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.
6
,
No
.
6
,
Dec
em
b
er
201
6
,
p
p
.
2
6
1
0
~
2
6
2
0
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
2
1
1
2
2610
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
Fault Diag
no
sis
and Reco
n
figura
ti
o
n of Multilev
el
Inv
erte
r
S
w
itch
Failure
-
A
Perf
o
r
m
a
nce
P
e
r
spectiv
e
T
.
G
.
M
a
njuna
t
h
1
,
Ash
o
k
K
u
s
a
g
ur
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
,
S
a
i
V
i
d
y
a
I
n
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Ba
n
g
a
lo
r
e
,
In
d
ia
2
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
,
UBD
T
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Da
v
a
n
g
e
re
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
7
,
2
0
1
6
R
ev
i
s
ed
Sep
1
7
,
2
0
1
6
A
cc
ep
ted
No
v
1
,
2
0
1
6
M
u
lt
il
e
v
e
l
In
v
e
rters
(M
L
I)
g
a
in
s
im
p
o
rtan
c
e
in
Distrib
u
ti
o
n
s
y
ste
m
s,
El
e
c
tri
c
a
l
Driv
e
s
y
ste
m
s,
HV
DC
s
y
ste
m
s
a
n
d
m
a
n
y
m
o
re
a
p
p
li
c
a
ti
o
n
s.
A
s
M
u
lt
il
e
v
e
l
In
v
e
rters
c
o
m
p
rise
s
o
f
n
u
m
b
e
r
o
f
p
o
w
e
r
sw
i
tch
e
s
th
e
f
a
u
lt
d
iag
n
o
sis
o
f
M
L
I
b
e
c
o
m
e
s
ted
io
u
s.
T
h
is
p
a
p
e
r
is
a
n
a
tt
e
m
p
t
to
d
e
v
e
lo
p
a
n
d
a
n
a
ly
z
e
th
e
f
a
u
lt
d
iag
n
o
sis
m
e
th
o
d
th
a
t
u
ti
li
z
e
s
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
to
g
e
t
it
train
e
d
w
it
h
th
e
f
a
u
lt
situ
a
ti
o
n
s.
A
p
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
o
f
G
e
n
e
ti
c
A
l
g
o
rit
h
m
(
G
A
)
a
n
d
th
e
M
o
d
if
ied
G
e
n
e
ti
c
A
lg
o
rit
h
m
(M
GA
),
w
h
ich
o
p
ti
m
ize
s
th
e
A
rti
f
icia
l
Ne
u
ra
l
N
e
tw
o
rk
(
A
N
N)
th
a
t
train
s
it
se
lf
o
n
th
e
f
a
u
lt
d
e
tec
ti
o
n
,
a
n
d
re
c
o
n
f
ig
u
ra
ti
o
n
o
f
th
e
Ca
sc
a
d
e
d
M
u
lt
il
e
v
e
l
In
v
e
rte
rs
(CM
L
I)
is
a
tt
e
m
p
ted
.
T
h
e
T
o
tal
H
a
r
m
o
n
ic
Disto
rti
o
n
(T
HD
)
o
c
c
u
rrin
g
d
u
e
to
s
w
it
c
h
f
a
il
u
re
s
o
r
d
riv
e
r
f
a
il
u
re
s
o
c
c
u
r
rin
g
in
th
e
CM
L
I
is
c
o
n
sid
e
re
d
f
o
r
th
is
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis.
El
a
p
se
d
ti
m
e
o
f
re
c
o
v
e
r
y
,
M
e
a
n
S
q
u
a
re
Err
o
r
(M
S
E)
a
n
d
th
e
c
o
m
p
u
tatio
n
a
l
b
u
d
g
e
ts
o
f
A
NN
a
re
th
e
p
e
r
f
o
r
m
a
n
c
e
p
a
ra
m
e
ter
s
c
o
n
sid
e
re
d
i
n
th
is
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis.
Op
ti
m
iza
ti
o
n
is
in
v
o
lv
e
d
in
t
h
e
p
ro
c
e
ss
o
f
u
p
d
a
ti
n
g
t
h
e
w
e
i
g
h
t
a
n
d
th
e
b
ias
v
a
lu
e
s
in
th
e
A
NN
n
e
tw
o
rk
.
M
a
tl
a
b
b
a
se
d
sim
u
latio
n
is
c
a
rried
o
u
t
a
n
d
th
e
re
su
lt
s
a
re
o
b
t
a
in
e
d
a
n
d
tab
u
late
d
f
o
r
th
e
p
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
.
It
w
a
s
o
b
se
rv
e
d
th
a
t
M
o
d
if
ied
G
e
n
e
ti
c
A
l
g
o
rit
h
m
p
e
r
f
o
r
m
e
d
b
e
tt
e
r
th
a
n
th
e
G
e
n
e
ti
c
A
lg
o
rit
h
m
w
h
il
e
o
p
ti
m
izin
g
th
e
A
NN
train
in
g
.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
C
ascad
ed
m
u
ltil
e
v
el
i
n
v
er
ter
Fau
lt d
etec
tio
n
an
d
r
ec
o
n
f
i
g
u
r
atio
n
Gen
etic
al
g
o
r
ith
m
Mo
d
if
ied
g
en
et
ic
alg
o
r
it
h
m
P
ar
am
eter
o
p
ti
m
izat
io
n
Co
p
y
rig
h
t
©
2
0
1
6
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
:
T
.
G.
Ma
n
j
u
n
ath
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
i
n
ee
r
in
g
,
Sai V
id
y
a
I
n
s
tit
u
te
o
f
T
ec
h
n
o
l
o
g
y
,
B
an
g
alo
r
e,
I
n
d
ia
.
E
m
ail:
t
g
m
n
at
h
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Dif
f
er
en
t
m
u
ltil
e
v
el
i
n
v
er
ter
(
ML
I
)
to
p
o
lo
g
ies
ar
e
ex
p
lo
r
ed
an
d
ar
e
r
ev
ie
w
ed
i
n
[
1
]
.
T
h
e
ca
s
ca
d
ed
m
u
ltil
e
v
el
in
v
er
ter
w
it
h
r
ed
u
ce
d
n
u
m
b
er
o
f
s
w
itc
h
es
a
r
e
d
is
cu
s
s
ed
[
2
]
.
T
h
e
C
ML
I
eli
m
i
n
ate
s
th
e
b
u
l
k
tr
an
s
f
o
r
m
er
s
av
a
ilab
le
in
th
e
m
u
lt
ip
u
ls
e
i
n
v
er
ter
s
,
cla
m
p
i
n
g
d
io
d
e
in
th
e
Dio
d
e
C
la
m
p
ed
ML
I
an
d
th
e
ca
p
ac
ito
r
s
in
Fl
y
i
n
g
C
ap
ac
ito
r
ML
I
[
3
]
.
C
M
L
I
g
ets
r
id
o
f
th
e
ca
p
ac
ito
r
v
o
lta
g
e
b
ala
n
cin
g
m
et
h
o
d
,
w
h
ic
h
is
a
m
aj
o
r
ch
allen
g
e
in
t
h
e
F
l
y
i
n
g
C
ap
ac
ito
r
Mu
l
tile
v
el
I
n
v
er
t
er
as;
i
t
n
ee
d
s
v
er
y
co
m
p
le
x
v
o
lta
g
e
b
ala
n
cin
g
tech
n
iq
u
es
[
4
].
Mo
d
u
lar
to
p
o
lo
g
y
o
f
th
e
C
M
L
I
f
ac
i
litates
th
e
to
p
o
lo
g
y
f
o
r
th
e
lo
ca
tio
n
o
f
f
au
lt
an
d
t
h
e
r
ec
o
n
f
i
g
u
r
atio
n
ap
p
lied
in
a
s
im
p
ler
m
an
n
er
[
5
]
.
W
h
er
ea
s
th
e
Dio
d
e
C
la
m
p
ed
ML
I
an
d
th
e
Fl
y
i
n
g
C
ap
ac
ito
r
ML
I
h
a
s
s
w
itc
h
es
co
n
tin
u
o
u
s
l
y
co
n
n
ec
ted
ac
co
r
d
in
g
to
th
e
n
u
m
b
er
o
f
v
o
lta
g
e
lev
e
ls
it
ca
n
d
eliv
er
,
w
h
ic
h
in
tr
o
d
u
ce
s
co
m
p
lex
i
t
y
w
h
ile
f
au
lt
lo
ca
tio
n
a
n
d
r
ec
o
n
f
i
g
u
r
atio
n
.
A
p
p
licatio
n
o
f
C
ML
I
r
an
g
es
f
r
o
m
ST
A
T
C
OM
[
6
]
t
o
A
ctiv
e
P
o
w
er
Fil
ter
,
w
h
ic
h
d
e
m
a
n
d
s
f
a
u
lt
f
r
ee
o
p
er
atio
n
s
in
ce
it
in
v
o
lv
es
p
o
w
er
q
u
alit
y
s
o
lu
tio
n
s
[
7
]
.
T
h
e
f
au
lt
d
ia
g
n
o
s
is
an
d
t
h
e
r
ec
o
n
f
i
g
u
r
atio
n
o
f
th
e
M
L
I
b
y
t
h
e
u
s
e
o
f
A
r
tific
i
al
Neu
r
al
Net
w
o
r
k
as
th
e
f
a
u
lt
d
ia
g
n
o
s
is
to
o
l
was
d
ev
elo
p
ed
w
h
ic
h
ex
h
ib
ite
d
9
5
%
ac
cu
r
ac
y
i
n
d
iag
n
o
s
is
o
f
th
e
f
a
u
lt
s
w
a
s
tab
u
lated
[
6
]
.
T
h
e
r
ec
o
n
f
ig
u
r
atio
n
m
et
h
o
d
p
r
o
p
o
s
ed
in
[
8
]
cl
ea
r
ed
b
o
th
th
e
o
p
en
cir
cu
it
an
d
th
e
clo
s
ed
cir
cu
it
f
au
lts
i
n
s
ix
p
er
io
d
ic
c
y
cles.
I
n
o
r
d
er
to
d
ev
elo
p
th
e
f
au
l
t
d
iag
n
o
s
is
t
h
e
d
ev
elo
p
m
e
n
t
o
f
a
m
at
h
e
m
a
tical
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
a
u
lt Dia
g
n
o
s
is
a
n
d
R
ec
o
n
fig
u
r
a
tio
n
o
f Mu
ltil
ev
el
I
n
ve
r
ter S
w
itch
F
a
ilu
r
e
-
A
…
(
T.G.
Ma
n
ju
n
a
th
)
2611
is
av
o
id
ed
d
u
e
to
th
e
u
s
e
o
f
AI
m
et
h
o
d
th
at
w
o
u
ld
g
r
ea
tl
y
r
e
d
u
ce
th
e
en
g
in
ee
r
i
n
g
an
d
d
ev
elo
p
m
e
n
t
ti
m
e.
T
h
e
r
eliab
ilit
y
o
f
t
h
e
A
d
j
u
s
tab
le
Sp
ee
d
Dr
iv
e
s
(
A
SD)
p
o
w
e
r
ed
b
y
C
M
L
I
i
s
i
m
p
r
o
v
ed
b
y
in
tr
o
d
u
cin
g
t
h
e
r
ed
u
n
d
an
t
m
o
d
u
les,
w
h
ic
h
wo
u
ld
w
o
r
k
w
h
en
a
n
y
o
f
t
h
e
m
o
d
u
les
f
ail
s
[
9
]
.
A
n
o
v
el
te
ch
n
iq
u
e
ca
lled
th
e
“n
eu
tr
al
s
h
if
t”
w
as
a
ls
o
i
n
tr
o
d
u
ce
d
w
h
ic
h
ad
o
p
ted
th
e
id
ea
t
h
at
co
m
p
e
n
s
ated
t
h
e
f
ail
u
r
e
i
n
o
n
e
m
o
d
u
le
w
i
th
th
e
r
ed
u
n
d
an
t
m
o
d
u
le
o
f
th
e
o
t
h
er
m
o
d
u
le.
A
9
9
.
9
9
%
d
r
iv
e
r
eliab
ilit
y
w
a
s
o
b
tain
ed
i
n
th
e
i
m
p
le
m
en
ta
tio
n
[
9
]
.
T
h
is
p
ap
er
u
s
es
th
e
r
ed
u
n
d
an
t
m
o
d
u
l
e
r
ep
lace
m
e
n
t
m
et
h
o
d
f
o
r
f
a
u
lt
d
iag
n
o
s
is
i
n
th
e
C
M
L
I
.
T
h
e
T
HD
o
b
tain
ed
f
r
o
m
t
h
e
M
L
I
is
th
e
s
o
u
r
ce
o
f
f
a
u
lt
d
etec
tio
n
in
t
h
e
m
et
h
o
d
u
s
ed
.
ANN
g
et
s
tr
ain
ed
b
y
g
etti
n
g
t
h
e
p
air
o
f
th
e
T
HD
v
alu
es
f
o
r
th
e
co
r
r
esp
o
n
d
in
g
f
a
u
lt
s
w
itc
h
p
o
s
itio
n
.
T
h
e
s
p
ee
d
o
f
tr
ain
i
n
g
t
h
e
A
NN
i
s
co
n
ce
n
tr
ated
in
th
i
s
p
ap
er
an
d
s
tep
s
ar
e
tak
en
to
i
m
p
r
o
v
e
i
t.
I
n
o
r
d
er
to
o
p
tim
ize
t
h
e
tr
ain
i
n
g
ti
m
e
o
f
t
h
e
A
NN
o
p
ti
m
izat
io
n
tech
n
iq
u
es
li
k
e
th
e
Gen
etic
A
l
g
o
r
ith
m
an
d
t
h
e
Mo
d
if
ied
Gen
etic
A
l
g
o
r
it
h
m
is
i
m
p
le
m
e
n
ted
o
n
th
e
tr
ai
n
i
n
g
o
f
th
e
A
NN.
T
h
e
w
ei
g
h
t
v
al
u
es
th
at
ar
e
u
s
ed
f
o
r
ea
ch
n
o
d
e
an
d
t
h
e
b
ias
v
al
u
es
ar
e
o
p
ti
m
ized
in
o
r
d
er
to
tr
ain
th
e
A
NN
f
aster
t
h
an
t
h
e
tr
ad
itio
n
al
tr
ai
n
i
n
g
m
eth
o
d
.
C
o
n
s
id
er
i
n
g
th
e
Me
a
n
Sq
u
ar
e
E
r
r
o
r
(
MSE
)
as
th
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
to
b
e
m
i
n
i
m
ized
,
th
e
m
o
d
u
le
n
u
m
b
er
w
h
er
e
f
au
l
t
o
cc
u
r
s
in
t
h
e
C
M
L
I
,
w
h
ich
h
a
s
to
b
e
p
r
ed
icte
d
,
is
th
e
o
u
tp
u
t,
w
h
ic
h
w
o
u
ld
b
e
tr
ain
ed
w
ith
T
HD
as th
e
in
p
u
t.
T
h
is
p
ap
er
is
o
r
g
an
ized
as,
Sectio
n
I
I
w
it
h
th
e
ANN
ap
p
lied
o
n
ML
I
f
a
u
lt
d
etec
tio
n
,
a
n
d
Sectio
n
I
I
I
ex
p
lain
s
th
e
Ge
n
etic
A
lg
o
r
it
h
m
a
n
d
Mo
d
if
ied
Gen
etic
A
l
g
o
r
ith
m
,
Sectio
n
I
V
d
ea
ls
ab
o
u
t
th
e
r
esu
l
ts
an
d
d
is
cu
s
s
io
n
o
f
th
e
i
m
p
le
m
en
ta
ti
o
n
w
ith
co
m
p
ar
ati
v
e
a
n
al
y
s
is
o
f
b
o
th
G
A
an
d
MG
A
.
2.
F
AULT
DIA
G
NO
SI
S
O
F
M
UL
T
I
L
E
VE
L
I
NV
E
R
T
E
R
USI
NG
ART
I
F
I
C
I
A
L
NE
URA
L
NE
T
WO
RK
2
.
1
.
T
ra
ini
ng
P
a
ra
m
et
er
Sel
ec
t
io
n f
o
r
ANN
T
h
e
s
elec
tio
n
o
f
th
e
tr
ain
i
n
g
p
ar
am
e
ter
is
t
h
e
p
r
i
m
e
s
tep
in
a
n
y
A
NN
i
m
p
le
m
e
n
tatio
n
.
I
n
t
h
i
s
i
m
p
le
m
en
ta
tio
n
th
e
m
o
d
u
le
i
n
w
h
ic
h
f
a
u
lt
o
cc
u
r
s
i
s
ta
k
e
n
as
t
h
e
o
u
tp
u
t
an
d
th
e
T
HD
is
co
n
s
id
er
ed
as
t
h
e
in
p
u
t
p
a
r
a
m
eter
.
T
h
e
n
ea
r
s
in
u
s
o
id
al
s
h
ap
e
o
f
th
e
m
u
l
tile
v
el
in
v
er
ter
o
u
tp
u
t
w
o
u
ld
b
e
lo
s
t
i
f
t
h
er
e
i
s
a
f
a
u
l
t
o
cc
u
r
s
in
t
h
e
m
u
ltil
e
v
el
i
n
v
er
t
er
.
T
h
e
T
HD
is
ca
lcu
lated
o
n
th
e
o
u
tp
u
t
w
a
v
e
f
o
r
m
b
y
ap
p
l
y
i
n
g
t
h
e
Fas
t
Fo
u
r
ier
T
r
an
s
f
o
r
m
.
Du
e
to
th
e
f
a
u
lt
o
cc
u
r
r
en
ce
th
e
T
HD
v
alu
e
w
o
u
ld
h
av
e
b
ee
n
c
h
an
g
ed
.
T
h
e
ch
an
g
e
in
t
h
e
T
HD
v
alu
e
i
s
i
n
f
l
u
e
n
ce
d
b
y
th
e
p
o
s
i
tio
n
w
h
er
e
t
h
e
f
a
u
lt i
s
o
cc
u
r
r
i
n
g
i
n
t
h
e
m
u
lti
lev
el
i
n
v
er
ter
.
2
.
2
.
F
a
ults in M
L
I
T
h
is
f
au
lt
d
ia
g
n
o
s
i
s
s
y
s
te
m
c
o
m
p
r
i
s
es
o
f
tr
ain
in
g
an
d
test
i
n
g
s
tep
s
.
Du
r
i
n
g
th
e
tr
a
i
n
in
g
s
t
ep
th
e
f
o
u
r
m
ai
n
s
tep
s
th
at
is
f
o
llo
w
ed
ar
e
1
)
T
HD
ca
lcu
latio
n
f
o
r
d
if
f
er
en
t
s
w
i
tch
f
ail
u
r
e
2
)
ANN
t
r
ain
in
g
.
T
h
e
test
i
n
g
p
h
ase
co
m
p
r
is
e
s
o
f
1
)
A
NN
cl
ass
i
f
icatio
n
f
o
r
f
a
u
lt p
r
ed
ictio
n
2
)
R
ec
o
n
f
ig
u
r
atio
n
T
HD
ca
lcu
latio
n
ca
n
al
s
o
b
e
ca
lled
as
f
ea
tu
r
e
e
x
tr
ac
tio
n
wh
er
e
th
e
Fas
t
Fo
u
r
ier
T
r
an
s
f
o
r
m
(
FF
T
)
ap
p
lied
o
n
th
e
M
L
I
o
u
tp
u
t
v
o
ltag
e
is
u
s
ed
f
o
r
t
h
e
T
HD
c
alcu
latio
n
.
T
h
e
ap
p
licatio
n
o
f
FF
T
o
n
t
h
e
o
u
tp
u
t
v
o
ltag
e
w
a
v
ef
o
r
m
o
f
th
e
C
M
L
I
p
r
o
v
id
es
th
e
a
m
p
lit
u
d
e
o
f
t
h
e
f
u
n
d
a
m
en
tal
an
d
th
e
h
ar
m
o
n
ic
v
o
ltag
e
f
o
r
th
e
d
if
f
er
e
n
t
h
ar
m
o
n
ic
f
r
eq
u
e
n
c
y
.
T
h
e
m
o
s
t
co
m
m
o
n
l
y
o
cc
u
r
r
in
g
f
a
u
lt
i
n
th
e
C
M
L
I
is
t
h
e
o
p
en
cir
cu
it
(
OC
)
f
au
lts
,
w
h
er
ea
s
t
h
e
s
h
o
r
t
cir
cu
it
f
au
l
ts
ar
e
r
e
m
o
v
ed
b
y
t
h
e
u
s
e
o
f
f
ast
ac
t
in
g
s
w
i
tch
t
h
a
t
w
o
u
ld
b
e
u
s
ed
to
r
e
m
o
v
e
t
h
e
le
g
f
r
o
m
th
e
h
ea
l
t
h
y
p
ar
t
o
f
t
h
e
M
L
I
[
1
0
]
,
co
n
v
er
tin
g
i
t
to
b
e
a
o
p
en
c
ir
cu
it
f
a
u
lt.
As
t
h
e
s
h
o
r
t
cir
cu
it
f
a
u
lt
is
also
co
n
v
er
ter
t
o
o
p
en
cir
cu
it
f
au
lt
th
e
n
u
m
b
e
r
o
f
th
e
tr
ain
in
g
d
ata
to
th
e
A
NN
is
r
ed
u
ce
d
.
A
s
p
u
ls
e
w
id
th
v
ar
iatio
n
also
wo
u
ld
in
tr
o
d
u
ce
th
e
ch
a
n
g
e
i
n
th
e
T
HD
v
alu
e
th
e
ANN
ca
n
b
e
u
s
ed
f
o
r
th
e
p
r
ed
ictio
n
o
f
P
W
M
ch
an
g
e.
2
.
3
.
ANN
T
ra
ini
ng
T
h
e
T
HD
v
alu
es
o
f
t
h
e
C
M
L
I
f
o
r
th
e
co
r
r
esp
o
n
d
in
g
f
ai
lu
r
e
o
f
th
e
s
w
i
tch
e
s
ar
e
tab
u
lated
.
T
h
is
p
air
o
f
o
b
s
er
v
atio
n
,
w
h
ich
co
m
p
r
i
s
es
o
f
t
h
e
p
o
s
itio
n
o
f
t
h
e
s
w
i
tch
an
d
t
h
e
T
HD
v
alu
es,
i
s
u
s
ed
f
o
r
tr
ain
in
g
t
h
e
A
N
N.
T
h
ese
T
HD
v
al
u
es
ar
e
tr
ain
ed
a
s
t
h
e
in
p
u
t
a
n
d
t
h
e
s
w
itc
h
n
u
m
b
er
i
s
g
i
v
en
as
t
h
e
o
u
tp
u
t.
T
h
e
f
au
l
t
d
etec
tio
n
an
d
th
e
r
ec
o
n
f
i
g
u
r
atio
n
is
a
n
o
n
-
li
n
ea
r
p
r
o
b
lem
to
b
e
s
o
lv
ed
,
as
th
er
e
is
n
o
p
r
ed
et
er
m
i
n
ed
ti
m
e
w
h
e
n
th
e
f
a
u
lt
ca
n
o
cc
u
r
in
th
e
C
M
L
I
.
A
NN
ac
t
s
as
t
h
e
s
o
l
u
tio
n
f
o
r
t
h
is
n
o
n
-
li
n
e
ar
p
r
o
b
lem
.
B
ac
k
P
r
o
p
ag
atio
n
Net
w
o
r
k
(
B
P
N)
alg
o
r
ith
m
i
s
u
s
ed
f
o
r
ap
p
l
y
i
n
g
t
h
e
A
N
N
o
n
th
i
s
n
o
n
-
li
n
ea
r
p
r
o
b
lem
.
Af
ter
t
h
e
B
P
N
alg
o
r
ith
m
i
s
ap
p
lied
o
n
t
h
e
A
NN
a
tr
ai
n
ed
A
NN
w
i
ll
b
e
r
ea
d
y
f
o
r
f
a
u
lt
d
ia
g
n
o
s
i
s
tes
t
in
g
.
T
h
e
p
r
o
ce
d
u
r
e
f
o
r
th
i
s
m
e
th
o
d
is
i
n
cl
u
d
ed
in
th
e
i
m
p
le
m
e
n
tat
io
n
s
ec
tio
n
.
T
h
e
P
s
eu
d
o
co
d
e
f
o
r
th
e
B
PN
alg
o
r
ith
m
f
o
r
th
e
f
au
lt d
iag
n
o
s
is
o
n
th
e
C
M
L
I
is
g
iv
e
n
as
f
o
llo
w
s
,
P
s
eu
d
o
C
o
d
e:
a.
A
f
ee
d
f
o
r
w
ar
d
Ne
u
r
al
Net
wo
r
k
alo
n
g
w
it
h
t
h
e
p
r
o
p
er
n
u
m
b
er
o
f
i
n
p
u
t,
o
u
tp
u
t
an
d
h
i
d
d
en
n
o
d
es
i
s
g
en
er
ated
.
b.
A
r
b
itra
r
y
T
r
an
s
f
er
f
u
n
ctio
n
is
ch
o
s
en
f
o
r
th
e
n
o
d
es.
c.
W
eig
h
t i
n
itia
lis
atio
n
f
o
r
ea
ch
n
o
d
e
is
p
r
o
v
id
ed
an
d
a
to
ler
an
ce
v
alu
e,
w
h
ic
h
is
v
er
y
lo
w
,
is
ch
o
s
en
.
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.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
6
1
0
–
2
6
2
0
2612
d.
T
h
e
tr
ain
i
n
g
s
et
o
f
i
n
p
u
t
an
d
o
u
tp
u
t
d
ata
i
s
ta
k
e
n
f
r
o
m
t
h
e
M
L
I
.
T
h
e
i
n
p
u
t
b
ein
g
th
e
T
HD
an
d
t
h
e
o
u
tp
u
t
th
e
leg
p
o
s
it
io
n
i
n
th
e
M
L
I
.
e.
T
h
e
in
p
u
t
is
tr
av
er
s
ed
f
r
o
m
t
h
e
in
p
u
t
la
y
er
to
th
e
o
u
tp
u
t
la
y
er
an
d
th
e
er
r
o
r
is
f
o
u
n
d
b
et
w
ee
n
th
e
ac
t
u
al
o
u
tp
u
t a
n
d
t
h
e
d
esire
d
o
u
tp
u
t.
f.
T
h
e
er
r
o
r
is
co
m
p
ar
ed
w
ith
th
e
to
ler
an
ce
v
al
u
e,
if
t
h
e
er
r
o
r
is
n
o
t
n
ea
r
er
to
th
e
to
ler
an
ce
th
e
n
th
e
f
o
llo
w
in
g
s
tep
s
h
a
s
to
r
ep
ea
t
g.
T
h
e
er
r
o
r
is
p
r
o
p
ag
ated
to
ea
ch
p
r
ev
io
u
s
n
o
d
e
b
y
ca
lc
u
lati
n
g
t
h
e
w
ei
g
h
t
co
r
r
ec
tio
n
ter
m
a
n
d
t
h
e
b
ia
s
co
r
r
ec
tio
n
ter
m
f
o
r
ea
ch
n
o
d
e.
h.
T
h
e
s
tep
s
5
to
7
ar
e
r
ep
ea
te
d
u
n
til
th
e
er
r
o
r
is
b
ec
o
m
i
n
g
le
s
s
th
a
n
o
r
eq
u
al
to
t
h
e
t
o
ler
an
ce
v
al
u
e
co
n
s
id
er
ed
.
i.
T
h
e
s
tep
s
2
to
8
a
r
e
r
ep
ea
te
d
f
o
r
all
th
e
in
p
u
t,
o
u
tp
u
t p
air
s
.
Af
ter
t
h
is
tr
ain
i
n
g
s
tep
a
tr
ai
n
ed
n
et
w
o
r
k
w
ill
b
e
r
ea
d
y
f
o
r
test
in
g
th
r
o
u
g
h
w
h
ich
an
y
T
HD
v
alu
e
f
r
o
m
t
h
e
ML
I
ca
n
b
e
p
r
o
v
id
ed
as th
e
i
n
p
u
t a
n
d
th
e
f
a
u
lt p
o
s
i
tio
n
ca
n
b
e
f
o
u
n
d
.
3.
P
ARAM
E
T
E
R
O
P
T
I
M
I
Z
A
T
I
O
N
O
F
ANN
US
I
N
G
G
A
AND
M
G
A
P
ar
am
eter
o
p
ti
m
izat
io
n
is
a
h
eu
r
i
s
tic
p
r
o
b
le
m
th
at
w
o
u
ld
h
elp
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
an
y
d
ec
is
io
n
-
m
a
k
i
n
g
p
r
o
b
le
m
lik
e
th
e
A
r
tific
ial
Neu
r
al
Net
w
o
r
k
(
A
NN)
.
P
ar
am
e
ter
o
p
tim
izatio
n
co
u
ld
b
e
u
s
ed
to
d
ec
id
e
th
e
w
e
ig
h
t
v
al
u
e
s
o
f
th
e
n
o
d
es
in
th
e
A
NN
o
r
th
e
b
ias
v
alu
e
s
in
o
r
d
er
to
im
p
r
o
v
e
th
e
lear
n
i
n
g
b
y
r
ed
u
cin
g
t
h
e
ti
m
e
r
eq
u
ir
ed
f
o
r
th
e
n
et
w
o
r
k
to
b
e
tr
ai
n
ed
.
T
h
e
ad
v
an
ta
g
e
o
f
p
ar
a
m
e
ter
o
p
tim
izatio
n
i
s
(
1
)
n
o
ex
p
er
ien
ce
h
o
w
to
ch
o
o
s
e
th
e
p
ar
am
eter
s
etti
n
g
o
f
th
e
al
g
o
r
ith
m
is
n
ee
d
ed
,
(
2
)
a
c
o
m
p
ar
i
s
o
n
w
it
h
o
th
e
r
alg
o
r
ith
m
s
i
s
n
ee
d
ed
,
(
3
)
a
alg
o
r
ith
m
h
as to
b
e
ap
p
lied
o
n
a
co
m
p
le
x
o
p
ti
m
iza
tio
n
p
r
o
b
lem
[
1
1
]
.
3
.
1
.
O
pti
m
is
ing
AN
N
us
i
ng
G
A
As
t
h
e
A
N
N
i
s
d
ef
i
n
ed
a
n
d
c
o
n
s
tr
u
cted
in
th
e
p
r
ev
io
u
s
s
ec
tio
n
tr
ai
n
i
n
g
ti
m
e
o
f
th
e
A
NN
h
as
to
b
e
i
m
p
r
o
v
ed
b
y
t
h
e
u
s
e
o
f
G
A
a
n
d
MG
A
.
T
h
is
s
u
b
s
ec
tio
n
w
o
u
l
d
d
ea
l a
b
o
u
t G
A
b
ased
p
ar
a
m
eter
o
p
tim
is
atio
n
o
f
th
e
A
NN.
T
h
e
p
ar
am
eter
t
h
u
s
ch
o
o
s
en
ar
e
n
o
d
e
w
e
ig
h
t
v
a
lu
es
a
n
d
th
e
b
ias
v
al
u
es.
As
t
w
o
p
ar
a
m
eter
s
ar
e
tak
en
f
o
r
o
p
ti
m
i
s
atio
n
th
i
s
p
r
o
b
lem
b
ec
o
m
e
s
t
h
e
m
u
l
ti
v
ar
i
ab
le
h
eu
r
i
s
tic
p
r
o
b
le
m
.
T
h
e
p
s
eu
d
o
co
d
e
f
o
r
th
i
s
i
m
p
le
m
en
ta
tio
n
is
a
s
ex
p
lai
n
e
d
b
elo
w
.
P
s
eu
d
o
C
o
d
e:
1.
W
ith
th
e
A
N
N
m
o
d
el
cr
ea
ted
g
e
t th
e
i
n
it
ial
w
ei
g
h
t
m
atr
i
x
o
f
all
th
e
n
o
d
es.
2.
Un
w
r
ap
w
e
ig
h
t a
n
d
th
e
B
ias
m
atr
ices i
n
to
a
s
i
n
g
le
ar
r
ay
ea
ch
.
3.
C
o
n
s
id
er
th
ese
ar
r
a
y
s
a
s
th
e
f
i
r
s
t c
h
r
o
m
o
s
o
m
es
4.
R
an
d
o
m
l
y
g
e
n
er
ate
th
e
r
est
o
f
th
e
ch
r
o
m
o
s
o
m
es
f
o
r
a
p
ar
ticu
lar
p
o
p
u
latio
n
s
ize,
w
h
ich
is
s
e
lecte
d
in
t
u
iti
v
el
y
.
5.
Fo
r
ev
er
y
ch
r
o
m
o
s
o
m
e
g
en
er
a
ted
in
th
e
p
r
ev
io
u
s
s
tep
r
ef
o
r
m
th
at
in
to
th
e
w
ei
g
h
t a
n
d
th
e
B
ias
m
atr
ice
s
.
6.
A
p
p
l
y
t
h
ese
m
atr
ice
s
o
n
th
e
ANN
an
d
o
b
tain
th
e
er
r
o
r
an
d
th
e
MSE
.
7.
Sav
e
t
h
e
m
i
n
i
m
u
m
MSE
i
f
o
b
tain
ed
in
a
ar
r
a
y
8.
Gen
er
ate
n
e
w
p
o
p
u
latio
n
o
f
c
h
r
o
m
o
s
o
m
es u
s
i
n
g
t
h
e
f
o
llo
w
i
n
g
s
tep
s
9
to
1
1
9.
Select
t
w
o
p
ar
en
ts
f
r
o
m
th
e
p
r
ev
io
u
s
l
y
g
e
n
er
ated
ch
r
o
m
o
s
o
m
es.
10.
A
p
p
l
y
cr
o
s
s
o
v
er
p
r
o
b
ab
ilit
y
o
n
th
e
s
e
p
ar
en
ts
to
g
e
t a
n
e
w
o
f
f
s
p
r
in
g
.
11.
A
p
p
l
y
m
u
tatio
n
p
r
o
b
ab
ilit
y
to
o
b
tain
th
e
n
e
w
c
h
ild
r
e
n
in
t
h
e
p
o
s
itio
n
o
f
th
e
p
ar
en
t c
h
r
o
m
o
s
o
m
e.
12.
R
ep
ea
t th
e
s
tep
s
5
to
7
u
n
til t
h
e
n
u
m
b
er
o
f
iter
atio
n
i
s
co
m
p
l
eted
.
13.
T
h
e
ar
r
ay
o
f
s
av
ed
MSE
is
tak
en
an
d
th
e
w
ei
g
h
t
a
n
d
b
ias
v
al
u
es
co
r
r
esp
o
n
d
in
g
to
th
e
m
i
n
i
m
u
m
MSE
ar
e
s
elec
ted
.
14.
T
h
e
s
elec
ted
w
ei
g
h
t
a
n
d
b
ias
v
alu
e
s
ar
e
p
r
o
v
id
ed
as
th
e
w
e
ig
h
t
an
d
b
ias
m
a
tr
ices
to
th
e
A
N
N
an
d
th
e
r
esu
lt
s
ar
e
u
p
d
ated
.
15.
A
N
N
p
er
f
o
r
m
an
ce
ca
n
b
e
ev
al
u
ated
u
s
in
g
t
h
e
s
elec
ted
w
ei
g
h
t a
n
d
th
e
b
ias
v
alu
e
s
.
16.
T
h
e
p
ar
en
t
s
elec
tio
n
f
o
r
th
e
p
o
p
u
latio
n
g
e
n
er
atio
n
i
s
ca
r
r
i
ed
u
s
i
n
g
th
e
R
o
u
let
te
Selecti
o
n
m
et
h
o
d
as
d
ef
in
ed
b
elo
w
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
a
u
lt Dia
g
n
o
s
is
a
n
d
R
ec
o
n
fig
u
r
a
tio
n
o
f Mu
ltil
ev
el
I
n
ve
r
ter S
w
itch
F
a
ilu
r
e
-
A
…
(
T.G.
Ma
n
ju
n
a
th
)
2613
w
h
er
e
is
t
h
e
s
et
o
f
all
f
it
n
es
s
v
alu
e
s
,
is
th
e
ith
f
it
n
es
s
v
a
lu
e.
L
et
b
e
s
o
m
e
r
an
d
o
m
v
al
u
e
an
d
an
d
ar
e
v
ar
iab
les.
T
h
e
R
o
u
lett
e
s
elec
tio
n
al
g
o
r
ith
m
ca
n
b
e
d
ef
i
n
ed
as f
o
llo
w
s
,
w
h
ile
th
e
f
o
llo
w
i
n
g
s
tep
s
h
as
to
f
o
llo
w
Fin
d
I
n
cr
e
m
e
n
t J
E
n
d
On
ce
th
e
w
h
ile
lo
o
p
is
b
ec
o
m
i
n
g
f
alse
t
h
e
v
alu
e
is
ta
k
e
n
an
d
th
e
p
o
p
u
latio
n
at
t
h
e
th
p
o
s
itio
n
i
s
s
elec
ted
as th
e
p
ar
en
t.
T
h
e
ar
ith
m
etic
cr
o
s
s
o
v
er
is
u
s
ed
to
c
r
ea
te
th
e
n
e
w
o
f
f
s
p
r
i
n
g
f
r
o
m
th
e
t
w
o
p
ar
en
t
s
s
el
ec
ted
u
s
in
g
t
h
e
R
o
u
lette
s
elec
tio
n
.
T
w
o
o
f
f
s
p
r
in
g
s
ar
e
g
en
er
ated
u
s
i
n
g
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
lae,
w
h
er
e,
a
is
th
e
r
an
d
o
m
w
ei
g
h
tin
g
f
ac
to
r
.
I
n
o
r
d
er
t
o
m
ai
n
t
ain
g
e
n
etic
d
iv
er
s
it
y
b
et
w
ee
n
th
e
o
f
f
s
p
r
i
n
g
s
th
e
m
u
tatio
n
o
p
er
atio
n
is
ca
r
r
ied
o
u
t.
Fo
r
t
h
e
ca
lc
u
latio
n
o
f
th
e
m
u
tatio
n
th
e
m
ax
i
m
u
m
a
n
d
th
e
m
i
n
i
m
u
m
w
ei
g
h
t
v
alu
e
s
ar
e
tak
en
f
r
o
m
t
h
e
a
v
alu
es
a
n
d
it
is
m
en
t
io
n
e
d
in
th
e
b
elo
w
eq
u
atio
n
s
a
s
„
m
ax
w
e
ig
h
t
‟
an
d
„
m
in
w
eig
h
t
‟
.
T
h
e
m
u
tatio
n
o
p
er
atio
n
is
d
ef
i
n
ed
in
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
lae
(
1
)
,
(
1
)
w
h
er
e
,
is
th
e
r
an
d
o
m
v
al
u
e.
Usi
n
g
t
h
e
ab
o
v
e
v
al
u
e
t
h
e
in
v
er
s
e
er
r
o
r
f
u
n
ctio
n
i
s
ca
lc
u
late
d
an
d
u
tili
s
ed
i
n
th
e
f
o
llo
w
i
n
g
f
o
r
m
u
lae,
(
2
)
T
h
e
o
f
f
s
p
r
in
g
is
ca
lc
u
lated
b
y
u
s
i
n
g
r
ed
u
ce
s
its
v
a
lu
e
f
o
r
ev
er
y
ite
r
atio
n
.
3
.
2
.
M
o
dified
G
enet
ic
Alg
o
rit
h
m
T
h
e
s
i
m
p
le
g
en
et
ic
alg
o
r
ith
m
ac
co
u
n
ts
f
o
r
o
n
l
y
o
n
e
p
o
p
u
l
atio
n
in
ea
ch
g
e
n
er
atio
n
a
n
d
th
e
g
e
n
etic
o
p
er
atio
n
s
ar
e
d
o
n
e
o
n
th
a
t
g
en
er
atio
n
.
I
t
b
ec
o
m
es
a
ti
m
e
c
o
n
s
u
m
i
n
g
p
r
o
ce
s
s
to
e
v
alu
ate
th
e
f
u
n
ctio
n
as
th
e
s
i
m
p
le
G
A
w
o
u
ld
co
n
s
u
m
e
m
o
r
e
iter
atio
n
s
.
I
n
o
r
d
er
to
m
a
k
e
th
i
s
co
n
v
er
g
e
n
ce
f
a
s
ter
th
e
alg
o
r
ith
m
m
u
s
t
b
e
m
o
d
i
f
ied
i
n
s
u
c
h
a
w
a
y
th
a
t
th
e
e
v
al
u
atio
n
o
f
th
e
f
u
n
c
tio
n
m
u
s
t
b
e
ca
r
r
ied
o
u
t
p
a
r
alell
y
i
n
s
tead
o
f
in
d
iv
id
u
all
y
.
T
h
e
m
u
ltico
r
e
p
r
o
ce
s
s
o
r
s
av
ailab
le
i
n
t
h
e
in
d
u
s
tr
y
w
o
u
ld
h
e
lp
in
i
m
p
le
m
en
t
in
g
t
h
is
s
i
m
u
lta
n
eo
u
s
i
m
p
le
m
en
tat
io
n
s
.
T
h
e
p
r
o
ce
s
s
o
r
s
ca
n
w
o
r
k
in
m
aster
a
n
d
s
la
v
e
ap
p
r
o
ac
h
i
n
w
h
ich
,
m
as
ter
s
to
r
es
a
s
i
n
g
le
p
o
p
u
latio
n
a
n
d
th
e
o
th
er
p
r
o
ce
s
s
o
r
ev
al
u
at
e
th
e
i
n
d
iv
id
u
als.I
n
t
h
e
liter
at
u
r
e
[
1
2
]
it
h
as
b
ee
n
p
r
o
p
o
s
ed
th
at
t
h
e
p
o
p
u
la
tio
n
m
u
s
t
b
e
s
p
litt
ed
i
n
to
m
a
n
y
s
u
b
p
o
p
u
latio
n
to
k
ee
p
d
i
v
er
s
it
y
in
t
h
e
co
u
r
s
e
o
f
t
h
e
o
p
tim
iatio
n
p
r
o
ce
s
s
.
T
h
e
p
r
o
c
ess
o
f
m
ig
r
atio
n
,
w
h
ic
h
h
elp
s
in
s
h
ar
i
n
g
a
s
in
g
le
in
d
i
v
id
u
al
w
ith
b
etter
f
itn
e
s
s
in
m
an
y
s
u
b
p
o
p
u
latio
n
is
ca
r
r
ied
o
u
t
f
o
r
w
h
ic
h
a
f
ter
cr
o
s
s
o
v
e
r
an
d
m
u
tatio
n
w
o
u
ld
g
e
n
er
ate
th
e
s
o
lu
tio
n
s
p
ac
e
th
at
is
n
o
t
m
u
s
t
ex
p
lo
r
e
d
.
T
h
e
am
o
u
n
t
o
f
d
iv
er
s
it
y
in
th
e
s
u
b
p
o
p
u
latio
n
is
p
r
o
p
o
r
t
io
n
al
to
th
e
r
ate
o
f
m
i
g
r
atio
n
.
3
.
3
.
Dy
na
m
ic
P
a
ra
m
et
er
Des
ig
n
in M
G
A
T
h
e
r
an
d
o
m
c
h
r
o
m
o
s
o
m
e
g
e
n
er
atio
n
in
t
h
e
b
eg
i
n
n
in
g
o
f
t
h
e
GA
al
g
o
r
ith
m
d
ec
id
es
t
h
e
q
u
alit
y
an
d
ef
f
icien
c
y
o
f
t
h
e
s
o
lu
tio
n
th
at
is
o
b
tain
ed
.
T
h
e
s
ea
r
ch
q
u
alit
y
w
i
ll
b
e
in
ef
f
icie
n
t
as
t
h
e
d
y
n
a
m
is
m
is
ch
o
o
s
i
n
g
th
e
p
ar
a
m
eter
is
m
i
s
s
i
n
g
.
T
h
e
cr
o
s
s
o
v
er
an
d
th
e
m
u
tat
io
n
p
r
o
b
ab
ilit
y
is
v
ar
ied
d
y
n
a
m
ica
l
l
y
in
t
h
e
MG
A
in
Y
Y
i
S
1
S
2
J
S
2
>
S
1
S
2
=
S
2
+
S
(
J
)
J
J
r
a
n
d
n
u
m
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.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
6
1
0
–
2
6
2
0
2614
o
r
d
er
in
tr
o
d
u
ce
th
e
d
y
n
a
m
ic
ch
ar
ac
ter
is
tic
s
in
c
h
o
o
s
i
n
g
t
h
e
p
ar
am
eter
s
.
At
th
e
b
e
g
i
n
n
i
n
g
o
f
t
h
e
ev
o
l
u
tio
n
p
r
o
ce
s
s
th
e
b
i
g
g
er
cr
o
s
s
o
v
er
a
n
d
m
u
tat
io
n
p
r
o
b
ab
ilit
y
is
ap
p
lied
to
g
et
th
e
o
f
f
s
p
r
i
n
g
s
b
u
t
a
s
t
h
e
co
n
v
er
g
e
n
ce
f
o
r
w
ar
d
s
,
t
h
e
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
p
r
o
b
ab
ilit
y
w
ill
b
ec
o
m
e
o
f
s
m
aller
r
an
g
e.
T
h
e
s
tep
s
in
v
o
l
v
ed
in
t
h
e
d
y
n
a
m
ic
p
ar
a
m
eter
d
esi
g
n
o
f
t
h
e
MG
A
ar
e
as f
o
llo
w
s
,
1.
T
h
e
p
r
o
b
lem
w
it
h
t
h
e
p
ar
a
m
eter
s
is
co
d
ed
i
n
t
h
e
f
o
r
m
o
f
th
e
s
tr
i
n
g
.
B
in
ar
y
co
d
in
g
m
et
h
o
d
is
u
s
ed
to
tr
an
s
f
er
th
e
p
ar
a
m
eter
f
r
o
m
th
e
p
r
o
b
lem
s
p
ac
e
to
t
h
e
co
d
in
g
s
p
ac
e.
T
h
e
len
g
t
h
o
f
th
e
co
d
e
is
d
eter
m
i
n
ed
b
y
t
h
e
f
o
llo
w
in
g
f
o
r
m
u
la
(
3
)
[
1
2
]
.
(
3
)
w
h
er
e
an
d
ar
e
th
e
m
a
x
i
m
u
m
an
d
m
i
n
i
m
u
m
v
al
u
es
o
f
th
e
in
d
ep
en
d
en
t
v
ar
iab
les
i
n
t
h
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
an
d
is
th
e
p
r
ec
is
io
n
r
eq
u
ir
ed
.
2.
I
n
d
iv
id
u
a
l
f
it
n
e
s
s
f
u
n
ctio
n
ar
e
ca
lcu
lated
b
y
th
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
i
n
t
h
e
s
i
m
p
le
G
A
,
b
u
t
i
n
th
i
s
MG
A
it
is
d
ef
i
n
ed
b
y
t
h
e
f
o
llo
w
in
g
f
o
r
m
u
lae
(
4
)
(
4
)
w
h
er
e,
is
th
e
o
r
d
er
p
o
s
itio
n
o
f
th
e
s
o
r
ted
in
d
iv
id
u
al
i,
an
d
is
th
e
to
tal
n
u
m
b
er
o
f
i
n
d
iv
id
u
al
s
.
3.
L
et
T
b
e
th
e
to
tal
n
u
m
b
er
o
f
g
en
er
atio
n
s
,
M
b
e
th
e
to
tal
n
u
m
b
er
o
f
s
u
b
p
o
p
u
latio
n
,
N
t
h
e
s
i
ze
o
f
ea
ch
s
u
b
p
o
p
u
latio
n
,
r
ate
o
f
m
ig
r
atio
n
r
,
p
r
o
b
a
b
ilit
y
o
d
s
elec
tio
n
d
en
o
ted
b
y
s
,
cr
o
s
s
o
v
er
an
d
m
u
tati
o
n
p
r
o
b
ab
ilit
y
as
c
an
d
m
r
esp
ec
ti
v
el
y
.
T
h
e
r
ec
o
m
m
e
n
d
e
d
v
alu
e
s
o
f
M
an
d
N
f
o
r
MG
A
ar
e
,
w
h
er
e
is
t
h
e
n
u
m
b
er
o
f
v
ar
iab
l
es.
4.
T
h
e
s
elec
tio
n
p
r
o
b
ab
ilit
y
f
o
r
th
e
ith
i
n
d
i
v
id
u
al
i
s
g
i
v
e
n
as
(
5
)
w
h
er
e,
s
elec
tio
n
p
r
o
b
ab
ilit
y
S
i
is
k
ep
t
co
n
s
tan
t
to
m
ak
e
th
e
cr
o
s
s
o
v
er
an
d
m
u
tat
io
n
p
r
o
b
a
b
ilit
y
to
v
ar
y
d
y
n
a
m
icall
y
.
T
h
e
cr
o
s
s
o
v
er
a
n
d
th
e
m
u
tat
io
n
p
r
o
b
ab
ilit
y
wo
u
ld
f
o
llo
w
t
h
e
r
u
le
o
f
b
ig
g
er
v
al
u
es
in
i
tiall
y
a
n
d
s
m
al
ler
v
al
u
es late
r
.
T
h
e
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
p
r
o
b
ab
ilit
y
ar
e
d
en
o
ted
a
s
in
(
6
)
an
d
(
7
)
,
(
6
)
(
7
)
w
h
er
e,
t
i
s
t
h
e
n
u
m
b
er
o
f
p
r
es
en
t
g
e
n
er
atio
n
,
,
is
th
e
i
n
itial
v
al
u
es
o
f
an
d
r
esp
ec
tiv
el
y
f
o
r
t
h
e
j
th
p
o
p
u
latio
n
,
is
t
h
e
s
ca
l
in
g
f
ac
to
r
,
w
h
ich
w
o
u
ld
b
e
lar
g
er
t
h
an
o
r
eq
u
al
to
.
T
h
e
v
alu
e
s
o
f
an
d
w
il
l b
e
in
itiated
w
it
h
an
d
b
u
t it
w
o
u
ld
d
ec
r
ea
s
e
in
th
e
i
ter
ati
o
n
s
th
a
t f
o
llo
w
s
.
5.
I
n
itial p
o
p
u
latio
n
i
s
cr
ea
ted
u
s
in
g
t
h
e
r
an
d
o
m
f
u
n
c
tio
n
as i
n
GA
.
6.
I
n
d
iv
id
u
a
l f
it
n
e
s
s
is
e
v
al
u
ated
u
s
i
n
g
th
e
p
o
p
u
latio
n
.
7.
T
h
e
in
d
iv
id
u
a
ls
w
i
th
b
etter
f
it
n
es
s
is
s
u
p
p
lied
to
th
e
s
u
b
p
o
p
u
latio
n
i=1
….
N
-
1
,
an
d
t
h
e
i
n
d
iv
id
u
al
w
it
h
w
o
r
s
t
f
it
n
es
s
is
s
u
b
s
ti
tu
ted
i
n
t
h
e
i+1
th
s
u
b
p
o
p
u
latio
n
.
8.
C
r
o
s
s
o
v
er
a
n
d
m
u
tatio
n
f
o
r
t
h
e
ad
j
u
s
ted
f
u
n
ct
io
n
is
ca
lc
u
l
ated
an
d
t
h
e
g
e
n
etic
o
p
er
ato
r
s
ar
e
ap
p
lied
to
d
ev
elo
p
th
e
n
e
w
g
en
er
atio
n
.
9.
C
h
ec
k
w
h
e
th
er
t
h
e
cu
r
r
en
t
g
e
n
er
atio
n
n
u
m
b
er
t
is
less
t
h
a
n
th
e
to
tal
n
u
m
b
er
o
f
g
en
er
atio
n
,
if
y
es
s
to
p
th
e
iter
atio
n
,
else c
o
n
ti
n
u
e
f
r
o
m
s
t
ep
5
.
x
m
a
x
x
m
i
n
p
i
Q
n
a
j
b
j
m
j
c
j
T
j
T
m
j
c
j
a
j
b
j
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
a
u
lt Dia
g
n
o
s
is
a
n
d
R
ec
o
n
fig
u
r
a
tio
n
o
f Mu
ltil
ev
el
I
n
ve
r
ter S
w
itch
F
a
ilu
r
e
-
A
…
(
T.G.
Ma
n
ju
n
a
th
)
2615
4.
F
AULT
D
I
A
G
NO
S
I
S IM
P
L
E
M
E
NT
AT
I
O
N
T
h
e
im
p
le
m
en
tatio
n
o
f
b
o
th
t
h
e
G
A
an
d
th
e
MG
A
f
o
r
o
p
ti
m
is
in
g
th
e
A
N
N‟
s
w
eig
h
t
a
n
d
b
ias
v
alu
e
s
is
ca
r
r
ied
o
u
t
o
n
a
th
r
ee
p
h
ase
s
ev
en
le
v
el
M
L
I
as
s
h
o
w
n
i
n
Fig
u
r
e
1
.
I
t
s
h
o
w
s
th
e
t
h
r
ee
p
h
ase
C
M
L
I
to
b
e
co
n
n
ec
ted
to
th
e
5
HP
m
o
to
r
d
r
iv
e.
Fig
u
r
e
1
.
T
h
r
ee
P
h
ase
C
M
L
I
Dr
iv
e
4
.
1
.
Ca
s
ca
ded
M
ultilev
el
I
nv
er
t
er
Driv
e
Fo
r
test
in
g
p
u
r
p
o
s
es a
s
e
v
e
n
-
l
ev
el
ca
s
ca
d
ed
m
u
lti
-
le
v
el
i
n
v
e
r
ter
d
r
iv
in
g
i
n
d
u
c
tio
n
m
o
to
r
is
u
s
ed
.
T
h
e
clo
s
ed
s
w
itc
h
f
au
l
ts
a
n
d
o
p
en
s
w
i
tch
f
a
u
lt
s
ar
e
ap
p
lied
to
th
e
s
in
g
le
p
h
ase
o
f
t
h
e
t
h
r
ee
-
p
h
a
s
e
i
n
v
er
ter
f
o
r
s
i
m
p
lic
it
y
.
D
u
e
to
t
h
e
ap
p
licatio
n
o
f
f
au
lt
t
h
e
o
u
tp
u
t
v
o
ltag
e
w
av
e
f
o
r
m
c
h
a
n
g
e
s
it
s
s
h
ap
e
d
u
e
to
t
h
e
u
n
a
v
ailab
ili
t
y
o
f
s
o
m
e
v
o
lta
g
e
lev
els.
T
h
is
w
a
v
e
f
o
r
m
an
a
l
y
s
ed
w
it
h
to
tal
h
ar
m
o
n
ic
d
i
s
t
o
r
tio
n
(
T
HD)
.
E
ac
h
s
w
itc
h
f
a
u
lt
cr
ea
tes
d
if
f
er
en
t
w
a
v
e
f
o
r
m
s
d
u
e
to
th
e
d
if
f
er
e
n
t
lev
el
s
.
E
ac
h
f
a
u
lt
s
h
as
d
i
f
f
er
en
t
T
HD
v
alu
es.
Fig
u
r
es
p
o
r
tr
a
y
ed
b
elo
w
s
h
o
w
s
th
e
w
av
e
f
o
r
m
s
d
u
e
to
t
h
e
f
au
lt
i
n
ea
ch
s
w
itc
h
o
f
a
s
in
g
le
ce
ll
a
n
d
it
T
HD
v
alu
e
s
.
Usi
n
g
th
e
T
HD
d
ata,
id
en
tific
atio
n
o
f
s
w
itc
h
f
a
u
lt c
a
n
b
e
d
o
n
e
b
y
tr
ai
n
i
n
g
t
h
e
n
e
u
r
al
n
et
w
o
r
k
(
NN)
.
4
.
2
.
Ca
s
ca
ded
M
ultilev
el
I
nv
er
t
er
Driv
e
Fo
r
test
in
g
p
u
r
p
o
s
es a
s
e
v
e
n
-
l
ev
el
ca
s
ca
d
ed
m
u
lti
-
le
v
el
i
n
v
e
r
ter
d
r
iv
in
g
i
n
d
u
c
tio
n
m
o
to
r
is
u
s
ed
.
T
h
e
clo
s
ed
s
w
itc
h
f
au
l
ts
a
n
d
o
p
en
s
w
i
tch
f
a
u
lt
s
ar
e
ap
p
lied
to
th
e
s
in
g
le
p
h
ase
o
f
t
h
e
t
h
r
ee
-
p
h
a
s
e
i
n
v
er
ter
f
o
r
s
i
m
p
lic
it
y
.
D
u
e
to
t
h
e
ap
p
licatio
n
o
f
f
au
lt
t
h
e
o
u
tp
u
t
v
o
ltag
e
w
av
e
f
o
r
m
c
h
a
n
g
e
s
it
s
s
h
ap
e
d
u
e
to
t
h
e
u
n
a
v
ailab
ili
t
y
o
f
s
o
m
e
v
o
lta
g
e
lev
els.
T
h
is
w
a
v
e
f
o
r
m
an
a
l
y
s
ed
w
it
h
to
tal
h
ar
m
o
n
ic
d
i
s
t
o
r
tio
n
(
T
HD)
.
E
ac
h
s
w
itc
h
f
a
u
lt
cr
ea
tes
d
if
f
er
en
t
w
a
v
e
f
o
r
m
s
d
u
e
to
th
e
d
if
f
er
e
n
t
lev
el
s
.
E
ac
h
f
a
u
lt
s
h
as
d
i
f
f
er
en
t
T
HD
v
alu
es.
Fig
u
r
es
p
o
r
tr
a
y
ed
b
elo
w
s
h
o
w
s
th
e
w
av
e
f
o
r
m
s
d
u
e
to
t
h
e
f
au
lt
i
n
ea
ch
s
w
itc
h
o
f
a
s
in
g
le
ce
ll
a
n
d
it
T
HD
v
alu
e
s
.
Usi
n
g
th
e
T
HD
d
ata,
id
en
tific
atio
n
o
f
s
w
itc
h
f
a
u
lt c
a
n
b
e
d
o
n
e
b
y
tr
ai
n
i
n
g
t
h
e
n
e
u
r
al
n
et
w
o
r
k
(
NN)
.
T
h
e
th
r
ee
p
h
ase
C
M
L
I
co
n
n
e
cted
to
th
e
i
n
d
u
ctio
n
m
o
to
r
d
r
iv
e
w
h
ic
h
h
a
s
t
h
e
ex
tr
a
r
ed
u
n
d
an
t
leg
th
at
w
o
u
ld
ac
t
w
h
e
n
t
h
er
e
is
a
f
a
u
lt o
cc
u
r
in
g
in
an
y
o
f
th
e
leg
i
n
t
h
e
C
ML
I
.
T
h
e
cir
cu
it
g
et
s
clo
s
ed
t
h
r
o
u
g
h
t
h
e
r
ed
u
n
d
an
t
leg
w
h
e
n
e
v
er
th
e
f
au
lt o
cc
u
r
s
in
an
y
o
f
t
h
e
le
g
in
t
h
e
C
M
L
I
.
4
.
3
.
G
A
a
nd
M
G
A
I
m
ple
m
e
nta
t
io
n
T
h
e
p
ar
am
eter
s
elec
tio
n
al
g
o
r
ith
m
t
h
at
i
s
e
x
p
lain
ed
i
n
t
h
e
p
r
ev
io
u
s
s
ec
t
io
n
s
ar
e
d
ev
elo
p
ed
u
s
i
n
g
t
h
e
Neu
r
al
Net
w
o
r
k
to
o
lb
o
x
in
M
atlab
an
d
M
-
f
i
les.
M
-
f
iles
ar
e
u
s
ed
to
d
e
v
elo
p
th
e
G
A
a
n
d
MG
A
o
p
ti
m
i
s
atio
n
o
n
th
e
p
ar
a
m
eter
s
elec
tio
n
o
f
A
N
N.
T
h
e
Ma
tlab
/Si
m
u
li
n
k
m
o
d
el
o
f
th
e
t
h
r
ee
p
h
ase
C
M
L
I
is
d
ev
elo
p
ed
f
o
r
a
5
HP
in
d
u
ctio
n
m
o
to
r
d
r
iv
e
f
o
r
a
o
p
en
lo
o
p
o
p
er
atio
n
.
T
h
e
O
C
f
au
lts
ar
e
in
tr
o
d
u
ce
d
in
s
o
m
e
o
f
t
h
e
le
g
s
i
n
t
h
e
ML
I
an
d
th
e
T
HD
o
f
th
e
o
u
tp
u
t
v
o
ltag
e
w
a
v
ef
o
r
m
i
s
ca
lc
u
lated
f
o
r
d
if
f
er
e
n
t
s
w
itc
h
f
ai
lu
r
es
an
d
tab
u
lated
.
T
h
e
T
HD
o
f
th
e
C
M
L
I
i
s
g
i
v
en
a
s
t
h
e
i
n
p
u
t
to
th
e
ANN
an
d
th
e
f
a
u
lt
p
o
s
i
tio
n
i
s
g
iv
en
as
th
e
o
u
tp
u
t
f
o
r
tr
ain
i
n
g
.
I
n
o
r
d
er
to
m
ak
e
th
e
ANN
tr
ai
n
q
u
ic
k
er
b
o
th
t
h
e
GA
an
d
MG
A
is
ap
p
lied
to
o
p
ti
m
ize
t
h
e
w
ei
g
h
t
an
d
th
e
b
ias
v
alu
e
s
o
f
t
h
e
A
N
N.
T
h
e
o
v
er
all
b
lo
ck
d
iag
r
a
m
o
f
th
e
i
m
p
le
m
en
tat
io
n
is
a
s
g
i
v
en
i
n
t
h
e
Fi
g
u
r
e
3
.
T
h
e
th
r
ee
p
h
a
s
e
C
M
L
I
i
s
co
n
n
ec
ted
to
i
n
d
u
ct
io
n
m
o
to
r
.
T
h
e
o
u
tp
u
t
o
f
t
h
e
M
L
I
i
s
ap
p
lied
w
it
h
F
FT
an
d
T
HD
is
ca
lcu
la
ted
.
T
h
e
T
HD
w
ill
b
e
g
iv
e
n
to
t
h
e
tr
ai
n
e
d
A
N
N,
w
h
ic
h
f
i
n
d
s
t
h
e
f
a
u
lt
p
o
s
itio
n
i
n
t
h
e
M
L
I
,
an
d
th
e
r
ec
o
n
f
ig
u
r
atio
n
is
ap
p
lied
u
s
i
n
g
t
h
e
r
ed
u
n
d
a
n
t le
g
.
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.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
6
1
0
–
2
6
2
0
2616
Fig
u
r
e
3
.
Ov
er
all
P
ar
am
e
ter
Selecti
o
n
I
m
p
le
m
en
tatio
n
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
test
s
e
tu
p
i
s
s
h
o
w
n
a
s
a
b
lo
ck
d
iag
r
a
m
.
T
h
e
M
L
I
D
i
s
o
p
er
ated
f
o
r
1
s
ec
.
w
it
h
in
t
h
a
t
0
.
0
1
s
ec
,
0
.
2
5
s
ec
,
0
.
5
s
ec
an
d
0
.
7
5
s
e
c
ar
e
in
d
u
ce
d
w
it
h
a
s
w
itc
h
f
au
lt
Q1
,
Q2
,
Q3
a
n
d
Q4
(
o
p
en
o
r
clo
s
ed
s
w
itc
h
)
r
esp
ec
tiv
el
y
.
W
it
h
an
d
w
it
h
o
u
t f
au
lt is
s
h
o
w
n
in
t
h
e
b
elo
w
f
i
g
u
r
e
s
.
Fig
u
r
e
4
.
P
h
ase
A
Vo
lta
g
e
W
av
ef
o
r
m
o
n
th
e
f
a
u
lt o
cc
u
r
r
en
c
e
at
0
.
0
1
s
ec
,
0
.
2
5
s
ec
,
0
.
5
an
d
0
.
7
5
s
ec
o
n
Q1
,
Q2
,
Q3
an
d
Q4
in
“
Vo
lta
g
e”
v
s
“
T
i
m
e”
Fro
m
th
e
F
ig
u
r
e
5
d
u
e
to
f
au
lt
in
s
w
itc
h
es
ch
a
n
g
e
in
T
HD
v
alu
es
ar
e
s
h
o
w
n
.
T
h
ese
v
alu
e
s
ar
e
g
iv
en
as
th
e
i
n
p
u
t
to
t
h
e
n
e
u
r
al
n
et
wo
r
k
an
d
o
u
tp
u
t
i
s
tak
e
n
as
ze
r
o
an
d
1
as
b
in
ar
ies.
Fig
u
r
e
5
s
h
o
w
s
t
h
e
p
atter
n
o
f
th
e
T
HD
f
o
r
th
e
f
a
u
lt
ap
p
lied
in
ce
ll
A
1
f
o
r
t
h
e
s
i
m
p
licit
y
.
Du
e
to
th
e
p
er
io
d
icall
y
ap
p
li
ed
f
au
lt
c
h
a
n
g
e
i
n
w
a
v
e
f
o
r
m
o
f
v
o
ltag
e
m
a
k
e
th
e
p
atter
n
in
T
HD
ca
lcu
latio
n
.
T
h
is
p
atter
n
is
f
ee
d
to
th
e
n
e
u
r
al
n
et
w
o
r
k
to
tr
ain
f
o
r
th
is
p
atter
n
.
T
h
en
i
f
a
n
y
o
f
t
h
is
f
au
lt
o
cc
u
r
s
it
ca
n
ea
s
il
y
c
lass
if
y
th
e
f
au
lt
p
h
a
s
e
a
n
d
ce
ll.
T
h
en
it
ca
n
p
er
f
o
r
m
t
h
e
r
e
m
ed
ial
ac
tio
n
.
Fig
u
r
e
6
d
ep
icts
th
e
m
u
l
tile
v
e
l
in
v
er
ter
v
o
lta
g
e
o
u
tp
u
t
f
o
r
th
e
C
ML
I
co
n
s
id
er
ed
in
th
is
p
ap
er
.
Fro
m
T
ab
le
1
it
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
tab
le
th
at
MG
A
alg
o
r
ith
m
g
i
v
es
les
s
er
v
al
u
e
o
f
m
e
an
s
q
u
ar
e
er
r
o
r
an
d
it
co
n
v
er
g
es
f
as
ter
d
u
e
to
it
s
lar
g
e
s
ea
r
ch
s
p
ac
e.
Mig
r
atio
n
ca
lcu
latio
n
m
a
k
es
th
e
s
ea
r
c
h
m
o
r
e
o
p
tim
ized
.
T
h
e
n
u
m
b
er
o
f
ep
o
ch
s
t
h
at
w
as
ca
r
r
ied
o
u
t
d
u
e
t
o
th
e
MG
A
is
les
s
t
h
an
t
h
at
o
f
t
h
e
G
A
an
d
a
ls
o
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
w
as
al
s
o
v
er
y
m
u
ch
r
ed
u
ce
d
as
co
m
p
ar
ed
to
th
e
g
en
e
tic
alg
o
r
it
h
m
.
T
h
e
n
u
m
b
er
o
f
c
y
cles t
h
at
to
o
k
to
clea
r
th
e
f
a
u
lt
w
as 1
4
c
y
cle
s
as see
n
in
t
h
e
Fig
u
r
e
7
.
T
h
e
p
ar
am
eter
s
t
h
at
ar
e
u
s
ed
f
o
r
th
e
Gen
etic
A
l
g
o
r
ith
m
i
m
p
l
e
m
en
tatio
n
i
s
Min
i
m
u
m
er
r
o
r
th
r
es
h
o
ld
=
0
.
0
4
.
P
o
p
u
latio
n
s
ize=
1
0
0
.
Ma
x
i
m
u
m
n
o
.
o
f
ep
o
ch
s
=1
7
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
a
u
lt Dia
g
n
o
s
is
a
n
d
R
ec
o
n
fig
u
r
a
tio
n
o
f Mu
ltil
ev
el
I
n
ve
r
ter S
w
itch
F
a
ilu
r
e
-
A
…
(
T.G.
Ma
n
ju
n
a
th
)
2617
Fit
n
e
s
s
f
u
n
ctio
n
=
Me
an
s
q
u
ar
ed
er
r
o
r
.
No
.
o
f
la
y
er
s
=2
.
No
.
o
f
n
eu
r
o
n
s
in
i
n
p
u
t la
y
er
=
4
.
Nu
m
b
er
o
f
ep
o
ch
s
tr
ain
ed
=
7
8.
Me
an
s
q
u
ar
ed
er
r
o
r
:
M
s
e
=
0
.
0
0
8
7
4
4
8
1
8
2
5
6
4
7
3
Fig
u
r
e
5
.
T
HD
Val
u
es f
o
r
th
e
S
w
itc
h
Fa
u
lt S1
,
S2
,
S3
an
d
S4
in
“
T
HD”
v
s
“
T
i
m
e”
Fig
u
r
e
6
.
W
ith
o
u
t a
n
y
Fa
u
lt i
n
th
e
ML
I
D
S
y
s
te
m
in
“
Vo
lta
g
e”
v
s
“
T
im
e”
Fig
u
r
e
7
.
Fau
lt a
t t
h
e
P
h
ase
A
at
C
ell
A
1
; Q
1
,
Q2
,
Q3
an
d
Q4
Fa
u
lt a
s
i
n
th
e
Fig
u
r
e
4
.
“
Vo
ltag
e”
v
s
“
T
i
m
e”
T
ab
le
1
.
Me
an
Sq
u
ar
e
E
r
r
o
r
a
n
d
Nu
m
b
er
o
f
E
p
o
ch
s
A
n
a
l
y
s
i
s
S
L
.
N
o
.
P
a
r
a
me
t
e
r
s
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
M
o
d
i
f
i
e
d
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
1
M
e
a
n
S
q
u
a
r
e
Er
r
o
r
0
.
0
0
8
7
4
4
8
1
8
2
5
6
4
7
3
7
7
.
0
9
7
7
X
1
0
-
4
2
N
u
mb
e
r
o
f
E
p
o
c
h
s
78
64
T
h
e
T
ab
le
2
tab
u
late
th
e
MSE
o
b
tain
ed
f
o
r
ev
er
y
iter
atio
n
u
n
til th
e
2
0
th
iter
atio
n
.
T
h
e
p
ar
am
eter
s
t
h
at
ar
e
en
g
a
g
ed
in
th
e
Mo
d
if
ied
Ge
n
etic
A
l
g
o
r
ith
m
Min
i
m
u
m
er
r
o
r
th
r
es
h
o
ld
=
0
.
0
0
0
9
.
P
o
p
u
latio
n
s
ize=
1
0
0
.
Ma
x
i
m
u
m
n
o
.
o
f
ep
o
ch
s
=1
7
0
0
.
Fit
n
e
s
s
f
u
n
ctio
n
=
Me
an
s
q
u
ar
ed
er
r
o
r
.
No
.
o
f
la
y
er
s
=2
.
No
.
o
f
n
eu
r
o
n
s
in
i
n
p
u
t la
y
er
=
4
.
Nu
m
b
er
o
f
ep
o
ch
s
tr
ain
ed
=
809.
Me
an
s
q
u
ar
ed
er
r
o
r
:
M
s
e
=
7
.
0
9
7
7
e
-
0
0
4
.
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.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
6
1
0
–
2
6
2
0
2618
T
h
e
g
r
ap
h
o
b
tain
ed
in
ter
m
s
o
f
th
e
n
u
m
b
er
o
f
i
ter
atio
n
v
e
r
s
u
s
t
h
e
M
SE
is
as
s
h
o
w
n
i
n
th
e
Fi
g
u
r
e
8
.
I
t
is
o
b
s
er
v
ed
th
at
T
ab
le
2
.
Me
an
Sq
u
ar
e
E
r
r
o
r
f
o
r
th
e
f
ir
s
t 2
0
I
ter
at
io
n
S
L
N
O
M
e
a
n
S
q
u
a
r
e
Er
r
o
r
G
A
w
i
t
h
A
N
N
M
G
A
w
i
t
h
A
N
N
A
N
N
1
0
.
0
0
8
7
4
4
8
1
8
2
5
6
4
7
3
7
.
7
3
1
8
e
-
0
0
4
1
.
2
3
7
8
e
-
0
0
8
2
0
.
0
1
6
5
6
9
7
9
8
5
6
5
8
7
3
7
.
2
0
5
0
e
-
0
0
4
1
.
6
4
0
1
e
-
0
0
7
3
0
.
0
3
6
8
4
8
9
2
2
1
2
4
4
7
6
6
.
2
2
3
9
e
-
0
0
4
1
.
1
7
4
7
e
-
0
1
0
4
0
.
0
3
9
0
0
6
8
3
3
6
7
8
9
8
0
8
.
9
8
6
5
e
-
0
0
4
8
.
8
2
9
5
e
-
0
0
8
5
0
.
0
2
8
2
1
4
2
3
3
9
9
3
6
1
1
8
.
7
4
1
6
e
-
0
0
4
1
.
3
9
2
2
e
-
0
0
9
6
0
.
0
2
5
9
5
4
9
7
5
6
5
5
5
4
5
6
.
9
9
7
3
e
-
0
0
4
2
.
6
9
5
5
e
-
0
1
0
7
0
.
0
2
4
6
6
3
4
6
7
7
9
3
9
9
9
8
.
9
2
0
8
e
-
0
0
4
6
.
7
7
1
0
e
-
0
1
0
8
0
.
0
3
4
7
2
0
3
7
3
7
2
5
7
7
0
8
.
6
3
7
6
e
-
0
0
4
2
.
1
6
6
2
e
-
0
0
9
9
0
.
0
2
3
5
8
6
8
0
5
1
9
7
2
5
8
8
.
7
5
2
3
e
-
0
0
4
3
.
4
1
9
8
e
-
0
0
8
10
0
.
0
3
2
6
6
8
1
8
7
6
0
8
5
4
7
5
.
0
0
7
8
e
-
0
0
4
6
.
7
6
3
6
e
-
0
1
0
11
0
.
0
3
9
0
7
7
2
3
3
0
9
8
4
9
4
8
.
8
5
2
6
e
-
0
0
4
6
.
9
3
8
6
e
-
0
1
3
12
0
.
0
1
6
9
2
3
0
6
1
6
2
4
2
0
3
7
.
0
1
0
3
e
-
0
0
4
5
.
9
8
1
6
e
-
0
0
8
13
0
.
0
3
8
7
6
1
7
2
8
0
4
9
2
5
1
7
.
4
7
5
0
e
-
0
0
4
3
.
8
8
3
4
e
-
0
1
0
14
0
.
0
3
8
4
0
3
1
6
6
4
7
4
4
5
2
7
.
2
4
4
7
e
-
0
0
4
3
.
4
9
1
2
e
-
0
1
0
15
0
.
0
3
5
1
7
1
2
9
5
3
1
9
1
8
3
4
.
5
8
9
4
e
-
0
0
4
9
.
5
2
3
1
e
-
0
0
9
16
0
.
0
3
9
7
8
7
6
7
7
1
6
6
0
5
7
5
.
8
2
1
4
e
-
0
0
4
1
.
9
7
4
8
e
-
0
0
9
17
0
.
0
3
5
8
0
1
7
7
5
2
5
5
1
4
4
4
.
1
5
8
3
e
-
0
0
4
4
.
3
7
4
7
e
-
0
1
0
18
0
.
0
3
8
2
4
9
5
6
8
9
1
1
9
0
8
7
.
4
4
9
2
e
-
0
0
4
4
.
9
7
3
6
e
-
0
1
2
19
0
.
0
3
4
7
5
8
6
1
7
7
2
3
5
0
3
7
.
5
9
1
2
e
-
0
0
4
1
.
3
3
5
1
e
-
0
0
9
20
0
.
0
3
0
5
1
4
1
8
3
3
9
7
5
1
3
8
.
1
7
5
6
e
-
0
0
4
3
.
2
4
4
6
e
-
0
1
4
Fig
u
r
e
8
.
“
I
ter
atio
n
”
v
s
“
MSE
”
Gr
a
p
h
f
o
r
A
NN,
ANN
w
it
h
GA
a
n
d
A
NN
w
it
h
MG
A
T
h
e
Ma
tlab
/Si
m
u
li
n
k
b
ased
s
i
m
u
latio
n
o
f
t
h
e
m
u
lti
lev
el
in
v
er
ter
an
d
th
e
M
-
f
ile
b
ased
ANN,
ANN
w
it
h
G
A
o
p
ti
m
i
s
atio
n
a
n
d
ANN
w
it
h
MG
A
o
p
ti
m
i
s
atio
n
o
f
th
e
A
NN
w
ei
g
h
t
s
an
d
b
ias
v
al
u
es
h
a
s
b
ee
n
i
m
p
le
m
en
ted
.
T
h
e
o
p
tim
i
s
atio
n
o
f
th
e
th
e
s
e
th
r
ee
m
et
h
o
d
s
h
as
b
ee
n
d
ep
icted
in
th
e
f
i
g
u
r
e
.
8
,
w
h
ic
h
s
h
o
w
s
th
at
t
h
e
A
NN
m
et
h
o
d
h
a
s
tak
e
n
ar
o
u
n
d
1
8
th
iter
atio
n
f
o
r
s
ett
l
in
g
to
th
e
lo
w
e
s
t
MSE
,
ANN
w
it
h
G
A
h
a
s
ta
k
en
4
iter
atio
n
to
r
ea
ch
t
h
e
lo
w
es
t
MSE
it
co
u
ld
attai
n
,
A
NN
w
it
h
M
G
A
w
o
u
ld
r
ea
ch
it
s
lo
w
e
s
t
MSE
in
j
u
s
t
2
iter
atio
n
s
.
An
d
als
o
w
e
co
u
l
d
o
b
s
er
v
e
th
at
th
e
MSE
is
a
t
its
lo
w
est
w
h
i
le
w
e
u
s
e
th
e
A
NN
w
it
h
MG
A
m
et
h
o
d
,
th
en
in
th
e
s
ec
o
n
d
p
o
s
itio
n
co
m
e
s
t
h
e
A
NN
w
it
h
GA
a
n
d
t
h
en
th
e
ANN.
I
f
a
p
ar
allel
p
r
o
ce
s
s
in
g
is
ap
p
lied
w
h
ich
w
o
u
ld
h
elp
in
m
ak
in
g
th
e
ca
lc
u
latio
n
s
in
G
A,
MG
A
an
d
ANN
p
o
s
s
ib
le
o
n
th
e
h
ar
d
w
ar
e
t
h
en
it
w
o
u
ld
b
e
s
u
g
g
e
s
ted
to
ap
p
ly
t
h
e
MG
A
w
it
h
A
NN
f
o
r
th
e
i
m
p
le
m
en
ta
tio
n
o
f
t
h
e
f
au
l
t d
etec
tio
n
o
n
th
e
C
M
L
I
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
a
u
lt Dia
g
n
o
s
is
a
n
d
R
ec
o
n
fig
u
r
a
tio
n
o
f Mu
ltil
ev
el
I
n
ve
r
ter S
w
itch
F
a
ilu
r
e
-
A
…
(
T.G.
Ma
n
ju
n
a
th
)
2619
6.
CO
NCLU
SI
O
N
T
h
e
f
au
lt
d
iag
n
o
s
is
s
y
s
te
m
i
s
ap
p
lied
to
th
e
m
eta
-
h
e
u
r
is
t
ic
alg
o
r
ith
m
s
to
g
et
o
p
ti
m
al
s
o
lu
tio
n
s
,
w
h
ic
h
m
a
k
e
s
th
e
d
iag
n
o
s
i
s
s
y
s
te
m
to
id
e
n
ti
f
y
f
aster
a
n
d
g
i
v
e
th
e
co
n
tr
o
l
s
ig
n
al.
T
h
e
G
A
,
an
d
MG
A
m
eth
o
d
s
ar
e
co
m
p
ar
ed
to
p
r
o
d
u
ce
o
p
ti
m
al
s
o
lu
t
io
n
if
t
h
e
f
au
l
t
o
cc
u
r
s
.
T
h
e
te
s
t
s
y
s
te
m
i
s
tes
ted
w
it
h
t
h
e
Ma
tlab
/Si
m
u
l
in
k
an
d
th
e
al
g
o
r
ith
m
s
ar
e
co
d
ed
as
p
er
th
e
alg
o
r
ith
m
u
s
in
g
M
-
f
ile
s
.
T
h
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
u
s
ed
f
o
r
th
is
test
s
y
s
te
m
is
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
o
n
cla
s
s
i
f
icatio
n
o
f
f
au
l
t
a
n
d
th
e
r
esu
l
ts
s
h
o
w
s
t
h
a
t
th
e
MG
A
al
g
o
r
ith
m
g
iv
e
s
f
a
s
t
an
d
ac
cu
r
ate
r
esu
lts
co
m
p
ar
ed
to
th
e
o
th
er
m
et
h
o
d
s
.
T
h
e
r
esu
lts
d
u
r
in
g
t
h
e
t
esti
n
g
p
o
r
tio
n
h
ad
g
i
v
e
n
1
0
0
%
ac
cu
r
ac
y
f
o
r
all
t
h
e
f
a
u
lt
co
n
d
itio
n
t
h
u
s
h
as
p
er
f
o
r
m
ed
w
el
l
th
a
n
t
h
e
[
1
2
]
w
h
er
e
at
s
o
m
e
f
a
u
lt c
o
n
d
itio
n
s
it h
as p
er
f
o
r
m
ed
8
0
% a
cc
u
r
ac
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
Au
t
h
o
r
s
g
r
ate
f
u
l
l
y
ac
k
n
o
w
le
d
g
e
th
e
s
u
p
p
o
r
t
o
f
Mr
.
V
Gan
es
h
a
n
an
d
Dh
a
m
o
d
h
ar
an
S
f
r
o
m
Vis
w
aJ
o
th
i T
ec
h
n
o
lo
g
ie
s
P
r
iv
ate
L
i
m
ited
,
I
n
c.
f
o
r
th
e
ir
v
al
u
ab
le
s
u
g
g
e
s
tio
n
s
an
d
s
o
f
t
w
ar
e
s
u
p
p
o
r
t.
RE
F
E
R
E
NC
E
S
[1
]
M
a
d
ich
e
tt
y
,
S
re
e
d
h
a
r,
“
M
o
d
u
lar
M
u
lt
il
e
v
e
l
Co
n
v
e
rters
P
a
rtI:
A
R
e
v
ie
w
o
n
T
o
p
o
lo
g
ies
M
o
d
u
lati
o
n
M
o
d
e
li
n
g
a
n
d
Co
n
tr
o
l
S
c
h
e
m
e
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
V
o
l
-
4
,
3
6
-
5
0
,
IJA
ES
2
0
1
4
.
[2
]
M
a
n
ju
n
a
th
a
,
Y.
R
,
”
M
u
lt
il
e
v
e
l
DC
L
in
k
In
v
e
rter
w
it
h
Re
d
u
c
e
d
N
u
m
b
e
r
o
f
S
w
it
c
h
e
s
a
n
d
Ba
tt
e
ries
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
V
o
l
4,
2
9
9
-
3
07,
IJ
A
ES
2
0
1
4
.
[3
]
M
a
ry
a
m
.
S
e
t
a
l.
,
“
A
n
a
l
y
sis a
n
d
Co
n
tr
o
l
o
f
DC Ca
p
a
c
it
o
rs
-
Vo
lt
a
g
e
-
Drif
t
P
h
e
n
o
m
e
n
o
n
o
f
a
P
a
ss
iv
e
F
ro
n
t
-
En
d
F
iv
e
-
L
e
v
e
l
Co
n
v
e
rter”
,
IEE
E
T
ra
n
s.
I
n
d
u
stria
l
El
e
c
tro
n
ics
,
V
o
l.
5
4
,
N
o
.
6
,
De
c
.
2
0
0
7
,
p
p
.
3
2
5
5
-
3
2
0
6
.
[4
]
J.S
.
L
a
i
a
n
d
F
.
Z
.
P
e
n
g
,
“
M
u
lt
i
lev
e
l
Co
n
v
e
rter
–
A
N
e
w
Bre
e
d
o
f
P
o
w
e
r
Co
n
v
e
rters
”
,
IEE
E
T
ra
n
s.
I
n
d
u
stry
Ap
p
li
c
a
ti
o
n
s
,
Vo
l.
3
2
,
No
.
3
,
M
a
y
/Ju
n
e
1
9
9
6
,
p
p
.
5
0
9
-
5
1
7
.
[5
]
A
.
L
e
sn
ica
r
a
n
d
R.
M
a
ru
a
rd
t
,
“
An
In
n
o
v
a
ti
v
e
M
o
d
u
lar
M
u
lt
i
lev
e
l
Co
n
v
e
rter
T
o
p
o
lo
g
y
S
u
it
a
b
le
f
o
r
a
W
id
e
P
o
w
e
r
Ra
n
g
e
”
,
IEE
E
Po
we
r T
e
c
h
C
o
n
fe
re
n
c
e
,
V
o
l
.
3
,
Bo
lo
g
n
a
,
Italy
,
2
3
-
2
6
J
u
n
e
2
0
0
3
.
[6
]
X
.
X
u
,
Y.
Zo
u
,
K.
Din
g
,
a
n
d
F
.
L
iu
,
“
Ca
s
c
a
d
e
m
u
lt
il
e
v
e
l
in
v
e
rt
e
r
w
it
h
p
h
a
se
-
sh
if
t
S
P
W
M
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
i
n
S
TAT
COM
”
,
in
Pro
c
.
I
EE
E
IEC
ON
,
2
0
0
4
,
v
o
l.
2
,
p
p
.
1
1
3
9
–
1
1
4
3
.
[7
]
C.
Ne
w
to
n
a
n
d
M
.
S
u
m
n
e
r,
“
N
e
u
tral
P
o
i
n
t
C
o
n
tr
o
l
f
o
r
M
u
lt
il
e
v
e
l
In
v
e
rters
:
T
h
e
o
r
y
,
De
s
i
g
n
a
n
d
O
p
e
ra
ti
o
n
a
l
L
i
m
it
a
ti
o
n
s
”
,
IEE
E
In
d
u
stry
Ap
p
li
c
a
ti
o
n
s
S
o
c
iety
An
n
u
a
l
M
e
e
ti
n
g
,
Ne
w
Orle
a
n
s,
L
o
u
isian
a
,
Oc
to
b
e
r
1
9
9
7
,
p
p
.
1
3
3
6
-
1
3
4
3
.
[8
]
S
u
rin
K
h
o
m
f
o
i
a
n
d
L
e
o
n
M
.
T
o
lb
e
rt
,
“
F
a
u
lt
Dia
g
n
o
s
is
a
n
d
Re
c
o
n
f
i
g
u
ra
ti
o
n
f
o
r
M
u
l
ti
lev
e
l
In
v
e
rter
D
riv
e
Us
in
g
A
I
-
Ba
se
d
T
e
c
h
n
iq
u
e
s”
,
IEE
E
T
ra
n
s
a
c
ti
o
n
s On
In
d
u
stri
a
l
El
e
c
tro
n
ics
,
V
o
l
.
5
4
,
N
o
.
6
,
De
c
e
m
b
e
r
2
0
0
7
.
[9
]
D.
Eato
n
,
J.
Ra
m
a
,
a
n
d
P
.
W
.
Ha
m
m
o
n
d
,
“
Ne
u
tral
sh
if
t”
,
IEE
E
In
d
.
Ap
p
l.
M
a
g
.
,
v
o
l.
9
,
n
o
.
6
,
p
p
.
4
0
–
4
9
,
No
v
.
/De
c
.
2
0
0
3
.
[1
0
]
Ka
ri
m
i
S
,
G
a
il
lard
A
,
P
o
u
re
d
P
,
e
t
a
l.
,
“
F
P
G
A
-
Ba
se
d
Re
a
l
-
T
i
m
e
P
o
w
e
r
Co
n
v
e
rter
F
a
il
u
re
Dia
g
n
o
sis
f
o
r
W
in
d
En
e
rg
y
Co
n
v
e
rsio
n
S
y
ste
m
s
”
,
IE
EE
T
ra
n
.
I
n
d
.
El
e
c
tro
n
.
,
v
o
l
.
5
5
,
n
o
.
1
2
,
p
p
.
4
2
9
9
-
4
3
0
8
,
De
c
.
2
0
0
8
.
[1
1
]
T
.
Ba
rtz
-
Be
ielst
e
in
,
C.
L
a
sa
rc
z
y
k
,
a
n
d
M
.
P
re
u
ss
,
“
S
e
q
u
e
n
ti
a
l
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
”
,
in
Pro
c
.
I
EE
E
CEC
,
S
a
n
F
ra
n
c
isc
o
,
CA
,
USA
,
S
e
p
.
2
0
0
5
,
p
p
.
7
7
3
–
7
8
0
.
[1
2
]
Ro
n
g
ju
n
L
i
a
n
d
X
ian
y
in
g
Ch
a
n
g
,
“
A
M
o
d
if
ied
G
e
n
e
ti
c
A
lg
o
rit
h
m
w
it
h
M
u
l
ti
p
le
S
u
b
p
o
p
u
latio
n
s
a
n
d
Dy
n
a
m
i
c
P
a
ra
m
e
ters
A
p
p
li
e
d
in
CV
a
R
m
o
d
e
l”,
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
fo
r
M
o
d
e
ll
in
g
Co
n
tro
l
a
n
d
A
u
to
m
a
ti
o
n
,
a
n
d
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
te
ll
ig
e
n
t
Ag
e
n
ts,
W
e
b
T
e
c
h
n
o
lo
g
i
e
s
a
n
d
In
ter
n
e
t
Co
mm
e
rc
e
(
CIM
CA
-
IAW
T
IC'
0
6
)
IEE
E
2
0
0
6
.
[1
3
]
Ra
m
m
o
h
a
n
Ra
o
Err
a
b
e
ll
i
e
t
a
l,
“
F
a
u
lt
-
T
o
lera
n
t
V
o
l
tag
e
so
u
rc
e
In
v
e
rter
f
o
r
P
e
rm
a
n
e
n
t
M
a
g
n
e
t
Driv
e
s”
,
IEE
E
T
ra
n
s.
O
n
P
o
we
r E
lec
tro
n
ics
,
Vo
l.
2
7
,
5
0
0
-
5
0
8
,
I
EE
E
2
0
1
2
.
[1
4
]
Jia
n
g
W
e
i
e
t
a
l,
“
F
a
u
lt
d
e
tec
ti
o
n
a
n
d
Re
m
e
d
y
o
f
M
u
lt
il
e
v
e
l
In
v
e
rter
b
a
se
d
o
n
B
P
Ne
u
ra
l
Ne
tw
o
rk
”
,
Po
we
r
a
n
d
En
e
rg
y
En
g
in
e
e
rin
g
C
o
n
fer
e
n
c
e
(
AP
PE
EC)
,
I
EE
E
2
0
1
2
A
sia
-
P
a
c
if
ic
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
T.
G
.
M
a
n
ju
n
a
th
,
e
m
a
il
ID:
tg
m
n
a
th
@g
m
a
il
.
c
o
m
,
w
o
rk
in
g
a
s
a
n
A
s
so
c
iate
p
ro
f
e
s
so
r
&
HO
D
a
t
S
a
i
V
i
d
y
a
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
Ba
n
g
a
lo
re
,
Ka
rn
a
tak
a
.
He
re
c
e
i
v
e
d
h
is
B.
E
De
g
re
e
f
ro
m
R.
V
.
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ba
n
g
a
lo
re
(Ba
n
g
a
lo
re
Un
iv
e
rsity
)
a
n
d
M
a
ste
r
De
g
re
e
f
ro
m
U.V
.
C.
E
.
Ba
n
g
a
lo
re
(Ba
n
g
a
lo
re
Un
iv
e
rsity
)
in
th
e
y
e
a
r
1
9
9
9
a
n
d
2
0
0
4
re
sp
e
c
ti
v
e
l
y
.
H
e
w
o
rk
e
d
in
Na
ti
o
n
a
l
A
e
ro
sp
a
c
e
L
a
b
o
ra
to
ries
(N
AL
)
a
s
p
ro
jec
t
A
ss
o
c
iate
&
h
a
v
in
g
a
ro
u
n
d
1
5
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
re
p
u
ted
In
ti
tu
ti
o
n
s.He
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
is
D
o
c
to
ra
l
re
se
a
rc
h
i
n
V
isv
e
sw
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lg
a
v
i.
His
re
se
a
rc
h
i
n
c
lu
d
e
s
i
n
th
e
f
ield
o
f
M
u
lt
i
lev
e
l
In
v
e
rters
,
DC
-
DC Co
n
v
e
rter
s an
d
A
NN
.
Evaluation Warning : The document was created with Spire.PDF for Python.