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
.
7
,
No
.
3
,
J
u
n
e
201
7
,
p
p
.
1538
~
1
5
4
5
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
7
i
3
.
p
p
1
5
3
8
-
1545
1538
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Neura
l Ne
tw
o
rk
-
ba
sed M
o
del P
re
dictive Co
n
trol w
i
th
CPS
O
G
SA
for S
M
BR Filt
ra
tion
Za
k
a
r
ia
h
Y
u
s
u
f
1
,
No
rha
liza
Abdu
l Wa
ha
b
2
,
Abda
lla
h
Ab
u
s
a
m
3
1,
2
Co
n
tro
l
&
M
e
c
h
a
tro
n
ics
En
g
i
n
e
e
rin
g
,
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
,
8
1
3
1
0
S
k
u
d
a
i
Jo
h
o
r
Ba
h
r
u
,
M
a
lay
sia
3
W
a
ter Res
e
a
rc
h
Ce
n
tre,
Ku
w
a
it
In
stit
u
te f
o
r
S
c
ien
ti
f
ic Re
se
a
rc
h
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
2
,
201
7
R
ev
i
s
ed
A
p
r
25
,
2
0
1
7
A
cc
ep
ted
Ma
y
20
,
2
0
1
7
T
h
is
p
a
p
e
r
p
re
se
n
ts
th
e
d
e
v
e
l
o
p
m
e
n
t
o
f
n
e
u
ra
l
n
e
t
w
o
rk
b
a
s
e
d
m
o
d
e
l
p
re
d
ictiv
e
c
o
n
t
ro
l
(NN
M
P
C)
f
o
r
c
o
n
tro
ll
in
g
s
u
b
m
e
rg
e
d
m
e
m
b
ra
n
e
b
i
o
re
a
c
to
r
(S
M
BR)
f
il
tratio
n
p
ro
c
e
ss
.
T
h
e
m
a
in
c
o
n
tri
b
u
ti
o
n
o
f
th
is
p
a
p
e
r
is
t
h
e
in
teg
ra
ti
o
n
o
f
n
e
w
l
y
d
e
v
e
lo
p
e
d
so
f
t
c
o
m
p
u
ti
n
g
o
p
t
im
iza
ti
o
n
tec
h
n
iq
u
e
n
a
m
e
a
s
c
o
o
p
e
ra
ti
v
e
h
y
b
rid
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iza
ti
o
n
a
n
d
g
ra
v
it
a
ti
o
n
a
l
se
a
rc
h
a
lg
o
rit
h
m
(CP
S
OG
S
A
)
w
it
h
th
e
m
o
d
e
l
p
re
d
ictiv
e
c
o
n
tro
l.
T
h
e
CP
S
OG
S
A
a
lg
o
rit
h
m
is
u
se
d
a
s
a
r
e
a
l
ti
m
e
o
p
ti
m
iza
ti
o
n
(RT
O)
in
u
p
d
a
ti
n
g
th
e
NN
M
P
C
c
o
st
f
u
n
c
ti
o
n
.
T
h
e
d
e
v
e
lo
p
e
d
c
o
n
tro
ll
e
r
is
u
ti
li
z
e
d
to
c
o
n
t
ro
l
S
M
BR
f
il
tratio
n
s
p
e
rm
e
a
te
f
lu
x
in
p
re
v
e
n
ti
n
g
f
lu
x
d
e
c
li
n
e
f
ro
m
m
e
m
b
ra
n
e
f
o
u
li
n
g
.
T
h
e
p
ro
p
o
se
d
NN
M
P
C
is
c
o
m
p
a
re
d
w
it
h
p
ro
p
o
rti
o
n
a
l
i
n
teg
ra
l
d
e
riv
a
ti
v
e
(P
ID)
c
o
n
tr
o
ll
e
r
i
n
term
o
f
th
e
p
e
rc
e
n
tag
e
o
v
e
rsh
o
o
t,
se
tt
li
n
g
ti
m
e
a
n
d
in
teg
ra
l
a
b
so
lu
te
e
rro
r
(IA
E)
c
rit
e
ria.
T
h
e
si
m
u
latio
n
re
su
lt
sh
o
w
s
NN
M
P
C
p
e
rf
o
r
m
b
e
tt
e
r
c
o
n
tro
l
c
o
m
p
a
re
d
w
it
h
P
ID
c
o
n
tro
l
ler
in
ter
m
m
e
a
su
re
d
c
o
n
tro
l
p
e
rf
o
rm
a
n
c
e
o
f
p
e
r
m
e
a
te
f
lu
x
.
K
ey
w
o
r
d
:
A
N
N
m
o
d
eli
n
g
C
P
SOGS
A
Mo
d
el
p
r
ed
ictiv
e
co
n
tr
o
l
R
ea
l ti
m
e
o
p
ti
m
izatio
n
SMB
R
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
h
aliza
A
b
d
u
l W
ah
ab
,
C
o
n
tr
o
l &
Me
c
h
atr
o
n
ic
s
E
n
g
i
n
ee
r
in
g
Dep
ar
t
m
e
n
t,
Fac
u
lt
y
o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
ala
y
s
ia
,
8
1
3
1
0
Sk
u
d
ai,
J
o
h
o
r
,
Ma
lay
s
i
a
.
E
m
ail:aliza
@
f
k
e.
u
t
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Me
m
b
r
an
e
b
io
r
ea
cto
r
(
MB
R
)
is
an
e
f
f
icie
n
t
tec
h
n
o
lo
g
y
in
w
a
s
te
w
ater
tr
ea
t
m
e
n
t
p
r
o
ce
s
s
.
T
h
e
co
m
b
i
n
atio
n
o
f
m
e
m
b
r
an
e
tech
n
o
lo
g
y
a
n
d
b
io
lo
g
ical
p
r
o
ce
s
s
r
ea
cto
r
is
a
n
an
s
w
er
f
o
r
h
i
g
h
q
u
alit
y
e
f
f
lu
e
n
t
i
n
w
a
s
te
w
ater
tr
ea
t
m
e
n
t.
Me
m
b
r
an
e
f
iltra
tio
n
p
r
o
ce
s
s
is
v
er
y
i
m
p
o
r
ta
n
t e
le
m
e
n
t
in
MB
R
s
y
s
te
m
th
i
s
is
th
e
p
lace
w
h
er
e
s
ep
ar
atio
n
p
r
o
ce
s
s
is
o
c
cu
r
.
Ho
w
e
v
er
,
MB
R
s
tr
u
g
g
le
w
it
h
a
f
e
w
li
m
itatio
n
s
s
u
c
h
as
m
e
m
b
r
a
n
e
f
o
u
li
n
g
an
d
h
i
g
h
e
n
er
g
y
co
n
s
u
m
p
tio
n
d
u
r
in
g
f
i
ltra
tio
n
p
r
o
ce
s
s
.
A
f
o
u
li
n
g
p
h
e
n
o
m
e
n
o
n
i
s
ca
u
s
e
d
b
y
m
an
y
f
ac
to
r
s
s
u
c
h
a
s
co
llo
id
al,
p
ar
ticu
late,
an
d
s
o
l
u
te
m
ater
ial
s
.
Me
m
b
r
a
n
e
f
o
u
li
n
g
i
s
a
co
m
p
lex
p
r
o
ce
s
s
,
af
f
ec
ted
b
y
m
an
y
p
ar
am
eter
s
,
in
cl
u
d
i
n
g
t
h
e
o
p
e
r
atio
n
,
in
f
l
u
en
t
p
r
o
p
er
ties
,
an
d
th
e
m
e
m
b
r
an
e
its
el
f
[
1
]
.
Fo
u
li
n
g
ca
n
lead
to
a
m
e
m
b
r
a
n
e
clo
g
g
i
n
g
,
r
es
u
lti
n
g
i
n
t
h
at
t
h
e
m
e
m
b
r
an
e
p
o
r
e
w
ill
b
e
b
lo
ck
ed
b
y
s
o
lid
m
ater
ial.
Fo
u
li
n
g
w
il
l
af
f
ec
t
t
h
e
o
v
er
all
p
er
f
o
r
m
a
n
c
e
o
f
a
f
iltra
tio
n
s
y
s
te
m
i
n
s
h
o
r
t
an
d
lo
n
g
ter
m
o
p
er
atio
n
,
b
y
in
d
u
cin
g
h
i
g
h
f
iltra
tio
n
r
esis
ta
n
ce
,
as
a
r
es
u
lt
o
f
t
h
e
co
m
p
ac
t
f
o
r
m
atio
n
o
f
f
o
u
li
n
g
o
n
th
e
m
e
m
b
r
a
n
e
s
u
r
f
ac
e
[2
]
.
T
h
e
clo
g
g
i
n
g
o
n
th
e
m
e
m
b
r
an
e
al
s
o
w
ill
r
ed
u
ce
t
h
e
p
er
m
ea
te
f
lu
x
o
u
tp
u
t
an
d
t
h
e
s
a
m
e
ti
m
e
th
e
o
v
er
all
s
y
s
te
m
ef
f
icien
c
y
w
ill
b
e
e
f
f
ec
ted
.
Sev
er
al
m
e
m
b
r
a
n
e
clea
n
i
n
g
tech
n
iq
u
es
w
er
e
i
n
tr
o
d
u
ce
d
to
co
n
tr
o
l
f
o
u
lin
g
d
ev
elo
p
m
en
t
s
u
c
h
as
r
ela
x
atio
n
,
b
ac
k
w
as
h
,
air
f
lo
w
a
n
d
ch
e
m
ical
clea
n
i
n
g
.
A
p
ar
t
f
r
o
m
t
h
at,
m
a
n
ip
u
latio
n
o
f
f
l
u
x
f
lo
w
r
ate
is
v
er
y
i
m
p
o
r
ta
n
t
in
m
e
m
b
r
a
n
e
f
iltra
tio
n
s
y
s
t
e
m
.
I
t
ca
n
b
e
u
tili
ze
to
r
ed
u
ce
f
o
u
li
n
g
b
y
ad
j
u
s
ti
n
g
th
e
p
er
m
ea
te
s
et
p
o
in
t
w
h
e
n
n
ec
ess
ar
y
[
3
]
.
C
o
n
tr
o
lli
n
g
a
p
er
m
ea
te
f
lu
x
a
t
d
if
f
er
e
n
t
s
et
p
o
in
t
i
s
a
ch
all
en
g
i
n
g
tas
k
b
ec
au
s
e
t
h
e
p
r
ess
u
r
e
o
f
th
e
f
iltra
tio
n
d
u
e
to
f
o
u
li
n
g
p
h
e
n
o
m
e
n
a
i
s
d
if
f
er
e
n
t
at
d
if
f
er
e
n
t
s
et
p
o
in
t.
Hi
g
h
er
s
et
p
o
in
t
w
il
l
r
es
u
lt
o
f
h
i
g
h
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
N
eu
r
a
l Net
w
o
r
k
b
a
s
ed
Mo
d
el
P
r
ed
ictive
C
o
n
tr
o
l wi
th
C
P
S
O
GS
A
fo
r
S
MBR
F
iltr
a
tio
n
(
Za
ka
r
ia
h
Yu
s
u
f)
1539
p
r
ess
u
r
e.
Hig
h
er
f
il
tr
atio
n
p
r
ess
u
r
e
is
d
u
e
to
th
e
f
i
ltra
tio
n
r
esis
ta
n
ce
s
t
h
at
in
cr
ea
s
e
at
t
h
e
h
ig
h
er
f
l
u
x
f
lo
w
r
ate.
E
v
en
t
h
o
u
g
h
MB
R
tech
n
o
lo
g
y
i
s
i
n
tr
o
d
u
ce
f
o
r
m
a
n
y
y
ea
r
s
a
g
o
,
th
e
ap
p
licatio
n
o
f
co
n
tr
o
l
s
y
s
te
m
in
MB
R
s
y
s
te
m
s
till
n
o
t
m
at
u
r
e.
A
t
t
h
e
m
o
m
en
t,
o
p
en
lo
o
p
co
n
tr
o
l
s
y
s
te
m
s
til
l
i
m
p
le
m
e
n
t
i
n
m
a
n
y
MB
R
p
lan
t
[
4
]
.
A
p
p
licatio
n
o
f
ad
v
a
n
ce
c
o
n
tr
o
l
s
y
s
te
m
f
o
r
SMB
R
p
r
o
ce
s
s
i
s
v
er
y
c
h
alle
n
g
in
g
ta
s
k
an
d
n
ee
d
s
a
lo
t
o
f
u
n
d
er
s
ta
n
d
in
g
o
f
th
e
s
y
s
te
m
o
p
er
atio
n
an
d
d
y
n
a
m
ic.
So
m
e
s
u
cc
es
s
f
u
l
i
m
p
le
m
e
n
tatio
n
o
f
clo
s
e
lo
o
p
co
n
tr
o
l
h
as
s
h
o
w
n
t
h
at
t
h
e
ap
p
licatio
n
o
f
co
n
tr
o
ller
h
as
g
i
v
es
i
m
p
r
o
v
e
m
e
n
t
to
t
h
e
s
y
s
te
m
a
n
d
p
r
o
ce
s
s
.
P
r
o
p
o
r
tio
n
al
in
te
g
r
al
d
er
iv
ativ
e
(
P
I
D)
co
n
tr
o
ller
is
s
till
th
e
m
ai
n
co
n
tr
o
lle
r
u
s
ed
in
m
a
n
y
in
d
u
s
tr
ie
s
.
T
h
is
co
n
tr
o
ller
is
v
er
y
p
o
p
u
lar
b
ec
au
s
e
o
f
its
s
i
m
p
lic
it
y
a
n
d
s
i
m
p
le
to
u
n
d
er
s
t
an
d
.
I
n
ad
d
itio
n
,
t
h
e
co
n
tr
o
ller
i
s
v
er
y
s
tab
le
a
n
d
ea
s
y
to
b
e
tu
n
ed
.
C
u
r
cio
et
al
[
5
]
p
r
esen
ts
th
e
P
I
an
d
P
I
D
c
o
n
tr
o
l
ap
p
licatio
n
to
th
e
UF
m
e
m
b
r
a
n
e
f
il
tr
atio
n
p
r
o
ce
s
s
.
Si
m
u
lat
io
n
o
f
t
h
e
s
y
s
te
m
w
a
s
d
o
n
e
u
s
in
g
h
y
b
r
id
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el.
T
h
e
co
n
tr
o
ller
s
w
er
e
u
s
ed
to
co
n
tr
o
l
th
e
p
er
m
ea
te
f
lu
x
o
f
t
h
e
f
iltra
tio
n
p
r
o
ce
s
s
.
T
h
e
co
n
t
r
o
ller
s
w
er
e
t
u
n
ed
u
s
in
g
zi
g
le
r
-
n
ic
h
o
ls
(
Z
N)
a
n
d
I
T
A
E
tu
n
in
g
m
et
h
o
d
s
.
T
h
e
a
u
th
o
r
s
f
o
u
n
d
I
T
A
E
t
u
n
i
n
g
m
eth
o
d
is
m
o
r
e
r
o
b
u
s
t
b
o
t
h
i
n
r
eg
u
lato
r
a
n
d
s
er
v
o
p
r
o
b
lem
in
p
r
ev
e
n
ti
n
g
f
lu
x
d
ec
lin
e
d
u
r
in
g
f
iltra
tio
n
p
r
o
ce
s
s
.
P
I
D
co
n
tr
o
ller
w
as
u
s
ed
f
o
r
p
er
m
ea
te
f
l
u
x
co
n
tr
o
l
in
s
u
b
m
er
g
ed
an
ae
r
o
b
ic
m
e
m
b
r
an
e
b
io
r
ea
cto
r
[
6
]
.
Ho
w
e
v
er
,
P
I
D
co
n
tr
o
ller
w
as
f
o
u
n
d
p
r
o
d
u
ce
h
ig
h
o
v
er
s
h
o
o
t a
t
th
e
in
i
tial
f
iltra
tio
n
c
y
cle
t
h
at
ca
n
ca
u
s
e
p
o
o
r
f
ilt
r
atio
n
p
er
f
o
r
m
a
n
ce
.
T
h
is
i
s
ca
u
s
e
b
y
t
h
e
ON
an
d
OFF
s
ta
g
es
in
t
h
e
f
iltra
tio
n
s
y
s
te
m
.
I
n
o
r
d
er
to
s
o
lv
e
th
i
s
p
r
o
b
lem
,
f
i
x
ed
f
r
eq
u
e
n
c
y
w
it
h
P
I
D
co
n
tr
o
ller
w
a
s
in
tr
o
d
u
ce
to
co
n
tr
o
l th
e
p
er
m
e
ate
p
u
m
p
.
No
n
li
n
ea
r
Mo
d
el
p
r
ed
ictiv
e
co
n
tr
o
l
(
NM
P
C
)
is
a
n
e
f
f
ec
tiv
e
m
o
d
el
b
ased
co
n
tr
o
ller
f
o
r
m
a
n
y
ap
p
licatio
n
s
s
u
c
h
as
in
[
7
]
,
[
8
]
an
d
[
9
]
.
T
h
is
tech
n
iq
u
e
i
s
v
er
y
ef
f
ec
ti
v
e
s
i
n
ce
m
a
n
y
o
f
th
e
p
r
o
ce
s
s
ar
e
n
o
n
li
n
ea
r
.
Neu
r
al
n
e
t
w
o
r
k
b
as
ed
m
o
d
el
p
r
ed
ictiv
e
co
n
tr
o
l
(
NNM
P
C
)
is
a
m
o
n
g
t
h
e
p
o
p
u
lar
NM
P
C
tech
n
iq
u
e
in
liter
at
u
r
e.
T
h
is
co
n
tr
o
ller
em
p
lo
y
ed
n
e
u
r
al
n
e
t
w
o
r
k
as
a
p
r
ed
ictio
n
m
o
d
el
in
th
e
co
n
t
r
o
ller
d
esig
n
.
T
h
is
w
o
r
k
e
m
p
lo
y
ed
th
e
NNM
P
C
t
ec
h
n
iq
u
e
to
co
n
tr
o
l
th
e
SMB
R
f
iltra
tio
n
p
er
m
ea
te
f
l
u
x
.
T
h
e
NNM
P
C
is
d
esig
n
w
it
h
co
o
p
er
ativ
e
p
ar
ticle
s
w
ar
m
o
p
ti
m
izatio
n
w
it
h
g
r
av
ita
ti
o
n
al
s
ea
r
c
h
al
g
o
r
ith
m
(
C
P
OS
GS
A
)
as
a
r
ea
l
ti
m
e
o
p
tim
izatio
n
(
R
T
O)
f
o
r
th
e
M
P
C
co
s
t
f
u
n
ctio
n
m
i
n
i
m
izatio
n
.
T
h
e
C
P
SOGS
A
o
p
ti
m
izatio
n
alg
o
r
it
h
m
i
s
n
e
w
an
d
ef
f
icien
t
tech
n
iq
u
e
f
o
r
o
p
tim
izatio
n
f
o
r
m
a
n
y
t
y
p
es
co
s
t
f
u
n
ctio
n
.
I
n
te
g
r
atio
n
o
f
th
i
s
o
p
ti
m
izatio
n
tech
n
iq
u
e
i
n
MP
C
w
ill p
r
o
d
u
ce
r
eliab
le
an
d
ef
f
ec
ti
v
e
NNM
P
C
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
P
ro
ce
s
s
M
o
delin
g
T
h
e
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
(
A
N
N)
m
o
d
el
w
it
h
r
ec
u
r
r
en
t
s
t
r
u
ctu
r
e
is
ap
p
lied
w
h
er
e
th
e
p
ast
o
u
tp
u
t
an
d
in
p
u
t
is
u
s
ed
to
p
r
ed
ict
th
e
cu
r
r
en
t
o
u
tp
u
t.
T
h
is
s
tr
u
ct
u
r
e
is
also
k
n
o
w
n
as
n
o
n
li
n
ea
r
au
to
r
eg
r
ess
i
v
e
w
it
h
ex
o
g
e
n
o
u
s
i
n
p
u
t (
N
A
R
X)
.
Fi
g
u
r
e
1
p
r
esen
ts
t
h
e
m
o
d
el
s
tr
u
c
t
u
r
e
e
m
p
lo
y
ed
i
n
th
i
s
w
o
r
k
.
Fig
u
r
e
1
.
Neu
r
al
Net
w
o
r
k
Str
u
ctu
r
e
(
)
is
th
e
v
o
ltag
e
ap
p
lied
to
th
e
p
er
m
ea
te
p
u
m
p
w
h
ile,
̅
1
(
)
an
d
̅
2
(
)
is
th
e
p
r
ed
icted
p
er
m
ea
te
f
l
u
x
a
n
d
T
MP
r
esp
ec
tiv
el
y
.
−
1
is
th
e
d
ela
y
o
p
er
ato
r
.
T
h
e
ex
p
er
i
m
e
n
ts
w
er
e
ca
r
r
ied
o
u
t
in
s
i
n
g
le
ta
n
k
s
u
b
m
er
g
ed
m
e
m
b
r
a
n
e
b
io
r
ea
cto
r
s
,
w
ith
w
o
r
k
i
n
g
v
o
lu
m
e
o
f
2
0
L
p
al
m
o
il
m
ill
e
f
f
l
u
en
t
(
P
OM
E
)
tak
e
n
f
r
o
m
Sed
en
ak
P
al
m
Oil
Mi
ll
Sd
n
.
B
h
d
.
in
J
o
h
o
r
,
Ma
la
y
s
ia.
T
h
e
w
o
r
k
i
n
g
te
m
p
er
atu
r
e
s
f
o
r
th
e
b
io
r
ea
cto
r
s
w
er
e
at
2
9
±
1
°C
.
T
h
e
p
lan
t
w
as
o
p
er
ated
w
ith
1
2
0
s
ec
o
n
d
p
er
m
ea
te
a
n
d
3
0
s
ec
o
n
d
f
o
r
r
elax
atio
n
p
er
io
d
.
T
h
e
air
f
lo
w
r
ate
is
m
ai
n
tai
n
ed
ar
o
u
n
d
6
-
8
L
P
M.
Fig
u
r
e
2
s
h
o
w
s
th
e
p
ilo
t
p
lan
t
s
etu
p
f
o
r
th
e
e
x
p
er
i
m
e
n
t.
T
h
e
d
ata
p
lan
t
w
a
s
co
n
tr
o
lled
an
d
m
o
n
i
to
r
ed
u
s
in
g
Natio
n
al
I
n
s
t
r
u
m
e
n
ts
,
L
ab
VI
E
W
2
0
0
9
s
o
f
t
w
ar
e
w
it
h
NI
USB
6
0
0
9
in
ter
f
ac
in
g
h
ar
d
w
ar
e.
T
ab
le
1
s
h
o
w
s
t
h
e
lis
t o
f
in
s
tr
u
m
e
n
ts
u
s
ed
in
th
e
p
ilo
t p
lan
t d
ev
elo
p
m
en
t.
−
1
−
2
−
1
−
2
−
2
̅
1
(
)
̅
2
(
)
−
1
A
N
N
(
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
5
3
8
–
1
5
4
5
1540
Fig
u
r
e
2
.
Sch
e
m
atic
Dia
g
r
a
m
o
f
th
e
S
u
b
m
er
g
ed
MB
R
T
ab
le
1
.
L
is
t o
f
I
n
s
tr
u
m
e
n
ts
/P
ar
ts
T
a
g
N
o
D
e
scri
p
t
i
o
n
C
-
1
0
1
2
0
L
2
H
P
A
i
r
c
o
mp
r
e
sso
r
PV
-
1
0
1
P
r
o
p
o
r
t
i
o
n
a
l
V
a
l
v
e
FA
-
101
A
i
r
f
l
o
w
S
e
n
so
r
PI
-
101
P
r
e
ssu
r
e
T
r
a
n
sd
u
c
e
r
SV
-
1
0
1
S
o
l
e
n
o
i
d
V
a
l
v
e
P
e
r
m
e
a
t
e
S
t
r
e
a
m
SV
-
1
0
2
S
o
l
e
n
o
i
d
V
a
l
v
e
B
a
c
k
w
a
sh
st
r
e
a
m
P
-
1
0
1
P
e
r
i
st
a
l
t
i
c
P
u
m
p
P
-
1
0
2
D
i
a
p
h
r
a
g
m P
u
m
p
FM
-
101
L
i
q
u
i
d
F
l
o
w
M
e
t
e
r
M
e
mb
r
a
n
e
H
o
l
l
o
w
F
i
b
e
r
M
e
mb
r
a
n
e
I
n
th
i
s
w
o
r
k
,
P
o
ly
et
h
er
s
u
l
f
o
n
e
(
P
E
S)
m
ater
ial
w
it
h
ap
p
r
o
x
i
m
atel
y
8
0
-
1
0
0
k
d
a
p
o
r
e
s
ize
m
e
m
b
r
a
n
e
w
a
s
u
s
ed
i
n
th
e
f
iltra
tio
n
s
y
s
t
e
m
.
T
h
e
d
ata
co
llectio
n
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
3
is
p
er
f
o
r
m
ed
u
s
i
n
g
r
an
d
o
m
s
tep
te
s
t to
th
e
p
er
m
ea
te
p
u
m
p
.
T
h
is
w
ill ex
c
ite
th
e
d
y
n
a
m
ic
o
f
th
e
f
iltra
tio
n
p
r
o
ce
s
s
.
7
0
p
er
ce
n
t o
f
th
e
d
ata
is
u
s
e
d
to
co
n
s
tr
u
c
t
t
h
e
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
u
s
i
n
g
s
elec
ted
tr
ain
i
n
g
m
e
th
o
d
,
w
h
ile
a
n
o
th
er
3
0
p
er
ce
n
t
is
u
s
ed
f
o
r
test
i
n
g
t
h
e
n
e
u
r
al
n
e
t
w
o
r
k
ac
c
u
r
ac
y
.
Fig
u
r
e
3
.
E
x
p
er
i
m
en
t d
ata
2
.
2
.
CP
SO
G
S
A
Alg
o
rit
h
m
T
h
e
C
P
SOGSA
i
s
an
ef
f
ec
ti
v
e
o
p
tim
izat
io
n
tech
n
iq
u
e
th
at
ca
n
p
r
o
v
id
e
o
p
tim
al
s
o
lu
tio
n
f
o
r
m
a
n
y
ap
p
licatio
n
s
.
Fu
n
d
a
m
e
n
tal
ap
p
r
o
ac
h
o
f
th
e
alg
o
r
ith
m
is
to
allo
w
m
o
r
e
g
r
o
u
p
s
w
it
h
d
if
f
er
en
t
ad
v
an
ta
g
es
to
s
ea
r
ch
f
o
r
t
h
e
b
est
s
o
lu
tio
n
.
W
ith
t
h
is
m
eth
o
d
,
it
is
les
s
p
o
s
s
ib
ilit
y
f
o
r
t
h
e
a
lg
o
r
it
h
m
to
tr
ap
at
th
e
lo
ca
l
m
i
n
i
m
a.
T
h
e
co
o
p
er
ativ
e
tech
n
iq
u
e
in
t
h
is
w
o
r
k
is
d
escr
i
b
ed
b
y
t
h
e
i
n
ter
ac
tio
n
b
et
w
ee
n
m
a
s
ter
a
n
d
s
la
v
e
s
.
0
500
1000
1500
2000
2500
3000
3500
4000
0
20
40
T
i
m
e
(
s
)
Fl
u
x
(
L
/
m
2
h
)
0
500
1000
1500
2000
2500
3000
3500
4000
0
100
200
300
T
i
m
e
(
s
)
TM
P
(
m
b
a
r
)
0
500
1000
1500
2000
2500
3000
3500
4000
0
10
20
T
i
m
e
(
s
)
A
i
r
f
l
o
w
(
S
L
P
M
)
0
500
1000
1500
2000
2500
3000
3500
4000
0
2
4
T
i
m
e
(
s
)
P
u
m
p
(
V
o
l
t
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
N
eu
r
a
l Net
w
o
r
k
b
a
s
ed
Mo
d
el
P
r
ed
ictive
C
o
n
tr
o
l wi
th
C
P
S
O
GS
A
fo
r
S
MBR
F
iltr
a
tio
n
(
Za
ka
r
ia
h
Yu
s
u
f)
1541
T
h
e
n
u
m
b
er
o
f
s
la
v
e
g
r
o
u
p
s
c
an
b
e
g
en
er
ated
ac
co
r
d
in
g
l
y
d
ep
en
d
in
g
o
n
t
h
e
co
m
p
lex
it
y
o
f
th
e
o
p
ti
m
iza
tio
n
p
r
o
b
lem
.
Fi
g
u
r
e
4
s
h
o
w
s
th
e
c
o
o
p
er
ativ
e
ar
ch
itectu
r
e
b
et
w
ee
n
m
a
s
ter
an
d
s
la
v
e
g
r
o
u
p
s
.
Fig
u
r
e
4
.
T
h
e
co
o
p
er
ativ
e
ar
c
h
itect
u
r
e
o
f
th
e
al
g
o
r
ith
m
E
ac
h
o
f
t
h
e
s
la
v
e
g
r
o
u
p
s
w
ill
l
o
o
k
f
o
r
th
e
b
est
f
it
n
es
s
an
d
t
h
i
s
f
it
n
e
s
s
v
alu
e
w
i
ll
b
e
co
m
p
ar
ed
am
o
n
g
th
e
s
la
v
e
g
r
o
u
p
.
T
h
e
b
est
f
itn
ess
o
f
t
h
e
s
la
v
e
g
r
o
u
p
w
ill
b
e
co
m
p
ar
ed
ag
ai
n
w
it
h
t
h
e
m
a
s
ter
g
r
o
u
p
an
d
t
h
e
b
est f
it
n
es
s
ag
e
n
t
w
ill b
e
u
s
ed
f
o
r
th
e
v
elo
cit
y
u
p
d
ate
ca
lcu
la
tio
n
u
s
in
g
eq
u
at
io
n
(
1
)
.
(
+
1
)
=
×
(
)
3
+
1
×
×
1
+
2
×
1
(
−
(
)
)
×
2
+
3
×
2
(
−
(
)
)
×
3
(
1
)
W
h
er
e
1
,
2
an
d
3
ar
e
th
e
co
n
s
ta
n
t.
1
,
2
an
d
3
ar
e
th
e
n
o
r
m
al
d
is
tr
ib
u
ti
o
n
r
an
d
o
m
n
u
m
b
er
0
to
1
.
is
th
e
b
est
p
o
s
itio
n
f
r
o
m
th
e
s
lav
e
g
r
o
u
p
s
w
h
ile
is
th
e
p
est
p
o
s
itio
n
f
r
o
m
th
e
m
a
s
ter
g
r
o
u
p
.
T
h
e
p
o
s
itio
n
u
p
d
ate
eq
u
atio
n
i
s
g
i
v
en
b
y
:
(
+
1
)
=
+
(
+
1
)
(
2
)
T
h
e
co
m
p
etiti
v
e
b
et
w
ee
n
t
h
e
s
lav
e
an
d
t
h
e
m
a
s
ter
w
h
ic
h
ad
o
p
ted
in
[
1
0
]
is
also
ap
p
lied
in
th
is
alg
o
r
ith
m
,
w
h
er
e:
I
F
g
B
est_
s
la
ve
>g
B
est_
Ma
s
ter
1
=1
,
2
=0
;
I
F
g
B
est_
s
la
ve
<g
B
est_
Ma
s
ter
1
=0
,
2
=1
;
IF
g
B
est_
s
la
ve
=g
B
est_
Ma
s
ter
1
=0
.
5
,
2
=0
.
5
I
n
th
i
s
w
o
r
k
t
w
o
s
la
v
e
g
r
o
u
p
s
w
er
e
u
tili
ze
i
n
th
e
r
ea
l
ti
m
e
o
p
ti
m
izatio
n
(
R
T
O)
f
o
r
th
e
MP
C
f
u
n
ctio
n
m
i
n
i
m
izatio
n
.
T
h
e
f
ir
s
t
s
la
v
e
i
s
t
h
e
GS
A
al
g
o
r
ith
m
t
h
at
a
s
d
ev
elo
p
ed
in
[
1
1
]
an
d
a
n
o
th
er
s
lav
e
i
s
f
r
o
m
i
n
er
tia
w
ei
g
h
t P
SO a
lg
o
r
it
h
m
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
o
f
C
P
SOGS
A
ca
n
b
e
d
escr
ib
ed
as th
e
f
o
llo
w
i
n
g
s
tep
s
:
Step
1
: I
n
itialize
t
h
e
p
o
p
u
latio
n
o
f
t
h
e
s
la
v
e
an
d
m
a
s
ter
g
r
o
u
p
s
p
o
s
itio
n
.
[
1
,
1
,
2
,
1
,
….
.
,
1
;
1
,
2
,
2
,
2
,
….
.
,
2
;
……
;
1
,
,
2
,
,
….
.
,
;
1
,
,
2
,
,
….
.
,
]
Step
2
: E
v
alu
ate
t
h
e
cu
r
r
en
t f
i
t
n
es
s
(
,
)
o
f
th
e
a
g
e
n
ts
.
Step
3
: Fin
d
th
e
p
er
s
o
n
al
b
est
an
d
w
o
r
s
t i
n
ea
ch
o
f
th
e
g
r
o
u
p
s
.
[
,
1
=
min
(
)
;
,
2
=
min
(
)
;
…
;
,
=
min
(
)
;
,
=
min
(
)
]
[
,
1
=
ma
x
(
)
;
,
2
=
ma
x
(
)
;
…
;
,
=
ma
x
(
)
;
,
=
ma
x
(
)
]
Step
4
:.Fin
d
1
an
d
2
u
s
in
g
co
m
p
et
itiv
e
al
g
o
r
ith
m
.
1
2
3
……….
……….
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
5
3
8
–
1
5
4
5
1542
Step
5
: Calcu
late
an
d
u
s
i
n
g
eq
u
atio
n
s
(
1
0
)
an
d
(
1
6
)
in
[
1
1
]
(
f
o
r
g
r
o
u
p
s
th
at
r
eq
u
ir
ed
th
i
s
v
ar
iab
les).
Step
6
: U
p
d
ate
v
elo
cit
y
an
d
p
o
s
itio
n
f
o
r
all
g
r
o
u
p
s
w
it
h
m
a
s
ter
g
r
o
u
p
b
y
u
s
i
n
g
eq
u
atio
n
(
1
)
an
d
(
2
)
.
Step
7
: Co
m
p
ar
e
if
m
ee
t th
e
o
p
ti
m
izatio
n
cr
iter
ia.
I
f
n
o
t,
r
etu
r
n
to
s
tep
2
Step
8
: Retu
r
n
to
t
h
e
b
est s
o
l
u
tio
n
2
.
3
.
Neura
l N
et
w
o
rk
M
o
del P
re
dict
iv
e
Co
ntr
o
l
NNM
P
C
is
a
m
o
d
el
b
ased
co
n
tr
o
l
s
y
s
te
m
w
h
ic
h
ex
p
lici
tl
y
e
m
p
lo
y
s
a
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
to
p
r
ed
ict
th
e
p
r
o
ce
s
s
o
u
tp
u
t
at
f
u
tu
r
e
ti
m
e
in
s
ta
n
t.T
h
e
s
u
cc
e
s
s
f
u
l
o
f
t
h
i
s
co
n
tr
o
ller
is
m
u
ch
d
ep
en
d
s
o
n
th
e
ac
cu
r
ac
y
o
f
t
h
e
m
o
d
e.
T
h
is
w
ill
en
s
u
r
e
o
p
ti
m
al
o
u
tp
u
t
f
r
o
m
t
h
e
co
n
tr
o
ller
.
T
h
e
C
P
SOGSA
al
g
o
r
ith
m
is
u
s
ed
to
o
p
ti
m
ize
i
n
p
u
t
o
f
t
h
e
co
n
t
r
o
ller
in
o
r
d
er
to
m
in
i
m
ize
MP
C
co
s
t
f
u
n
ct
io
n
.
T
h
is
o
p
tim
izatio
n
p
r
o
ce
s
s
is
r
ep
ea
ted
at
ev
er
y
s
a
m
p
li
n
g
i
n
t
er
v
al.
Fig
u
r
e
5
s
h
o
w
s
th
e
MP
C
b
lo
ck
d
iag
r
a
m
.
Fig
u
r
e
5
.
B
lo
ck
Diag
r
a
m
o
f
t
h
e
NNM
P
C
f
o
r
SMB
R
Fil
tr
atio
n
P
r
o
ce
s
s
T
h
e
co
s
t f
u
n
ctio
n
o
f
t
h
e
NNM
P
C
is
g
i
v
en
b
y
:
(
,
)
=
{
∑
=
1
[
(
+
)
−
(
+
|
)
]
2
+
∑
[
∆
(
+
)
]
2
=
1
}
(
3
)
w
h
er
e,
is
p
r
ed
ictio
n
h
o
r
izo
n
,
is
co
n
tr
o
l
h
o
r
izo
n
.
,
is
a
s
et
p
o
in
t.
∆
(
+
)
is
th
e
c
h
a
n
g
e
o
f
in
p
u
t
.
an
d
ar
e
th
e
co
n
tr
o
l
w
ei
g
h
t
in
g
c
o
ef
f
icie
n
t
to
ad
d
w
eig
h
t
to
t
h
e
r
elativ
e
i
m
p
o
r
ta
n
ce
o
f
t
h
e
c
o
n
tr
o
l
an
d
tr
ac
k
i
n
g
er
r
o
r
s
.
Fo
r
th
e
co
n
s
tr
ain
ted
ca
s
es,
th
e
u
p
p
p
er
an
d
lo
w
er
b
o
u
n
d
o
f
th
e
m
a
n
ip
u
lted
v
ar
iab
les
ar
e
g
iv
e
n
b
y
:
≤
(
)
≤
≤
(
)
≤
(
4
)
∆
≤
(
)
−
(
−
1
)
≤
∆
.
I
n
t
h
is
w
o
r
k
,
t
h
e
i
n
p
u
t
co
n
s
tr
ain
i
s
d
eter
m
i
n
e
b
y
t
h
e
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
p
er
m
e
ate
p
u
m
p
v
o
ltag
e
f
r
o
m
th
e
cr
itical
f
l
u
x
test
.
I
n
t
h
i
s
w
o
r
k
th
e
m
i
n
i
m
u
m
v
o
ltag
e
(
)
is
s
et
to
0
,
w
h
ile
th
e
m
a
x
i
m
u
m
v
o
ltag
e
(
)
is
3
.
5
v
o
lt.
L
et
t
h
e
s
tate
o
f
th
e
s
y
s
te
m
i
n
e
ac
h
s
a
m
p
lin
g
i
n
ter
v
al,
is
d
ef
i
n
ed
as f
o
llo
w
s
:
̂
(
)
=
[
̂
0
(
)
̂
1
(
)
⋮
̂
−
1
(
)
]
(
5
)
w
h
er
e
̂
(
)
=
(
+
)
f
o
r
Δ
(
+
)
=
0
;
≥
0
I
n
th
i
s
ap
p
r
o
ac
h
th
e
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
is
u
s
ed
to
p
r
ed
ict
f
u
tu
r
e
o
u
tp
u
ts
s
e
v
er
al
s
tep
s
in
f
u
t
u
r
e
o
v
er
th
e
p
r
ed
ictio
n
h
o
r
izo
n
(
)
.
T
h
is
iter
ativ
e
tech
n
iq
u
e
i
s
wh
er
eo
u
tp
u
t
f
r
o
m
t
h
e
f
ir
s
t
p
r
ed
ictio
n
(
+
1
)
w
il
l
b
e
u
s
ed
as
in
p
u
ts
f
o
r
t
h
e
n
e
x
t
p
r
ed
ictio
n
i
n
p
r
ed
ictin
g
(
+
2
)
,
w
ith
th
is
i
ter
ativ
e
p
r
o
ce
d
u
r
e,
th
e
p
r
ed
ictio
n
o
f
m
u
l
tip
le
o
u
tp
u
t
f
u
t
u
r
e
s
tep
s
ca
n
b
e
d
o
n
e.
T
h
e
s
et
tin
g
o
f
t
h
e
NNM
P
C
p
ar
a
m
eter
s
e
m
p
lo
y
ed
in
th
is
w
o
r
k
i
s
p
r
esen
t
s
in
T
ab
le
2
.
C
o
s
t F
u
n
c
tio
n
Me
m
b
r
an
e
Fil
tr
atio
n
S
y
s
te
m
R
ef
er
e
n
ce
(
)
(
)
(
)
C
P
S
O
G
S
A
O
p
t
i
mi
z
a
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
N
eu
r
a
l Net
w
o
r
k
b
a
s
ed
Mo
d
el
P
r
ed
ictive
C
o
n
tr
o
l wi
th
C
P
S
O
GS
A
fo
r
S
MBR
F
iltr
a
tio
n
(
Za
ka
r
ia
h
Yu
s
u
f)
1543
T
ab
le
2
.
NNM
P
C
p
ar
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
P
r
e
d
i
c
t
i
o
n
H
o
r
i
z
o
n
,
5
C
o
n
t
r
o
l
H
o
r
i
z
o
n
,
3
W
e
i
g
h
t
,
(
φ
,
μ
)
10
S
a
mp
l
i
n
g
t
i
me
1
se
c
o
n
d
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
s
i
m
u
latio
n
r
e
s
u
l
t
f
o
r
to
w
c
y
cle
f
iltra
tio
n
s
h
o
w
s
t
h
e
f
il
tr
atio
n
p
r
o
ce
s
s
w
it
h
o
u
t
co
n
tr
o
ller
ca
u
s
e
th
e
f
lu
x
d
ec
li
n
e
at
t
h
e
en
d
ea
c
h
o
f
t
h
e
c
y
cle.
T
h
e
ap
p
licatio
n
o
f
co
n
tr
o
ller
ca
n
m
ain
tain
t
h
e
p
er
m
ea
te
f
l
u
x
at
th
e
d
esire
d
s
et
p
o
in
t.
Ho
w
e
v
er
,
h
ig
h
o
v
er
s
h
o
o
t
co
n
tr
o
ller
ill
ef
f
ec
t
th
e
f
iltra
tio
n
p
er
f
o
r
m
a
n
ce
.
Fro
m
t
h
e
r
esu
lt
,
it c
an
b
e
o
b
s
er
v
ed
t
h
at
t
h
e
N
N
MP
C
p
er
f
o
r
m
b
etter
co
m
p
ar
e
w
it
h
t
h
e
P
I
D
co
n
tr
o
ller
.
T
h
e
f
i
r
s
t c
y
cle
co
n
tr
o
ller
p
er
f
o
r
m
a
n
ce
i
n
d
icate
s
th
e
NN
MP
C
co
n
tr
o
ller
p
r
o
d
u
ce
o
n
l
y
1
.
1
7
%
o
f
o
v
er
s
h
o
o
t
co
m
p
ar
ed
w
it
h
th
e
P
I
D
w
it
h
2
0
.
6
4
%.
T
h
e
s
ettlin
g
ti
m
e
s
o
f
t
h
e
co
n
tr
o
ller
s
ar
e
1
8
.
2
s
ec
o
n
d
f
o
r
th
e
NNM
P
C
a
n
d
1
7
.
9
s
ec
o
n
d
f
o
r
P
I
D
co
n
tr
o
ller
.
I
n
ter
m
o
f
th
e
ac
c
u
r
ac
y
o
f
th
e
co
n
tr
o
ller
th
e
I
AE
s
h
o
w
s
NNM
P
C
co
n
tr
o
ller
p
er
f
o
r
m
at
7
2
.
8
an
d
th
e
P
I
D
co
n
tr
o
ller
is
at
1
1
4
.
2
.
Fig
u
r
e
6
s
h
o
w
s
th
e
r
esp
o
n
s
e
o
f
th
e
co
n
tr
o
ller
s
f
o
r
t
w
o
c
y
c
le
f
iltra
tio
n
is
s
h
o
ws
in
Fi
g
u
r
e
6
.
T
h
e
s
tep
r
esp
o
n
s
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
co
n
tr
o
ller
s
is
p
r
esen
ts
i
n
T
ab
le
3
.
Fig
u
r
e
6
.
P
er
f
o
r
m
a
n
ce
C
o
n
tr
o
l
ler
f
o
r
T
w
o
C
y
cles
T
ab
le
3
.
C
o
n
tr
o
ller
P
e
r
f
o
r
m
a
n
ce
at
First C
y
cle
C
o
n
t
r
o
l
l
e
r
%Ov
e
r
sh
o
o
t
S
e
t
t
l
i
n
g
T
i
me
(
se
c
.
)
I
A
E
P
I
D
2
0
.
6
4
1
7
.
9
1
1
4
.
2
N
N
M
P
C
1
.
1
7
1
7
.
2
7
2
.
8
T
h
e
s
ec
o
n
d
s
i
m
u
latio
n
r
es
u
lt
s
is
f
o
u
r
c
y
cle
s
w
it
h
c
h
an
g
e
in
s
et
p
o
in
t.
I
t
ca
n
b
e
o
b
s
e
r
v
ed
,
th
e
NNM
P
C
p
r
o
d
u
ce
ap
p
r
o
p
r
iate
r
esp
o
n
s
e
at
e
v
er
y
s
et
p
o
in
t
te
s
ted
.
T
h
e
P
I
D
co
n
tr
o
ller
p
r
o
d
u
ce
h
ig
h
o
v
er
s
h
o
o
t
at
h
i
g
h
er
s
e
t
p
o
in
t
a
n
d
th
er
e
is
n
o
e
x
ce
s
s
iv
e
o
v
er
s
h
o
o
t
f
o
r
s
et
p
o
in
t
1
5
L
/
m
2
h
w
h
ic
h
i
s
in
t
h
e
f
o
r
t
h
c
y
cle.
Fig
u
r
e
7
s
h
o
w
s
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
co
n
tr
o
ller
s
f
o
r
th
e
s
et
p
o
in
t c
h
an
g
e.
0
50
100
150
200
250
0
5
10
15
20
25
30
T
i
m
e
(
s
)
Fl
u
x
(
L
/
m
2
h
)
S
e
t
p
o
i
n
t
W
i
t
h
o
u
t
c
o
n
t
r
o
l
l
e
r
P
I
D
N
N
M
P
C
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
5
3
8
–
1
5
4
5
1544
Fig
u
r
e
7
.
Fo
u
r
c
y
cles
w
i
th
s
et
p
o
in
t c
h
an
g
e
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ts
t
h
e
ap
p
licatio
n
o
f
NNM
P
C
w
it
h
C
P
S
OGS
A
f
o
r
SMB
R
f
iltra
tio
n
c
o
n
tr
o
l.
T
h
e
C
P
SOGS
A
a
lg
o
r
it
h
m
p
er
f
o
r
m
s
as
a
R
T
O
o
f
th
e
co
n
tr
o
ller
c
o
s
t
f
u
n
ctio
n
w
it
h
i
n
1
s
ec
o
n
d
s
a
m
p
lin
g
ti
m
e.
T
h
is
w
o
r
k
u
tili
ze
d
t
h
e
n
e
u
r
al
n
e
t
wo
r
k
m
o
d
el
th
e
SMB
R
f
il
tr
atio
n
p
r
o
ce
s
s
.
T
h
e
s
i
m
u
latio
n
r
es
u
lt
f
o
r
t
w
o
f
iltra
tio
n
c
y
cles
i
n
d
icate
s
t
h
e
co
n
tr
o
ller
ca
n
p
r
ev
en
t
f
r
o
m
f
lu
x
d
ec
l
in
e
d
u
r
in
g
th
e
f
iltra
tio
n
p
r
o
c
ess
.
I
n
ter
m
o
f
t
h
e
ap
p
licatio
n
o
f
th
e
co
n
tr
o
ller
it
ca
n
b
e
co
n
clu
d
ed
th
e
N
NM
P
C
co
n
tr
o
ller
p
er
f
o
r
m
b
etter
th
an
th
e
P
I
D
co
n
tr
o
ller
f
o
r
esp
ec
iall
y
f
o
r
th
e
o
v
er
s
h
o
o
t
an
d
p
r
ec
is
io
n
o
f
th
e
co
n
tr
o
ller
.
Si
m
u
latio
n
f
o
r
s
et
p
o
in
t
ch
an
g
e
in
d
icate
s
th
e
NNM
P
C
g
i
v
es
a
g
o
o
d
tr
ac
k
i
n
g
at
all
s
et
p
o
i
n
t
w
i
th
o
u
t
s
ig
n
i
f
ica
n
t
o
v
er
s
h
o
o
t.
Me
an
w
h
i
le,
th
e
P
I
D
co
n
tr
o
ller
also
ca
n
tr
ac
k
t
h
e
s
et
p
o
in
t;
h
o
w
e
v
er
t
h
er
e
is
an
o
v
er
s
h
o
o
t
w
as
o
b
s
er
v
ed
at
th
e
h
ig
h
s
e
t
p
o
in
t.
Fin
all
y
,
t
h
e
N
NM
P
C
w
it
h
C
P
SOGS
A
is
a
g
o
o
d
p
o
ten
tial
co
n
tr
o
ller
to
b
e
ap
p
lied
in
m
an
y
p
r
o
ce
s
s
co
n
tr
o
l
ap
p
licatio
n
s
.
Ho
w
e
v
er
,
f
u
r
th
e
r
s
tu
d
y
n
ee
d
s
to
b
e
d
o
n
e
f
o
r
ap
p
licatio
n
s
th
at
r
eq
u
ir
ed
m
u
ch
f
a
s
ter
s
a
m
p
l
in
g
ti
m
e
a
n
d
R
T
O.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
li
k
e
to
t
h
an
k
t
h
e
R
esear
ch
Un
iv
er
s
it
y
Gr
an
t
(
GUP
)
v
o
te
1
3
H7
0
,
Un
i
v
er
s
iti
T
ek
n
o
lo
g
i
Ma
la
y
s
ia
f
o
r
th
e
f
i
n
an
cia
l
s
u
p
p
o
r
t.
T
h
e
f
ir
s
t
au
th
o
r
w
an
t
s
to
th
an
k
th
e
U
n
iv
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A
(
UiT
M)
an
d
th
e
MO
H
E
f
o
r
th
e
T
P
M
-
SLA
I
s
c
h
o
lar
s
h
ip
.
RE
F
E
R
E
NC
E
S
[1
]
P
.
L
.
Clec
h
,
e
t
a
l.
,
“
F
o
u
li
n
g
in
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs
u
se
d
in
w
a
ste
w
a
ter
tr
e
a
t
m
e
n
t,
”
J
.
M
e
mb
.
S
c
i.
,
v
o
l
/i
ss
u
e
:
284
(
1
–
2
)
,
p
p
.
1
7
–
5
3
,
2
0
0
6
.
[2
]
Z.
Yu
su
f
,
e
t
a
l.
,
“
F
o
u
li
n
g
c
o
n
tro
l
stra
teg
y
f
o
r
su
b
m
e
rg
e
d
m
e
m
b
ra
n
e
b
i
o
re
a
c
to
r
f
il
tratio
n
p
r
o
c
e
ss
e
s
u
sin
g
a
e
ra
ti
o
n
a
irf
lo
w
,
b
a
c
k
w
a
sh
,
a
n
d
re
lax
a
ti
o
n
:
a
re
v
ie
w
,
”
De
sa
li
n
.
W
a
ter
T
re
a
t.
,
p
p
.
1
–
1
3
,
2
0
1
5
.
[3
]
J.
Bu
sc
h
,
e
t
a
l.
,
“
Ru
n
-
to
-
r
u
n
c
o
n
t
ro
l
o
f
m
e
m
b
ra
n
e
f
il
tratio
n
p
ro
c
e
ss
e
s,”
AICh
E
J
.
,
v
o
l
/
issu
e
:
53
(
9
)
,
p
p
.
2
3
1
6
–
2
3
2
8
,
2
0
0
7
.
[4
]
G
.
F
e
rre
ro
,
e
t
a
l.
,
“
A
u
to
m
a
ti
c
c
o
n
tr
o
l
sy
ste
m
s
f
o
r
su
b
m
e
r
g
e
d
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs:
A
sta
te
-
of
-
th
e
-
a
rt
re
v
ie
w
,
”
W
a
ter
Res
.
,
v
o
l.
4
6
,
p
p
.
3
4
2
1
–
3
4
3
3
,
2
0
1
2
.
[5
]
S
.
Cu
rc
io
,
e
t
a
l.
,
“
De
sig
n
a
n
d
tu
n
i
n
g
o
f
fe
e
d
b
a
c
k
c
o
n
tro
ll
e
rs:
e
ff
e
c
t
s o
n
p
r
o
tein
s
u
lt
ra
f
il
tratio
n
p
ro
c
e
s
s
m
o
d
e
led
b
y
a
h
y
b
rid
sy
st
e
m
,
”
De
sa
li
n
.
W
a
ter
T
re
a
t.
,
v
o
l
/i
ss
u
e
:
34
(
1
–
3
)
,
p
p
.
2
9
5
–
3
0
3
,
2
0
1
1
.
[6
]
Á
.
Ro
b
les
,
e
t
a
l.
,
“
In
str
u
m
e
n
tatio
n
,
c
o
n
tr
o
l
,
a
n
d
a
u
to
m
a
ti
o
n
f
o
r
su
b
m
e
rg
e
d
a
n
a
e
ro
b
ic
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs,”
En
v
iro
n
.
T
e
c
h
n
o
l.
,
v
o
l
/i
ss
u
e
:
36
(
14
)
,
p
p
.
3
7
–
4
1
,
2
0
1
5
.
[7
]
H.
G
.
Ha
n
,
e
t
a
l.
,
“
M
o
d
e
l
p
re
d
i
c
ti
v
e
c
o
n
tro
l
o
f
d
isso
lv
e
d
o
x
y
g
e
n
c
o
n
c
e
n
tratio
n
b
a
se
d
o
n
a
se
lf
-
o
rg
a
n
izin
g
RBF
n
e
u
ra
l
n
e
tw
o
rk
,
”
Co
n
tr
o
l
E
n
g
.
Pr
a
c
t.
,
v
o
l
/
issu
e
:
20
(
4
)
,
p
p
.
4
6
5
–
4
7
6
,
2
0
1
2
.
[8
]
K.
O
w
a
,
e
t
a
l.
,
“
A
W
a
v
e
let
Ne
u
ra
l
Ne
t
w
o
rk
Ba
se
d
No
n
-
li
n
e
a
r
M
o
d
e
l
P
re
d
ictiv
e
Co
n
tr
o
ll
e
r
f
o
r
a
M
u
lt
i
-
v
a
riab
le
Co
u
p
led
T
a
n
k
S
y
ste
m
,
”
In
t.
J
.
A
u
to
m.
Co
m
p
u
t
.
,
v
o
l
.
1
2
,
p
p
.
1
5
6
–
1
7
0
,
2
0
1
5
.
[9
]
L
.
Ch
e
n
g
,
e
t
a
l.
,
“
Ne
u
ra
l
-
Ne
tw
o
r
k
-
Ba
se
d
No
n
li
n
e
a
r
M
o
d
e
l
P
re
d
ic
ti
v
e
Co
n
tro
l
f
o
r
P
iez
o
e
lec
tri
c
A
c
tu
a
to
rs,”
IEE
E
T
ra
n
s.
I
n
d
.
El
e
c
tro
n
.
,
v
o
l
/i
ss
u
e
:
62
(
12
)
,
p
p
.
7
7
1
7
–
7
7
2
7
,
2
0
1
5
.
[1
0
]
B.
Niu
a
n
d
H.
W
u
,
“
M
C
P
S
O:
A
m
u
lt
i
-
sw
a
r
m
c
o
o
p
e
ra
ti
v
e
p
a
rti
c
le
s
w
a
r
m
o
p
ti
m
ize
r,
”
Ap
p
l.
M
a
th
.
Co
mp
u
t
.
,
v
o
l.
1
8
5
,
p
p
.
1
0
5
0
–
1
0
6
2
,
2
0
0
7
.
[1
1
]
E.
Ra
sh
e
d
i,
e
t
a
l.
,
“
G
S
A
:
A
G
r
a
v
it
a
ti
o
n
a
l
S
e
a
rc
h
A
l
g
o
rit
h
m
,
”
In
f.
S
c
i.
(
Ny
).
,
v
o
l
/i
ss
u
e
:
179
(
13
)
,
p
p
.
2
2
3
2
–
2
2
4
8
,
2
0
0
9
.
0
100
200
300
400
500
0
5
10
15
20
25
30
T
i
m
e
(
s
)
Fl
u
x
(
L
/
m
2
h
)
S
e
t
p
o
i
n
t
P
I
D
N
N
M
P
C
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
N
eu
r
a
l Net
w
o
r
k
b
a
s
ed
Mo
d
el
P
r
ed
ictive
C
o
n
tr
o
l wi
th
C
P
S
O
GS
A
fo
r
S
MBR
F
iltr
a
tio
n
(
Za
ka
r
ia
h
Yu
s
u
f)
1545
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Zak
a
riah
Yu
su
f
re
c
e
i
v
e
d
h
is
B.
En
g
.
Ho
n
s
(El
e
c
tri
c
a
l)
a
n
d
M
S
c
.
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
M
a
la
y
sia
in
2
0
0
7
a
n
d
2
0
1
2
re
sp
e
c
ti
v
e
l
y
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
to
w
a
rd
h
is
P
h
D
in
p
ro
c
e
s
s
c
o
n
tr
o
l
a
t
th
e
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
a
la
y
sia
.
He
h
a
s
a
f
e
w
y
e
a
rs’
e
x
p
e
rien
c
e
s
in
c
o
n
tro
l
a
n
d
in
stru
m
e
n
tatio
n
f
ro
m
v
a
rio
u
s
in
d
u
stries
.
His
c
u
rre
n
t
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
m
e
m
b
ra
n
e
f
il
tratio
n
a
n
d
a
p
p
l
ica
ti
o
n
o
f
so
f
t
c
o
m
p
u
ti
n
g
in
th
e
a
re
a
o
f
p
ro
c
e
ss
m
o
d
e
li
n
g
a
n
d
c
o
n
tro
l.
Ir.
Dr.
No
r
h
a
li
z
a
A
b
d
u
l
W
a
h
a
b
is
c
u
rre
n
t
ly
a
n
A
ss
o
c
iate
P
ro
f
e
ss
o
r
a
t
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
(U
T
M
).
S
h
e
is
c
u
rre
n
t
l
y
th
e
He
a
d
De
p
a
rt
m
e
n
t
o
f
Co
n
tr
o
l
a
n
d
M
e
c
h
a
tro
n
ics
E
n
g
in
e
e
rin
g
De
p
a
rtme
n
t
a
t
th
e
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
UT
M
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
D
i
n
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
m
a
jo
rin
g
in
C
o
n
tr
o
l
in
Ju
ly
2
0
0
9
.
S
h
e
is
a
c
ti
v
e
ly
in
v
o
lv
e
d
in
re
se
a
rc
h
in
g
a
n
d
tea
c
h
in
g
in
t
h
e
f
ield
o
f
in
d
u
strial
p
r
o
c
e
ss
c
o
n
tr
o
l.
He
r
e
x
p
e
rti
se
is
in
m
o
d
e
ll
in
g
a
n
d
c
o
n
tro
l
o
f
in
d
u
str
ial
p
ro
c
e
ss
p
lan
t.
Re
c
e
n
tl
y
sh
e
h
a
s
w
o
rk
e
d
p
rima
ril
y
o
n
d
if
f
e
re
n
t
t
y
p
e
s
o
f
d
o
m
e
stic
a
n
d
in
d
u
strial
w
a
ste
w
a
ter t
re
a
t
m
e
n
t
tec
h
n
o
l
o
g
y
to
w
a
rd
s o
p
ti
m
iza
ti
o
n
a
n
d
e
n
e
rg
y
sa
v
in
g
s
y
st
e
m
.
Dr.
En
g
.
A
b
d
a
ll
a
h
A
b
u
sa
m
h
a
s
b
o
th
B.
S
c
.
in
Civ
il
En
g
in
e
e
rin
g
a
n
d
M
.
S
c
.
in
S
a
n
i
tary
En
g
in
e
e
rin
g
f
ro
m
th
e
Un
iv
e
r
sit
y
o
f
Kh
a
rto
u
m
,
S
u
d
a
n
.
His
P
h
D
in
En
v
ir
o
n
m
e
n
tal
En
g
in
e
e
rin
g
is
f
ro
m
W
a
g
e
n
in
g
e
n
Un
iv
e
rsit
y
,
T
h
e
Ne
th
e
rlan
d
s.
He
is
c
u
rre
n
tl
y
a
R
e
se
a
rc
h
S
c
ien
ti
st
a
t
th
e
K
u
w
a
it
In
stit
u
te
f
o
r
S
c
ien
ti
f
ic
Re
se
a
rc
h
,
Ku
w
a
it
.
His
re
s
e
a
rc
h
in
tere
sts
in
c
lu
d
e
m
o
d
e
li
n
g
,
sim
u
latio
n
a
n
d
c
o
n
tro
l
o
f
e
n
v
iro
n
m
e
n
tal
sy
ste
m
s.
Evaluation Warning : The document was created with Spire.PDF for Python.