I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
w
er
E
lect
ro
nics
a
nd
Driv
e
Sy
s
t
e
m
(
I
J
P
E
DS
)
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
,
p
p
.
601
~
6
1
1
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
p
ed
s
.
v
8
i2
.
p
p
6
0
1
-
611
601
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
JP
E
DS
Senso
r F
a
ult
De
te
ction a
nd Iso
la
tion
B
a
sed o
n Ar
tif
i
cia
l Neural
Netw
o
rk
s a
nd F
u
zz
y
Lo
g
ic
Applica
ted
o
n
Ind
uction
M
o
tor
for
Electrical
Vehicle
So
uh
a
B
o
uk
a
di
da
1
,
So
ufie
n
G
da
i
m
2
,
A
bd
ella
t
if
M
t
iba
3
L
a
b
o
ra
to
ry
EµE
o
f
th
e
F
S
M
,
U
n
i
v
e
rsit
y
o
f
M
o
n
a
stir,
T
u
n
isia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
9
,
2
0
1
7
R
ev
i
s
ed
Ma
r
2
9
,
2
0
1
7
A
cc
ep
ted
A
p
r
1
0
,
2
0
1
7
Re
c
e
n
tl
y
,
re
se
a
rc
h
h
a
s
p
ick
e
d
u
p
a
f
e
r
v
e
n
t
p
a
c
e
in
t
h
e
a
re
a
o
f
f
a
u
lt
d
iag
n
o
sis
o
f
e
lec
tri
c
a
l
v
e
h
icle
.
L
i
k
e
f
a
il
u
re
s
o
f
a
p
o
siti
o
n
se
n
s
o
r,
a
v
o
lt
a
g
e
se
n
so
r,
a
n
d
c
u
rre
n
t
se
n
so
rs.
T
h
re
e
-
p
h
a
se
in
d
u
c
ti
o
n
m
o
to
rs
a
re
th
e
“
w
o
rk
h
o
rse
s”
o
f
in
d
u
stry
a
n
d
a
re
th
e
m
o
st
w
id
e
l
y
u
se
d
e
lec
tri
c
a
l
m
a
c
h
in
e
s.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
sc
h
e
m
e
f
o
r
F
a
u
lt
De
tec
ti
o
n
a
n
d
Iso
latio
n
(F
DI).
T
h
e
p
ro
p
o
se
d
a
p
p
ro
a
c
h
is
a
se
n
so
r
-
b
a
se
d
tec
h
n
iq
u
e
u
sin
g
t
h
e
m
a
in
s
c
u
rre
n
t
m
e
a
su
re
m
e
n
t.
Cu
rre
n
t
se
n
s
o
rs
a
re
w
id
e
sp
re
a
d
in
p
o
w
e
r
c
o
n
v
e
rters
c
o
n
tro
l
a
n
d
i
n
e
lec
tri
c
a
l
d
riv
e
s.
T
h
u
s,
to
e
n
su
re
c
o
n
ti
n
u
o
u
s
o
p
e
ra
ti
o
n
w
it
h
re
c
o
n
f
i
g
u
ra
ti
o
n
c
o
n
tr
o
l,
a
f
a
st
s
e
n
so
r
f
a
u
lt
d
e
tec
ti
o
n
a
n
d
is
o
latio
n
is
re
q
u
ired
.
I
n
th
is
p
a
p
e
r,
a
n
e
w
a
n
d
f
a
st
f
a
u
lt
y
c
u
rre
n
t
se
n
so
r
d
e
tec
ti
o
n
a
n
d
iso
lati
o
n
is
p
re
se
n
ted
.
It
is
d
e
riv
e
d
f
ro
m
in
telli
g
e
n
t
tec
h
n
iq
u
e
s.
T
h
e
m
a
in
in
tere
st
o
f
f
ield
p
r
o
g
ra
m
m
a
b
le
g
a
te
a
rr
a
y
is
th
e
e
x
tre
m
e
l
y
f
a
st
c
o
m
p
u
tatio
n
c
a
p
a
b
il
it
ies
.
T
h
a
t
a
ll
o
w
s
a
f
a
st
re
sid
u
a
l
g
e
n
e
ra
ti
o
n
w
h
e
n
a
se
n
so
r
f
a
u
lt
o
c
c
u
rs.
Us
in
g
o
f
X
i
li
n
x
S
y
ste
m
G
e
n
e
r
a
to
r
in
M
a
tl
a
b
/
S
im
u
li
n
k
a
ll
o
w
s
th
e
re
a
l
-
ti
m
e
si
m
u
latio
n
a
n
d
im
p
le
m
e
n
ted
o
n
a
f
ield
p
ro
g
ra
m
m
a
b
le
g
a
te
a
rra
y
c
h
i
p
w
it
h
o
u
t
a
n
y
V
HSIC
Ha
rd
w
a
r
e
De
sc
rip
ti
o
n
L
a
n
g
u
a
g
e
c
o
d
in
g
.
T
h
e
se
n
so
r
f
a
u
lt
d
e
tec
ti
o
n
a
n
d
iso
latio
n
a
lg
o
rit
h
m
wa
s
i
m
p
le
m
e
n
ted
targ
e
ti
n
g
a
V
irt
e
x
5
.
S
im
u
latio
n
re
su
lt
s
a
re
g
iv
e
n
to
d
e
m
o
n
stra
te t
h
e
e
ff
ic
ien
c
y
o
f
th
is
F
DI ap
p
ro
a
c
h
.
K
ey
w
o
r
d
:
F
au
lt d
etec
tio
n
an
d
is
o
latio
n
FP
GA
I
n
d
u
ctio
n
m
o
to
r
Xilin
x
S
y
s
te
m
Ge
n
er
ato
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
:
So
u
h
a
B
o
u
k
ad
id
a
,
L
ab
o
r
ato
r
y
E
µE
o
f
t
h
e
FS
M
U
n
iv
er
s
it
y
o
f
Mo
n
a
s
tir,
T
u
n
is
ia
.
E
m
ail:
b
o
u
k
ad
id
aso
u
h
a@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Dev
elo
p
m
e
n
t
a
n
d
r
esear
ch
i
n
t
h
e
f
ield
o
f
elec
tr
ic
v
eh
ic
les
ap
p
ea
r
ed
w
i
th
t
h
e
co
llecti
v
e
a
w
a
r
en
ess
o
n
g
lo
b
al
w
ar
m
i
n
g
.
I
n
d
ee
d
,
th
e
tr
an
s
p
o
r
t
s
ec
to
r
is
o
n
e
o
f
th
e
m
a
in
ca
u
s
es
i
n
th
e
e
m
is
s
io
n
o
f
g
r
ee
n
h
o
u
s
e
g
a
s
e
m
is
s
io
n
s
.
T
h
is
co
n
te
x
t
t
h
at
m
an
u
f
ac
t
u
r
er
s
ar
e
f
ac
i
n
g
t
h
e
c
h
alle
n
g
e
o
f
r
ed
u
cin
g
C
ar
b
o
n
Dio
x
id
e
n
o
t
r
ej
ec
ted
co
m
b
u
s
t
io
n
v
e
h
icles
[
1
]
.
T
o
ad
d
r
ess
th
e
s
e
e
n
v
ir
o
n
m
e
n
ta
l
co
n
s
tr
ai
n
t
s
,
th
e
m
o
s
t
p
r
o
m
is
in
g
tech
n
o
lo
g
ica
l
s
o
lu
tio
n
is
th
e
s
u
b
s
ti
tu
t
io
n
o
f
th
e
en
g
i
n
e
w
ith
a
n
elec
tr
ic
m
o
to
r
.
Ho
w
e
v
er
,
th
e
elec
tr
ical
p
r
o
p
u
ls
io
n
ch
ai
n
is
b
u
ilt
ar
o
u
n
d
a
lar
g
e
n
u
m
b
er
o
f
co
m
p
o
n
e
n
ts
(
elec
tr
ical
m
ac
h
in
e,
s
e
n
s
o
r
s
,
co
n
v
er
ter
s
p
o
w
er
elec
tr
o
n
ics
.
.
.
etc.
)
w
h
ic
h
m
a
y
b
e
t
h
e
s
ite
o
f
a
h
i
g
h
n
u
m
b
er
o
f
d
e
f
ec
ts
.
T
h
e
d
etec
tio
n
an
d
lo
ca
tio
n
o
f
t
h
ese
d
ef
ec
ts
ar
e
es
s
en
t
ial
b
u
t n
o
t s
u
f
f
ic
ien
t t
o
e
n
s
u
r
e
th
e
s
af
et
y
an
d
o
p
er
atio
n
in
d
eg
r
a
d
ed
m
o
d
e.
Mu
ch
w
o
r
k
h
as
b
ee
n
d
o
n
e
i
n
o
r
d
er
to
li
m
it
th
e
i
m
p
ac
t
o
f
th
e
s
e
d
ef
ec
ts
i
n
p
o
w
er
p
lan
t
[
2
]
-
[
4
]
.
A
n
u
m
b
er
s
o
f
ap
p
r
o
ac
h
es
f
o
r
f
au
lt
d
etec
tio
n
a
n
d
is
o
latio
n
ar
e
d
ev
elo
p
ed
,
b
u
t
m
o
s
t
o
f
t
h
e
m
f
o
cu
s
ed
o
n
th
e
s
ta
to
r
w
i
n
d
in
g
s
o
f
a
m
o
to
r
a
n
d
p
o
w
er
s
e
m
ico
n
d
u
cto
r
o
f
an
in
v
er
ter
.
Su
d
d
en
s
e
v
er
e
f
au
lts
o
f
a
cu
r
r
en
t
s
e
n
s
o
r
r
esu
lt
in
t
h
e
o
v
er
cu
r
r
en
t
m
al
f
u
n
ct
io
n
o
f
th
e
s
y
s
te
m
,
an
d
if
t
h
er
e
is
n
o
p
r
o
p
e
r
p
r
o
tectio
n
s
ch
e
m
e
i
n
th
e
g
ate
-
d
r
iv
e
cir
cu
it,
it
lead
s
to
ir
r
ec
o
v
er
ab
le
f
a
u
lts
o
f
p
o
w
er
s
e
m
ico
n
d
u
cto
r
s
i
n
t
h
e
i
n
v
er
ter
.
T
h
e
lar
g
el
y
u
s
ed
ap
p
r
o
ac
h
f
o
r
s
en
s
o
r
F
DI
is
b
a
s
ed
o
n
r
esid
u
a
ls
g
e
n
er
ated
b
y
co
m
p
ar
is
o
n
b
et
w
ee
n
m
ea
s
u
r
e
d
s
en
s
o
r
o
u
tp
u
t
a
n
d
r
ec
o
n
s
tr
u
cted
s
e
n
s
o
r
o
u
tp
u
t,
u
s
i
n
g
o
th
er
s
y
s
te
m
s
e
n
s
o
r
s
.
I
t
co
u
ld
b
e
class
ed
in
to
t
w
o
ca
teg
o
r
ies:
o
n
e
b
ased
f
r
ee
m
o
d
el
m
e
th
o
d
s
a
n
d
th
e
s
e
co
n
d
b
ased
an
al
y
tical
m
o
d
el.
T
h
e
m
et
h
o
d
u
s
ed
t
h
e
m
o
d
el
o
f
s
y
s
te
m
to
g
en
er
at
e
a
r
esid
u
al
w
h
ich
b
ec
o
m
es
s
m
a
ll i
n
t
h
e
ab
s
e
n
ce
o
f
d
e
f
ec
t a
n
d
lar
g
e
i
n
t
h
e
ca
s
e
o
f
f
a
u
lt.
Sen
s
o
r
f
au
l
t i
s
d
etec
ted
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
IJ
PEDS
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
:
601
–
6
1
1
602
an
d
id
en
tifie
d
u
s
i
n
g
an
al
y
tic
al
r
ed
u
n
d
an
c
y
a
s
p
r
esen
ted
in
th
e
d
if
f
er
en
t
w
o
r
k
s
[
5
]
-
[
8
]
.
Un
f
o
r
tu
n
atel
y
,
th
e
an
al
y
tical
m
o
d
el
co
u
ld
b
e
i
m
p
r
ec
is
e
an
d
u
n
ce
r
tain
t
h
at
‟
s
w
h
y
th
e
r
es
id
u
al
co
u
ld
in
d
ica
te
a
f
alse
a
lar
m
.
Fo
r
th
is
r
ea
s
o
n
th
e
s
e
tec
h
n
iq
u
es
ar
e
w
ell
-
s
u
ited
f
o
r
d
eter
m
i
n
i
s
tic
m
o
d
els.
T
o
s
o
lv
e
th
i
s
p
r
o
b
lem
,
i
n
telli
g
e
n
t
tech
n
iq
u
es
ar
e
u
s
ed
.
T
h
is
ca
teg
o
r
y
h
a
s
m
a
n
y
ad
v
a
n
ta
g
es:
u
n
ce
r
tai
n
t
y
,
co
m
p
le
x
an
d
d
is
tu
r
b
an
ce
s
y
s
te
m
m
o
d
eli
n
g
.
T
h
er
ef
o
r
e,
th
ese
tech
n
iq
u
es
ar
e
r
eq
u
ir
ed
in
th
is
p
r
o
b
lem
t
y
p
e,
w
h
er
e
t
h
e
d
etec
tio
n
an
d
th
e
is
o
la
tio
n
o
f
th
e
f
a
u
lt
f
o
r
th
e
s
en
s
o
r
s
o
f
s
p
ec
if
y
i
n
g
s
y
s
te
m
w
ill
b
e
g
u
ar
a
n
teed
w
it
h
d
esire
d
p
er
f
o
r
m
an
ce
s
.
Ma
n
y
w
o
r
k
s
h
a
v
e
u
s
ed
in
tel
lig
e
n
t
te
ch
n
iq
u
es
to
ad
o
p
t
th
e
d
etec
tio
n
s
e
n
s
o
r
f
ail
u
r
es
f
o
r
v
ar
io
u
s
s
y
s
te
m
s
a
s
p
r
esen
ted
in
[
9
]
-
[
1
1
]
.
A
u
t
h
o
r
s
d
ev
elo
p
ed
th
is
ap
p
r
o
ac
h
tak
in
g
a
d
v
an
ta
g
es
o
n
t
h
e
o
n
e
h
an
d
o
f
d
ig
ital
co
n
tr
o
l
i
m
p
le
m
en
ta
tio
n
h
ar
d
w
ar
e
a
n
d
s
o
f
t
w
ar
e
s
p
ec
if
icatio
n
s
a
n
d
o
n
th
e
o
th
er
h
a
n
d
,
o
f
elec
tr
ical
s
y
s
te
m
s
s
p
ec
if
icatio
n
s
.
T
h
e
s
i
m
p
lic
it
y
o
f
th
e
f
in
al
al
g
o
r
ith
m
lead
s
to
lo
w
ex
ec
u
tio
n
ti
m
e
an
d
lo
w
c
o
n
s
u
m
ed
r
eso
u
r
ce
s
f
o
r
d
ig
ital i
m
p
le
m
e
n
tat
io
n
.
T
o
s
u
cc
ess
f
u
ll
y
i
m
p
le
m
e
n
t
o
n
t
h
e
FP
GA
b
o
ar
d
th
e
FDI
alg
o
r
ith
m
f
o
r
t
h
e
in
d
u
ctio
n
m
o
to
r
an
d
r
ea
lized
an
e
m
b
ed
d
ed
s
y
s
te
m
.
T
h
er
e
ar
e
th
r
ee
m
et
h
o
d
s
:
t
h
e
f
ir
s
t
is
to
d
ir
ec
tl
y
p
r
o
g
r
a
m
o
u
r
FP
G
A
u
s
i
n
g
VHDL
,
th
e
d
i
s
ad
v
a
n
tag
e
o
f
t
h
is
m
eth
o
d
it
is
t
h
at
w
e
ca
n
n
o
t
v
is
u
alize
th
e
b
e
h
av
io
r
o
f
r
ea
l
-
t
i
m
e
o
f
t
h
e
co
n
tr
o
l.
T
h
e
s
ec
o
n
d
is
to
u
s
e
t
h
e
to
o
lb
o
x
ad
d
ed
to
Ma
tlab
/ S
i
m
u
li
n
k
HD
L
co
d
er
,
th
e
d
i
s
ad
v
a
n
tag
e
o
f
t
h
is
m
et
h
o
d
t
h
at
th
e
to
o
lb
o
x
m
i
s
s
i
n
g
a
lo
t
an
d
w
e
ar
e
o
b
lig
ed
to
m
a
k
e
s
e
v
er
al
ap
p
r
o
x
im
a
tio
n
s
an
d
th
e
r
e
s
u
l
tin
g
p
r
o
g
r
a
m
is
n
o
t
o
p
tim
ized
.
An
d
th
e
las
t
co
n
s
i
s
ts
to
u
s
e
th
e
to
o
lb
o
x
ad
d
ed
t
o
Si
m
u
lin
k
Xil
in
x
S
y
s
te
m
Ge
n
er
ato
r
(
XSG)
,
th
e
ad
v
an
ta
g
e
o
f
th
i
s
p
r
o
g
r
a
m
m
i
n
g
m
et
h
o
d
is
t
h
e
r
eso
l
u
tio
n
o
f
all
p
r
o
b
le
m
s
o
f
d
is
p
la
y
.
W
e
ca
n
also
ta
k
e
ad
v
an
ta
g
e
o
f
Si
m
u
li
n
k
an
d
v
i
s
u
alize
t
h
e
ac
tu
al
b
e
h
av
io
r
o
f
t
h
e
m
ac
h
i
n
e
b
ef
o
r
e
i
m
p
le
m
e
n
t
atio
n
.
T
h
is
p
ap
er
g
iv
es
d
etailed
i
n
f
o
r
m
atio
n
o
n
a
n
e
w
cu
r
r
en
t
s
e
n
s
o
r
FDI
alg
o
r
ith
m
,
w
h
ic
h
is
d
ev
elo
p
ed
u
s
i
n
g
i
n
telli
g
e
n
t
tec
h
n
iq
u
es
(
Neu
r
o
Fu
zz
y
)
.
Af
ter
t
h
is
i
n
tr
o
d
u
cto
r
y
s
ec
tio
n
,
t
h
e
p
r
o
b
le
m
s
ta
te
m
e
n
t
is
p
r
esen
ted
,
w
ith
a
d
escr
ip
tio
n
o
f
t
h
e
m
ac
h
i
n
e
m
o
d
el
an
d
it
s
co
n
tr
o
l
s
y
s
te
m
.
T
h
e
ar
ch
ite
ctu
r
e
o
f
t
h
e
Ne
u
r
o
Fu
zz
y
s
c
h
e
m
a
u
s
ed
f
o
r
g
en
er
atio
n
an
d
e
v
al
u
atio
n
is
d
is
c
u
s
s
ed
in
s
ec
tio
n
3
.
Si
m
u
latio
n
r
esu
lt
s
ar
e
g
iv
e
n
i
n
s
ec
tio
n
4
to
ill
u
s
tr
ate
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
Neu
r
o
-
F
u
zz
y
FDI
s
ch
e
m
e
f
o
r
s
en
s
o
r
f
a
u
lt
d
ia
g
n
o
s
is
o
f
th
e
in
d
u
ctio
n
m
o
to
r
.
2.
SYST
E
M
O
VE
RVI
E
W
2.
1
.
P
re
s
ent
a
t
i
o
n
Au
to
m
o
ti
v
e
ap
p
licatio
n
d
r
iv
es
(
E
V)
h
as
s
o
m
e
m
aj
o
r
r
eq
u
ir
e
m
e
n
ts
t
h
at
ar
e
s
u
m
m
ar
ized
as
f
o
llo
w
s
[
3
]
-
[
4
]
:
1.
h
ig
h
to
r
q
u
e
at
lo
w
s
p
ee
d
s
f
o
r
s
tar
tin
g
,
as
w
ell
as
h
i
g
h
p
o
w
er
at
h
ig
h
s
p
ee
d
f
o
r
cr
u
i
s
in
g
;
2.
f
ast to
r
q
u
e
r
esp
o
n
s
e;
3.
h
ig
h
p
o
w
er
d
en
s
it
y
an
d
h
ig
h
i
n
s
ta
n
t p
o
w
er
;
4.
h
ig
h
e
f
f
icien
c
y
f
o
r
r
eg
en
er
ati
v
e
b
r
ak
in
g
,
o
v
er
w
id
e
s
p
ee
d
an
d
to
r
q
u
e;
5.
r
ea
s
o
n
ab
le
co
s
t.
T
h
e
tr
ac
tio
n
o
f
an
elec
tr
ic
v
e
h
icle
ca
n
s
u
b
d
iv
id
e
in
t
h
r
ee
p
ar
ts
:
a
p
o
w
er
s
o
u
r
ce
,
an
i
n
v
er
ter
an
d
a
r
ec
eiv
er
(
s
ee
Fi
g
u
r
e
1
)
.
T
h
e
s
o
u
r
ce
is
t
h
e
b
atter
y
an
d
t
h
e
r
ec
eiv
er
is
th
e
m
ec
h
a
n
ical
c
h
a
in
.
T
h
e
p
o
w
er
tr
ai
n
co
m
p
o
s
ed
o
f
t
h
e
in
v
er
ter
(
an
d
its
co
n
tr
o
l)
an
d
th
e
m
o
to
r
is
th
e
elec
tr
o
m
ec
h
a
n
ical
p
o
w
er
co
n
v
er
ter
.
Fau
lt
s
ca
n
a
f
f
ec
t
all
t
h
e
co
m
p
o
n
en
t
s
o
f
th
e
s
y
s
te
m
:
in
d
u
cti
o
n
m
o
to
r
,
p
o
w
er
co
n
v
er
ter
s
,
co
n
n
ec
to
r
s
an
d
s
en
s
o
r
s
.
T
h
e
f
ailu
r
e
s
in
t
h
e
elec
tr
ic
m
o
to
r
ca
n
h
a
v
e
v
ar
i
o
u
s
o
r
ig
i
n
s
:
a.
Failu
r
es r
elate
d
to
th
e
e
x
p
lo
ita
tio
n
th
at
ca
n
lead
to
f
au
lts
a
n
d
also
a
p
r
em
at
u
r
e
d
eg
r
ad
atio
n
;
b.
Failu
r
es r
elate
d
to
w
r
o
n
g
w
ea
k
d
i
m
e
n
s
io
n
i
n
g
a
n
d
d
esig
n
w
h
ich
lead
to
a
p
r
em
at
u
r
e
d
eg
r
ad
atio
n
I
t is v
er
y
i
m
p
o
r
ta
n
t to
d
etec
t a
s
en
s
o
r
f
ail
u
r
e
o
n
a
r
ea
l
-
ti
m
e
b
asis
f
o
r
s
tr
u
ct
u
r
al
h
ea
lt
h
m
o
n
it
o
r
in
g
a
n
d
v
ib
r
at
io
n
co
n
tr
o
l.
Ma
n
y
f
a
u
lt
d
etec
tio
n
an
d
is
o
latio
n
FDI
te
ch
n
iq
u
es
f
o
r
c
u
r
r
en
t
s
e
n
s
o
r
s
h
av
e
b
ee
n
d
is
c
u
s
s
ed
o
v
er
th
e
p
as
t
d
ec
ad
es
Fra
n
k
1
9
9
0
,
Ger
tler
1
9
9
1
.
T
h
e
t
w
o
m
aj
o
r
s
en
s
o
r
f
ail
u
r
e
d
etec
ti
o
n
m
e
th
o
d
s
ca
n
b
e
d
is
tin
g
u
is
h
ed
:
a.
Dir
ec
t
p
atter
n
r
ec
o
g
n
itio
n
o
f
s
en
s
o
r
r
ea
d
in
g
s
t
h
at
in
d
icate
a
f
au
lt
a
n
d
an
a
n
al
y
s
i
s
o
f
th
e
d
is
cr
ep
an
c
y
b
et
w
ee
n
th
e
s
e
n
s
o
r
r
ea
d
in
g
s
a
n
d
ex
p
ec
ted
v
alu
e
s
,
d
er
iv
ed
f
r
o
m
s
o
m
e
m
o
d
el.
I
n
t
h
e
latter
ca
s
e,
it
is
t
y
p
ical
th
a
t a
f
a
u
lt is
s
aid
to
b
e
d
etec
ted
if
th
e
d
is
cr
ep
an
c
y
o
r
r
esid
u
al
g
o
es a
b
o
v
e
a
c
er
tai
n
t
h
r
es
h
o
ld
.
b.
I
n
s
i
g
n
al
p
r
o
ce
s
s
i
n
g
b
ased
F
DI
,
s
o
m
e
m
a
th
e
m
atica
l
o
r
s
ta
tis
tical
o
p
er
atio
n
s
ar
e
p
er
f
o
r
m
ed
o
n
th
e
m
ea
s
u
r
e
m
e
n
t
s
,
o
r
s
o
m
e
i
n
t
ellig
e
n
t
tec
h
n
iq
u
e
is
tr
ain
e
d
u
s
i
n
g
m
ea
s
u
r
e
m
e
n
t
s
to
ex
tr
ac
t
t
h
e
in
f
o
r
m
atio
n
ab
o
u
t t
h
e
f
au
lt.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
PEDS
I
SS
N:
2
0
8
8
-
8
694
S
en
s
o
r
F
a
u
lt De
tectio
n
a
n
d
I
s
o
la
tio
n
B
a
s
ed
o
n
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
s
…
(
S
o
u
h
a
B
o
u
k
a
d
id
a
)
603
Fig
u
r
e
1
.
Ma
in
co
m
p
o
n
e
n
ts
o
f
an
E
V
tr
ac
tio
n
d
r
iv
e.
2
.
2
.
B
a
s
ic
P
rinciple
o
f
DT
C
SVM
T
h
e
co
n
v
en
t
io
n
al
DT
C
s
tr
ateg
y
is
a
d
e
v
elo
p
ed
d
r
iv
e
co
n
tr
o
l te
ch
n
iq
u
e
o
f
th
e
I
M.
T
h
is
t
y
p
e
o
f
to
r
q
u
e
an
d
f
l
u
x
co
n
tr
o
l
w
as
f
ir
s
t
p
r
o
p
o
s
ed
as
d
ir
ec
t
s
elf
-
co
n
tr
o
l
b
y
Dep
en
b
r
o
ck
[
1
7
]
an
d
DT
C
b
y
T
ak
a
h
as
h
i
an
d
No
g
u
c
h
i
[
1
8
]
.
T
h
e
D
T
C
m
e
t
h
o
d
is
ch
ar
ac
ter
ized
b
y
its
s
i
m
p
le
i
m
p
le
m
e
n
tatio
n
,
f
ast
d
y
n
a
m
ic
r
esp
o
n
s
e,
an
d
r
o
b
u
s
tn
es
s
to
th
e
r
o
to
r
p
ar
am
eter
v
ar
iat
io
n
es
s
en
tiall
y
.
T
h
e
m
a
in
id
ea
o
f
DT
C
SV
M
is
to
r
ec
o
v
er
th
e
r
ed
u
ctio
n
o
f
t
h
e
r
ip
p
les
o
f
to
r
q
u
e
an
d
f
lu
x
,
a
n
d
to
h
a
v
e
s
u
p
er
io
r
d
y
n
a
m
ic
p
er
f
o
r
m
a
n
ce
s
.
Fig
u
r
e
2
p
r
esen
t
a
p
o
s
s
ib
le
s
ch
e
m
atic
o
f
Dir
ec
t
T
o
r
q
u
e
C
o
n
tr
o
l
b
y
u
s
in
g
Sp
a
ce
Vec
to
r
Mo
d
u
latio
n
.
T
h
er
e
ar
e
t
w
o
d
if
f
er
en
t
lo
o
p
s
co
r
r
esp
o
n
d
in
g
to
th
e
m
ag
n
i
tu
d
es
o
f
t
h
e
s
tato
r
f
l
u
x
a
n
d
to
r
q
u
e.
T
h
e
er
r
o
r
b
etw
ee
n
th
e
est
i
m
a
ted
s
tato
r
f
l
u
x
m
a
g
n
i
tu
d
e
φ
s
an
d
t
h
e
r
ef
e
r
en
ce
s
tato
r
f
l
u
x
m
a
g
n
itu
d
e
φ
s
*
is
th
e
i
n
p
u
t o
f
a
b
lo
c
SVM.
Kn
o
w
i
n
g
t
h
at
i
n
th
e
g
r
ad
u
atio
n
p
h
ase
v
o
ltag
e
s
(
V
a
,
V
b
,
V
c
)
ar
e
r
ep
r
esen
ted
in
th
e
p
lan
e
b
y
a
v
ec
to
r
V
s
.
E
ac
h
m
o
d
u
latio
n
p
er
io
d
T
m
o
d
o
f
t
h
e
in
v
er
ter
,
th
e
p
r
o
j
ec
ted
v
ec
to
r
Vs
o
n
th
e
t
w
o
ad
j
ac
en
t
v
ec
to
r
s
as
s
u
r
e
s
th
e
s
w
itc
h
i
n
g
ti
m
e
o
f
ca
lc
u
la
tio
n
.
T
h
e
v
alu
e
s
o
f
t
h
ese
p
r
o
j
ec
tio
n
s
p
r
o
v
id
e
t
h
e
d
esire
d
c
o
m
m
u
tatio
n
t
i
m
e
s
.
T
h
e
k
e
y
s
tep
o
f
t
h
e
SVM
tec
h
n
iq
u
e
i
s
th
e
d
eter
m
in
at
io
n
o
f
T
i
an
d
T
i+
1
d
u
r
in
g
e
v
er
y
m
o
d
u
l
atio
n
p
er
io
d
T
m
od
.
T
o
illu
s
tr
ate
t
h
e
m
et
h
o
d
o
lo
g
y
w
e
co
n
s
id
er
t
h
e
ca
s
e
w
h
er
e
V
s
ca
n
b
e
co
m
p
o
u
n
d
ed
b
y
th
e
ac
tiv
e
v
o
ltag
e
v
ec
to
r
s
V
1
an
d
V
2
.
Fig
u
r
e
2
.
B
lo
c
d
iag
r
am
o
f
DT
C
T
h
e
s
tato
r
v
o
ltag
e
an
d
s
tato
r
cu
r
r
en
t
ar
e
ca
lcu
lated
f
r
o
m
th
e
s
tate
o
f
th
r
ee
p
h
ase
(
S
a
,S
b
,S
c
)
an
d
m
ea
s
u
r
ed
cu
r
r
en
t
s
(
i
a
, i
b
, i
c
).
In
d
u
c
ti
o
n
mo
t
o
r
In
v
er
ter
Batter
y
Sa
Sb
Sc
I
M
V
o
l
t
a
g
e
s
o
u
r
c
e
In
v
e
r
t
e
r
T
φ
T*
s
φ*
s
T
i
T
i+
1
V
sα
V
sβ
F
l
u
x
a
n
d
t
o
rq
u
e
e
st
i
m
a
t
o
r
C
a
l
c
u
l
a
t
i
o
n
S
a
,
S
b
,
S
c
PI
PI
C
a
l
c
u
l
a
t
i
o
n
T
i
, T
i
+1
α
,
β
d
,
q
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
IJ
PEDS
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
:
601
–
6
1
1
604
24
33
0
24
33
2
(
,
,
)
(
)
3
2
(
,
,
)
(
)
3
jj
s
a
b
c
a
b
c
jj
s
a
b
c
a
b
c
V
S
S
S
E
S
S
e
S
e
i
i
i
i
i
i
e
i
e
E
x
p
r
ess
i
n
g
t
h
e
v
o
ltag
e
v
ec
to
r
Vs in
t
h
e
g
r
ad
u
atio
n
(
α
,
β)
w
e
h
av
e:
12
12
m
o
d
m
o
d
s
s
s
TT
V
V
j
V
V
V
TT
E
x
p
an
d
in
g
t
h
is
eq
u
atio
n
i
t
is
p
o
s
s
ib
le
to
ex
p
r
ess
t
h
e
ti
m
e
T
1
an
d
T
2
in
ter
m
s
o
f
V
sα
a
n
d
V
sβ
.
T
h
e
co
n
d
u
ctio
n
ti
m
e
w
il
l b
e
ex
p
r
ess
ed
as f
o
llo
w
s
:
m
o
d
1
m
o
d
2
31
(
.
)
.
22
2.
.
ss
s
T
T
V
V
E
T
TV
E
C
o
n
s
eq
u
en
tl
y
,
t
h
e
d
u
tie
s
ex
p
r
ess
io
n
s
ar
e
g
i
v
en
a
s
f
o
llo
w
s
:
ss
1
s
2
0
1
2
3
V
1
V
.
EE
22
V
2
E
1
D
D
D
D
D
T
h
e
s
p
ac
e
v
ec
to
r
in
s
ec
to
r
1
is
s
h
o
w
n
in
f
i
g
u
r
e
3
.
T
h
e
ti
m
e
d
u
r
atio
n
o
f
ze
r
o
v
ec
to
r
s
is
d
iv
id
ed
eq
u
all
y
i
n
to
(
V0
,
V1
,
V2
,
V7
,
V2
,
V1
,
V0
)
,
w
h
er
ea
s
t
h
e
ti
m
e
d
u
r
atio
n
o
f
ea
ch
n
o
n
ze
r
o
v
ec
to
r
is
d
is
tr
ib
u
ted
in
to
t
w
o
p
ar
ts
.
T
h
is
s
eq
u
e
n
ce
ca
n
e
n
s
u
r
e
th
a
t
is
o
n
e
p
h
a
s
e
s
w
i
tch
e
s
w
h
e
n
t
h
e
s
w
itc
h
in
g
p
atter
n
s
w
itc
h
es,
t
h
u
s
ca
n
r
ed
u
ce
th
e
h
ar
m
o
n
ic
co
m
p
o
n
e
n
t
o
f
t
h
e
o
u
tp
u
t
c
u
r
r
en
t
a
n
d
th
e
lo
s
s
o
f
s
w
itc
h
i
n
g
d
ev
ices.
T
h
e
d
u
tie
s
o
f
ea
ch
p
h
ase
o
f
th
e
in
v
er
ter
ar
e
p
r
esen
ted
as
f
o
llo
w
s
:
12
12
12
0
.
5
(
1
)
0
.
5
(
1
)
0
.
5
(
1
)
a
b
c
S
D
D
S
D
D
S
D
D
Fig
u
r
e.
3
Seq
u
en
ce
s
o
f
th
e
s
w
i
tch
es
s
tates i
n
s
ec
to
r
N1
(
1
)
(
2
)
(
3
)
(
4
)
(
5
)
S
c
S
b
S
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
PEDS
I
SS
N:
2
0
8
8
-
8
694
S
en
s
o
r
F
a
u
lt De
tectio
n
a
n
d
I
s
o
la
tio
n
B
a
s
ed
o
n
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
s
…
(
S
o
u
h
a
B
o
u
k
a
d
id
a
)
605
3.
F
AULT
D
E
T
E
C
T
I
O
N
a
n
d
I
SO
L
A
T
I
O
N
(
F
DI)
FDI
s
y
s
te
m
i
s
d
esi
g
n
ed
as
a
h
y
b
r
id
s
y
s
te
m
i
n
w
h
ic
h
f
u
zz
y
s
y
s
te
m
a
n
d
n
e
u
r
al
n
et
w
o
r
k
s
m
a
y
co
o
p
er
ate
an
d
in
ter
ac
t
to
i
m
p
le
m
en
t
e
f
f
ic
ien
t
l
y
th
e
r
eq
u
ir
ed
FDI
tas
k
s
.
T
h
e
s
tr
u
ct
u
r
e
o
f
Ne
u
r
o
Fu
zz
y
i
s
s
u
cc
e
s
s
f
u
l
ap
p
licatio
n
s
r
el
y
o
n
th
e
ea
s
e
o
f
r
u
le
b
ase
d
esig
n
,
ap
p
licab
ilit
y
to
co
m
p
lex
,
u
n
c
er
tain
an
d
n
o
n
l
in
ea
r
s
y
s
te
m
s
,
li
n
g
u
is
tic
m
o
d
eli
n
g
,
lear
n
in
g
ab
ilit
ies,
p
ar
allel
p
r
o
ce
s
s
in
g
.
T
h
e
FDI
s
ch
e
m
e
i
s
d
iv
id
ed
in
to
t
w
o
s
tep
s
(
d
etec
tio
n
s
tep
an
d
lo
ca
l
izatio
n
s
tep
)
.
T
h
e
f
ir
s
t
s
tep
i
s
b
ased
o
n
g
e
n
er
atin
g
a
s
ig
n
al
c
alled
r
esid
u
al.
I
t‟
s
u
s
ed
li
k
e
in
d
icto
r
o
f
t
h
e
o
cc
u
r
r
en
ce
o
f
t
h
e
f
a
u
lt.
I
f
th
e
d
i
f
f
er
en
ce
is
eq
u
a
l
to
ze
r
o
,
th
en
t
h
e
eq
u
ip
m
e
n
t
s
y
s
te
m
o
p
er
ate
in
h
ea
lt
h
y
ca
s
e,
o
t
h
er
w
i
s
e
(
r
esid
u
a
l
≠
0
)
t
h
e
y
ar
e
af
f
ec
ted
b
y
a
f
a
u
lt
w
h
ich
s
h
o
u
ld
b
e
is
o
lated
.
T
h
e
r
o
le
o
f
t
h
e
s
ec
o
n
d
s
t
ep
i
s
to
d
eter
m
i
n
e
t
h
e
ti
m
e
o
f
t
h
e
d
e
f
a
u
lt
a
p
p
licatio
n
.
I
n
o
r
d
er
to
g
et
t
h
e
ad
eq
u
ate
d
ec
is
io
n
,
th
is
p
h
ase
r
eq
u
ir
es
a
tec
h
n
iq
u
e
d
ea
ls
w
it
h
u
n
ce
r
tai
n
d
ata.
T
h
e
m
o
s
t
ap
p
r
o
p
r
iate
tech
n
iq
u
e
is
t
h
e
Neu
r
o
F
u
zz
y
lo
g
ic.
I
t n
ee
d
s
an
e
x
p
er
t s
y
s
te
m
.
T
h
e
F
ig
u
r
e
4
s
h
o
w
s
t
h
e
d
if
f
er
en
t
s
tag
e
s
o
f
t
h
e
ad
o
p
ted
s
tr
ateg
y
.
Fig
u
r
e
4
.
A
d
o
p
ted
s
tr
ateg
y
3
.
1
.
P
ha
s
e
Det
ec
t
io
n
I
n
th
e
ca
s
e
o
f
n
o
n
li
n
ea
r
s
y
s
te
m
s
,
a
r
esid
u
e
g
en
er
ato
r
b
y
co
n
v
e
n
tio
n
al
q
u
a
n
titati
v
e
m
e
th
o
d
s
is
n
o
t
an
ea
s
y
ta
s
k
.
I
t
w
o
u
ld
b
e
b
etter
to
u
s
e
n
eu
r
al
n
et
w
o
r
k
s
to
g
en
er
ate
r
esid
u
e
s
f
u
n
ctio
n
s
,
u
s
in
g
th
e
ir
ab
ilit
y
to
m
o
d
el
n
o
n
lin
ea
r
f
u
n
ct
io
n
s
.
B
e
f
o
r
eh
an
d
,
a
d
atab
ase
m
u
s
t
b
e
p
er
f
o
r
m
ed
o
f
f
l
in
e
w
i
th
ex
p
er
t
k
n
o
w
led
g
e.
I
t
m
u
s
t
in
cl
u
d
e
th
e
m
ai
n
c
h
ar
ac
ter
is
t
ics
o
f
th
e
p
r
o
ce
s
s
(
o
p
er
atin
g
p
o
in
t
,
s
tab
ilit
y
,
n
o
is
e
.
.
.
)
.
I
n
o
r
d
er
to
m
a
k
e
t
h
e
n
eu
r
al
n
e
t
w
o
r
k
d
escr
ib
e
th
e
b
eh
av
io
r
o
f
t
h
e
s
y
s
te
m
,
i
t
s
h
o
u
ld
b
e
lear
n
ed
w
i
th
d
ata
b
ase
r
ich
i
n
in
f
o
r
m
a
tio
n
.
On
ce
th
is
b
ase
is
r
ea
lized
,
a
s
t
r
u
ctu
r
e
o
f
t
h
e
n
e
u
r
al
n
e
t
w
o
r
k
m
u
s
t b
e
ch
o
s
e
n
.
3
.
2
.
P
ha
s
e
o
f
lo
ca
liza
t
io
n
T
h
e
r
o
le
o
f
th
e
r
esid
u
al
Fu
zz
if
icatio
n
\
E
v
al
u
atio
n
s
tep
is
to
id
en
tify
t
h
e
ele
m
e
n
t
(
cu
r
r
e
n
t
s
en
s
o
r
s
)
attac
h
ed
b
y
th
e
f
au
lt.
I
n
o
r
d
er
to
g
et
th
e
ad
eq
u
ate
d
ec
is
io
n
,
th
is
p
h
a
s
e
r
eq
u
ir
es
a
tech
n
iq
u
e
d
ea
ls
w
it
h
u
n
ce
r
tai
n
d
ata.
T
h
e
m
o
s
t
ap
p
r
o
p
r
iate
tech
n
iq
u
e
is
th
e
f
u
zz
y
lo
g
ic.
I
t
n
ee
d
s
a
n
e
x
p
er
t
s
y
s
te
m
.
T
h
e
Fi
g
u
r
e
5
s
h
o
w
s
t
h
e
d
if
f
er
e
n
t sta
g
es o
f
t
h
e
ad
o
p
ted
s
tr
ateg
y
.
An
NF
g
en
er
al
l
y
co
n
s
is
ts
o
f
t
w
o
p
r
in
cip
al
u
n
i
ts
:
(
a)
a
f
u
z
zif
ie
w
h
ic
h
co
n
v
er
t
s
an
alo
g
i
n
p
u
t
s
in
to
f
u
zz
y
v
ar
iab
les.
T
h
ese
v
ar
ia
b
les
ar
e
p
r
o
d
u
ce
d
b
y
u
s
i
n
g
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
(
MF
)
;
(
b
)
th
e
r
esid
u
al
ev
alu
a
tio
n
s
tep
is
b
ased
R
N
N.
T
h
e
in
p
u
ts
o
f
th
e
n
et
w
o
r
k
ar
e
th
e
f
u
zz
i
f
ier
r
esid
u
es
(
th
r
ee
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
f
o
r
ea
ch
r
esid
u
e)
an
d
in
th
e
o
u
tp
u
ts
w
e
h
av
e
t
h
e
d
ec
is
io
n
s
.
3
.
2
.
1
.
F
uzzy
v
a
ria
bles
E
ac
h
r
esid
u
al
(
R
1
,
R
2
,
R
3
)
co
u
ld
b
e
d
escr
ib
ed
w
it
h
th
r
ee
m
e
m
b
er
s
h
ip
s
(
N=
Neg
at
iv
e,
Z
=
Z
er
o
a
n
d
P
=Po
s
itiv
e)
.
Fo
r
ea
ch
r
es
id
u
e
th
r
ee
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
ar
e
s
elec
ted
:
t
w
o
f
u
n
ctio
n
s
t
y
p
e
tr
ap
ez
o
id
al
an
d
o
n
e
f
u
n
ctio
n
t
y
p
e
tr
ian
g
u
lar
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
Fo
r
t
h
e
c
h
o
ice
o
f
p
ar
a
m
eter
s
,
m
a
n
y
tes
ts
ar
e
a
f
f
ec
ted
.
T
h
e
lin
g
u
i
s
tic
v
ar
iab
le
s
d
escr
ib
in
g
th
e
f
u
zz
i
f
ie
r
esid
u
als
ar
e
d
ef
i
n
ed
b
y
t
h
e
f
o
llo
w
i
n
g
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
:
„
„
N:
n
eg
at
iv
e
r
esid
u
al
w
it
h
tr
ap
ez
o
id
al
MF”,
„
„
Z
:
ze
r
o
r
esid
u
al
w
it
h
tr
ian
g
u
lar
MF”,
„
„
P
:
p
o
s
iti
v
e
r
esid
u
al
w
it
h
tr
ap
ez
o
id
al
MF”.
T
h
e
u
n
i
v
er
s
e
o
f
d
is
co
u
r
s
e
h
a
s
b
ee
n
n
o
r
m
ali
ze
d
to
[
−1
,
1
]
b
an
d
.
Pha
se
d
e
t
e
c
t
i
o
n
C
u
r
r
e
n
t
S
e
n
so
r
N
o
mi
n
a
l
mo
d
e
l
F
a
u
lt
Re
s
id
u
al
ge
n
e
r
at
i
on
S
y
st
e
m
o
u
t
p
u
t
Ou
t
p
u
t
M
o
d
e
l
A
n
aly
z
e
o
f
s
ym
p
t
om
E
x
p
e
r
t
sy
st
e
R
e
si
d
u
a
l
Pha
se
o
f
l
o
c
a
l
i
z
a
t
i
o
n
R1
μ
R1
-
1
0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
IJ
PEDS
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
:
601
–
6
1
1
606
Fig
u
r
e
5
.
Fu
zz
y
M
F o
f
t
h
e
in
p
u
t R
1
Fig
u
r
e
6
.
Neu
r
o
Fu
zz
y
d
ia
g
n
o
s
tic
s
c
h
e
m
e
3
.
2
.
2
.
I
nfe
re
nce
T
h
e
r
esid
u
al
ev
alu
atio
n
s
tep
is
b
ased
R
NN.
T
h
e
in
p
u
ts
o
f
t
h
e
n
et
w
o
r
k
ar
e
th
e
f
u
zz
i
f
ie
r
esid
u
es
(
µ
R1
,
µ
R2
,
µ
R3
)
an
d
in
th
e
o
u
tp
u
t
s
w
e
h
av
e
t
h
e
d
ec
is
io
n
s
(
D
1
,
D
2
,
D
3
)
.
T
h
e
n
et
w
o
r
k
R
NN
is
co
n
s
i
s
ts
o
f
:
n
i
n
e
n
eu
r
o
n
s
i
n
th
e
i
n
p
u
t
la
y
er
r
ep
r
esen
ti
n
g
th
e
in
p
u
ts
o
f
th
e
v
ar
i
o
u
s
p
o
s
s
ib
le
s
ta
tes
o
f
r
es
id
u
es
at
a
ti
m
e
(
k
)
(
a
f
ter
f
u
zz
if
ica
tio
n
)
,
f
o
u
r
n
e
u
r
o
n
s
in
th
e
h
id
d
en
la
y
er
a
n
d
th
r
ee
n
e
u
r
o
n
s
i
n
t
h
e
o
u
tp
u
t
la
y
er
.
T
h
e
R
NN
u
s
ed
i
n
th
is
s
i
m
u
lat
io
n
s
tu
d
y
is
b
ased
o
n
t
h
e
r
u
le
s
s
u
m
m
ar
ized
in
T
ab
le
1
w
h
ich
h
a
v
e
b
ee
n
o
b
tain
ed
af
ter
m
a
n
y
s
i
m
u
lat
io
n
tes
ts
.
E
ac
h
r
o
w
o
f
th
e
in
f
er
e
n
ce
tab
le
r
ep
r
esen
t
s
a
r
u
le.
E
ac
h
co
n
tr
o
l
r
u
le
f
r
o
m
T
ab
le
1
ca
n
b
e
d
escr
ib
ed
u
s
in
g
th
e
i
n
p
u
t
v
ar
iab
les
R
1
,
R
2
a
n
d
R
3
,
an
d
t
h
e
o
u
tp
u
ts
v
ar
iab
le
s
D
1
,
D
2
an
d
D
3
.
Fo
r
ex
am
p
le
r
u
le
3
is
e
x
p
r
ess
ed
as
f
o
llo
w:
I
f
{r
esid
u
al
1
is
P
o
s
iti
v
e
a
n
d
r
esid
u
al
2
is
P
o
s
iti
v
e
a
n
d
r
esid
u
al
3
i
s
Z
er
o
}
T
HE
N
s
en
s
o
r
2
is
f
au
lt
y
.
T
ab
le
1
.
I
n
f
er
en
ce
T
ab
le
N
N1
Z1
P1
N2
Z2
P2
N3
Z3
P3
D1
D2
D3
1
0
1
0
0
1
0
0
1
0
0
0
0
2
0
0
1
1
0
0
0
1
0
1
0
0
3
0
0
1
0
0
1
0
1
0
0
1
0
4
0
1
0
0
1
0
0
0
1
0
0
1
5
0
0
1
1
0
0
0
0
1
1
0
1
6
0
0
1
0
0
1
0
0
1
0
1
1
7
0
0
1
0
0
1
0
1
0
1
1
0
D
1
D
2
D3
F
au
l
t
Inf
e
r
e
nc
e
: In
t
h
i
s
st
e
p
w
e
w
i
l
l
anal
yz
e
t
he
f
uz
z
y
r
e
si
du
e
p
r
e
v
i
o
u
sl
y
o
bt
ai
ne
d
by
a
n
e
ur
al
ne
t
w
ork
Inp
ut
s
F
u
zz
i
f
i
c
a
t
i
o
n
(
M
e
mb
e
rs
h
i
p
f
u
n
c
t
i
o
n
)
µ
R1
µ
R2
µ
R3
R
1
R
2
R
3
Ia
Ib
S
en
s
o
r
of
c
u
r
r
e
n
t
R
e
si
du
al
g
e
ne
r
at
i
o
n
I
n
d
u
c
t
i
o
n
m
o
t
o
r
M
F
(
N1
,
Z1
,
P
1
)
M
F
(
N2
,
Z2
,
P
2
)
M
F
(
N3
,
Z3
,
P
3
)
R1
μ
R1
-
1
0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
PEDS
I
SS
N:
2
0
8
8
-
8
694
S
en
s
o
r
F
a
u
lt De
tectio
n
a
n
d
I
s
o
la
tio
n
B
a
s
ed
o
n
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
s
…
(
S
o
u
h
a
B
o
u
k
a
d
id
a
)
607
T
h
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
a
n
eu
r
o
n
i
s
g
iv
e
n
b
y
:
1
(
)
(
)
N
ii
i
D
i
µ
w
R
b
W
h
er
e
(
R
1
,
R
2
,
R
3
)
ar
e
in
p
u
ts
s
ig
n
al
o
f
t
h
e
n
e
u
r
o
n
,
(
w
1
,
w
2
,
…
w
N
)
ar
e
th
e
co
r
r
esp
o
n
d
in
g
w
ei
g
h
ts
a
n
d
b
is
th
e
b
ias
o
f
t
h
e
n
e
u
r
o
n
,
µ
is
th
e
t
an
g
e
n
t
s
ig
m
o
id
f
u
n
ctio
n
an
d
y
is
t
h
e
o
u
tp
u
t
s
ig
n
al
o
f
t
h
e
n
eu
r
o
n
.
T
h
e
m
o
s
t
p
o
p
u
lar
s
u
p
er
v
is
ed
tr
ain
in
g
alg
o
r
ith
m
i
s
th
e
b
ac
k
-
p
r
o
p
ag
atio
n
[
1
3
]
,
w
h
ich
co
n
s
i
s
ts
o
f
a
f
o
r
w
ar
d
an
d
b
ac
k
w
ar
d
ac
tio
n
.
I
n
t
h
e
f
ir
s
t,
t
h
e
f
r
ee
p
ar
a
m
eter
s
o
f
th
e
n
et
w
o
r
k
ar
e
f
i
x
ed
,
an
d
t
h
e
i
n
p
u
t
s
ig
n
al
i
s
p
r
o
p
ag
ated
th
r
o
u
g
h
th
e
n
et
w
o
r
k
la
y
er
b
y
l
a
y
er
.
T
h
e
f
o
r
w
ar
d
p
h
ase
f
i
n
is
h
es
w
i
th
th
e
co
m
p
u
tatio
n
o
f
a
m
ea
n
s
q
u
ar
e
er
r
o
r
.
On
ce
t
h
e
A
N
N
is
tr
ain
ed
p
r
o
p
er
l
y
,
it s
h
o
u
ld
b
e
ad
eq
u
atel
y
t
ested
w
it
h
i
n
ter
m
ed
iate
d
ata
t
o
v
er
if
y
t
h
at
tr
ai
n
i
n
g
is
co
r
r
ec
t a
n
d
co
m
p
lete.
4.
DE
V
E
L
O
P
M
E
NT
o
f
t
he
P
RO
P
O
SE
D
NE
U
RO
F
U
Z
Z
Y
L
O
G
I
C
DIA
G
NO
SI
S A
RC
H
I
T
E
CT
U
RE
4
.1
.
P
re
s
ent
a
t
i
o
n
o
f
Xilin
x
S
y
s
t
e
m
G
ener
a
t
o
r
Xilin
x
S
y
s
te
m
Ge
n
er
ato
r
T
o
o
l
d
ev
elo
p
ed
f
o
r
Ma
tlab
Si
m
u
li
n
k
p
ac
k
a
g
e
is
w
id
el
y
u
s
ed
f
o
r
alg
o
r
ith
m
d
ev
elo
p
m
en
t
a
n
d
v
er
i
f
icatio
n
p
u
r
p
o
s
es
in
Dig
ital
Si
g
n
a
l
P
r
o
ce
s
s
o
r
s
(
DSP
)
an
d
Field
P
r
o
g
r
am
m
ab
le
Gate
A
r
r
a
y
s
(
FP
G
A
s
)
.
X
ili
n
x
S
y
s
t
e
m
Ge
n
er
ato
r
(
XSG)
a
h
i
g
h
-
lev
el
to
o
l
f
o
r
d
esi
g
n
in
g
h
i
g
h
-
p
er
f
o
r
m
a
n
ce
D
SP
s
y
s
te
m
s
u
n
d
er
Si
m
u
lin
k
en
v
ir
o
n
m
e
n
t,
I
t
is
a
h
ig
h
l
y
d
es
ir
ab
le
to
h
a
v
e
t
h
i
s
s
i
m
u
la
tio
n
to
o
l t
h
at
ca
n
ea
s
il
y
m
a
k
e
th
e
d
ir
ec
t
tr
an
s
latio
n
in
to
h
ar
d
w
ar
e
o
f
co
n
tr
o
l
alg
o
r
ith
m
s
w
it
h
n
o
-
k
n
o
w
led
g
e
o
f
an
y
H
ar
d
w
ar
e
Descr
ip
tio
n
L
a
n
g
u
a
g
e
(
HDL
)
.
S
y
s
te
m
Ge
n
er
ato
r
T
o
o
l
allo
w
s
an
a
b
s
tr
a
ctio
n
lev
el
al
g
o
r
it
h
m
d
e
v
elo
p
m
en
t
w
h
ile
k
ee
p
i
n
g
th
e
tr
ad
itio
n
al
Si
m
u
li
n
k
b
lo
ck
s
et
s
,
b
u
t
at
t
h
e
s
a
m
e
ti
m
e
au
to
m
at
icall
y
tr
an
s
lati
n
g
d
esi
g
n
s
i
n
to
h
ar
d
w
ar
e
i
m
p
le
m
en
ta
tio
n
s
t
h
at
ar
e
f
ait
h
f
u
l,
s
y
n
th
e
s
izab
le,
an
d
e
f
f
icie
n
t.
Fo
r
r
ap
id
p
r
o
to
ty
p
i
n
g
,
th
e
ch
o
ice
o
f
th
i
s
to
o
l
i
s
ea
s
il
y
ex
p
lai
n
ed
b
y
th
e
ad
v
a
n
t
ag
e
to
s
i
m
u
late
t
h
e
co
n
tr
o
l a
l
g
o
r
ith
m
is
th
e
p
o
s
s
ib
ilit
y
to
g
e
n
er
ate
co
d
e
th
at
ca
n
b
e
u
s
ed
to
p
r
o
g
r
a
m
an
FP
GA
d
ir
ec
tl
y
f
r
o
m
th
e
s
i
m
u
latio
n
m
o
d
el.
W
h
en
t
h
e
co
n
tr
o
l
alg
o
r
ith
m
d
esi
g
n
o
f
th
e
co
n
tr
o
ller
is
co
m
p
lete
d
i
n
Ma
tlab
Si
m
u
l
in
k
e
n
v
ir
o
n
m
e
n
t
b
y
u
s
in
g
Xili
n
x
S
y
s
te
m
Gen
er
ato
r
,
it
ca
n
b
e
tr
an
s
lated
a
u
to
m
a
ticall
y
i
n
to
VHDL
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
ag
e
an
d
t
h
en
ca
n
b
e
e
m
b
ed
d
ed
in
to
t
h
e
Xili
n
x
FP
G
A
ap
p
licatio
n
b
o
ar
d
.
4
.
2
.
F
uzzif
ica
t
i
o
n
B
lo
ck
T
o
ev
alu
ate
t
h
e
r
u
le
p
r
e
m
is
e,
it
is
n
ec
e
s
s
ar
y
to
ca
lcu
late
t
h
e
v
alu
e
o
f
m
e
m
b
er
s
h
ip
o
f
ea
ch
in
p
u
t
to
a
s
p
ec
if
ied
MF.
T
h
e
r
esid
u
al
R
1
is
r
ep
r
esen
ted
b
y
t
h
r
ee
f
u
zz
y
s
et,
as
s
h
o
w
n
in
Fi
g
u
r
e
6
.
Fo
r
th
is
in
p
u
t
w
e
h
av
e
2
m
at
h
e
m
a
tical
f
u
n
c
tio
n
s
d
ep
en
d
in
g
:
tr
ap
ez
o
id
al
f
u
n
cti
o
n
an
d
tr
ian
g
u
lar
f
u
n
ct
io
n
.
T
h
e
tr
ap
ez
o
id
al
cu
r
v
e
d
ep
en
d
s
o
n
f
o
u
r
s
ca
lar
p
ar
a
m
e
t
er
s
a,
b
,
c,
an
d
d
,
as g
iv
e
n
b
y
,
f
(
x
,
a,
b
,
c,
d
)
=
{
}
T
h
is
E
q
u
atio
n
i
s
i
m
p
le
m
e
n
te
d
in
th
e
h
ar
d
w
ar
e
u
s
i
n
g
s
u
b
s
tr
ac
to
r
s
,
m
u
lt
ip
li
er
s
an
d
co
m
p
ar
ato
r
as
s
h
o
w
n
i
n
F
ig
u
r
e
7
.
T
h
e
f
u
zz
i
f
icat
io
n
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
u
s
i
n
g
t
h
r
ee
f
u
zz
i
f
ie
u
n
its
.
T
h
e
f
u
zz
i
f
i
e
b
lo
ck
o
f
R
1
,
th
e
f
u
zz
if
ie
b
lo
ck
o
f
R
2
a
n
d
th
e
f
u
zif
ie
b
lo
ck
o
f
R
3
tak
e
s
t
h
e
in
p
u
t a
n
d
p
r
o
d
u
ce
s
th
r
ee
o
u
tp
u
t v
alu
e
s.
(
6
)
(7
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
IJ
PEDS
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
:
601
–
6
1
1
608
Fig
u
r
e
7
.
Fu
zz
i
f
ier
u
n
it o
f
R
1
.
4
.
3
.
I
nfe
re
nce
T
h
e
h
ar
d
w
ar
e
i
m
p
le
m
en
ta
tio
n
o
f
th
e
in
f
er
en
ce
b
lo
ck
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
8
,
ac
ce
p
ts
t
h
r
ee
in
p
u
t
s
(µ
R1
,
µ
R2
,
µ
R3
)
f
r
o
m
th
e
f
u
zz
if
i
ca
tio
n
b
lo
ck
.
T
h
e
n
eu
r
al
p
r
o
ce
s
s
i
n
g
p
r
o
p
ag
ates
t
h
e
in
p
u
ts
t
o
o
u
tp
u
ts
(
D
1
,
D
2
,
D
3
)
.
P
r
o
p
ag
atio
n
o
cc
u
r
s
th
r
o
u
g
h
t
h
e
d
i
f
f
er
e
n
t la
y
er
s
o
f
n
e
u
r
o
n
s
,
ea
c
h
n
eu
r
o
n
N
m
,
j
o
f
t
h
e
la
y
er
m
ca
lc
u
late
s
t
h
e
o
u
tp
u
t
X
m
,
j
.
T
h
e
la
y
er
m
o
d
u
le
is
m
ad
e
b
asic
u
n
it
o
f
t
h
e
n
e
u
r
o
n
.
I
n
ef
f
ec
t,
ea
ch
la
y
er
is
co
m
p
o
s
ed
o
f
s
e
v
er
al
n
eu
r
o
n
s
o
p
er
atin
g
in
p
ar
allel.
T
h
at
is
w
h
y
o
u
r
ap
p
r
o
ac
h
to
d
escr
ip
tio
n
o
f
th
e
n
e
u
r
o
n
m
o
d
u
le
is
d
esi
g
n
ed
in
co
m
p
lia
n
ce
w
it
h
t
h
e
co
n
s
tr
ai
n
t
o
f
r
e
u
s
ab
ilit
y
.
I
n
t
h
e
ca
s
e
o
f
th
is
w
o
r
k
w
e
d
ev
elo
p
ed
o
u
r
t
h
r
ee
la
y
er
s
f
o
r
m
i
n
g
th
e
n
e
u
r
al
n
et
w
o
r
k
.
T
h
e
f
ir
s
t
h
id
d
en
la
y
er
co
n
tai
n
s
9
n
eu
r
o
n
s
.
T
h
e
s
ec
o
n
d
la
y
er
co
m
p
r
is
es
4
n
eu
r
o
n
s
.
T
h
e
p
r
o
ce
s
s
in
g
i
n
th
is
b
lo
ck
is
s
i
m
ilar
to
th
at
d
eter
m
i
n
ed
in
t
h
e
f
ir
s
t
la
y
er
.
T
h
e
in
ter
n
al
s
tr
u
ctu
r
e
o
f
a
n
eu
r
o
n
i
s
co
m
p
o
s
ed
o
f
a
s
et
o
f
ad
d
er
s
,
m
u
ltip
lier
s
a
n
d
co
m
p
ar
ato
r
.
T
h
e
th
ir
d
la
y
er
co
n
tai
n
s
o
n
l
y
th
r
ee
n
e
u
r
o
n
s
(
t
h
e
o
u
tp
u
t
la
y
er
)
.
T
h
is
last
la
y
er
d
etr
m
i
n
e
t
h
e
s
e
n
s
o
r
w
h
ic
h
i
s
d
ef
ec
ted
;
T
h
e
m
at
h
e
m
at
ical
p
r
o
ce
s
s
in
g
i
n
t
h
is
b
lo
ck
is
s
i
m
ilar
to
th
at
d
eter
m
i
n
ed
later
.
Fig
u
r
e
8
.
Stru
ct
u
r
e
o
f
a
n
eu
r
o
n
o
f
t
h
e
s
ec
o
n
d
la
y
er
.
5.
Si
m
ula
t
io
n a
nd
I
nte
rpre
t
a
t
io
n Re
s
ults
Fig
u
r
e
9
s
h
o
w
ed
t
h
e
m
o
d
el
t
h
at
u
s
e
s
th
e
Xili
n
x
b
lo
c
k
s
et
s
f
o
r
to
ler
an
t
co
n
tr
o
l.
T
h
is
m
o
d
el
is
u
s
ed
f
o
r
co
-
s
i
m
u
latio
n
.
On
ce
th
e
d
e
s
ig
n
is
v
er
i
f
ied
,
a
h
ar
d
w
ar
e
co
-
s
i
m
u
latio
n
b
lo
ck
ca
n
b
e
g
e
n
er
at
ed
an
d
th
e
n
it
w
il
l
b
e
u
s
ed
to
p
r
o
g
r
a
m
t
h
e
FP
GA
.
T
h
e
S
y
s
te
m
Gen
er
ato
r
w
il
l
f
i
r
s
t d
o
w
n
lo
ad
t
h
e
b
it
s
tr
ea
m
.
W
h
en
th
e
d
o
w
n
l
o
ad
is
co
m
p
lete,
S
y
s
te
m
Ge
n
er
ato
r
s
r
ea
d
th
e
in
p
u
t
s
f
r
o
m
Si
m
u
li
n
k
s
i
m
u
la
tio
n
e
n
v
ir
o
n
m
e
n
t
a
n
d
s
en
d
th
e
m
to
th
e
d
esig
n
o
n
th
e
b
o
ar
d
u
s
i
n
g
t
h
e
J
T
A
G
co
n
n
ec
t
io
n
.
S
y
s
te
m
G
en
er
ato
r
th
en
r
ea
d
s
t
h
e
o
u
tp
u
t
b
ac
k
f
r
o
m
J
T
A
G
an
d
s
en
d
s
i
t to
Si
m
u
li
n
k
f
o
r
d
is
p
la
y
ed
.
T
o
s
t
u
d
y
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
is
ap
p
r
o
ac
h
,
th
e
s
i
m
u
latio
n
o
f
th
e
s
y
s
te
m
w
a
s
co
n
d
u
c
ted
u
s
in
g
MA
T
L
A
B
.
Mo
to
r
s
p
ar
a
m
eter
s
f
o
r
s
i
m
u
latio
n
ar
e
g
i
v
en
in
T
ab
le
2
.
T
h
e
s
i
m
u
latio
n
r
es
u
lts
ar
e
s
h
o
w
n
i
n
Fig
u
r
e
s
10
-
12
.
T
h
e
to
r
q
u
e
a
n
d
f
l
u
x
r
e
f
er
en
ce
s
th
a
t
ar
e
u
s
ed
in
t
h
e
s
i
m
u
latio
n
r
e
s
u
l
ts
o
f
t
h
e
DT
C
-
SVM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
PEDS
I
SS
N:
2
0
8
8
-
8
694
S
en
s
o
r
F
a
u
lt De
tectio
n
a
n
d
I
s
o
la
tio
n
B
a
s
ed
o
n
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
s
…
(
S
o
u
h
a
B
o
u
k
a
d
id
a
)
609
s
tr
ateg
y
ar
e
1
0
N
·
m
an
d
0
.
9
1
W
b
,
r
esp
ec
tiv
ely
.
T
h
e
s
a
m
p
l
in
g
p
er
io
d
o
f
t
h
e
s
y
s
te
m
i
s
5
0
µs.
R
es
u
lt
s
u
s
i
n
g
h
ar
d
w
ar
e
co
-
s
i
m
u
latio
n
i
s
p
r
esen
ted
to
ass
e
s
s
th
e
ab
ilit
y
o
f
t
h
is
d
iag
n
o
s
is
ap
p
r
o
ac
h
b
ased
Neu
r
o
Fu
zz
y
tech
n
iq
u
e
to
d
et
ec
t
an
d
is
o
lat
e
s
en
s
o
r
f
a
u
lt
s
in
a
n
i
n
d
u
ctio
n
m
o
to
r
.
Si
m
u
latio
n
i
s
ca
r
r
ied
o
u
t
w
it
h
5
0
0
V
a
nd
5
0
Hz
s
in
u
s
o
id
al
in
p
u
t
s
.
Fi
g
u
r
e
1
0
s
h
o
w
s
s
p
ee
d
,
to
r
q
u
e
an
d
cu
r
r
en
t.
Fig
u
r
e
9
.
T
h
e
h
ar
d
w
ar
e
C
o
-
s
i
m
u
latio
n
b
lo
ck
.
T
h
e
m
ac
h
i
n
e
p
ar
am
e
ter
s
u
s
e
d
f
o
r
s
i
m
u
la
tio
n
ar
e
g
i
v
en
i
n
T
a
b
le
2
.
Var
io
u
s
s
i
m
u
latio
n
test
s
h
a
v
e
b
ee
n
p
er
f
o
r
m
ed
in
o
r
d
er
to
v
alid
ate
th
e
e
f
f
ic
ien
t
l
y
o
f
t
h
is
d
iag
n
o
s
is
s
c
h
e
m
e
a
n
d
th
e
r
esu
lts
ar
e
q
u
ite
co
n
clu
s
iv
e.
B
ias a
n
d
d
r
if
t t
y
p
e
s
en
s
o
r
f
a
u
lt
s
ar
e
in
tr
o
d
u
c
ed
d
u
r
in
g
s
tead
y
s
tate
co
n
d
it
io
n
s
o
f
th
e
s
y
s
te
m
.
Fo
r
illu
s
tr
ati
v
e
p
u
r
p
o
s
es o
n
l
y
a
f
e
w
f
a
u
lt
s
ce
n
ar
io
s
s
u
m
m
ar
i
ze
d
in
T
ab
les 3
an
d
4
ar
e
d
is
c
u
s
s
ed
.
C
ase
1
:
A
b
ias
t
y
p
e
f
au
lt is
in
j
ec
ted
o
n
s
en
s
o
r
1
as d
escr
ib
ed
in
T
ab
le
3
.
T
h
e
co
r
r
esp
o
n
d
in
g
r
esid
u
a
ls
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
1
1
.
Alt
h
o
u
g
h
a
s
i
n
g
le
f
a
u
lt
m
a
y
i
n
d
u
ce
ch
a
n
g
e
s
i
n
s
e
v
er
al
r
esi
d
u
als.
T
h
e
d
ec
is
io
n
f
u
n
ctio
n
s
e
n
s
u
r
e
s
u
cc
es
s
f
u
l d
e
tectio
n
an
d
i
s
o
latio
n
o
f
th
e
f
a
u
lt o
n
s
e
n
s
o
r
1
as s
h
o
w
n
i
n
F
ig
u
r
e
1
1
.
T
h
e
Neu
r
o
-
Fu
zz
y
cla
s
s
i
f
ier
h
as
b
ee
n
tr
ain
ed
to
r
ec
o
g
n
ize
t
h
e
f
a
u
lt
y
s
itu
a
tio
n
s
f
r
o
m
t
h
e
f
u
zz
i
f
i
e
r
esid
u
al
p
atter
n
s
ac
co
r
d
in
g
to
th
e
r
u
le
b
ase
g
i
v
e
n
in
T
ab
le
1
.
C
ase
2
:
T
h
is
f
a
u
lt
s
ce
n
ar
io
o
f
b
ias f
a
u
lt
s
o
n
s
en
s
o
r
s
1
a
n
d
2
is
d
escr
ib
ed
i
n
T
ab
le
4
.
T
h
e
r
esid
u
al
an
d
th
e
co
r
r
esp
o
n
d
in
g
d
ec
is
io
n
f
u
n
ctio
n
s
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
1
2
.
T
h
e
f
au
lt
y
s
e
n
s
o
r
s
ar
e
p
r
o
m
p
tl
y
d
etec
ted
an
d
co
r
r
ec
tly
i
s
o
lated
.
T
ab
le
2
.
I
n
d
u
ctio
n
m
ac
h
in
e
p
a
r
a
m
eter
s
V
o
l
t
a
g
e
2
2
0
/
3
8
0
v
S
t
a
t
o
r
r
e
si
st
a
n
c
e
R
s
5
.
7
1
7
Ω
R
o
t
o
r
r
e
si
st
a
n
c
e
R
r
4
.
2
8
2
Ω
S
t
a
t
o
r
i
n
d
u
c
t
a
n
c
e
L
s
0
.
4
6
4
H
R
o
t
o
r
i
n
d
u
c
t
a
n
c
e
L
r
0
.
4
6
4
H
M
u
t
u
a
l
i
n
d
u
c
t
a
n
c
e
M
0
.
4
4
1
H
M
o
me
n
t
o
f
i
n
e
r
t
i
a
J
0
.
0
0
4
9
K
g
.
m
2
Fig
u
r
e
10
.
(
a)
Sp
ee
d
(
r
a
d
/s
)
,
(
b
)
to
r
q
u
e(
N/m
)
a
n
d
(
c)
cu
r
r
en
t(
A
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
IJ
PEDS
Vo
l.
8
,
No
.
2
,
J
u
n
e
2
0
1
7
:
601
–
6
1
1
610
Fig
u
r
e
11
.
Facu
lt
y
r
es
id
u
als a
n
d
co
r
r
esp
o
n
d
in
g
d
ec
is
io
n
s
u
s
in
g
XSG
Fig
u
r
e
12
.
Facu
lt
y
r
es
id
u
als a
n
d
co
r
r
esp
o
n
d
in
g
d
ec
is
io
n
s
u
s
in
g
XSG
T
ab
le
3
.
C
A
S
E
1
S
e
n
so
r
N
F
a
u
l
t
t
i
me
B
i
a
s
f
a
u
l
t
1
1
0
.
1
5
T
ab
le
4
.
C
A
S
E
2
S
e
n
so
r
N
F
a
u
l
t
t
i
me
B
i
a
s
f
a
u
l
t
1
1
0
.
4
2
1
.
5
1
6
.
CO
NCLUS
I
O
N
T
h
is
p
ap
er
p
r
o
p
o
s
ed
a
n
ew
cu
r
r
en
t
s
e
n
s
o
r
f
au
l
t
d
etec
tio
n
an
d
is
o
lat
io
n
al
g
o
r
ith
m
f
o
r
elec
tr
ical
d
r
iv
es.
T
h
e
d
esi
g
n
w
as
b
ase
d
o
n
i
n
telli
g
e
n
t
tec
h
n
iq
u
e.
T
h
e
d
ev
e
lo
p
ed
FDI
alg
o
r
it
h
m
is
a
v
ailab
le
f
o
r
an
y
cu
r
r
en
t
s
en
s
o
r
in
p
o
w
er
co
n
v
e
r
ter
s
o
r
elec
tr
ical
d
r
iv
es.
T
h
e
in
n
o
v
ati
v
e
F
DI
alg
o
r
it
h
m
p
r
o
p
o
s
ed
in
th
is
p
ap
er
d
o
es
n
o
t
r
eq
u
ir
e
th
e
k
n
o
w
led
g
e
o
f
th
e
s
y
s
te
m
m
o
d
el
an
d
o
n
l
y
co
n
ce
r
n
ed
s
en
s
o
r
o
u
tp
u
t
s
ar
e
r
eq
u
ir
ed
.
T
h
e
p
r
o
p
o
s
ed
FDI
s
ch
e
m
e
is
b
ased
o
n
a
t
w
o
s
tep
p
r
o
ce
d
u
r
e:
a
Ne
u
r
al
Net
w
o
r
k
i
s
u
s
ed
f
o
r
r
esid
u
al
g
e
n
er
at
io
n
a
n
d
a
f
u
zz
y
n
eu
r
al
n
et
w
o
r
k
p
er
f
o
r
m
s
t
h
e
r
esid
u
al
e
v
al
u
atio
n
tas
k
.
T
h
e
s
u
cc
e
s
s
f
u
l
r
e
s
u
lt
s
o
b
t
ain
ed
i
n
s
i
m
u
la
tio
n
d
em
o
n
s
tr
ate
t
h
e
e
f
f
icie
n
c
y
o
f
th
is
n
e
u
r
o
-
f
u
zz
y
d
iag
n
o
s
i
s
s
ch
e
m
e
to
d
etec
t
an
d
is
o
late
b
ias
an
d
d
r
if
t
s
en
s
o
r
f
au
lts
i
n
an
i
n
d
u
ct
io
n
m
o
to
r
.
R
E
FE
R
E
N
C
E
S
[1
]
X
.
S
.
L
i
,
e
t
a
l.
,
"
A
n
a
l
y
sis
a
n
d
S
i
m
p
li
f
ica
ti
o
n
o
f
T
h
re
e
-
Di
m
e
n
sio
n
a
l
S
p
a
c
e
V
e
c
to
r
P
W
M
f
o
r
T
h
re
e
-
P
h
a
se
F
o
u
r
-
L
e
g
In
v
e
rters
,
"
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
In
d
u
stria
l
El
e
c
tro
n
ics
,
v
o
l
.
5
8
,
p
p
.
4
5
0
-
4
6
4
,
F
e
b
2
0
1
1
.
[2
]
B
.
J
u
s
tu
s
R
ab
i
,
e
t
a
l.
,
“
F
a
u
lt
T
o
lera
n
t
Co
n
t
r
o
l
i
n
Z
-
S
o
u
rc
e
I
n
v
e
rter
F
e
d
In
d
u
c
ti
o
n
M
o
to
r
"
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
P
o
w
e
r
El
e
c
tro
n
ics
a
n
d
Driv
e
S
y
ste
m
s,
pp.
29
-
35
,
2
0
1
1
.
[3
]
W
.
Yu
n
-
li
a
n
g
,
G
.
Qi
-
li
a
n
g
,
“
H
y
st
e
re
sis
Cu
rre
n
t
Co
n
tro
l
tec
h
n
iq
u
e
b
a
se
d
o
n
S
p
a
c
e
V
e
c
to
r
M
o
d
u
la
ti
o
n
f
o
r
A
c
ti
v
e
P
o
w
e
r
F
il
ter
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
P
o
we
r E
lec
tro
n
ics
a
n
d
Dr
i
v
e
S
y
ste
ms
,
pp.
1
-
6
,
2
0
1
1
.
[4
]
K.
S
rin
iv
a
sa
n
,
S
.
V
ij
a
y
a
n
,
S
.
P
a
r
a
m
a
siv
a
m
,
K.
S
u
n
d
a
ra
m
o
o
rth
i
,
“
P
o
w
e
r
Qu
a
li
ty
A
n
a
l
y
sis
o
f
V
ien
n
a
Re
c
ti
f
ier
f
o
r
BL
DC
m
o
to
r
Driv
e
A
p
p
li
c
a
ti
o
n
"
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Po
we
r E
lec
tr
o
n
ics
a
n
d
Dr
ive
S
y
ste
ms
,
p
p
.
7
-
1
6
,
2
0
1
6
.
[5
]
H.Be
rrir
i,
“
Eas
y
a
n
d
F
a
st
S
e
n
s
o
r
F
a
u
lt
De
tec
ti
o
n
a
n
d
Is
o
latio
n
A
lg
o
rit
h
m
f
o
r
El
e
c
tri
c
a
l
Driv
e
s”
,
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
p
o
we
r ele
c
tro
n
ics
,
v
o
l.
2
7
,
n
o
.
2
,
F
e
b
ru
a
ry
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.