
t
o
a
c
h
iev
e
th
e
lea
st
m
is
c
las
si
f
ica
ti
o
n
ra
te
a
n
d
m
e
a
n
sq
u
a
re
d
e
rro
r.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
is
train
e
d
u
si
n
g
a
se
t
o
f
b
o
il
e
r
o
p
e
ra
ti
o
n
a
l
p
a
ra
m
e
t
e
rs.
S
u
b
se
q
u
e
n
lt
y
,
th
e
train
e
d
m
o
d
e
l
is
u
se
d
to
v
a
li
d
a
te
it
s
p
re
d
ictio
n
a
c
c
u
ra
c
y
a
g
a
in
st
a
c
tu
a
l
fa
u
lt
v
a
lu
e
f
ro
m
a
c
o
ll
e
c
ted
re
a
l
p
lan
t
d
a
ta.
W
it
h
re
f
e
re
n
c
e
to
th
e
stu
d
y
a
n
d
t
e
st
re
su
lt
s,
tw
o
se
t
o
f
in
it
ial
w
e
i
g
h
ts
h
a
v
e
b
e
e
n
tes
ted
to
v
e
rify
th
e
re
p
e
a
tab
il
it
y
o
f
th
e
c
o
rre
c
t
p
re
d
ictio
n
.
T
h
e
re
su
lt
s
sh
o
w
th
a
t
t
h
e
a
rti
f
icia
l
n
e
u
r
a
l
n
e
tw
o
rk
im
p
le
m
e
n
ted
is
a
b
le
to
p
ro
v
id
e
a
n
a
v
e
r
a
g
e
o
f
a
b
o
v
e
9
2
%
p
re
d
icti
o
n
ra
te
o
f
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
C
o
al
-
f
ir
ed
p
o
w
er
p
lan
t b
o
iler
Fau
lt p
r
ed
ictio
n
Mu
lti la
y
er
ed
p
er
ce
p
tr
o
n
R
esil
ie
n
t b
ac
k
p
r
o
p
ag
atio
n
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
All
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
n
g
N
u
r
n
ie
Mo
h
d
Nis
ta
h
,
Dep
ar
t
m
en
t o
f
Fo
u
n
d
atio
n
o
f
Scien
ce
&
E
n
g
i
n
ee
r
in
g
,
C
u
r
ti
n
U
n
i
v
er
s
it
y
Ma
la
y
s
ia
,
Ma
la
y
s
ia.
E
m
ail: E
m
ail:
n
o
n
g
.
n
u
r
n
ie
@
c
u
r
tin
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
a
lar
g
e
co
al
-
f
ir
ed
p
o
w
er
p
l
an
t,
e
f
f
ec
ti
v
e
eq
u
ip
m
e
n
t
m
o
n
i
to
r
in
g
a
n
d
co
n
tr
o
l
s
tr
ate
g
ies
a
r
e
cr
u
cial
to
av
o
id
a
ca
ta
s
tr
o
p
h
ic
ac
cid
e
n
t.
I
n
e
x
is
t
in
g
s
y
s
te
m
s
,
h
i
s
to
r
ical
d
ata
ar
e
u
s
ed
m
ai
n
l
y
f
o
r
m
o
n
ito
r
i
n
g
,
co
n
tr
o
l
an
d
o
v
er
-
l
i
m
it
alar
m
;
b
u
t
n
o
t
f
o
r
f
a
u
lt
p
r
ed
ictio
n
o
r
d
iag
n
o
s
is
[
1
]
.
Fu
r
th
er
m
o
r
e,
co
al
-
f
ir
ed
p
o
w
er
p
lan
t
b
o
iler
(
C
FB
)
u
n
its
h
a
v
e
co
m
p
le
x
c
h
ar
ac
ter
is
tic
s
an
d
m
ec
h
an
i
s
m
s
d
u
e
to
it
s
h
ig
h
te
m
p
er
atu
r
e
an
d
h
i
g
h
p
r
ess
u
r
e
ch
ar
ac
ter
is
tic
s
.
T
h
e
m
o
s
t
co
m
m
o
n
t
y
p
es
o
f
f
a
u
lts
r
elate
d
to
b
o
iler
in
co
al
-
f
ir
ed
p
o
w
e
r
p
lan
t
i
n
cl
u
d
e
as
h
d
ep
o
s
it
f
o
u
lin
g
an
d
s
la
g
g
in
g
[
2
]
-
[
5
]
,
a
b
n
o
r
m
al
h
i
g
h
s
u
p
er
h
ea
ter
in
let
te
m
p
er
atu
r
e
r
ea
d
in
g
,
ab
n
o
r
m
a
l
te
m
p
er
atu
r
e
o
f
t
h
e
f
lu
e
g
as a
n
d
th
e
b
o
iler
’
s
p
r
ess
u
r
e
r
ea
d
in
g
d
u
r
in
g
d
ep
r
ess
u
r
izatio
n
b
e
f
o
r
e
s
tar
t u
p
[
6
]
.
T
h
e
m
o
s
t
co
m
m
o
n
tech
n
iq
u
es
in
d
ev
elo
p
in
g
a
p
o
w
er
p
lan
t
s
y
s
te
m
s
i
n
v
o
l
v
e
m
at
h
e
m
atica
l
o
r
ca
u
s
al
m
o
d
el
s
,
d
ata
m
i
n
i
n
g
an
d
ar
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN
)
ap
p
r
o
ac
h
[
1
]
,
[
7
]
-
[
1
3
]
.
T
h
e
b
asi
c
id
ea
o
f
m
o
d
elli
n
g
is
to
ap
p
r
o
x
i
m
ate
t
h
e
r
ea
l
g
eo
m
e
tr
y
to
an
id
ea
l
g
eo
m
etr
y
w
it
h
an
as
s
u
m
p
tio
n
th
at
t
h
e
v
alu
es
ar
e
p
er
f
ec
t
o
r
ac
cu
r
ate.
I
t
in
tr
o
d
u
ce
s
u
n
ce
r
tain
tie
s
b
ec
au
s
e
all
th
e
m
ater
ial
p
r
o
p
e
r
ties
ar
e
d
ep
en
d
en
t
o
n
t
h
e
in
s
i
g
h
t
s
an
d
t
h
e
r
ig
h
t
s
elec
tio
n
o
f
th
e
co
n
s
ta
n
t
p
r
o
p
er
ty
v
al
u
es
o
f
t
h
e
ac
tu
a
l
eq
u
ip
m
e
n
t
u
n
d
er
s
t
u
d
y
[
1
4
]
.
R
am
ad
h
a
s
et
a
l
.
[
1
5
]
co
n
clu
d
ed
th
a
t
r
es
u
lts
f
r
o
m
t
h
eir
th
eo
r
etica
l
m
o
d
el
o
f
t
h
e
c
o
m
p
lete
co
m
b
u
s
tio
n
s
t
u
d
ies
f
o
r
a
b
io
d
iesel f
u
elled
en
g
i
n
e
w
er
e
p
r
o
v
ed
to
b
e
r
e
liab
le
an
d
ad
eq
u
ate,
alt
h
o
u
g
h
i
n
g
e
n
er
al
it
is
s
ti
ll
d
i
f
f
ic
u
lt
to
attai
n
ac
t
u
al
co
m
p
lete
co
m
b
u
s
tio
n
.
T
h
is
i
s
d
u
e
to
t
h
e
f
ac
t
th
at
t
h
eir
ap
p
r
o
ac
h
is
b
ased
o
n
t
h
e
n
u
m
e
r
ical
ca
lcu
lat
io
n
o
f
m
as
s
,
m
o
m
e
n
t
u
m
a
n
d
en
er
g
y
eq
u
atio
n
s
in
eit
h
er
o
n
e,
t
w
o
o
r
th
r
ee
d
im
en
s
io
n
s
to
f
o
llo
w
th
e
p
r
o
p
ag
atio
n
o
f
f
la
m
e
o
r
co
m
b
u
s
t
io
n
f
r
o
n
t
with
i
n
t
h
e
e
n
g
i
n
e
co
m
b
u
s
t
io
n
ch
a
m
b
er
.
W
h
er
ea
s
,
A
NN
ap
p
r
o
ac
h
h
as
a
h
i
g
h
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:
2
0
8
8
-
8708
A
N
N
to
P
r
ed
ict
C
o
a
l
-
F
ir
ed
B
o
iler
F
a
u
lt
u
si
n
g
B
o
iler
Op
era
tio
n
a
l
…
(
N
o
n
g
N
u
r
n
ie
Mo
h
d
N
is
ta
h
)
2487
d
eg
r
ee
o
f
f
au
lt
to
ler
an
ce
an
d
h
ig
h
p
r
o
ce
s
s
i
n
g
s
p
ee
d
b
ec
au
s
e
o
f
its
s
i
m
p
li
f
ied
co
n
n
ec
tio
n
s
w
h
ile
d
ea
l
in
g
w
it
h
co
m
p
le
x
ca
lc
u
latio
n
s
[
7
]
.
T
h
is
i
s
o
b
tain
ed
w
it
h
h
i
g
h
a
cc
u
r
a
cy
w
it
h
o
u
t
th
e
u
s
e
o
f
tech
n
icall
y
ad
v
an
ce
d
ev
elo
p
ed
s
o
f
t
w
ar
e
[
1
6
]
.
Mo
r
eo
v
er
,
A
NN
is
ab
le
to
lear
n
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
s
elec
ted
i
n
p
u
t
a
n
d
o
u
tp
u
t
t
h
r
o
u
g
h
a
p
r
o
ce
s
s
k
n
o
w
n
as
n
e
t
w
o
r
k
tr
ai
n
in
g
.
T
h
is
ap
p
r
o
ac
h
allo
w
s
u
s
er
to
t
est
an
d
ex
p
lo
r
e
th
e
s
i
m
u
lat
io
n
f
a
s
ter
an
d
ea
s
ier
.
T
o
en
s
u
r
e
th
a
t
th
e
A
NN
m
o
d
el
is
r
ea
d
y
to
b
e
d
ep
lo
y
ed
,
it
is
f
i
r
s
t
v
alid
ated
u
s
i
n
g
u
n
s
ee
n
d
ata
to
co
m
p
ar
e
its
ac
c
u
r
ac
y
o
f
t
h
e
o
u
tp
u
t a
g
ai
n
s
t th
e
ac
tu
al
o
u
tp
u
t v
al
u
e
[
3
]
.
T
h
er
e
ar
e
a
g
r
ea
t
n
u
m
b
er
o
f
s
t
u
d
ies
ca
r
r
ied
o
u
t
i
m
p
le
m
e
n
ti
n
g
A
NN
i
n
p
r
ed
ictio
n
an
d
r
ep
li
ca
tin
g
th
e
b
eh
av
io
r
o
f
an
e
n
er
g
y
g
en
er
at
io
n
p
lan
t
b
o
iler
.
On
e
o
f
t
h
e
m
o
s
t
r
e
s
ea
r
ch
ed
ar
ea
s
i
n
clu
d
e
f
a
u
lt
d
etec
tio
n
a
n
d
class
i
f
icatio
n
o
f
a
p
o
w
er
tr
an
s
m
is
s
io
n
li
n
e
to
p
r
o
v
id
e
q
u
ick
r
esp
o
n
d
ti
m
e
w
h
ile
av
o
id
in
g
a
tr
ip
o
cc
u
r
an
ce
in
th
e
cir
c
u
it
b
r
ea
k
er
b
et
w
ee
n
its
s
u
b
s
tatio
n
s
[
1
7
]
,
[
1
8
]
.
A
s
f
o
r
a
p
o
w
er
p
lan
t
f
au
l
t
d
iag
n
o
s
i
s
,
an
A
N
N
ap
p
r
o
ac
h
is
i
n
teg
r
ated
w
i
th
an
ex
p
er
t
s
y
s
te
m
i
n
ter
f
ac
e
to
i
m
p
r
o
v
e
t
h
e
s
y
s
te
m
’
s
o
v
er
all
p
er
f
o
r
m
a
n
ce
[
1
9
]
,
[
2
0
]
.
I
n
th
e
late
9
0
s
,
a
p
r
ed
ictiv
e
co
n
tr
o
ller
h
as
b
ee
n
d
er
iv
ed
f
r
o
m
a
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
b
ased
n
o
n
li
n
ea
r
alg
o
r
it
h
m
t
h
at
p
r
o
v
id
es
an
o
f
f
s
et
f
r
ee
c
lo
s
ed
lo
o
p
b
eh
av
io
r
f
o
r
a
t
h
er
m
al
p
o
w
er
p
lan
t
co
n
tr
o
l
[
2
1
]
.
A
s
tu
d
y
w
as
ca
r
r
ied
o
u
t
to
s
i
m
u
late
th
e
e
v
o
lu
t
io
n
o
f
b
o
iler
h
ea
t
ab
s
o
r
p
tio
n
u
n
d
er
r
ea
lis
tic
co
n
d
itio
n
o
f
th
e
as
h
d
ep
o
s
itio
n
in
a
co
al
f
ir
ed
b
o
iler
u
s
in
g
A
NN
[
2
]
.
An
o
th
er
w
o
r
k
b
y
[
1
6
]
r
ep
o
r
t
ed
h
o
w
A
NN
w
as
d
e
v
elo
p
ed
to
m
o
n
i
to
r
b
o
iler
’
s
b
eh
av
io
r
an
d
ev
al
u
ate
t
h
e
b
io
m
as
s
f
o
u
li
n
g
a
s
a
m
ea
n
o
f
i
m
p
r
o
v
in
g
th
e
e
x
is
t
in
g
b
o
iler
m
o
n
ito
r
in
g
tec
h
n
iq
u
e.
Me
an
w
h
ile
i
n
a
m
o
r
e
r
ec
en
t
w
o
r
k
b
y
S
m
r
e
k
ar
et
a
l
.
[
2
2
]
,
an
A
NN
w
a
s
d
ev
elo
p
ed
to
p
r
ed
ict
f
r
esh
s
tea
m
p
r
o
p
er
ties
f
o
r
s
u
itab
le
c
o
m
b
i
n
atio
n
o
f
i
n
p
u
t
p
ar
a
m
ete
r
s
.
I
n
th
e
ir
w
o
r
k
,
th
e
y
w
er
e
a
b
le
to
id
en
tify
t
h
r
ee
h
ig
h
i
m
p
ac
t
in
p
u
t
p
ar
a
m
eter
s
th
at
allo
w
s
t
h
e
m
to
ac
h
iev
e
a
cc
ep
tab
le
ac
cu
r
ac
y
.
T
h
e
p
ar
am
eter
s
i
n
cl
u
d
e
m
as
s
f
lo
w
r
ate
o
f
co
al,
w
h
ic
h
is
d
e
p
en
d
en
t
o
n
t
h
e
b
elt
co
n
v
e
y
o
r
s
p
ee
d
,
v
alv
e
o
p
en
i
n
g
s
o
f
t
h
e
s
tea
m
l
in
e
a
n
d
th
e
f
ee
d
w
ater
p
r
ess
u
r
e.
R
u
s
i
n
o
wsk
i
e
t
a
l
.
[
2
3
]
d
ev
elo
p
ed
an
ANN
m
o
d
el
to
m
ap
t
h
e
i
n
f
l
u
e
n
ce
o
f
f
lu
e
g
a
s
lo
s
s
e
s
an
d
en
er
g
y
lo
s
s
e
s
d
u
e
to
u
n
b
u
r
n
ed
co
m
b
u
s
tib
les
o
n
t
h
e
m
ai
n
o
p
er
atio
n
al
p
ar
am
e
ter
s
o
f
th
e
b
o
iler
.
T
h
e
d
ev
elo
p
ed
m
o
d
el
w
as
ab
le
to
co
n
f
ir
m
t
h
at
t
h
e
a
ir
ex
ce
s
s
r
atio
an
d
f
l
u
e
g
as
te
m
p
er
at
u
r
e
e
x
er
t
a
d
o
m
i
n
a
n
t
in
f
lu
e
n
ce
u
p
o
n
th
e
f
l
u
e
g
as
lo
s
s
es.
O
v
er
th
e
p
a
s
t
d
ec
ad
e,
th
ese
s
t
u
d
ies
h
av
e
s
h
o
w
n
t
h
e
ca
p
ab
ilit
y
o
f
a
n
A
NN
as a
to
o
l in
en
er
g
y
p
r
ed
ictio
n
an
d
m
o
d
ellin
g
.
T
h
is
p
ap
er
in
v
es
tig
a
te
s
t
h
e
u
s
e
o
f
an
A
NN
w
it
h
a
s
p
ec
if
i
c
s
et
o
f
p
ar
a
m
eter
s
to
p
r
ed
ict
th
e
b
o
iler
f
au
lt
y
co
n
d
itio
n
i
n
a
co
al
-
f
ir
ed
p
o
w
er
p
la
n
t
an
d
r
ep
o
r
t
th
e
f
in
d
in
g
s
w
it
h
t
h
e
s
u
p
p
o
r
t
o
f
ex
is
t
in
g
liter
atu
r
e
.
T
h
e
o
u
tco
m
e
o
f
t
h
i
s
s
i
m
u
lat
io
n
w
i
ll
b
e
u
s
ed
as
p
ar
t
o
f
an
o
n
g
o
i
n
g
s
t
u
d
y
i
n
d
ev
e
lo
p
in
g
an
i
n
t
ellig
e
n
t
m
o
n
ito
r
in
g
s
y
s
te
m
in
ter
f
ac
e
f
o
r
a
p
o
w
er
p
lan
t
b
o
iler
co
n
d
itio
n
m
o
n
i
to
r
in
g
.
T
h
i
s
p
ap
er
is
d
iv
id
ed
in
t
o
t
w
o
s
ec
t
io
n
s
.
T
h
e
f
ir
s
t
s
ec
tio
n
w
ill
b
e
a
b
r
ief
d
i
s
cu
s
s
io
n
o
n
t
h
e
u
s
e
o
f
Mu
l
ti
-
la
y
er
ed
P
er
ce
p
tr
o
n
(
ML
P
)
in
A
N
N.
T
h
en
,
in
th
e
s
ec
o
n
d
s
ec
t
io
n
;
th
e
i
n
v
e
s
ti
g
at
io
n
o
f
t
h
e
i
m
p
le
m
en
ted
m
o
d
el
ar
e
d
is
c
u
s
s
ed
to
r
ep
o
r
t
th
e
p
r
ed
ictio
n
o
u
tco
m
e
an
d
p
er
f
o
r
m
an
ce
.
2.
M
UL
T
I
-
L
AY
E
R
E
D
P
E
RC
E
P
T
RO
NS (
M
L
P
)
NE
URAL
NE
T
WO
RK
On
e
o
f
t
h
e
m
o
s
t
w
ell
d
o
cu
m
e
n
ted
a
n
d
f
r
eq
u
e
n
tl
y
u
s
ed
t
y
p
e
s
o
f
ANN
i
s
M
L
P
[
2
4
]
.
An
M
L
P
is
a
f
ee
d
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
co
n
s
i
s
tin
g
o
f
a
n
u
m
b
er
o
f
n
e
u
r
o
n
s
co
n
n
ec
ted
b
y
w
ei
g
h
ted
li
n
k
s
.
T
h
e
n
eu
r
o
n
s
ar
e
o
r
g
an
ized
in
s
e
v
er
al
la
y
er
s
,
n
a
m
el
y
th
e
i
n
p
u
t
la
y
er
,
h
id
d
en
l
a
y
er
(
s
)
an
d
o
u
tp
u
t
la
y
er
.
An
e
x
a
m
p
le
o
f
a
t
y
p
ical
o
n
e
h
id
d
en
l
a
y
er
M
L
P
is
illu
s
t
r
ated
in
Fig
u
r
e
1
.
A
s
ill
u
s
tr
ate
d
in
Fig
u
r
e
1
,
th
e
in
p
u
t
la
y
er
r
ec
eiv
es
a
n
ex
ter
n
al
ac
tiv
atio
n
v
ec
to
r
,
an
d
p
ass
e
s
it
th
r
o
u
g
h
th
e
w
eig
h
ted
co
n
n
ec
tio
n
s
(
W
ij
)
o
f
t
h
e
n
e
u
r
o
n
s
i
n
th
e
h
id
d
en
la
y
er
.
T
h
is
p
r
o
ce
s
s
co
m
p
u
tes
t
h
eir
a
ctiv
atio
n
s
(
W
kj
)
a
n
d
p
ass
e
s
t
h
e
m
to
n
e
u
r
o
n
s
i
n
s
u
cc
ee
d
i
n
g
la
y
er
s
u
n
til
it r
ea
c
h
es
th
e
o
u
tp
u
t
la
y
er
[
2
5
]
.
B
asicall
y
,
t
h
e
i
n
p
u
t
v
ec
to
r
is
p
r
o
p
ag
ated
f
o
r
w
ar
d
t
h
r
o
u
g
h
th
e
n
et
w
o
r
k
p
r
o
d
u
ci
n
g
a
n
ac
tiv
atio
n
v
ec
to
r
in
t
h
e
o
u
tp
u
t
la
y
er
at
th
e
e
n
d
o
f
th
e
p
r
o
ce
s
s
.
T
h
e
m
ap
p
in
g
o
f
i
n
p
u
t
v
ec
to
r
o
n
to
o
u
tp
u
t
v
ec
to
r
is
in
f
ac
t d
eter
m
i
n
ed
b
y
t
h
e
co
n
n
ec
t
io
n
w
ei
g
h
ts
o
f
t
h
e
n
e
t.
Fig
u
r
e
1
.
A
to
p
o
lo
g
y
o
f
a
g
en
er
al
ML
P
w
it
h
o
n
e
h
id
d
en
la
y
er
X
1
X
2
X
32
V
1
V
32
I
n
p
u
t
Y
Ou
tp
u
t
W
ij
W
kj
V
2
Hid
d
en
.
.
.
.
.
.
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.
8
,
No
.
4
,
A
u
g
u
s
t
2018
:
2
4
8
6
–
2
4
9
3
2488
T
ab
le
1
.
I
n
p
u
t p
ar
am
eter
s
d
ata
d
escr
ip
tio
n
I
n
p
u
t
p
a
ram
et
e
rs
D
at
a
s
e
t
d
e
s
cr
i
p
t
i
o
n
U
n
i
t
T
e
mp
e
r
a
t
u
r
e
•
B
o
i
l
e
r
r
e
-
h
e
a
t
e
r
a
n
d
s
u
p
e
r
h
e
a
t
e
r
i
n
l
e
t
/
o
u
t
l
e
t
a
n
d
e
x
c
h
a
n
g
e
me
t
a
l
t
e
mp
e
r
a
t
u
r
e
•
Ec
o
n
o
mi
z
e
r
i
n
l
e
t
/
o
u
t
l
e
t
t
e
mp
e
r
a
t
u
r
e
°
C
P
r
e
ssu
r
e
•
B
o
i
l
e
r
d
r
u
m
p
r
e
ssu
r
e
•
S
u
p
e
r
h
e
a
t
e
d
st
e
a
m
p
r
e
ssu
r
e
•
C
i
r
c
u
l
a
t
i
o
n
p
u
m
p
p
r
e
ssu
r
e
•
T
e
mp
e
r
a
t
u
r
e
a
n
d
st
e
a
m o
u
t
l
e
t
p
r
e
ss
u
r
e
•
Ec
o
n
o
mi
z
e
r
i
n
l
e
t
p
r
e
ssu
r
e
Bar
F
l
o
w
r
a
t
e
•
S
t
e
a
m fl
o
w
•
F
e
e
d
w
a
t
e
r
f
l
o
w
•
S
u
p
e
r
h
e
a
t
e
r
w
a
t
e
r
i
n
j
e
c
t
i
o
n
c
o
m
p
e
n
sa
t
e
d
f
l
o
w
T
o
n
/
h
r
On
e
o
f
th
e
m
ai
n
co
m
p
o
n
en
t
s
o
f
a
n
M
L
P
is
t
h
e
tr
ai
n
in
g
alg
o
r
ith
m
.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
e
tr
ain
i
n
g
alg
o
r
ith
m
is
to
f
i
n
d
th
e
ap
p
r
o
x
i
m
ate
s
o
lu
t
io
n
s
to
m
i
n
i
m
ized
er
r
o
r
s
[
2
4
]
.
Fr
o
m
e
x
is
ti
n
g
lite
r
atu
r
es
[
2
6
]
-
[
2
8
]
,
it
is
ev
id
en
t
th
at
t
h
e
m
o
s
t
co
m
m
o
n
tr
ain
i
n
g
al
g
o
r
ith
m
s
u
s
ed
f
o
r
A
NN
m
o
d
el
p
r
ed
ictio
n
an
d
f
o
r
ec
asti
n
g
ar
e
th
e
g
r
ad
ien
t
d
escen
t
m
et
h
o
d
s
class
o
f
alg
o
r
it
h
m
.
O
n
e
o
f
th
e
p
r
ef
er
r
ed
alg
o
r
ith
m
s
o
f
t
h
is
class
,
in
ter
m
s
o
f
co
n
v
er
g
e
n
ce
s
p
ee
d
,
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
es
s
w
it
h
r
esp
ec
t
to
its
lear
n
in
g
p
ar
a
m
eter
s
,
is
th
e
R
esil
ien
t
B
ac
k
p
r
o
p
ag
atio
n
(
R
P
r
o
p
)
alg
o
r
ith
m
in
tr
o
d
u
ce
d
b
y
[
2
8
]
.
T
h
e
b
asic
p
r
in
cip
le
o
f
R
P
r
o
p
is
t
h
e
d
ir
ec
t
ad
ap
tatio
n
o
f
t
h
e
w
ei
g
h
t
u
p
d
ate
v
al
u
es
W
ij
.
I
t
m
o
d
if
ies
t
h
e
s
ize
o
f
th
e
w
ei
g
h
t
s
tep
d
ir
ec
tl
y
b
y
i
n
tr
o
d
u
cin
g
th
e
co
n
ce
p
t
o
f
r
esil
ien
t
u
p
d
ate
v
al
u
e
s
.
T
h
is
r
esu
lt
s
i
n
a
n
ad
ap
tatio
n
e
f
f
o
r
t
t
h
at
i
s
n
o
t
d
is
to
r
ted
b
y
a
n
u
n
f
o
r
eseea
b
le
g
r
ad
ien
t
b
eh
av
io
r
[
2
5
]
.
I
n
th
is
p
ap
er
,
th
e
A
NN
m
o
d
el
w
ill
u
s
e
R
P
r
o
p
as
th
e
tr
ai
n
in
g
al
g
o
r
ith
m
f
o
r
th
is
s
i
m
u
latio
n
f
o
r
th
e
b
o
iler
f
au
l
t p
r
ed
ictio
n
.
3.
B
O
I
L
E
R
O
P
E
RAT
I
O
NA
L
P
ARAM
E
T
E
RS
Gen
er
all
y
,
a
p
h
y
s
ical
m
o
d
el
r
eq
u
ir
es
an
ex
ac
t
n
u
m
b
er
o
f
p
a
r
a
m
eter
s
v
al
u
es
f
o
r
ca
lcu
latio
n
s
.
Hen
ce
,
th
e
ch
o
ice
s
ar
e
d
ictated
b
y
th
e
eq
u
atio
n
r
ep
r
esen
ti
n
g
t
h
e
p
r
o
ce
s
s
es
i
n
v
o
l
v
ed
.
T
h
is
li
m
it
s
th
e
ch
o
ice
o
f
i
n
p
u
t
an
d
o
u
tp
u
t
p
ar
a
m
eter
s
b
y
t
h
e
―
ca
u
s
e
an
d
ef
f
ec
t‖
r
elatio
n
s
[
2
2
]
.
Un
lik
e
a
p
h
y
s
ical
m
o
d
el,
th
e
in
p
u
t
an
d
o
u
tp
u
t
p
ar
am
eter
s
in
A
NN
m
o
d
ellin
g
ar
e
m
o
s
tl
y
s
elec
ted
o
n
th
e
b
asis
o
f
th
e
o
b
j
ec
tiv
e
o
f
th
e
m
o
d
ell
in
g
an
d
t
h
e
b
o
iler
’
s
o
p
er
ato
r
s
’
ex
p
er
ien
ce
.
I
n
f
ac
t,
th
e
in
p
u
t
p
ar
am
e
ter
s
ar
e
u
s
u
all
y
o
p
ti
m
ized
to
co
m
p
r
o
m
is
e
b
et
w
ee
n
t
h
e
n
u
m
b
er
o
f
p
ar
am
eter
s
an
d
th
e
d
esire
d
ac
cu
r
ac
y
o
f
th
e
A
NN
p
r
ed
ictio
n
.
T
h
e
f
in
al
s
et
o
f
in
p
u
t
p
ar
am
eter
s
w
a
s
d
ef
in
ed
o
n
th
e
b
a
s
is
o
f
o
b
s
e
r
v
atio
n
s
r
elate
d
o
n
l
y
to
t
h
e
b
o
iler
u
n
it,
ad
v
ice
an
d
f
ee
d
b
ac
k
f
r
o
m
t
h
e
p
lan
t
o
p
er
ato
r
,
r
em
o
v
al
o
f
p
ar
a
m
et
er
s
th
at
h
as
n
o
n
-
e
f
f
ec
t
iv
e
f
a
cto
r
s
o
n
th
e
f
au
lt
y
s
ce
n
ar
io
an
d
an
y
r
ed
u
n
d
a
n
t
r
ea
d
in
g
s
f
r
o
m
t
h
e
s
a
m
e
s
e
n
s
o
r
s
[
2
9
]
.
T
h
e
in
p
u
t p
ar
a
m
eter
s
a
n
d
th
eir
d
ataset
d
escr
ip
tio
n
ar
e
lis
ted
in
T
ab
le
1
.
T
h
e
p
ar
am
eter
s
lis
ted
ar
e
i
m
p
o
r
tan
t
to
m
o
n
ito
r
th
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
o
f
th
e
b
o
iler
.
P
r
i
m
ar
il
y
,
t
h
e
te
m
p
er
atu
r
e
o
f
t
h
e
s
tea
m
p
r
o
d
u
ce
d
in
t
h
e
b
o
iler
is
d
ep
en
d
an
t
o
n
th
e
s
u
p
er
h
ea
ter
an
d
r
e
h
ea
ter
to
r
ea
ch
it
s
o
p
ti
m
u
m
te
m
p
er
at
u
r
e
b
ef
o
r
e
it
is
tr
an
s
f
er
r
ed
to
th
e
t
u
r
b
in
e
.
T
h
er
ef
o
r
e,
th
e
w
ater
s
u
p
p
l
y
an
d
f
u
e
l
f
lo
w
r
ate
lead
in
g
to
t
h
e
b
u
r
n
er
n
ee
d
to
b
e
at
th
e
r
ig
h
t
p
r
es
s
u
r
e
a
n
d
t
e
m
p
er
atu
r
e
le
v
el
to
p
r
o
v
id
e
t
h
e
e
x
ac
t
a
m
o
u
n
t
o
f
co
m
b
u
s
t
io
n
f
o
r
th
e
s
tea
m
p
r
o
d
u
ctio
n
.
L
i
k
e
w
i
s
e,
th
e
w
ater
leav
in
g
t
h
e
h
i
g
h
p
r
ess
u
r
e
f
ee
d
w
ater
h
ea
ter
n
ee
d
ed
to
b
e
r
aised
to
r
ea
ch
th
e
s
at
u
r
atio
n
te
m
p
er
at
u
r
e
to
co
r
r
esp
o
n
d
to
th
e
b
o
iler
d
r
u
m
p
r
ess
u
r
e
as
a
s
af
et
y
m
ea
s
u
r
e.
T
h
is
is
ac
h
ie
v
ed
th
r
o
u
g
h
t
h
e
ec
o
n
o
m
izer
b
y
ex
c
h
a
n
g
i
n
g
h
ea
t
w
it
h
th
e
g
as
leav
in
g
t
h
e
s
u
p
er
h
ea
ter
in
th
e
te
m
p
er
atu
r
e
a
n
d
p
r
ess
u
r
e
i
n
l
et
an
d
o
u
tlet
t
u
b
e
u
p
to
t
h
e
s
tack
.
He
n
ce
,
a
s
u
m
m
ar
y
o
f
th
e
d
atase
t
th
a
t
co
r
r
esp
o
n
d
s
to
th
e
te
m
p
er
atu
r
e,
p
r
ess
u
r
e
an
d
f
lo
w
r
ate
o
f
t
h
e
b
o
iler
ef
f
icie
n
c
y
ar
e
id
en
ti
f
i
ed
in
T
ab
le
1
.
Nex
t
s
tep
is
to
f
ee
d
th
e
s
e
lecte
d
p
ar
am
eter
d
ata
to
th
e
n
et
w
o
r
k
f
o
r
s
i
m
u
latio
n
.
Firstl
y
,
i
t
is
k
n
o
w
n
th
at
t
h
e
s
tar
ti
n
g
v
al
u
e
s
o
f
t
h
e
w
ei
g
h
ts
i
n
a
n
et
w
o
r
k
h
av
e
a
s
i
g
n
i
f
ica
n
t
e
f
f
ec
t
o
n
t
h
e
tr
ai
n
in
g
p
r
o
ce
s
s
[
3
0
]
,
[
3
1
]
.
A
c
h
ie
v
in
g
t
h
i
s
r
eq
u
ir
es
co
o
r
d
in
atio
n
b
et
w
ee
n
t
h
e
tr
ai
n
i
n
g
s
et
n
o
r
m
aliza
tio
n
,
t
h
e
ch
o
ice
o
f
tr
ain
in
g
f
u
n
ctio
n
an
d
th
e
ch
o
ice
o
f
w
ei
g
h
t
i
n
iti
aliza
tio
n
.
T
o
ev
alu
ate
h
o
w
m
u
ch
in
f
l
u
e
n
ce
ea
ch
ass
u
m
ed
i
n
itial
w
eig
h
t
s
h
as
o
n
th
e
o
u
tp
u
t
an
d
t
h
er
eb
y
to
id
en
ti
f
y
t
h
e
b
est
in
itial
w
eig
h
t
f
o
r
t
h
e
s
i
m
u
la
tio
n
,
a
s
e
n
s
it
iv
it
y
a
n
al
y
s
i
s
w
a
s
p
er
f
o
r
m
ed
.
T
h
e
f
ir
s
t
i
n
i
tia
l
s
e
t
o
f
t
h
e
w
ei
g
h
t
(
W
1
)
v
al
u
e
w
a
s
s
et
to
ze
r
o
a
n
d
t
h
e
s
ec
o
n
d
i
n
itial
s
e
t
o
f
w
ei
g
h
ts
(
W
2
)
is
a
p
r
e
-
s
elec
ted
an
d
r
a
n
d
o
m
ized
v
al
u
e
s
e
t.
T
h
ese
weig
h
ts
ar
e
ap
p
lied
to
th
e
s
a
m
e
s
elec
ted
d
ata
s
et
i
n
o
r
d
er
t
o
ex
a
m
i
n
e
h
o
w
m
u
c
h
i
t
ch
an
g
ed
th
e
ac
c
u
r
ac
y
o
f
t
h
e
m
is
cla
s
s
i
f
ied
r
ate
(
MC
R
)
p
r
o
d
u
ce
d
w
h
en
u
s
i
n
g
R
P
r
o
p
.
T
h
e
tr
ain
in
g
an
d
te
s
ti
n
g
r
e
s
u
lt
ar
e
r
ec
o
r
d
ed
an
d
s
av
ed
ac
co
r
d
in
g
l
y
f
o
r
a
n
al
y
s
is
an
d
co
m
p
ar
is
o
n
.
I
n
o
r
d
er
t
o
co
m
p
ar
e
th
e
r
es
u
lt f
a
i
r
l
y
,
th
e
f
o
llo
w
in
g
cr
iter
ia
w
er
e
s
et:
a.
Data
n
o
r
m
a
lizatio
n
is
i
m
p
o
r
tan
t
to
a
v
o
id
b
ias
an
d
n
o
is
e
d
is
t
u
r
b
an
ce
s
.
Sin
ce
th
e
tar
g
et
o
u
t
p
u
t
is
s
et
to
b
e
eith
er
0
f
o
r
n
o
r
m
al
a
n
d
1
f
o
r
f
au
lt
y
;
all
t
h
e
s
a
m
p
le
d
ata
ar
e
n
o
r
m
alize
d
a
n
d
s
ca
led
to
b
e
b
et
w
ee
n
0
a
n
d
1
u
s
i
n
g
th
e
Mi
n
-
Ma
x
n
o
r
m
al
izat
io
n
m
et
h
o
d
E
q
u
atio
n
(
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:
2
0
8
8
-
8708
A
N
N
to
P
r
ed
ict
C
o
a
l
-
F
ir
ed
B
o
iler
F
a
u
lt
u
si
n
g
B
o
iler
Op
era
tio
n
a
l
…
(
N
o
n
g
N
u
r
n
ie
Mo
h
d
N
is
ta
h
)
2489
Data
n
o
r
m
alize
d
(
1
)
W
h
er
e
Ax
r
ep
r
esen
ts
t
h
e
o
r
ig
i
n
al
d
ata
v
al
u
e
b
ef
o
r
e
n
o
r
m
aliz
atio
n
b.
T
h
e
n
et
w
o
r
k
co
n
s
is
ts
o
f
3
la
y
er
s
;
in
p
u
t
la
y
er
,
o
n
e
h
id
d
en
la
y
er
an
d
o
n
e
o
u
tp
u
t
la
y
er
.
I
n
th
e
h
id
d
en
la
y
er
,
th
er
e
ar
e
3
2
h
id
d
en
n
eu
r
o
n
s
,
an
d
t
w
o
o
u
tp
u
t
v
alu
e
o
f
0
an
d
1
f
o
r
th
e
o
u
tp
u
t
la
y
er
.
T
h
e
n
u
m
b
er
o
f
iter
atio
n
s
f
o
r
ea
ch
ep
o
ch
is
s
et
to
5
0
0
an
d
ea
ch
d
ata
s
et
w
i
ll
b
e
tr
ain
ed
f
o
r
1
0
r
u
n
s
.
c.
T
h
e
s
elec
ted
tr
ain
i
n
g
al
g
o
r
ith
m
u
s
ed
f
o
r
th
i
s
s
i
m
u
latio
n
i
s
R
P
r
o
p
d
u
e
to
its
h
ig
h
s
p
ee
d
co
n
v
er
g
e
n
ce
,
ac
cu
r
ac
y
a
n
d
r
o
b
u
s
tn
e
s
s
.
B
y
s
etti
n
g
t
h
e
lear
n
in
g
r
ate
to
it
s
d
ef
au
lt
v
al
u
e
o
f
0
.
1
,
all
th
e
w
ei
g
h
ts
i
n
t
h
e
n
et
w
o
r
k
co
n
v
er
g
e
r
o
u
g
h
l
y
at
t
h
e
s
a
m
e
s
p
ee
d
.
d.
On
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
f
o
r
m
s
o
f
ac
ti
v
atio
n
f
u
n
ct
io
n
is
th
e
H
y
p
er
b
o
lic
tan
g
e
n
t
s
i
g
m
o
id
f
u
n
ctio
n
Eq
u
atio
n
(
2
)
.
T
h
is
f
u
n
ctio
n
is
s
elec
ted
b
ec
au
s
e
t
h
e
y
ar
e
m
o
r
e
lik
el
y
to
p
r
o
d
u
ce
o
u
tp
u
ts
th
a
t a
r
e
o
n
av
er
ag
e
clo
s
e
to
ze
r
o
[
3
2
]
.
(
2
)
e.
On
e
p
r
e
-
r
an
d
o
m
ized
d
ata
s
et
w
a
s
u
s
ed
f
o
r
ea
ch
A
NN
m
o
d
el.
T
h
is
is
to
en
s
u
r
e
th
at
t
h
e
s
a
m
e
d
ata
w
er
e
u
s
ed
i
n
tr
ai
n
in
g
a
n
d
test
i
n
g
.
T
h
is
p
r
o
v
id
ed
th
e
co
m
m
o
n
p
l
atf
o
r
m
f
o
r
co
m
p
ar
is
o
n
o
f
r
es
u
lts
f
o
r
d
if
f
er
e
n
t
in
itial
w
e
ig
h
t
s
s
et.
f.
T
h
e
s
am
e
p
r
o
p
o
r
tio
n
o
f
d
ata
f
o
r
tr
ain
in
g
,
an
d
test
i
n
g
w
a
s
u
s
ed
f
o
r
ea
ch
A
NN
(
7
0
%
tr
ain
i
n
g
a
n
d
3
0
%
test
i
n
g
)
.
g.
T
o
d
eter
m
in
e
t
h
e
m
i
n
i
m
u
m
d
i
f
f
er
en
ce
b
et
w
ee
n
t
h
e
an
s
w
er
o
f
th
e
o
u
tp
u
t
n
eu
r
o
n
Y
an
d
t
h
e
tar
g
et
v
alu
e
o
f
Z
,
t
h
e
m
in
i
m
iza
tio
n
o
f
th
e
er
r
o
r
u
s
in
g
Me
a
n
Sq
u
ar
ed
E
r
r
o
r
(
MSE
)
m
et
h
o
d
E
q
u
atio
n
(
3
)
is
u
s
ed
,
w
h
er
e
Z
j
is
th
e
tar
g
et
o
u
tp
u
t a
n
d
Yj
r
ep
r
esen
t
s
th
e
o
u
tp
u
t o
f
t
h
e
n
et
w
o
r
k
.
∑
(
)
(
3
)
h.
T
o
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
c
e
o
f
th
e
n
et
w
o
r
k
i
n
ac
h
ie
v
i
n
g
a
n
ac
ce
p
tab
le
ac
cu
r
ac
y
r
ate,
th
e
Miss
-
C
las
s
i
f
icatio
n
R
ate
(
MCR
)
s
h
o
w
n
i
n
Eq
u
atio
n
(
4
)
is
u
s
ed
w
h
er
e
T
P
r
ep
r
esen
ts
tr
u
e
p
o
s
itiv
e,
T
N
r
ep
r
esen
ts
tr
u
e
n
eg
a
tiv
e
a
n
d
T
S is
th
e
to
tal
n
u
m
b
er
o
f
s
a
m
p
l
es.
(
∑
∑
∑
)
(
4
)
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
I
n
t
h
is
p
ap
er
,
d
ata
f
r
o
m
a
lo
ca
l
th
er
m
al
p
o
w
er
p
lan
t
co
n
tai
n
in
g
1
2
8
6
tr
ain
i
n
g
d
ata
a
n
d
5
5
1
test
in
g
d
ata
ar
e
p
r
e
-
r
an
d
o
m
ized
a
n
d
n
o
r
m
al
ized
f
o
r
th
e
ANN
m
o
d
el
.
T
h
e
s
elec
ted
n
et
w
o
r
k
is
a
th
r
ee
la
y
er
M
L
P
w
it
h
3
2
in
p
u
t
p
ar
am
eter
s
an
d
t
w
o
t
ar
g
et
class
e
s
o
f
0
an
d
1
.
T
h
e
h
id
d
en
la
y
er
co
n
s
is
t
s
o
f
3
2
h
id
d
en
n
eu
r
o
n
s
an
d
a
s
ig
m
o
id
f
u
n
ctio
n
is
u
s
ed
a
s
th
e
ac
tiv
atio
n
f
u
n
ctio
n
.
M
A
T
L
A
B
p
lat
f
o
r
m
i
s
u
s
ed
to
co
n
d
u
c
t th
i
s
s
i
m
u
latio
n
i
n
a
2
.
2
0
GHz
I
n
tel® Co
r
e™
i5
-
5
2
0
0
U
C
P
U
w
ith
8
GB
R
A
M.
I
n
T
ab
le
2
,
th
e
n
et
w
o
r
k
s
i
m
u
latio
n
r
esu
l
t
i
m
p
le
m
en
tin
g
b
o
th
in
i
tial
w
ei
g
h
t
s
e
tu
p
s
f
o
r
W
1
an
d
W
2
ar
e
r
ep
o
r
ted
.
B
ased
o
n
th
e
r
esu
lt,
it
is
e
v
id
en
t
t
h
at
th
e
s
elec
ted
tr
ain
in
g
alg
o
r
it
h
m
(
R
P
r
o
p
)
w
as
ab
le
to
co
m
p
u
te
th
e
tr
ain
in
g
in
an
a
v
e
r
ag
e
o
f
1
.
4
2
m
ill
is
ec
o
n
d
s
f
o
r
5
0
0
iter
atio
n
s
u
s
i
n
g
W
1
.
Fro
m
t
h
e
o
b
s
er
v
atio
n
,
it
w
a
s
also
ab
le
to
ac
h
ie
v
e
t
h
e
h
ig
h
e
s
t
ac
c
u
r
ac
y
f
o
r
MSE
o
f
0
.
0
3
1
7
,
w
h
i
le
ac
h
iev
i
n
g
a
v
er
y
g
o
o
d
MC
R
o
f
3
.
5
3
%.
Me
an
w
h
ile,
w
h
en
th
e
in
itial
w
ei
g
h
t
W
2
w
as
ap
p
li
ed
,
th
e
tr
ain
i
n
g
r
es
u
lt
h
as
a
s
lig
h
t
i
m
p
r
o
v
e
m
e
n
t
.
B
ased
o
n
th
e
o
u
tco
m
e,
alt
h
o
u
g
h
it to
o
k
1
.
6
3
m
illi
s
ec
o
n
d
to
co
m
p
u
te;
t
h
e
M
SE
ac
h
ie
v
ed
is
0
.
0
2
5
4
an
d
it h
as
a
lo
w
er
m
is
cla
s
s
i
f
icatio
n
r
ate
o
f
2
.
7
1
%.
T
ab
le
2
.
T
r
ain
in
g
an
d
T
esti
n
g
R
es
u
lt
s
o
f
Mu
l
tila
y
er
P
er
ce
p
tr
o
n
Neu
r
al
Net
w
o
r
k
s
W
e
i
g
h
t
S
a
mp
l
e
M
S
E
M
i
s
c
l
a
ssi
f
i
e
d
r
a
t
e
T
r
a
i
n
i
n
g
r
e
su
l
t
W1
0
.
0
3
1
7
3
.
5
3
%
W2
0
.
0
2
5
4
2
.
7
1
%
T
e
st
i
n
g
r
e
su
l
t
W1
0
.
0
4
8
7
5
.
8
6
%
W2
0
.
0
4
9
1
6
.
0
6
%
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.
8
,
No
.
4
,
A
u
g
u
s
t
2018
:
2
4
8
6
–
2
4
9
3
2490
Fig
u
r
e
2
.
I
n
itial
w
ei
g
h
t
s
et
u
p
co
m
p
ar
is
o
n
f
o
r
t
h
e
f
a
u
lt p
r
ed
ictio
n
Fig
u
r
e
3
.
T
r
ain
in
g
r
esu
lt o
f
t
h
e
A
NN
m
o
d
el
u
s
in
g
W
2
T
o
ch
ec
k
f
o
r
th
e
b
est
p
ar
a
m
e
ter
s
etu
p
f
o
r
th
e
A
NN
in
t
h
is
in
v
e
s
ti
g
atio
n
,
th
e
te
s
ti
n
g
r
es
u
lts
o
f
t
h
e
s
a
m
e
d
ata
s
et
s
a
m
p
le
ar
e
also
r
ec
o
r
d
e
d
f
o
r
co
m
p
ar
is
o
n
.
A
lt
h
o
u
g
h
t
h
e
co
m
p
u
tatio
n
ti
m
e
r
e
co
r
d
ed
is
th
e
s
a
m
e
w
it
h
t
h
e
tr
ain
i
n
g
r
es
u
lt;
t
h
er
e
is
a
s
ig
n
i
f
ican
t
d
if
f
er
e
n
ce
in
t
h
e
MSE
an
d
MCR
r
ec
o
r
d
ed
.
T
h
e
test
in
g
s
a
m
p
le
f
o
r
W
1
p
r
o
d
u
ce
s
an
a
v
er
ag
e
o
f
0
.
0
4
8
7
f
o
r
its
MSE
w
i
th
a
v
er
y
s
m
all
d
i
f
f
er
en
ce
o
f
2
.
3
3
%
h
i
g
h
er
MC
R
o
f
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:
2
0
8
8
-
8708
A
N
N
to
P
r
ed
ict
C
o
a
l
-
F
ir
ed
B
o
iler
F
a
u
lt
u
si
n
g
B
o
iler
Op
era
tio
n
a
l
…
(
N
o
n
g
N
u
r
n
ie
Mo
h
d
N
is
ta
h
)
2491
5
.
8
6
%
co
m
p
ar
ed
to
t
h
e
tr
ai
n
i
n
g
o
u
tco
m
e
p
r
ese
n
ted
i
n
T
ab
le
2
f
o
r
W
1
.
Me
an
w
h
ile
a
s
m
all
d
if
f
er
e
n
ce
o
f
MSE
an
d
MC
R
v
al
u
e
is
r
ec
o
r
d
ed
w
h
e
n
th
e
i
n
itia
l
w
eig
h
t
s
ar
e
m
o
d
i
f
ied
u
s
i
n
g
W
2
,
an
a
v
er
ag
e
o
f
0
.
0
4
9
1
f
o
r
its
MSE
an
d
6
.
0
6
% M
C
R
r
esp
ec
t
iv
el
y
.
I
n
Fi
g
u
r
e
2
,
a
s
a
m
p
le
o
f
1
0
0
p
r
ed
icted
o
u
tp
u
t
w
er
e
ex
tr
ac
ted
f
r
o
m
a
co
n
ti
n
u
o
u
s
r
ec
o
r
d
ed
s
i
m
u
latio
n
o
f
1
2
8
6
s
im
u
lat
ed
d
ata
s
a
m
p
l
e
to
co
m
p
ar
e
th
e
m
ag
ai
n
s
t
th
e
ac
tu
al
m
ea
s
u
r
ed
o
u
tp
u
t.
Her
e,
th
e
in
it
ial
w
eig
h
t
f
o
r
W
2
s
h
o
w
s
a
b
etter
ac
c
u
r
a
c
y
r
ate
o
f
9
5
.
5
%
co
m
p
ar
ed
to
W
1
f
o
r
th
e
f
ir
s
t
1
0
0
s
a
m
p
le
o
f
1
m
i
n
u
te
i
n
ter
v
al
s
tr
ain
i
n
g
.
B
ased
o
n
t
h
e
f
a
u
lt
a
n
d
n
o
r
m
al
t
h
r
es
h
o
ld
lin
e
i
n
F
ig
u
r
e
2
,
p
r
ed
icted
o
u
tp
u
t
f
r
o
m
r
an
d
o
m
ized
i
n
itia
l
w
ei
g
h
ts
s
h
o
w
s
m
o
r
e
d
ata
p
o
i
n
ts
t
h
at
h
a
s
th
e
lea
s
t
p
r
ed
ictio
n
er
r
o
r
c
o
m
p
ar
ed
to
th
e
p
r
e
d
icted
o
u
tp
u
t
u
s
i
n
g
ze
r
o
s
as
in
itial
w
eig
h
t
s
.
Ho
w
e
v
er
,
w
h
en
t
h
e
n
et
w
o
r
k
u
s
i
n
g
r
an
d
o
m
w
eig
h
t
s
(
W
2
)
is
p
r
esen
ted
w
it
h
n
e
w
s
et
o
f
d
ata
f
o
r
tes
tin
g
,
t
h
e
r
ec
o
g
n
i
ti
o
n
r
ate
h
ad
a
s
li
g
h
t
d
r
o
p
r
esu
ltin
g
i
n
to
9
1
.
8
%
o
u
tp
u
t
p
r
ed
i
ctio
n
ac
c
u
r
ac
y
,
s
ee
Fig
u
r
e
3
an
d
Fi
g
u
r
e
4.
T
h
is
m
a
y
b
e
d
u
e
to
th
e
f
ac
t
t
h
at
d
ata
u
s
ed
f
o
r
tes
tin
g
h
as
n
e
v
er
b
e
en
u
s
ed
to
tr
ai
n
t
h
e
n
et
w
o
r
k
.
T
h
e
ac
cu
r
ac
y
r
ate
m
a
y
i
m
p
r
o
v
e
i
f
m
o
r
e
d
ata
ar
e
co
llected
an
d
u
s
ed
f
o
r
tr
ain
in
g
in
f
u
t
u
r
e
w
o
r
k
to
allo
w
b
etter
lear
n
i
n
g
r
ate
f
o
r
th
e
n
et
w
o
r
k
.
Fig
u
r
e
4
.
T
esti
n
g
r
esu
lt o
f
t
h
e
A
N
N
m
o
d
el
u
s
in
g
W
2
5.
CO
NCLU
SI
O
N
T
h
e
p
r
im
ar
y
tar
g
et
o
f
t
h
is
p
ap
er
w
as
to
in
v
e
s
ti
g
ate
an
i
m
p
le
m
en
tatio
n
o
f
A
NN
f
o
r
a
f
a
u
lt
p
r
ed
ictiv
e
to
o
l
f
o
r
a
C
FB
to
f
ac
ilit
a
te
p
la
n
t
o
p
er
ato
r
s
to
id
en
tify
a
n
d
n
a
r
r
o
w
d
o
w
n
t
h
e
ope
r
atio
n
al
b
o
iler
p
ar
a
m
eter
s
t
h
at
ca
u
s
e
s
th
e
f
a
u
lt
q
u
ic
k
l
y
.
Fro
m
th
e
an
a
l
y
s
is
o
f
t
h
e
s
i
m
u
lati
o
n
u
s
i
n
g
th
e
A
NN
m
e
th
o
d
,
it
h
as
s
h
o
w
n
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
te
m
th
at
p
r
ed
icts
t
h
e
co
n
d
it
io
n
o
f
t
h
e
lis
ted
p
ar
a
m
eter
s
in
T
ab
le
1
w
it
h
a
s
ati
s
f
ac
to
r
y
co
m
p
ar
is
o
n
s
u
p
p
o
r
ted
b
y
th
e
ex
p
er
i
m
e
n
tal
v
a
lu
e
s
.
T
h
e
d
ev
elo
p
ed
m
o
d
el
w
a
s
ab
le
to
p
r
o
v
id
e
an
in
d
icat
io
n
o
f
th
e
i
m
p
o
r
tan
ce
o
f
t
h
e
v
ar
io
u
s
in
p
u
t
p
ar
a
m
eter
s
,
in
ter
m
s
o
f
th
e
e
f
f
ec
t
s
o
f
v
ar
iatio
n
in
t
h
eir
o
u
tp
u
t
v
a
lu
e
s
.
Mo
r
eo
v
er
,
t
h
e
in
iti
aliza
tio
n
o
f
th
e
r
an
d
o
m
w
ei
g
h
ts
i
n
th
e
m
e
th
o
d
also
r
esu
lts
in
a
n
i
m
p
r
o
v
ed
ac
cu
r
ac
y
r
ate
o
f
9
7
.
3
%
d
u
r
in
g
tr
ai
n
i
n
g
a
n
d
a
s
lig
h
t
d
i
f
f
er
en
ce
o
f
9
3.
9
%
ac
cu
r
ac
y
i
n
t
h
e
te
s
tin
g
p
h
ase
.
T
o
co
n
clu
d
e,
th
e
p
r
o
p
o
s
ed
m
o
d
el
u
s
in
g
r
an
d
o
m
w
ei
g
h
t
s
p
er
f
o
r
m
b
etter
an
d
ca
n
b
e
u
s
ed
to
p
r
ed
ict
th
e
C
FB
f
au
lt
o
p
er
atio
n
al
p
ar
am
eter
s
ac
cu
r
atel
y
.
RE
F
E
R
E
NC
E
S
[1
]
P
.
Ya
n
g
a
n
d
S
.
L
iu
,
―
F
a
u
lt
D
iag
n
o
sis
f
o
r
Bo
il
e
rs
in
T
h
e
rm
a
l
P
o
w
e
r
P
lan
t
b
y
Da
ta
M
in
in
g
,
‖
De
c
e
m
b
e
r,
p
p
.
6
-
9
,
2
0
0
4
.
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.
8
,
No
.
4
,
A
u
g
u
s
t
2018
:
2
4
8
6
–
2
4
9
3
2492
[2
]
E.
T
e
ru
e
l,
C.
Co
rtes
,
L
.
Ig
n
a
c
io
Die
z
,
a
n
d
I
.
A
ra
u
z
o
,
―
M
o
n
it
o
ri
n
g
a
n
d
p
re
d
icti
o
n
o
f
f
o
u
li
n
g
i
n
c
o
a
l
-
f
ired
u
ti
li
ty
b
o
il
e
rs
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s,‖
Ch
e
m.
En
g
.
S
c
i.
,
v
o
l
.
6
0
,
n
o
.
1
8
,
p
p
.
5
0
3
5
-
5
0
4
8
,
2
0
0
5
.
[3
]
Y.
S
h
i
a
n
d
J.
W
a
n
g
,
―
A
sh
f
o
u
li
n
g
m
o
n
it
o
ri
n
g
a
n
d
k
e
y
v
a
riab
les
a
n
a
ly
sis
f
o
r
c
o
a
l
f
ired
p
o
w
e
r
p
lan
t
b
o
i
ler,‖
T
h
e
rm
.
S
c
i.
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
2
5
3
-
2
6
5
,
2
0
1
5
.
[4
]
R.
D.
P
a
tel
a
n
d
I.
J.
P
a
tel
,
―
A
R
e
v
ie
w
P
a
p
e
r
o
n
Ero
si
o
n
a
n
d
C
o
r
ro
sio
n
Be
h
a
v
io
r
o
f
Co
a
l
Co
m
b
u
s
ti
o
n
C
h
a
m
b
e
r,
‖
v
o
l.
1
,
n
o
.
7
,
p
p
.
7
2
-
7
6
,
2
0
1
4
.
[5
]
A
.
U
.
M
a
li
k
,
I.
A
n
d
ij
a
n
i,
M
.
M
o
b
in
,
F
.
A
l
-
m
u
a
il
i,
a
n
d
M
.
A
l
-
h
a
jri
,
―
Co
rro
sio
n
o
f
Bo
il
e
r
T
u
b
e
s
S
o
m
e
Ca
se
,
‖
S
y
mp
.
A
Q.
J
.
M
o
d
.
F
o
re
ig
n
L
it
.
,
p
p
.
7
3
9
-
7
6
3
.
[6
]
F
.
B.
I.
A
ln
a
im
i
a
n
d
H.
H.
A
l
-
Ka
y
ie
m
,
―
AI
s
y
ste
m
f
o
r
S
tea
m
Bo
il
e
r
Dia
g
n
o
sis
b
a
se
d
o
n
S
u
p
e
rh
e
a
ter
M
o
n
i
to
r
i
n
g
.
p
d
f
,
‖
J
.
Ap
p
l
.
S
c
i.
,
p
.
7
,
2
0
1
1
.
[7
]
E.
M
e
sb
a
h
i,
M
.
G
e
n
ru
p
,
a
n
d
M
.
A
ss
a
d
i,
―
F
a
u
lt
p
re
d
ictio
n
/d
iag
n
o
sis
a
n
d
se
n
s
o
r
v
a
li
d
a
ti
o
n
tec
h
n
i
q
u
e
f
o
r
a
ste
a
m
p
o
w
e
r
p
l
a
n
t,
‖
p
p
.
3
3
-
4
0
,
2
0
0
5
.
[8
]
M
.
A
d
d
e
l
-
G
e
li
e
l,
S
.
Zak
z
o
u
k
,
a
n
d
M
.
El
S
e
n
g
a
b
y
,
―
A
p
p
li
c
a
ti
o
n
o
f
M
o
d
e
l
b
a
se
d
F
a
u
lt
De
tec
ti
o
n
f
o
r
a
n
In
d
u
stria
l
Bo
il
e
r,
‖
Ap
p
l.
In
d
.
C
o
n
tr
o
l
S
o
l
u
t.
L
L
C
,
p
p
.
9
8
-
1
0
3
,
2
0
0
0
.
[9
]
P
.
Ilam
a
th
i,
V
.
S
e
ll
a
d
u
ra
i
,
a
n
d
K.
Ba
lam
u
ru
g
a
n
,
―
P
re
d
ictiv
e
m
o
d
e
ll
in
g
a
n
d
o
p
ti
m
iza
ti
o
n
o
f
n
it
ro
g
e
n
o
x
id
e
s
e
m
issio
n
in
c
o
a
l
p
o
w
e
r
p
lan
t
u
si
n
g
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
a
n
d
S
im
u
late
d
A
n
n
e
a
li
n
g
,
‖
IAE
S
In
t.
J
.
Arti
f.
In
tell.
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
1
1
-
1
8
,
2
0
1
2
.
[1
0
]
J.
S
m
r
e
k
a
r,
D.
P
a
n
d
it
,
M
.
F
a
st,
M
.
A
ss
a
d
i,
a
n
d
S
.
De
,
―
P
re
d
ictio
n
o
f
p
o
w
e
r
o
u
tp
u
t
o
f
a
c
o
a
l
-
f
ired
p
o
w
e
r
p
lan
t
b
y
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,
‖
Ne
u
ra
l
Co
mp
u
t
.
A
p
p
l
.
,
v
o
l.
1
9
,
n
o
.
5
,
p
p
.
7
2
5
-
7
4
0
,
2
0
1
0
.
[1
1
]
M
.
F
a
st
a
n
d
T
.
P
a
lm
é
,
―
A
p
p
li
c
a
ti
o
n
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
to
th
e
c
o
n
d
it
io
n
m
o
n
it
o
r
in
g
a
n
d
d
iag
n
o
sis
o
f
a
c
o
m
b
in
e
d
h
e
a
t
a
n
d
p
o
w
e
r
p
lan
t,
‖
En
e
rg
y
,
v
o
l.
3
5
,
n
o
.
2
,
p
p
.
1
1
1
4
-
1
1
2
0
,
2
0
1
0
.
[1
2
]
M
.
S
.
P
riy
a
,
R.
K
a
n
th
a
v
e
l,
a
n
d
M
.
S
a
ra
v
a
n
a
n
,
―
F
a
u
lt
Dia
g
n
o
stics
o
n
S
tea
m
Bo
il
e
rs
a
n
d
F
o
re
c
a
stin
g
S
y
ste
m
Ba
se
d
o
n
Hy
b
rid
F
u
z
z
y
Clu
ste
rin
g
a
n
d
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
in
Early
D
e
tec
ti
o
n
o
f
Ch
a
m
b
e
r
S
lag
g
in
g
/F
o
u
li
n
g
,
‖
Circ
u
it
s S
y
st.
,
v
o
l.
7
,
n
o
.
1
2
,
p
p
.
4
0
4
6
-
4
0
7
0
,
2
0
1
6
.
[1
3
]
K.
Ro
ste
k
,
Ł.
M
o
ry
tk
o
,
a
n
d
A
.
J
a
n
k
o
w
s
k
a
,
―
Earl
y
d
e
tec
ti
o
n
a
n
d
p
re
d
ictio
n
o
f
lea
k
s
in
f
lu
id
ize
d
-
b
e
d
b
o
il
e
rs
u
si
n
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,‖
En
e
rg
y
,
v
o
l.
8
9
,
p
p
.
9
1
4
-
9
2
3
,
2
0
1
5
.
[1
4
]
I.
M
a
rti
n
e
z
,
―
He
a
t
T
ra
n
sf
e
r
a
n
d
Th
e
r
m
a
l
Ra
d
iatio
n
M
o
d
e
ll
i
n
g
,
‖
p
p
.
1
-
4
9
.
[1
5
]
A
.
S
.
Ra
m
a
d
h
a
s,
S
.
Ja
y
a
ra
j,
a
n
d
C.
M
u
ra
lee
d
h
a
ra
n
,
―
T
h
e
o
re
ti
c
a
l
m
o
d
e
li
n
g
a
n
d
e
x
p
e
ri
m
e
n
tal
stu
d
ies
o
n
b
io
d
ies
e
l
-
f
u
e
led
e
n
g
in
e
,
‖
Ren
e
w.
En
e
rg
y
,
v
o
l.
3
1
,
n
o
.
1
1
,
p
p
.
1
8
1
3
-
1
8
2
6
,
2
0
0
6
.
[1
6
]
L
.
M
.
Ro
m
e
o
a
n
d
R
.
G
a
re
ta,
―
Ne
u
ra
l
n
e
tw
o
rk
f
o
r
e
v
a
lu
a
ti
n
g
b
o
il
e
r
b
e
h
a
v
io
u
r
,
‖
Ap
p
l.
T
h
e
rm
.
En
g
.
,
v
o
l.
2
6
,
n
o
.
1
4
-
1
5
,
p
p
.
1
5
3
0
-
1
5
3
6
,
2
0
0
6
.
[1
7
]
P
.
S
h
a
rm
a
,
D.
S
a
in
i,
a
n
d
A
.
S
a
x
e
n
a
,
―
F
a
u
lt
De
te
c
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
in
T
ra
n
s
m
is
sio
n
L
in
e
u
sin
g
W
a
v
e
let
T
ra
n
s
f
o
r
m
a
n
d
A
NN
,
‖
Bu
ll
.
El
e
c
t
r.
En
g
.
I
n
fo
rm
a
t
ics
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
4
5
6
-
4
6
5
,
2
0
1
6
.
[1
8
]
A
z
ri
y
e
n
n
i,
M
.
M
W
,
D.
S
u
k
m
a
,
a
n
d
M
.
Da
m
e
,
―
Ba
c
k
p
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
t
w
o
rk
M
o
d
e
li
n
g
f
o
r
F
a
u
lt
L
o
c
a
ti
o
n
i
n
T
ra
n
s
m
issio
n
L
in
e
1
5
0
k
V
,
‖
I
n
d
o
n
e
s.
J
.
El
e
c
tr.
E
n
g
.
In
f
o
r
ma
ti
c
s
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
1
-
1
2
,
2
0
1
4
.
[1
9
]
N.
M
a
y
a
d
e
v
i,
S
.
Us
h
a
k
u
m
a
ri,
a
n
d
V
.
C.
S
S
,
―
A
Re
v
ie
w
o
n
Ex
p
e
rt
S
y
ste
m
A
p
p
li
c
a
ti
o
n
s
in
P
o
w
e
r
P
lan
ts,
‖
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
E
n
g
.
J
.
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
2
0
8
8
-
8
7
0
8
,
2
0
1
4
.
[2
0
]
W
.
R.
Be
c
r
a
f
t,
P
.
L
.
L
e
e
,
a
n
d
R.
B.
Ne
w
e
ll
,
―
In
teg
ra
ti
o
n
o
f
n
e
u
ra
l
n
e
tw
o
rk
s
a
n
d
e
x
p
e
rt
s
y
ste
m
s
f
o
r
p
ro
c
e
ss
fa
u
l
t
d
iag
n
o
sis,‖
Pro
c
.
1
2
th
I
n
t.
J
t.
Co
n
f.
Arti
f.
I
n
tell.
,
p
p
.
8
3
2
-
8
3
7
,
1
9
9
1
.
[2
1
]
G
.
P
ra
sa
d
,
E.
S
w
id
e
n
b
a
n
k
,
a
n
d
B.
W
.
Ho
g
g
,
―
A
n
e
u
ra
l
n
e
t
m
o
d
e
l
-
b
a
se
d
m
u
lt
iv
a
riab
le
lo
n
g
-
ra
n
g
e
p
re
d
ictiv
e
c
o
n
tro
l
stra
teg
y
a
p
p
li
e
d
in
t
h
e
rm
a
l
p
o
w
e
r
p
lan
t
c
o
n
tr
o
l,
‖
IE
EE
T
r
a
n
s.
En
e
r
g
y
Co
n
v
e
rs
.
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
7
6
-
1
8
2
,
1
9
9
8
.
[2
2
]
J.
S
m
re
k
a
r,
M
.
As
sa
d
i,
M
.
F
a
st,
I
.
Ku
štrin
,
a
n
d
S
.
De
,
―
De
v
e
lo
p
m
e
n
t
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l
f
o
r
a
c
o
a
l
-
f
ired
b
o
il
e
r
u
si
n
g
re
a
l
p
lan
t
d
a
ta,‖
En
e
rg
y
,
v
o
l
.
3
4
,
n
o
.
2
,
p
p
.
1
4
4
-
1
5
2
,
2
0
0
9
.
[2
3
]
H.
Ru
sin
o
w
sk
i
a
n
d
W
.
S
tan
e
k
,
―
Ne
u
ra
l
m
o
d
e
ll
in
g
o
f
ste
a
m
b
o
il
e
rs,‖
En
e
rg
y
Co
n
v
e
rs
.
M
a
n
a
g
.
,
v
o
l.
4
8
,
n
o
.
1
1
,
p
p
.
2
8
0
2
-
2
8
0
9
,
2
0
0
7
.
[2
4
]
M.
-
C.
P
o
p
e
sc
u
,
V.
E.
Ba
las
,
L
.
P
e
re
sc
u
-
P
o
p
e
sc
u
,
a
n
d
N.
M
a
sto
ra
k
is,
―
M
u
lt
il
a
y
e
r
P
e
rc
e
p
t
ro
n
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
s,‖ v
o
l.
8
,
n
o
.
7
,
p
p
.
5
7
9
-
5
8
8
,
2
0
0
9
.
[2
5
]
M
.
Ried
m
il
ler,
―
A
d
v
a
n
c
e
d
su
p
e
rv
ise
d
lea
rn
in
g
in
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
s
—
f
ro
m
b
a
c
k
p
ro
p
a
g
a
ti
o
n
t
o
a
d
a
p
ti
v
e
lea
rn
in
g
a
lg
o
rit
h
m
s,‖
Co
mp
u
t
.
S
t
a
n
d
.
I
n
ter
fa
c
e
s
,
v
o
l.
1
6
,
n
o
.
3
,
p
p
.
2
6
5
-
2
7
8
,
1
9
9
4
.
[2
6
]
Ö.
Kisi
a
n
d
E.
Un
c
u
o
g
lu
,
―
Co
m
p
a
riso
n
o
f
th
re
e
b
a
c
k
-
p
ro
p
a
g
a
ti
o
n
train
in
g
a
lg
o
rit
h
m
f
o
r
tw
o
c
a
se
st
u
d
y
,
‖
In
d
i
a
n
J
.
En
g
.
M
a
ter
.
S
c
i.
,
v
o
l.
1
2
,
Oc
to
b
e
r
,
p
p
.
4
3
4
-
4
4
2
,
2
0
0
5
.
[2
7
]
A
.
D.
A
n
a
sta
sia
d
is,
G
.
D.
M
a
g
o
u
las
,
a
n
d
M
.
N.
V
ra
h
a
ti
s,
―
Ne
w
g
l
o
b
a
ll
y
c
o
n
v
e
rg
e
n
t
train
in
g
sc
h
e
m
e
b
a
se
d
o
n
t
h
e
re
sili
e
n
t
p
r
o
p
a
g
a
ti
o
n
a
lg
o
rit
h
m
,
‖
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l
.
6
4
,
n
o
.
1
-
4
S
P
EC.
I
S
S
.
,
p
p
.
2
5
3
-
2
7
0
,
2
0
0
5
.
[2
8
]
M
.
Ried
m
il
ler
a
n
d
H.
Bra
u
n
,
―
A
d
irec
t
a
d
a
p
ti
v
e
m
e
th
o
d
f
o
r
f
a
ste
r
b
a
c
k
p
ro
p
a
g
a
ti
o
n
lea
rn
in
g
:
T
h
e
RP
R
O
P
a
lg
o
rit
h
m
,
‖
IEE
E
In
t.
Co
n
f.
Ne
u
r
a
l
Ne
two
rk
s
-
C
o
n
f.
Pro
c
.
,
v
o
l.
1
9
9
3
-
Ja
n
u
a
,
p
p
.
5
8
6
-
5
9
1
,
1
9
9
3
.
[2
9
]
F
.
B.
I.
A
ln
a
im
i,
R.
I.
B.
Ism
a
il
,
a
n
d
P
.
J.
Ke
r,
―
De
v
e
lo
p
m
e
n
t
a
n
d
im
p
le
m
e
n
tatio
n
o
f
in
tell
ig
e
n
t
c
o
n
d
i
ti
o
n
m
o
n
it
o
rin
g
sy
ste
m
f
o
r
ste
a
m
tu
rb
in
e
tri
p
s
,
‖
v
o
l
.
1
1
,
n
o
.
2
4
,
p
p
.
1
4
2
7
5
-
1
4
2
8
3
,
2
0
1
6
.
[3
0
]
S
.
T
im
o
th
e
o
u
,
―
A
n
o
v
e
l
w
e
ig
h
t
in
it
ializa
ti
o
n
m
e
th
o
d
f
o
r
t
h
e
ra
n
d
o
m
n
e
u
ra
l
n
e
tw
o
rk
,
‖
Ne
u
ro
c
o
m
p
u
ti
n
g
,
v
o
l.
7
3
,
n
o
.
1
-
3
,
p
p
.
1
6
0
-
1
6
8
,
2
0
0
9
.
[3
1
]
Y.
F
.
Ya
m
,
C.
T
.
Leu
n
g
,
P
.
K.
S
.
T
a
m
,
a
n
d
W
.
C.
S
iu
,
―
A
n
in
d
e
p
e
n
d
e
n
t
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
b
a
se
d
w
e
i
g
h
t
in
it
ializa
ti
o
n
m
e
th
o
d
f
o
r
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
s,‖
Ne
u
r
o
c
o
mp
u
ti
n
g
,
v
o
l.
4
8
,
p
p
.
8
0
7
-
8
1
8
,
2
0
0
2
.
[3
2
]
Y.
A
.
L
e
Cu
n
,
L
.
Bo
tt
o
u
,
G
.
B.
Orr,
a
n
d
K.
R.
M
u
ll
e
r,
―
E
f
f
i
c
ien
t
b
a
c
k
p
ro
p
,
‖
L
e
c
t.
No
tes
Co
mp
u
t.
S
c
i.
(
in
c
lu
d
i
n
g
S
u
b
se
r.
L
e
c
t.
No
tes
Arti
f.
I
n
tell.
L
e
c
t.
No
tes
Bi
o
i
n
f
o
rm
a
ti
c
s)
,
v
o
l
.
7
7
0
0
L
ECT
U,
p
p
.
9
-
4
8
,
2
0
1
2
.
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:
2
0
8
8
-
8708
A
N
N
to
P
r
ed
ict
C
o
a
l
-
F
ir
ed
B
o
iler
F
a
u
lt
u
si
n
g
B
o
iler
Op
era
tio
n
a
l
…
(
N
o
n
g
N
u
r
n
ie
Mo
h
d
N
is
ta
h
)
2493
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
No
n
g
N
u
r
n
ie
is
c
u
rre
n
tl
y
c
o
m
p
letin
g
h
e
r
M
a
ste
r
o
f
P
h
il
o
so
p
h
y
(M
P
h
i
l
)
w
it
h
Cu
rt
in
U
n
iv
e
rsity
M
a
la
y
sia
a
n
d
h
a
s
b
e
e
n
tea
c
h
in
g
in
th
e
d
e
p
a
rtm
e
n
t
o
f
F
o
u
n
d
a
ti
o
n
in
S
c
ien
c
e
&
En
g
in
e
e
rin
g
a
t
Cu
rti
n
Un
iv
e
rsit
y
M
a
la
y
sia
sin
c
e
2
0
0
8
.
S
h
e
h
a
s
h
a
d
5
y
e
a
r
s
o
f
w
o
rk
in
g
e
x
p
e
rien
c
e
in
th
e
in
d
u
stry
p
ri
o
r
to
tea
c
h
in
g
in
th
e
tertiary
e
d
u
c
a
ti
o
n
.
He
r
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
i
n
tel
li
g
e
n
t
sy
ste
m
,
in
tera
c
ti
v
e
s
y
ste
m
a
n
d
so
f
t
w
a
re
in
terfa
c
e
d
e
v
e
lo
p
m
e
n
t
in
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
e
-
c
o
m
m
u
n
it
y
.
K
in
g
H
a
n
n
Li
m
re
c
e
iv
e
d
h
is
M
a
ste
r
o
f
En
g
in
e
e
rin
g
(M
.
En
g
)
a
n
d
P
h
D
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
E
n
g
in
e
e
rin
g
in
2
0
0
7
a
n
d
2
0
1
2
re
sp
e
c
ti
v
e
ly
.
He
is
c
u
rre
n
tl
y
a
sta
ff
m
e
m
b
e
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
a
t
Cu
rti
n
Un
iv
e
rsit
y
M
a
la
y
sia
.
His
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s
im
a
g
e
/
v
id
e
o
p
ro
c
e
ss
in
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
a
n
d
in
telli
g
e
n
t
tran
sp
o
rtatio
n
sy
ste
m
.
H
e
is
a
IEE
E
se
n
io
r
m
e
m
b
e
r
in
2
0
1
7
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
5
0
jo
u
rn
a
ls
a
n
d
c
o
n
f
e
r
e
n
c
e
p
a
p
e
rs
in
th
e
re
late
d
a
re
a
s
o
f
h
is
re
se
a
rc
h
i
n
tere
st.
Dr
.
Le
n
in
G
o
p
a
l
is
w
o
rk
in
g
a
s
a
se
n
io
r
lec
tu
re
r
in
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
Cu
rti
n
M
a
lay
sia
a
n
d
h
e
o
b
tain
e
d
h
is
P
h
D
d
e
g
re
e
f
ro
m
Cu
rti
n
Un
iv
e
rsit
y
,
A
u
stra
li
a
.
P
rio
r
to
jo
i
n
in
g
Cu
rt
in
S
a
ra
w
a
k
M
a
l
a
y
sia
,
h
e
h
a
s
h
a
d
m
o
re
th
a
n
f
i
f
te
e
n
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
I
n
d
ia
a
n
d
M
a
lay
sia
.
His
p
re
v
io
u
s
p
o
sit
i
o
n
w
a
s
a
s
a
n
As
sista
n
t
P
r
o
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
at
Bh
a
ra
th
iy
a
r
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
P
o
n
d
ice
rry
,
In
d
ia.
Dr
Fi
r
a
s
B
.
Is
m
a
il
Aln
a
i
m
i
is
a
He
a
d
o
f
P
o
w
e
r
G
e
n
e
ra
ti
o
n
,
In
stit
u
te
o
f
P
o
w
e
r
En
g
in
e
e
rin
g
(I
P
E),
Un
iv
e
rsiti
T
e
n
a
g
a
N
a
sio
n
a
l
,
M
a
l
a
y
sia
.
He
h
a
s
1
2
y
e
a
rs
w
o
rk
in
g
e
x
p
e
rien
c
e
in
in
d
u
stry
a
n
d
a
c
a
d
e
m
i
c
f
ield
s.
His
re
s
e
a
rc
h
f
o
c
u
s
is
o
n
In
telli
g
e
n
t
M
o
n
it
o
rin
g
S
y
ste
m
s,
w
it
h
sp
e
c
ial
in
tere
sts
in
F
ire,
F
lo
w
A
s
su
ra
n
c
e
,
S
m
a
rt
P
ig
g
in
g
S
y
ste
m
s,
G
a
s
H
y
d
ra
te
F
o
r
m
a
ti
o
n
,
Early
Co
n
d
it
i
o
n
W
a
rn
in
g
S
y
ste
m
s
,
P
la
n
t
M
o
n
i
to
ri
n
g
S
y
ste
m
s,
a
n
d
Ro
b
o
ti
s
e
d
In
d
u
stry
A
p
p
li
c
a
ti
o
n
s.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
80
p
u
b
li
c
a
ti
o
n
s
in
re
p
u
tab
le i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
l
s
a
n
d
c
o
n
f
e
re
n
c
e
p
ro
c
e
e
d
in
g
s.
Evaluation Warning : The document was created with Spire.PDF for Python.