I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
wer
E
lect
ro
nics
a
nd
Driv
e
S
y
s
t
em
(
I
J
P
E
DS)
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
,
p
p
.
2
8
3
1
~
2
8
4
0
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
16
.
i
4
.
p
p
2
8
3
1
-
2
8
4
0
2831
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
Lithium
-
i
o
n
ba
tt
e
ry
charg
e
-
discha
r
g
e cycle f
o
recas
ti
ng
using
LST
M
neura
l ne
t
wo
rks
Vim
a
la
Cha
nn
a
pa
t
a
na
Srika
nta
pp
a
,
Ses
ha
cha
la
m
Dev
a
r
a
k
o
nd
a
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
B
M
S
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
5
,
2
0
2
4
R
ev
is
ed
Dec
2
5
,
2
0
2
4
Acc
ep
ted
Sep
2
,
2
0
2
5
An
imp
o
rtan
t
c
o
m
p
o
n
e
n
t
fo
r
t
h
e
d
e
p
e
n
d
a
b
le
a
n
d
sa
fe
u
ti
li
z
a
ti
o
n
o
f
li
th
iu
m
-
io
n
b
a
tt
e
ries
is
t
h
e
a
b
il
it
y
to
a
c
c
u
ra
tely
a
n
d
e
fficie
n
t
ly
p
re
d
ict
th
e
ir
re
m
a
in
in
g
u
se
fu
l
li
fe
(R
UL).
In
th
is
re
se
a
rc
h
,
a
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
r
k
(L
S
TM
RNN
)
m
o
d
e
l
is
train
e
d
t
o
lea
rn
fro
m
se
q
u
e
n
ti
a
l
d
a
ta
o
n
d
isc
h
a
rg
e
c
a
p
a
c
it
ies
a
c
ro
ss
d
iffere
n
t
c
y
c
les
a
n
d
v
o
lt
a
g
e
s.
Th
e
m
o
d
e
l
is
a
lso
d
e
sig
n
e
d
to
f
u
n
c
ti
o
n
a
s
a
c
y
c
le
li
fe
p
re
d
icto
r
f
o
r
b
a
tt
e
ry
c
e
ll
s
th
a
t
h
a
v
e
b
e
e
n
c
y
c
led
u
n
d
e
r
v
a
r
y
in
g
c
o
n
d
it
io
n
s.
By
l
e
v
e
ra
g
in
g
e
x
p
e
rime
n
tal
d
a
ta
fr
o
m
t
h
e
NA
S
A
b
a
tt
e
r
y
d
a
tas
e
t,
t
h
e
m
o
d
e
l
a
c
h
iev
e
s
a
p
ro
m
isin
g
lev
e
l
o
f
p
re
d
ictio
n
a
c
c
u
ra
c
y
o
n
tes
t
se
ts
c
o
n
s
isti
n
g
o
f
a
p
p
ro
x
ima
tely
2
0
0
sa
m
p
les
.
K
ey
w
o
r
d
s
:
C
h
ar
g
e
cy
cle
Dis
ch
ar
g
e
cy
cle
Li
-
io
n
L
STM
R
NN
NASA
d
ataset
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Vim
ala
C
h
an
n
ap
atan
a
Srik
an
t
ap
p
a
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
B
MS
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
B
an
g
alo
r
e,
I
n
d
ia
E
m
ail: v
im
alasr
ik
an
tap
p
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
L
ith
iu
m
-
io
n
b
atter
ies
ar
e
wid
ely
em
p
lo
y
e
d
in
elec
tr
o
n
ic
d
ev
ices
d
u
e
to
th
eir
h
ig
h
en
e
r
g
y
d
en
s
ity
,
af
f
o
r
d
a
b
ilit
y
,
an
d
lo
n
g
ev
ity
.
Me
asu
r
in
g
th
e
r
em
ain
in
g
u
s
e
f
u
l
life
(
R
UL
)
o
f
th
ese
b
atter
ies
is
e
s
s
en
tial
to
u
n
d
er
s
tan
d
th
eir
life
s
p
an
,
an
d
th
is
is
ac
c
o
m
p
lis
h
ed
b
y
a
b
atter
y
m
an
a
g
em
en
t
s
y
s
tem
(
B
MS)
.
T
h
e
B
MS
p
r
o
v
id
es
a
f
u
t
u
r
e
f
o
r
ec
ast
o
f
t
h
e
b
atter
y
'
s
life
.
Ho
wev
er
,
th
is
task
is
ch
allen
g
in
g
b
ec
a
u
s
e
b
atter
y
m
ath
em
atica
l
m
o
d
els
ar
e
n
o
t
s
tan
d
a
r
d
ized
.
E
ac
h
m
a
n
u
f
ac
tu
r
er
d
ev
elo
p
s
th
eir
o
wn
m
o
d
el
b
ased
o
n
v
ar
y
in
g
p
h
y
s
ical
p
r
o
p
er
ties
.
A
s
u
b
s
tan
tial
n
u
m
b
e
r
o
f
e
x
e
m
p
lar
y
r
esear
ch
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
to
p
r
ed
ict
t
h
e
R
UL
o
f
b
atter
ies.
T
h
is
s
tu
d
y
f
o
cu
s
es
o
n
f
o
r
ec
asti
n
g
th
e
b
atter
y
c
h
ar
g
e
-
d
is
ch
ar
g
e
cy
cle,
wh
ich
m
ay
co
n
tr
ib
u
te
to
m
o
r
e
ac
cu
r
ate
R
UL
p
r
ed
ictio
n
s
.
T
h
e
o
b
jectiv
e
o
f
m
o
d
el
-
b
ased
ap
p
r
o
ac
h
es
is
to
d
ev
el
o
p
m
ath
em
atica
l
o
r
s
em
i
-
em
p
ir
ical
m
o
d
els
th
at
el
u
cid
at
e
th
e
r
elatio
n
s
h
ip
s
am
o
n
g
i
n
ter
n
al
p
r
o
ce
s
s
es,
o
p
er
atin
g
c
o
n
d
itio
n
s
,
an
d
b
atter
y
ca
p
ac
ity
d
eg
r
a
d
atio
n
.
Pre
v
io
u
s
s
tu
d
ies
d
is
cu
s
s
in
g
b
atter
y
life
an
d
n
eu
r
al
n
etwo
r
k
s
ar
e
r
ev
iewe
d
f
u
r
th
er
.
T
h
e
w
o
r
k
s
in
[
1
]
-
[
4
]
ex
p
lo
r
e
b
atter
y
m
o
d
els,
e
x
am
in
in
g
th
e
d
ec
r
ea
s
e
in
elec
tr
o
ly
te
v
o
lu
m
e
p
er
ce
n
tag
e
a
n
d
th
e
d
ep
letio
n
o
f
cy
clab
le
lith
iu
m
.
T
h
e
p
ar
ticle
f
ilter
[
5
]
is
a
f
u
n
d
am
en
tal
m
eth
o
d
co
m
m
o
n
ly
em
p
lo
y
ed
a
n
d
in
teg
r
ated
with
v
ar
io
u
s
th
eo
r
ies
an
d
s
tr
ateg
ies
f
o
r
en
h
an
ce
m
en
t.
E
x
a
m
p
les
in
clu
d
e
th
e
Dem
p
s
ter
-
Sh
af
er
T
h
eo
r
y
[
6
]
an
d
th
e
Ak
aik
e
in
f
o
r
m
atio
n
cr
iter
io
n
[
7
]
.
Ho
wev
er
,
m
o
d
el
-
b
ased
s
o
lu
tio
n
s
co
n
s
is
ten
tly
f
ac
e
ch
allen
g
es
d
u
e
to
th
e
lack
o
f
r
eliab
le
a
g
in
g
m
o
d
els
an
d
th
e
is
s
u
e
o
f
p
ar
ticle
d
eg
e
n
er
ac
y
.
Data
-
d
r
iv
en
ap
p
r
o
ac
h
es,
u
n
lik
e
m
o
d
el
-
b
ased
m
eth
o
d
s
,
d
o
n
o
t
r
eq
u
ir
e
a
m
ath
em
atica
l
o
r
s
em
i
-
em
p
ir
ical
m
o
d
el.
I
n
s
tead
,
th
e
y
r
ely
o
n
ex
p
e
r
im
en
tal
d
ata
f
r
o
m
b
atter
y
cy
clin
g
.
T
o
d
ev
elo
p
ac
cu
r
ate
life
p
r
ed
ictio
n
s
,
it is
ess
en
tial to
ex
tr
ac
t r
elev
an
t f
ea
tu
r
es f
r
o
m
t
h
e
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2831
-
2
8
4
0
2832
Sev
er
s
o
n
an
d
co
lleag
u
es
[
8
]
ex
am
in
e
a
n
o
v
el
ch
ar
ac
ter
is
tic
th
at
s
h
o
ws
a
s
tr
o
n
g
co
r
r
ela
tio
n
with
cy
cle
life
,
b
ased
o
n
v
ar
iatio
n
s
in
d
is
ch
ar
g
e
ca
p
ac
ities
a
s
f
u
n
ctio
n
s
o
f
cy
cles
a
n
d
v
o
ltag
es.
Alo
n
g
s
id
e
co
n
v
en
tio
n
al
lin
ea
r
r
eg
r
ess
io
n
m
eth
o
d
s
,
th
is
ap
p
r
o
ac
h
y
ield
s
p
r
o
m
is
in
g
r
esu
lts
f
o
r
p
r
e
d
ictin
g
cy
cle
life
b
e
f
o
r
e
n
o
ticea
b
le
ca
p
ac
ity
d
eg
r
ad
ati
o
n
—
u
s
in
g
o
n
ly
d
ata
f
r
o
m
th
e
f
ir
s
t
1
0
0
cy
cles.
T
h
e
tr
ait
d
is
cu
s
s
ed
in
[
8
]
o
n
ly
co
n
s
id
er
s
th
e
ch
an
g
e
b
etwe
en
cy
cles
1
0
0
an
d
1
0
.
W
h
en
ad
d
itio
n
al
cy
cles
(
e.
g
.
,
cy
cle
2
0
,
cy
cle
3
0
,
etc.
)
ar
e
in
clu
d
ed
,
o
n
e
m
ig
h
t
wo
n
d
er
wh
eth
er
th
e
m
o
d
el'
s
p
r
ed
ict
iv
e
ac
cu
r
ac
y
im
p
r
o
v
es.
Dis
ch
ar
g
e
ca
p
ac
ities
at
d
if
f
er
en
t
v
o
ltag
es
ca
n
b
e
r
e
p
r
esen
ted
ac
r
o
s
s
cy
cles,
wh
e
r
e
ea
ch
tim
e
s
tep
co
r
r
esp
o
n
d
s
t
o
a
c
y
cle,
a
n
d
t
h
e
d
is
ch
ar
g
e
ca
p
ac
ities
d
u
r
in
g
t
h
at
cy
cle
r
ep
r
esen
t th
e
tim
e
s
tep
.
I
t is p
o
s
s
ib
le
to
o
r
g
an
ize
d
is
ch
ar
g
e
ca
p
ac
ities
o
f
d
if
f
er
en
t
v
o
ltag
es
in
a
s
p
ec
if
ic
s
eq
u
en
ce
.
T
h
e
r
e
f
o
r
e
,
i
t
i
s
c
r
u
c
i
a
l
t
o
u
s
e
a
d
a
t
as
e
t
o
f
b
a
t
t
e
r
y
d
i
s
c
h
a
r
g
e
c
a
p
a
c
it
i
es
(
a
s
a
f
u
n
c
t
i
o
n
o
f
v
o
l
t
a
g
e
a
n
d
cy
c
l
e
)
t
o
d
e
t
e
r
m
i
n
e
h
o
w
l
o
n
g
e
a
c
h
c
a
p
a
c
i
t
y
v
a
l
u
e
w
i
ll
l
as
t
a
c
r
o
s
s
c
y
cl
e
s
.
Usi
n
g
th
e
r
ig
h
t
m
o
d
el
to
lear
n
f
r
o
m
s
eq
u
en
tial
d
ata
o
n
ca
p
ac
ity
lo
s
s
is
v
ital.
Giv
e
n
th
e
p
r
esen
ce
o
f
in
ter
n
al
s
tates
th
at
co
n
v
ey
in
f
o
r
m
atio
n
ab
o
u
t
ca
p
ac
ity
d
eg
r
a
d
atio
n
,
r
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
m
ay
b
e
a
s
u
itab
le
ch
o
ice.
T
h
is
to
p
ic
h
as
b
ee
n
ex
p
lo
r
ed
in
[
9
]
,
[
1
0
]
.
Ad
d
itio
n
ally
,
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
R
NNs
ar
e
ef
f
ec
tiv
e
in
ca
p
tu
r
in
g
lo
n
g
-
ter
m
d
ep
en
d
en
cie
s
,
wh
ich
ar
e
ess
en
tial
f
o
r
m
o
d
ellin
g
ca
p
ac
ity
d
eg
r
ad
atio
n
o
v
e
r
tim
e,
as th
ey
ad
d
r
ess
th
e
"g
r
ad
ien
t
v
an
is
h
i
n
g
"
p
r
o
b
lem
.
R
esear
ch
er
s
in
[
1
1
]
–
[
1
5
]
d
is
cu
s
s
th
e
ap
p
licatio
n
o
f
L
STM
R
NNs
f
o
r
p
r
ed
ictin
g
b
atter
y
R
UL
.
T
h
eir
p
er
f
o
r
m
an
ce
s
u
r
p
ass
es
th
at
o
f
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs)
an
d
s
tan
d
ar
d
R
NNs.
W
h
ile
m
o
d
el
-
b
ased
m
eth
o
d
s
o
f
f
er
in
ter
p
r
etab
ilit
y
an
d
ar
e
g
r
o
u
n
d
e
d
in
p
h
y
s
ical
p
r
i
n
cip
les,
th
ey
o
f
te
n
s
tr
u
g
g
le
with
ad
ap
tin
g
to
co
m
p
lex
a
n
d
v
ar
y
in
g
b
atter
y
a
g
i
n
g
b
e
h
av
io
r
s
.
Data
-
d
r
iv
en
ap
p
r
o
ac
h
es,
s
u
ch
as
L
STM
R
NN
s
,
ex
ce
l
at
ca
p
tu
r
in
g
n
o
n
lin
ea
r
p
atter
n
s
an
d
h
an
d
lin
g
d
iv
er
s
e
co
n
d
itio
n
s
b
u
t
r
eq
u
ir
e
lar
g
e
,
h
ig
h
-
q
u
ality
d
atasets
.
T
h
is
s
tu
d
y
lev
er
ag
es
th
e
s
tr
en
g
th
s
o
f
d
a
ta
-
d
r
iv
en
m
o
d
elin
g
to
ac
h
iev
e
ac
c
u
r
ate
cy
cle
life
p
r
ed
ictio
n
s
u
s
in
g
s
eq
u
en
tial
d
is
ch
ar
g
e
d
ata.
R
ec
en
t
liter
atu
r
e
o
n
r
e
g
r
ess
io
n
an
d
b
atter
y
m
o
d
ellin
g
in
clu
d
es:
−
T
h
e
n
o
v
el
au
to
-
r
eg
r
ess
io
n
n
es
ted
s
eq
u
en
ce
(
AR
NS)
m
eth
o
d
[
1
6
]
.
−
E
x
tr
ac
tio
n
o
f
in
d
ir
ec
t
h
ea
lth
in
d
icato
r
s
(
I
HI
s
)
[
1
7
]
.
−
Activ
e
ch
ar
g
e
b
ala
n
cin
g
(
AC
B
)
[
1
8
]
.
−
R
an
d
o
m
f
o
r
est (
R
F)
r
eg
r
ess
io
n
esti
m
ato
r
[
1
9
]
.
−
C
o
m
p
lete
en
s
em
b
le
em
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
itio
n
with
ad
a
p
tiv
e
n
o
is
e
(
C
E
E
MD
AN)
[
2
0
]
–
[
2
2
]
.
−
E
f
f
ec
tiv
e
b
atter
y
SOH
p
r
ed
ictio
n
[
2
2
]
.
−
Par
ticle
f
ilter
in
g
(
PF
)
[
2
3
]
.
−
A
r
ev
iew
s
tu
d
y
[
2
4
]
ex
am
i
n
in
g
th
e
f
ea
s
ib
ilit
y
an
d
ec
o
n
o
m
ics
o
f
"Bi
g
Data
"
an
aly
tics
-
b
ased
b
atter
y
h
ea
lth
esti
m
atio
n
.
−
B
ay
esian
non
-
p
ar
am
etr
ic
Ga
u
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
[
2
5
]
,
wh
ich
p
r
esen
ts
an
ex
t
en
s
ib
le
h
ea
lth
esti
m
atio
n
m
o
d
el.
T
h
is
s
tu
d
y
aim
s
to
in
teg
r
ate
s
ev
er
al
k
ey
f
ea
tu
r
es
id
en
tif
ied
in
p
r
ev
i
o
u
s
r
esear
ch
b
y
in
p
u
ttin
g
s
eq
u
en
tial d
ata
o
f
ch
ar
g
e
an
d
d
is
ch
ar
g
e
ca
p
ac
ities
at
d
if
f
er
e
n
t v
o
ltag
es a
n
d
cy
cles in
to
an
L
STM
R
NN
m
o
d
el.
T
h
is
ap
p
r
o
ac
h
s
h
o
ws p
o
ten
tial
f
o
r
f
u
r
th
er
im
p
r
o
v
em
en
ts
b
y
:
−
E
lim
in
atin
g
th
e
n
ee
d
f
o
r
m
an
u
al
f
ea
tu
r
e
ex
tr
ac
tio
n
.
−
An
aly
s
in
g
f
u
tu
r
e
ch
ar
g
e
an
d
d
is
ch
ar
g
e
cy
cle
d
ata
f
o
r
u
p
to
2
0
0
s
am
p
les.
−
Pre
d
ictin
g
cy
cle
d
u
r
atio
n
s
with
s
atis
f
ac
to
r
y
ac
cu
r
ac
y
u
s
in
g
f
ewe
r
in
p
u
ts
.
−
R
ed
u
cin
g
ass
o
ciate
d
co
s
ts
.
2.
M
E
T
H
O
D
T
h
e
L
STM
R
NN
m
o
d
el
i
s
d
e
s
ig
n
ed
f
o
r
th
e
ap
p
r
o
p
r
iate
b
a
tter
y
d
ata
s
et.
T
h
is
s
ec
tio
n
d
etails
th
e
L
STM
R
NN
m
o
d
el
MSE
eq
u
a
tio
n
.
T
h
en
th
e
r
esu
lts
s
ec
tio
n
d
etails
th
e
ac
tu
al
im
p
lem
en
tatio
n
.
I
n
th
e
L
STM
R
NN
m
o
d
el,
th
e
n
u
m
b
er
o
f
L
STM
lay
er
s
an
d
th
e
in
p
u
t
s
eq
u
en
ce
len
g
th
(
e.
g
.
,
1
0
0
–
3
0
0
cy
cles)
d
eter
m
in
e
h
o
w
well
th
e
m
o
d
el
ca
p
tu
r
es
tem
p
o
r
al
d
ep
en
d
en
cies
in
b
atter
y
d
eg
r
a
d
atio
n
.
T
h
e
tan
h
ac
t
iv
atio
n
f
u
n
ctio
n
is
co
m
m
o
n
l
y
u
s
ed
i
n
L
STM
ce
l
ls
to
r
eg
u
late
th
e
f
lo
w
o
f
i
n
f
o
r
m
atio
n
,
wh
ile
d
r
o
p
o
u
t
r
e
g
u
lar
izatio
n
(
ty
p
ically
0
.
2
–
0
.
5
)
h
elp
s
p
r
e
v
en
t
o
v
er
f
itti
n
g
b
y
r
an
d
o
m
ly
d
ea
ctiv
atin
g
n
eu
r
o
n
s
d
u
r
in
g
tr
ain
i
n
g
.
T
o
g
eth
er
,
th
ese
co
m
p
o
n
en
ts
en
h
an
ce
th
e
m
o
d
el’
s
ab
ilit
y
to
g
en
er
alize
ac
r
o
s
s
v
ar
y
in
g
b
atter
y
co
n
d
itio
n
s
a
n
d
cy
cle
p
atter
n
s
.
2
.
1
.
L
ST
M
RNN
m
o
del
I
n
th
is
L
STM
R
NN
[
1
2
]
,
th
e
i
n
p
u
t
lay
er
is
f
ed
in
to
t
h
e
L
STM
lay
er
.
T
h
is
R
NN
L
STM
is
b
etter
in
co
n
v
er
g
en
ce
an
d
ac
cu
r
ac
y
.
I
n
t
h
i
s
,
t
h
e
M
S
E
i
s
m
i
n
i
m
i
z
e
d
,
a
n
d
t
h
e
a
l
g
o
r
i
t
h
m
a
lw
a
y
s
t
r
i
e
s
t
o
m
i
n
i
m
i
z
e
t
h
e
M
S
E
.
=
1
∑
(
̿
−
)
2
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i
Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Lit
h
iu
m
-
io
n
b
a
tter
y
ch
a
r
g
e
-
d
i
s
ch
a
r
g
e
cy
cle
fo
r
ec
a
s
tin
g
u
s
in
g
LS
TM
…
(
V
ima
la
C
h
a
n
n
a
p
a
ta
n
a
S
r
ika
n
t
a
p
p
a
)
2833
T
h
e
r
ate
o
f
lear
n
in
g
is
1
e
-
3
,
an
d
th
e
Ad
am
o
p
tim
izer
is
u
s
ed
h
er
e
f
o
r
th
e
tr
ain
i
n
g
.
T
h
e
tr
a
in
in
g
an
d
test
in
g
o
f
th
e
L
STM
R
NN
is
d
o
n
e
in
th
e
MA
T
L
AB
s
o
f
twar
e
2
0
2
3
b
.
T
h
e
s
y
s
tem
u
s
ed
h
er
e
is
AM
D
R
y
ze
n
4
0
0
0
s
er
ies,
with
1
6
GB
R
AM
an
d
NVI
DI
A
R
T
X
1
0
8
0
g
r
ap
h
ics
ca
r
d
.
T
h
e
f
lo
w
ch
a
r
t
o
f
th
e
L
STM
R
NN
im
p
lem
en
tatio
n
p
r
o
ce
d
u
r
e
is
s
tated
as sh
o
wn
in
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
Flo
w
ch
a
r
t o
f
t
h
e
L
STM
R
NN
im
p
lem
en
tatio
n
p
r
o
ce
d
u
r
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
B
y
iter
atin
g
o
v
er
tim
e
s
tep
s
an
d
c
h
an
g
i
n
g
th
e
R
NN
s
tate,
an
L
STM
n
etwo
r
k
p
r
o
ce
s
s
es
in
co
m
i
n
g
d
ata
s
eq
u
en
tially
.
All
p
r
ev
io
u
s
tim
e
s
tep
s
ar
e
s
to
r
ed
in
th
e
R
NN
s
tate.
An
L
STM
R
N
N
m
ay
p
r
ed
ict
f
u
tu
r
e
v
alu
es
o
f
a
tim
e
s
er
ies
o
r
s
eq
u
en
ce
u
s
in
g
p
r
ev
i
o
u
s
tim
e
s
tep
s
.
C
r
ea
te
a
r
eg
r
ess
io
n
L
STM
R
NN
with
s
eq
u
en
ce
o
u
tp
u
t
to
tr
ai
n
an
L
STM
R
NN
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
T
h
e
r
ep
lies
(
tar
g
ets)
ar
e
th
e
tr
ain
in
g
s
eq
u
en
ce
s
with
v
alu
es
d
is
p
lace
d
b
y
o
n
e
tim
e
s
tep
.
At
ea
ch
in
p
u
t
s
eq
u
en
ce
tim
e
s
tep
,
th
e
L
STM
R
NN
le
ar
n
s
to
p
r
ed
ict
th
e
n
ex
t tim
e
s
tep
.
T
wo
f
o
r
ec
asti
n
g
m
eth
o
d
s
ex
is
t:
o
p
en
lo
o
p
an
d
clo
s
ed
lo
o
p
.
Op
en
-
lo
o
p
f
o
r
ec
asti
n
g
p
r
e
d
ict
s
th
e
n
ex
t
tim
e
s
tep
u
s
in
g
ju
s
t
in
p
u
t
d
at
a.
Actu
al
v
alu
es
f
r
o
m
y
o
u
r
d
ata
s
o
u
r
ce
ar
e
u
s
ed
to
p
r
ed
ict
f
u
tu
r
e
tim
e
s
tep
s
.
C
lo
s
ed
-
lo
o
p
f
o
r
ec
asti
n
g
u
s
es
p
ast
f
o
r
ec
asts
to
p
r
ed
ict
f
u
tu
r
e
tim
e
s
tep
s
.
Actu
al
v
alu
es
ar
e
n
o
t
n
ee
d
ed
f
o
r
th
e
m
o
d
el
to
p
r
ed
ict.
T
h
e
W
av
ef
o
r
m
d
ataset
co
n
tain
s
2
0
0
0
s
y
n
th
etic
wav
ef
o
r
m
s
o
f
v
ar
io
u
s
len
g
th
s
ac
r
o
s
s
th
r
e
e
ch
an
n
els
u
s
ed
b
y
th
is
s
o
f
twar
e.
T
h
e
ex
am
p
le
u
s
es
clo
s
ed
-
lo
o
p
an
d
o
p
en
-
lo
o
p
f
o
r
ec
asti
n
g
to
let
an
L
STM
n
eu
r
al
n
etwo
r
k
p
r
ed
ict
f
u
t
u
r
e
wav
ef
o
r
m
v
alu
es f
r
o
m
p
ast tim
e
s
tep
v
alu
es.
3
.
1
.
L
o
a
d da
t
a
Fig
u
r
e
2
s
h
o
ws
th
e
s
tr
u
ctu
r
e
o
f
th
e
d
ata
u
s
ed
in
th
e
an
aly
s
is
.
T
h
is
d
ata
is
tak
en
f
r
o
m
th
e
NASADAT
A
s
et.
I
t
h
as
f
o
u
r
m
at
f
iles
in
it.
T
h
ey
ar
e
B
0
0
0
5
,
B
0
0
0
6
,
B
0
0
0
7
a
n
d
B
0
0
1
8
.
I
n
th
is
B
0
0
1
8
is
a
to
tally
im
p
ed
an
ce
d
ataset
wh
ich
is
n
o
t similar
to
o
th
e
r
s
.
So
,
we
n
eg
lecte
d
th
e
B
0
0
0
8
in
t
h
e
tr
ain
in
g
.
Fig
u
r
e
2
.
T
h
e
s
tr
u
ctu
r
e
o
f
th
e
DAT
A
f
o
r
th
e
b
atter
y
u
s
ed
in
th
is
an
aly
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2831
-
2
8
4
0
2834
3
.
2
.
Def
ine LS
T
M
RN
N
a
rc
h
it
ec
t
ure
An
L
STM
R
NN
lay
er
co
n
s
is
ti
n
g
o
f
1
2
8
h
i
d
d
en
u
n
its
s
h
o
u
ld
b
e
im
p
lem
e
n
ted
.
A
s
eq
u
e
n
ce
i
n
p
u
t
la
y
er
s
h
o
u
ld
b
e
u
s
ed
,
an
d
th
e
s
ize
o
f
th
e
in
p
u
t
s
h
o
u
ld
b
e
d
eter
m
in
ed
b
y
th
e
n
u
m
b
er
o
f
ch
an
n
els
p
r
esen
t
in
th
e
in
p
u
t
d
ata.
T
h
e
q
u
a
n
tity
o
f
h
id
d
en
u
n
its
is
th
e
d
eter
m
in
in
g
f
ac
to
r
i
n
th
e
am
o
u
n
t
o
f
in
f
o
r
m
atio
n
t
h
at
th
e
lay
er
is
ab
le
to
g
ath
er
.
T
h
e
u
s
e
o
f
m
o
r
e
h
id
d
en
u
n
its
h
as
th
e
p
o
te
n
tial
to
i
m
p
r
o
v
e
ac
cu
r
ac
y
,
b
u
t
it
also
r
aises
th
e
p
o
s
s
ib
ilit
y
o
f
ex
ce
s
s
iv
e
f
itti
n
g
t
o
th
e
d
ata
s
et
th
at
was
u
s
ed
f
o
r
tr
ai
n
in
g
.
I
n
co
r
p
o
r
atin
g
an
e
n
tire
ly
co
n
n
ec
ted
lay
er
with
a
n
o
u
tp
u
t size
th
at
m
atch
es th
e
n
u
m
b
er
o
f
in
p
u
t c
h
an
n
els is
n
ec
ess
ar
y
in
o
r
d
er
to
g
e
n
er
ate
s
eq
u
en
ce
s
th
at
co
n
tain
th
e
s
am
e
n
u
m
b
e
r
o
f
c
h
an
n
els
as
th
e
d
ata
th
at
is
b
ein
g
en
t
er
ed
.
Ad
d
itio
n
ally
,
a
r
e
g
r
ess
io
n
lay
er
s
h
o
u
ld
b
e
in
co
r
p
o
r
ated
.
I
n
p
r
ac
tical
ap
p
licatio
n
s
s
u
ch
as
B
MS
in
elec
tr
ic
v
eh
icles
E
Vs,
th
e
d
is
tin
ctio
n
b
etwe
en
clo
s
ed
-
lo
o
p
an
d
o
p
en
-
l
o
o
p
p
r
e
d
ictio
n
r
esu
lts
is
cr
itical.
Op
en
-
lo
o
p
p
r
e
d
i
ctio
n
in
v
o
lv
es
esti
m
atin
g
b
att
er
y
h
ea
lth
o
r
R
UL
b
ased
s
o
lely
o
n
in
itial
d
ata
in
p
u
ts
,
with
o
u
t
in
co
r
p
o
r
atin
g
f
e
ed
b
ac
k
f
r
o
m
o
n
g
o
in
g
b
atter
y
p
er
f
o
r
m
an
ce
.
T
h
is
ap
p
r
o
ac
h
is
co
m
p
u
tatio
n
ally
ef
f
icien
t
an
d
s
u
itab
le
f
o
r
ea
r
l
y
d
iag
n
o
s
tics
o
r
o
f
f
lin
e
an
al
y
s
is
b
u
t
m
ay
b
ec
o
m
e
in
ac
cu
r
ate
o
v
e
r
tim
e
as
b
atter
y
co
n
d
itio
n
s
ev
o
lv
e
d
u
e
t
o
f
ac
to
r
s
lik
e
tem
p
er
atu
r
e,
lo
a
d
,
an
d
ag
in
g
.
I
n
co
n
t
r
ast,
clo
s
ed
-
lo
o
p
p
r
ed
ictio
n
co
n
tin
u
o
u
s
ly
u
p
d
ates
its
f
o
r
ec
asts
u
s
in
g
r
ea
l
-
tim
e
d
ata,
m
a
k
in
g
it
h
ig
h
ly
a
d
ap
tiv
e
an
d
r
o
b
u
s
t.
T
h
is
d
y
n
am
ic
f
ee
d
b
a
ck
m
ec
h
an
is
m
is
es
s
en
tial
f
o
r
r
ea
l
-
tim
e
B
MS
o
p
er
atio
n
s
,
en
ab
lin
g
p
r
o
ac
tiv
e
m
ain
ten
an
ce
,
f
au
lt
d
etec
tio
n
,
an
d
o
p
tim
ize
d
ch
a
r
g
in
g
s
tr
a
teg
ies.
C
lo
s
ed
-
lo
o
p
s
y
s
tem
s
en
h
an
ce
s
af
ety
b
y
id
en
tify
in
g
an
o
m
alies
ea
r
ly
,
i
m
p
r
o
v
e
ef
f
icien
c
y
b
y
e
x
ten
d
i
n
g
b
atter
y
life
,
an
d
co
n
tr
ib
u
te
to
co
s
t
s
av
in
g
s
an
d
b
etter
u
s
er
ex
p
er
ien
ce
th
r
o
u
g
h
r
eliab
le
r
an
g
e
esti
m
atio
n
.
Fro
m
a
m
ac
h
in
e
lear
n
in
g
p
e
r
s
p
ec
tiv
e,
o
p
en
-
lo
o
p
r
esem
b
les
o
n
e
-
s
h
o
t
p
r
ed
ictio
n
,
wh
ile
clo
s
ed
-
lo
o
p
alig
n
s
with
s
eq
u
en
ce
-
to
-
s
eq
u
en
ce
lear
n
i
n
g
with
f
ee
d
b
ac
k
,
o
f
ten
im
p
lem
en
ted
u
s
in
g
r
ec
u
r
s
iv
e
f
o
r
ec
asti
n
g
o
r
o
n
lin
e
r
et
r
ain
in
g
i
n
m
o
d
els
lik
e
L
STM
.
C
ases
:
i)
C
ase
1
:
Data
s
et:
B
0
0
0
5
;
ii)
C
ase
2
:
Data
s
et:
B
0
0
0
6
;
an
d
C
ase
3
:
Data
s
et:
B
0
0
0
7
.
C
ase
1
d
ea
ls
with
th
e
B
0
0
0
5
d
ataset,
ca
s
e
2
d
ea
ls
with
th
e
B
0
0
0
6
d
ataset
,
an
d
ca
s
e
3
d
ea
l
s
with
th
e
B
0
0
0
7
d
ataset.
Fig
u
r
e
3
s
h
o
ws
th
e
co
n
v
er
g
en
ce
g
r
ap
h
f
o
r
ca
s
e
1
,
wh
er
e
th
e
iter
atio
n
is
4
0
0
.
T
h
e
ep
o
c
h
s
to
d
is
p
lay
ar
e
2
0
0
.
T
h
e
iter
atio
n
p
er
ep
o
ch
is
2
.
T
h
e
lear
n
in
g
r
ate
is
s
et
to
0
.
0
0
1
.
Fig
u
r
e
4
co
n
v
er
g
en
ce
g
r
ap
h
f
o
r
ca
s
e
2
,
wh
er
e
th
e
iter
atio
n
is
4
0
0
.
T
h
e
ep
o
ch
s
to
d
is
p
lay
ar
e
2
0
0
.
T
h
e
iter
atio
n
p
er
ep
o
c
h
is
2
.
T
h
e
lear
n
in
g
r
ate
is
s
et
to
0
.
0
0
1
.
Fig
u
r
e
5
:
co
n
v
e
r
g
en
ce
g
r
ap
h
f
o
r
ca
s
e
3
,
wh
e
r
e
th
e
iter
atio
n
is
4
0
0
.
T
h
e
e
p
o
ch
s
to
d
is
p
lay
ar
e
2
0
0
.
T
h
e
iter
atio
n
p
e
r
ep
o
ch
is
2
.
T
h
e
lear
n
in
g
r
ate
is
s
et
to
0
.
0
0
1
.
Fig
u
r
e
3
.
C
o
n
v
er
g
e
n
ce
g
r
a
p
h
f
o
r
ca
s
e
1
A
f
r
eq
u
en
c
y
v
s
.
R
MSE
p
lo
t
i
s
ty
p
ically
u
s
ed
to
ev
alu
ate
t
h
e
d
is
tr
ib
u
tio
n
o
f
p
r
e
d
ictio
n
e
r
r
o
r
s
(
r
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
)
ac
r
o
s
s
d
if
f
er
en
t te
s
t sam
p
les o
r
m
o
d
el
r
u
n
s
.
Her
e'
s
wh
at
it m
ea
n
s
:
−
X
-
ax
is
(
R
MSE
)
:
R
ep
r
esen
ts
th
e
r
a
n
g
e
o
f
R
MSE
v
alu
es
o
b
tain
e
d
f
r
o
m
p
r
ed
ictio
n
s
—
lo
wer
v
alu
es
in
d
icate
b
etter
ac
cu
r
ac
y
.
−
Y
-
ax
is
(
Fre
q
u
en
cy
)
: Sh
o
ws h
o
w
o
f
ten
ea
ch
R
MSE
v
alu
e
(
o
r
r
an
g
e)
o
cc
u
r
s
ac
r
o
s
s
th
e
d
atas
et
o
r
m
u
ltip
le
ex
p
er
im
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i
Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Lit
h
iu
m
-
io
n
b
a
tter
y
ch
a
r
g
e
-
d
i
s
ch
a
r
g
e
cy
cle
fo
r
ec
a
s
tin
g
u
s
in
g
LS
TM
…
(
V
ima
la
C
h
a
n
n
a
p
a
ta
n
a
S
r
ika
n
t
a
p
p
a
)
2835
Fig
u
r
e
6
s
h
o
ws
th
e
f
r
eq
u
e
n
c
y
v
s
R
MSE
v
alu
e
with
b
in
ar
y
b
in
s
f
o
r
ca
s
e
1
.
Her
e
it
s
h
o
ws
th
at
th
e
R
MSE
b
etwe
en
0
to
1
is
m
o
r
e
c
o
m
p
ar
ed
to
o
th
er
s
.
T
h
is
s
h
o
ws
th
e
m
o
d
el
tr
ain
ed
is
clo
s
e
to
th
e
o
r
ig
in
al.
Fig
u
r
e
7
s
h
o
ws
th
e
f
r
eq
u
en
c
y
v
s
R
MSE
v
alu
e
with
b
in
ar
y
b
in
s
f
o
r
c
ase
2
.
Her
e
,
it
s
h
o
ws
th
at
th
e
R
MSE
b
etwe
en
0
to
1
is
h
ig
h
er
co
m
p
ar
e
d
to
o
th
e
r
s
.
T
h
is
s
h
o
ws
th
e
m
o
d
el
tr
ai
n
ed
is
clo
s
e
to
th
e
o
r
ig
in
al.
Fig
u
r
e
8
s
h
o
ws
th
e
Fre
q
u
en
cy
v
s
R
MSE
v
alu
e
wi
th
b
in
ar
y
b
in
s
f
o
r
ca
s
e
3
.
Her
e
,
it
also
s
h
o
ws
th
at
th
e
R
MSE
b
etwe
en
0
to
1
is
h
ig
h
er
c
o
m
p
ar
e
d
to
o
th
er
s
.
T
h
is
s
h
o
ws th
e
m
o
d
el
tr
ain
ed
is
c
lo
s
e
to
th
e
o
r
ig
i
n
al.
Fig
u
r
e
4
.
C
o
n
v
er
g
e
n
ce
g
r
a
p
h
f
o
r
ca
s
e
2
Fig
u
r
e
5
.
C
o
n
v
er
g
e
n
ce
g
r
a
p
h
f
o
r
ca
s
e
3
T
ab
le
1
.
R
MSE
f
o
r
all
th
e
ca
s
es
C
a
ses
R
M
S
E
C
a
se
1
0
.
2
3
3
5
C
a
se
2
0
.
2
3
7
6
C
a
se
3
0
.
2
2
5
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2831
-
2
8
4
0
2836
Fig
u
r
e
6
.
Fre
q
u
en
cy
v
s
R
MSE
v
alu
e
with
b
in
a
r
y
b
i
n
s
f
o
r
ca
s
e
1
Fig
u
r
e
7
.
Fre
q
u
en
cy
v
s
R
MSE
v
alu
e
with
b
in
a
r
y
b
i
n
s
f
o
r
ca
s
e
2
Fig
u
r
e
8
.
Fre
q
u
en
cy
v
s
R
MSE
v
alu
e
with
b
in
a
r
y
b
i
n
s
f
o
r
ca
s
e
3
T
h
e
c
a
s
e
-
w
is
e
R
M
S
E
is
s
h
o
w
n
i
n
T
a
b
l
e
1
.
F
i
g
u
r
e
s
9
,
1
0
,
a
n
d
1
1
s
h
o
w
t
h
e
s
i
x
d
a
t
a
u
s
e
d
f
o
r
t
r
a
i
n
i
n
g
:
V
m
e
a
s
u
r
e
d
,
I
m
e
a
s
u
r
e
d
,
T
e
m
p
e
r
a
t
u
r
e
m
e
as
u
r
e
d
,
c
h
a
r
g
e
c
u
r
r
e
n
t,
c
h
a
n
g
e
v
o
l
t
a
g
e
,
a
n
d
ti
m
e
t
a
k
en
f
o
r
c
a
s
e
1
,
ca
s
e
2
,
a
n
d
c
a
s
e
3
,
r
e
s
p
e
c
t
i
v
el
y
.
F
i
g
u
r
e
1
2
s
h
o
w
s
t
h
e
o
p
e
n
-
l
o
o
p
p
r
e
d
i
c
t
i
o
n
/
f
o
r
e
c
as
t
i
n
g
f
o
r
c
a
s
e
1
.
Fi
g
u
r
e
1
3
s
h
o
w
s
t
h
e
o
p
e
n
-
l
o
o
p
p
r
e
d
i
c
t
i
o
n
/
f
o
r
e
c
a
s
tin
g
f
o
r
c
a
s
e
2
.
F
i
g
u
r
e
1
4
s
h
o
ws
t
h
e
o
p
e
n
-
l
o
o
p
p
r
e
d
i
c
t
i
o
n
/
f
o
r
e
ca
s
t
i
n
g
f
o
r
c
as
e
3
.
Fig
u
r
e
9
.
C
ase
1
: th
e
s
ix
d
ata
u
s
ed
f
o
r
tr
ai
n
in
g
V
m
ea
s
u
r
ed
,
I
m
ea
s
u
r
ed
,
tem
p
er
atu
r
e
m
ea
s
u
r
ed
,
ch
ar
g
e
cu
r
r
en
t,
c
h
an
g
e
v
o
ltag
e,
an
d
ti
m
e
tak
en
Fig
u
r
e
1
0
.
C
ase
2
: th
e
s
ix
d
ata
u
s
ed
f
o
r
tr
ain
in
g
V
m
ea
s
u
r
ed
,
I
m
ea
s
u
r
ed
,
tem
p
er
atu
r
e
m
ea
s
u
r
ed
,
ch
ar
g
e
cu
r
r
en
t,
c
h
an
g
e
v
o
ltag
e,
an
d
ti
m
e
tak
en
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i
Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Lit
h
iu
m
-
io
n
b
a
tter
y
ch
a
r
g
e
-
d
i
s
ch
a
r
g
e
cy
cle
fo
r
ec
a
s
tin
g
u
s
in
g
LS
TM
…
(
V
ima
la
C
h
a
n
n
a
p
a
ta
n
a
S
r
ika
n
t
a
p
p
a
)
2837
Fig
u
r
e
1
1
.
C
ase
3
: th
e
s
ix
d
ata
u
s
ed
f
o
r
tr
ain
in
g
V
m
ea
s
u
r
ed
,
I
m
ea
s
u
r
ed
,
tem
p
er
atu
r
e
m
ea
s
u
r
ed
,
c
h
ar
g
e
cu
r
r
en
t,
c
h
an
g
e
v
o
ltag
e,
an
d
ti
m
e
tak
en
Fig
u
r
e
1
2
.
Op
en
-
lo
o
p
p
r
ed
icti
o
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
1
Fig
u
r
e
1
3
.
Op
en
-
lo
o
p
p
r
ed
icti
o
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
2
Fig
u
r
e
1
4
.
Op
en
-
lo
o
p
p
r
ed
icti
o
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2831
-
2
8
4
0
2838
T
h
is
s
h
o
ws
th
at
th
e
o
p
en
-
lo
o
p
p
r
e
d
ictio
n
is
clo
s
e
en
o
u
g
h
t
o
th
e
o
r
ig
i
n
al
d
ata.
T
h
e
b
l
u
e
l
in
e
s
h
o
ws
th
e
o
r
i
g
in
al
d
ata
.
T
h
e
d
o
tted
o
r
an
g
e
lin
e
s
h
o
ws
th
e
p
r
ed
ict
ed
d
ata.
T
h
e
o
r
a
n
g
e
lin
e
f
alls
o
n
th
e
b
l
u
e.
W
h
ic
h
m
ea
n
s
th
e
o
p
e
n
-
lo
o
p
f
o
r
ec
ast is
ac
cu
r
ate.
Fig
u
r
e
1
5
s
h
o
ws
th
e
clo
s
ed
-
lo
o
p
p
r
ed
ictio
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
1
.
Fig
u
r
e
1
6
s
h
o
ws
th
e
clo
s
ed
-
lo
o
p
p
r
ed
ictio
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
2
.
Fig
u
r
e
1
7
s
h
o
ws
th
e
o
p
en
-
lo
o
p
p
r
ed
ictio
n
/f
o
r
ec
asti
n
g
f
o
r
ca
s
e
3
.
T
h
is
s
h
o
ws
th
at
th
e
clo
s
ed
-
lo
o
p
p
r
ed
ictio
n
f
o
r
2
0
0
s
am
p
les
s
h
o
ws
th
e
f
u
tu
r
e
o
f
th
e
ce
ll
b
eh
a
v
io
r
f
o
r
th
e
n
e
x
t
2
0
0
s
am
p
le
tim
es
.
T
h
e
b
lu
e
lin
e
s
o
lid
o
n
e
s
h
o
ws
th
e
ac
tu
al
v
alu
es
,
an
d
th
e
d
o
tted
o
r
an
g
e
lin
e
s
h
o
ws
th
e
f
o
r
ec
asted
o
n
es
.
I
n
th
e
ar
ticle
[
2
6
]
,
th
e
a
u
th
o
r
s
r
ep
o
r
t
th
e
f
o
llo
win
g
p
er
f
o
r
m
a
n
ce
m
etr
ics:
T
h
e
m
u
lti
-
ch
a
n
n
el
L
STM
m
o
d
el
ac
h
iev
es
a
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
r
a
n
g
in
g
f
r
o
m
0
.
4
7
%
to
1
.
8
8
%.
I
n
o
u
r
ca
s
e
,
we
g
o
t
0
.
2
%
ap
p
r
o
x
.
Fig
u
r
e
1
5
.
C
ase
1
: c
lo
s
ed
lo
o
p
f
o
r
ec
ast f
o
r
2
0
0
d
ata
Fig
u
r
e
1
6
.
C
ase
2
: c
lo
s
ed
lo
o
p
f
o
r
ec
ast f
o
r
2
0
0
d
ata
Fig
u
r
e
1
7
.
C
ase
3
: c
lo
s
ed
lo
o
p
f
o
r
ec
ast f
o
r
2
0
0
d
ata
4.
CO
NCLU
SI
O
N
T
h
e
p
u
r
p
o
s
e
o
f
th
is
wo
r
k
is
t
o
co
n
s
tr
u
ct
an
L
STM
R
NN
m
o
d
el
f
o
r
th
e
ea
r
ly
p
r
e
d
ictio
n
o
f
th
e
cy
cle
life
tim
e
o
f
b
atter
y
ce
lls
.
T
h
e
in
p
u
t
d
ata
co
n
s
is
ts
o
f
cy
cle
s
eq
u
en
ce
s
o
f
ca
p
ac
ities
with
in
ch
ar
g
e
an
d
d
is
ch
ar
g
e
win
d
o
ws.
T
h
is
f
ea
tu
r
e
is
clo
s
ely
ass
o
ciate
d
with
cy
cle
life
tim
e.
W
ith
in
th
e
f
ir
s
t
3
0
0
s
am
p
les
o
f
d
ata,
o
u
r
m
o
d
el
ac
h
iev
es
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
v
alu
es
th
at
ar
e
s
atis
f
ac
to
r
y
o
n
t
h
e
p
r
im
ar
y
test
s
et.
Ad
d
itio
n
ally
,
t
h
e
m
o
d
el
d
e
m
o
n
s
tr
ates
ac
ce
p
tab
le
p
r
ed
ic
tio
n
p
e
r
f
o
r
m
an
ce
o
n
th
e
s
ec
o
n
d
ar
y
test
s
et
b
y
u
tili
zin
g
f
ewe
r
cy
cles
o
f
d
ata,
m
ad
e
p
o
s
s
ib
le
th
r
o
u
g
h
t
h
e
ap
p
licatio
n
o
f
d
ata
au
g
m
e
n
tatio
n
d
u
r
in
g
tr
ain
in
g
.
I
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i
Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Lit
h
iu
m
-
io
n
b
a
tter
y
ch
a
r
g
e
-
d
i
s
ch
a
r
g
e
cy
cle
fo
r
ec
a
s
tin
g
u
s
in
g
LS
TM
…
(
V
ima
la
C
h
a
n
n
a
p
a
ta
n
a
S
r
ika
n
t
a
p
p
a
)
2839
s
u
m
m
ar
y
,
t
h
is
wo
r
k
aim
s
to
e
x
p
lo
r
e
a
n
L
STM
R
NN
m
o
d
el
th
at
lev
er
ag
es
a
n
o
v
el
in
p
u
t
f
o
r
m
at
o
f
s
eq
u
en
tial
d
ata.
T
h
e
m
o
d
el
s
h
o
ws
p
o
te
n
tial
to
r
ed
u
ce
t
h
e
n
u
m
b
er
o
f
ea
r
ly
c
y
cles
r
eq
u
ir
e
d
f
o
r
ac
cu
r
ate
cy
cle
life
p
r
ed
ictio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
r
ec
ei
v
ed
f
o
r
th
is
r
esear
ch
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Vim
ala
C
h
an
n
ap
atan
a
Srik
an
tap
p
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ses
h
ac
h
alam
Dev
ar
ak
o
n
d
a
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
er
e
is
n
o
c
o
n
f
lict o
f
in
ter
est
.
DATA AV
AI
L
AB
I
L
I
T
Y
Pu
b
licly
av
ailab
le
d
atasets
wer
e
an
aly
ze
d
i
n
th
is
s
tu
d
y
.
T
h
e
L
i
-
io
n
B
atter
y
Ag
in
g
Data
s
ets
ca
n
b
e
f
o
u
n
d
at
th
e
NASA
Op
en
Dat
a
Po
r
tal: h
ttp
s
://d
ata.
n
asa.
g
o
v
/
d
ataset/li
-
io
n
-
b
atter
y
-
ag
i
n
g
-
d
a
tasets
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
R
i
c
h
a
r
d
,
W
.
R
a
l
f
,
H
.
G
e
r
h
a
r
d
,
P
.
To
b
i
a
s,
a
n
d
W
.
M
a
r
t
i
n
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
d
c
o
st
o
f
ma
t
e
r
i
a
l
s
f
o
r
l
i
t
h
i
u
m
-
b
a
se
d
r
e
c
h
a
r
g
e
a
b
l
e
a
u
t
o
m
o
t
i
v
e
b
a
t
t
e
r
i
e
s
,
”
N
a
t
u
re
E
n
e
r
g
y
,
v
o
l
.
3
,
n
o
.
A
p
r
i
l
,
p
p
.
2
6
7
–
2
7
8
,
2
0
1
8
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
d
x
.
d
o
i
.
o
r
g
/
1
0
.
1
0
3
8
/
s
4
1
5
6
0
-
0
1
8
-
0
1
0
7
-
2
[
2
]
R
a
ma
d
a
ss
P
.
,
H
a
r
a
n
B
a
l
a
,
G
o
m
a
d
a
m
M
.
P
a
r
t
h
a
s
a
r
a
t
h
y
,
W
h
i
t
e
R
a
l
p
h
,
a
n
d
P
o
p
o
v
N
.
B
r
a
n
k
o
,
“
D
e
v
e
l
o
p
me
n
t
o
f
f
i
r
st
p
r
i
n
c
i
p
l
e
s
c
a
p
a
c
i
t
y
f
a
d
e
m
o
d
e
l
f
o
r
Li
-
i
o
n
c
e
l
l
s,”
J
o
u
rn
a
l
o
f
T
h
e
El
e
c
t
ro
c
h
e
m
i
c
a
l
S
o
c
i
e
t
y
,
v
o
l
.
1
5
1
,
n
o
.
2
,
p
p
.
A
1
9
6
–
A
2
0
3
,
2
0
0
4
.
[
3
]
G
.
N
i
n
g
,
R
.
E.
W
h
i
t
e
,
a
n
d
B
.
N
.
P
o
p
o
v
,
“
A
g
e
n
e
r
a
l
i
z
e
d
c
y
c
l
e
l
i
f
e
m
o
d
e
l
o
f
r
e
c
h
a
r
g
e
a
b
l
e
L
i
-
i
o
n
b
a
t
t
e
r
i
e
s
,
”
E
l
e
c
t
r
o
c
h
i
m
i
c
a
Ac
t
a
,
v
o
l
.
5
1
,
n
o
.
1
0
,
p
p
.
2
0
1
2
–
2
0
2
2
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
l
e
c
t
a
c
t
a
.
2
0
0
5
.
0
6
.
0
3
3
.
[
4
]
H
.
Ek
s
t
r
ö
m
a
n
d
G
.
L
i
n
d
b
e
r
g
h
,
“
A
m
o
d
e
l
f
o
r
p
r
e
d
i
c
t
i
n
g
c
a
p
a
c
i
t
y
f
a
d
e
d
u
e
t
o
S
EI
f
o
r
mat
i
o
n
i
n
a
c
o
mm
e
r
c
i
a
l
g
r
a
p
h
i
t
e
/
L
i
F
e
P
O
4
c
e
l
l
,
”
J
o
u
r
n
a
l
o
f
T
h
e
E
l
e
c
t
r
o
c
h
e
m
i
c
a
l
S
o
c
i
e
t
y
,
v
o
l
.
1
6
2
,
n
o
.
6
,
p
p
.
A
1
0
0
3
–
A
1
0
0
7
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
4
9
/
2
.
0
6
4
1
5
0
6
j
e
s.
[
5
]
X
.
S
u
,
S
.
W
a
n
g
,
M
.
P
e
c
h
t
,
L.
Z
h
a
o
,
a
n
d
Z.
Y
e
,
“
I
n
t
e
r
a
c
t
i
n
g
mu
l
t
i
p
l
e
mo
d
e
l
p
a
r
t
i
c
l
e
f
i
l
t
e
r
f
o
r
p
r
o
g
n
o
s
t
i
c
s o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
,
”
Mi
c
r
o
e
l
e
c
t
r
o
n
i
c
s R
e
l
i
a
b
i
l
i
t
y
,
v
o
l
.
7
0
,
p
p
.
5
9
–
6
9
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mi
c
r
o
r
e
l
.
2
0
1
7
.
0
2
.
0
0
3
.
[
6
]
W
.
H
e
,
N
.
W
i
l
l
i
a
r
d
,
M
.
O
s
t
e
r
ma
n
,
a
n
d
M
.
P
e
c
h
t
,
“
P
r
o
g
n
o
st
i
c
s
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
b
a
s
e
d
o
n
d
e
mp
s
t
e
r
-
s
h
a
f
e
r
t
h
e
o
r
y
a
n
d
t
h
e
b
a
y
e
s
i
a
n
m
o
n
t
e
c
a
r
l
o
m
e
t
h
o
d
,
”
J
o
u
r
n
a
l
o
f
P
o
w
e
r
S
o
u
r
c
e
s
,
v
o
l
.
1
9
6
,
n
o
.
2
3
,
p
p
.
1
0
3
1
4
–
1
0
3
2
1
,
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
p
o
w
s
o
u
r
.
2
0
1
1
.
0
8
.
0
4
0
.
[
7
]
Y
.
X
i
n
g
,
E.
W
.
M
.
M
a
,
K
.
L
.
Ts
u
i
,
a
n
d
M
.
P
e
c
h
t
,
“
A
n
e
n
sem
b
l
e
mo
d
e
l
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
r
e
m
a
i
n
i
n
g
u
s
e
f
u
l
p
e
r
f
o
r
ma
n
c
e
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
,
”
Mi
c
r
o
e
l
e
c
t
r
o
n
i
c
s R
e
l
i
a
b
i
l
i
t
y
,
v
o
l
.
5
3
,
n
o
.
6
,
p
p
.
8
1
1
–
8
2
0
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
i
c
r
o
r
e
l
.
2
0
1
2
.
1
2
.
0
0
3
.
[
8
]
K
.
A
.
S
e
v
e
r
so
n
e
t
a
l
.
,
“
D
a
t
a
-
d
r
i
v
e
n
p
r
e
d
i
c
t
i
o
n
o
f
b
a
t
t
e
r
y
c
y
c
l
e
l
i
f
e
b
e
f
o
r
e
c
a
p
a
c
i
t
y
d
e
g
r
a
d
a
t
i
o
n
,
”
N
a
t
u
re
En
e
r
g
y
,
v
o
l
.
4
,
n
o
.
5
,
p
p
.
3
8
3
–
3
9
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
6
0
-
0
1
9
-
0
3
5
6
-
8.
[
9
]
J.
Li
u
,
A
.
S
a
x
e
n
a
,
K
.
G
o
e
b
e
l
,
B
.
S
a
h
a
,
a
n
d
W
.
W
a
n
g
,
“
A
n
a
d
a
p
t
i
v
e
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
r
e
mai
n
i
n
g
u
se
f
u
l
l
i
f
e
p
r
e
d
i
c
t
i
o
n
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s,”
A
n
n
u
a
l
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
P
ro
g
n
o
s
t
i
c
s
a
n
d
H
e
a
l
t
h
M
a
n
a
g
e
m
e
n
t
S
o
c
i
e
t
y
,
PH
M
2
0
1
0
,
2
0
1
0
,
d
o
i
:
1
0
.
3
6
0
0
1
/
p
h
mc
o
n
f
.
2
0
1
0
.
v
2
i
1
.
1
8
9
6
.
[
1
0
]
M
.
R
e
z
v
a
n
i
,
M
.
A
b
u
a
l
i
,
S
.
Le
e
,
J.
Le
e
,
a
n
d
J.
N
i
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
t
e
c
h
n
i
q
u
e
s
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
y
p
r
o
g
n
o
s
t
i
c
s
a
n
d
h
e
a
l
t
h
ma
n
a
g
e
m
e
n
t
(
P
H
M
)
,
”
S
A
E
T
e
c
h
n
i
c
a
l
P
a
p
e
rs
,
2
0
1
1
,
d
o
i
:
1
0
.
4
2
7
1
/
2
0
1
1
-
01
-
2
2
4
7
.
[
1
1
]
Y
.
Zh
a
n
g
,
R
.
X
i
o
n
g
,
H
.
H
e
,
a
n
d
M
.
G
.
P
e
c
h
t
,
“
Lo
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
r
e
ma
i
n
i
n
g
u
sef
u
l
l
i
f
e
p
r
e
d
i
c
t
i
o
n
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
7
,
n
o
.
7
,
p
p
.
5
6
9
5
–
5
7
0
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
1
8
.
2
8
0
5
1
8
9
.
[
1
2
]
J.
B
r
o
w
n
l
e
e
,
“
D
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
p
y
t
h
o
n
:
D
e
v
e
l
o
p
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
o
n
t
h
e
a
n
o
a
n
d
t
e
n
so
r
f
l
o
w
,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
a
st
e
ry
,
p
p
.
1
–
1
7
,
2
0
1
7
.
[
1
3
]
S
.
B
r
a
u
n
,
“
LST
M
b
e
n
c
h
m
a
r
k
s f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
s
,
”
Ju
n
.
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2831
-
2
8
4
0
2840
[
1
4
]
G
.
H
i
n
t
o
n
,
A
.
K
r
i
z
h
e
v
s
k
y
,
I
.
S
u
t
s
k
e
v
e
r
,
R
.
S
a
l
a
k
h
u
t
d
i
n
o
v
,
a
n
d
N
.
S
r
i
v
a
s
t
a
v
a
,
“
D
r
o
p
o
u
t
:
a
si
m
p
l
e
w
a
y
t
o
p
r
e
v
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
r
o
m o
v
e
r
f
i
t
t
i
n
g
,”
J
o
u
r
n
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
9
2
9
–
1
9
5
8
,
2
0
1
4
.
[
1
5
]
D
.
P
.
K
i
n
g
ma
a
n
d
J.
B
a
,
“
A
d
a
m
:
a
m
e
t
h
o
d
f
o
r
s
t
o
c
h
a
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
,
”
Ja
n
.
2
0
1
7
.
[
1
6
]
T.
P
h
a
m
e
t
a
l
.
,
“
A
R
N
S
:
a
d
a
t
a
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
f
o
r
S
o
H
e
st
i
ma
t
i
o
n
o
f
L
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
u
si
n
g
n
e
st
e
d
s
e
q
u
e
n
c
e
mo
d
e
l
s
w
i
t
h
c
o
n
si
d
e
r
i
n
g
r
e
l
a
x
a
t
i
o
n
e
f
f
e
c
t
,”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
1
7
0
6
7
–
1
1
7
0
8
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
1
7
4
7
8
.
[
1
7
]
D
.
Y
.
R
e
d
d
y
,
B
.
R
o
u
t
h
,
A
.
P
a
t
r
a
,
a
n
d
S
.
M
u
k
h
o
p
a
d
h
y
a
y
,
“
G
a
u
ssi
a
n
p
r
o
c
e
ss
r
e
g
r
e
ss
i
o
n
b
a
se
d
st
a
t
e
o
f
h
e
a
l
t
h
e
s
t
i
m
a
t
i
o
n
o
f
Li
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
u
si
n
g
i
n
d
i
r
e
c
t
b
a
t
t
e
r
y
h
e
a
l
t
h
i
n
d
i
c
a
t
o
r
s
,
”
i
n
2
0
2
1
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Pr
o
g
n
o
st
i
c
s
a
n
d
H
e
a
l
t
h
Ma
n
a
g
e
m
e
n
t
(
I
C
PH
M)
,
J
u
n
.
2
0
2
1
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
H
M
5
1
0
8
4
.
2
0
2
1
.
9
4
8
6
5
1
9
.
[
1
8
]
A
.
La
m
p
r
e
c
h
t
,
M
.
R
i
e
st
e
r
e
r
,
a
n
d
S
.
S
t
e
i
n
h
o
r
s
t
,
“
R
a
n
d
o
m
f
o
r
e
st
r
e
g
r
e
ss
i
o
n
o
f
c
h
a
r
g
e
b
a
l
a
n
c
i
n
g
d
a
t
a
:
a
s
t
a
t
e
o
f
h
e
a
l
t
h
e
s
t
i
m
a
t
i
o
n
met
h
o
d
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
i
e
s
,
”
i
n
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
O
m
n
i
-
l
a
y
e
r
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
(
C
O
I
N
S
)
,
A
u
g
.
2
0
2
0
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
C
O
I
N
S
4
9
0
4
2
.
2
0
2
0
.
9
1
9
1
4
2
1
.
[
1
9
]
L.
M
a
o
,
H
.
H
u
,
J.
C
h
e
n
,
J.
Zh
a
o
,
K
.
Q
u
,
a
n
d
L.
J
i
a
n
g
,
“
O
n
l
i
n
e
st
a
t
e
-
of
-
h
e
a
l
t
h
e
st
i
mat
i
o
n
m
e
t
h
o
d
f
o
r
Li
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
b
a
se
d
o
n
C
EE
M
D
A
N
f
o
r
f
e
a
t
u
r
e
a
n
a
l
y
s
i
s
a
n
d
R
B
F
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
EEE
J
o
u
r
n
a
l
o
f
Em
e
r
g
i
n
g
a
n
d
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
P
o
w
e
r
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
1
8
7
–
2
0
0
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JES
TPE.
2
0
2
1
.
3
1
0
6
7
0
8
.
[
2
0
]
K
.
A
.
S
e
v
e
r
so
n
e
t
a
l
.
,
“
D
a
t
a
-
d
r
i
v
e
n
p
r
e
d
i
c
t
i
o
n
o
f
b
a
t
t
e
r
y
c
y
c
l
e
l
i
f
e
b
e
f
o
r
e
c
a
p
a
c
i
t
y
d
e
g
r
a
d
a
t
i
o
n
,
”
N
a
t
u
re
En
e
r
g
y
,
v
o
l
.
4
,
n
o
.
5
,
p
p
.
3
8
3
–
3
9
1
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
6
0
-
0
1
9
-
0
3
5
6
-
8.
[
2
1
]
J.
Y
a
n
g
,
B
.
X
i
a
,
W
.
H
u
a
n
g
,
Y
.
F
u
,
a
n
d
C
.
M
i
,
“
O
n
l
i
n
e
s
t
a
t
e
-
of
-
h
e
a
l
t
h
e
s
t
i
mat
i
o
n
f
o
r
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
u
si
n
g
c
o
n
s
t
a
n
t
-
v
o
l
t
a
g
e
c
h
a
r
g
i
n
g
c
u
r
r
e
n
t
a
n
a
l
y
s
i
s,
”
A
p
p
l
i
e
d
E
n
e
r
g
y
,
v
o
l
.
2
1
2
,
p
p
.
1
5
8
9
–
1
6
0
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
1
8
.
0
1
.
0
1
0
.
[
2
2
]
P
.
Le
i
j
e
n
,
D
.
A
.
S
t
e
y
n
-
R
o
ss,
a
n
d
N
.
K
u
l
a
r
a
t
n
a
,
“
U
se
o
f
e
f
f
e
c
t
i
v
e
c
a
p
a
c
i
t
a
n
c
e
v
a
r
i
a
t
i
o
n
a
s
a
mea
s
u
r
e
o
f
st
a
t
e
-
of
-
h
e
a
l
t
h
i
n
a
s
e
r
i
e
s
-
c
o
n
n
e
c
t
e
d
a
u
t
o
m
o
t
i
v
e
b
a
t
t
e
r
y
p
a
c
k
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
V
e
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
7
,
n
o
.
3
,
p
p
.
1
9
6
1
–
1
9
6
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
1
7
.
2
7
3
3
0
0
2
.
[
2
3
]
G
.
D
o
n
g
,
Z.
C
h
e
n
,
J.
W
e
i
,
a
n
d
Q
.
Li
n
g
,
“
B
a
t
t
e
r
y
h
e
a
l
t
h
p
r
o
g
n
o
s
i
s
u
s
i
n
g
b
r
o
w
n
i
a
n
mo
t
i
o
n
mo
d
e
l
i
n
g
a
n
d
p
a
r
t
i
c
l
e
f
i
l
t
e
r
i
n
g
,”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
6
5
,
n
o
.
1
1
,
p
p
.
8
6
4
6
–
8
6
5
5
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
E.
2
0
1
8
.
2
8
1
3
9
6
4
.
[
2
4
]
Y
.
Li
e
t
a
l
.
,
“
D
a
t
a
-
d
r
i
v
e
n
h
e
a
l
t
h
e
st
i
m
a
t
i
o
n
a
n
d
l
i
f
e
t
i
m
e
p
r
e
d
i
c
t
i
o
n
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
:
A
r
e
v
i
e
w
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
En
e
r
g
y
Re
v
i
e
w
s
,
v
o
l
.
1
1
3
,
p
.
1
0
9
2
5
4
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.
2
0
1
9
.
1
0
9
2
5
4
.
[
2
5
]
R
.
R
.
R
i
c
h
a
r
d
s
o
n
,
M
.
A
.
O
s
b
o
r
n
e
,
a
n
d
D
.
A
.
H
o
w
e
y
,
“
B
a
t
t
e
r
y
h
e
a
l
t
h
p
r
e
d
i
c
t
i
o
n
u
n
d
e
r
g
e
n
e
r
a
l
i
z
e
d
c
o
n
d
i
t
i
o
n
s
u
si
n
g
a
G
a
u
s
si
a
n
p
r
o
c
e
ss
t
r
a
n
si
t
i
o
n
m
o
d
e
l
,
”
J
o
u
r
n
a
l
o
f
En
e
r
g
y
S
t
o
ra
g
e
,
v
o
l
.
2
3
,
p
p
.
3
2
0
–
3
2
8
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
t
.
2
0
1
9
.
0
3
.
0
2
2
.
[
2
6
]
K
.
P
a
r
k
,
Y
.
C
h
o
i
,
W
.
J
.
C
h
o
i
,
H
.
-
Y
.
R
y
u
,
a
n
d
H
.
K
i
m,
“
LST
M
-
b
a
se
d
b
a
t
t
e
r
y
r
e
m
a
i
n
i
n
g
u
sefu
l
l
i
f
e
p
r
e
d
i
c
t
i
o
n
w
i
t
h
mu
l
t
i
-
c
h
a
n
n
e
l
c
h
a
r
g
i
n
g
p
r
o
f
i
l
e
s
,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
2
0
7
8
6
–
2
0
7
9
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
6
8
9
3
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vim
a
l
a
Cha
n
n
a
p
a
ta
n
a
S
r
ik
a
n
t
a
p
p
a
h
a
s
c
o
m
p
lete
d
h
e
r
g
ra
d
u
a
ti
o
n
in
B
.
E
.
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ics
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
fro
m
K.V
.
G
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
M
a
n
g
a
lo
re
U
n
iv
e
rsit
y
.
M
BA
a
d
istan
t
e
d
u
c
a
ti
o
n
fro
m
S
ik
k
i
m
M
a
n
ip
a
l
Un
i
v
e
rsity
a
n
d
M
.
Tec
h
.
in
p
o
we
r
s
y
ste
m
s
fro
m
G
h
o
u
sia
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
,
Ra
m
a
n
a
g
ra
m
.
At
p
re
se
n
t
a
re
se
a
rc
h
s
c
h
o
lar
a
t
BM
S
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
,
I
n
d
ia
,
a
n
d
a
lso
wo
r
k
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tr
o
n
ic
s
En
g
i
n
e
e
rin
g
,
S
JB
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
l
o
re
.
M
e
m
b
e
r
o
f
M
IE
(
M
-
6
1
2
7
9
9
)
.
S
h
e
h
a
s
9
+
y
e
a
rs
o
f
in
d
u
str
y
e
x
p
e
rien
c
e
in
a
b
r
o
a
d
a
s
we
ll
a
s
in
I
n
d
ia
a
n
d
1
0
+
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
.
He
r
a
re
a
o
f
e
x
p
e
rti
se
is
in
p
o
we
r
sy
ste
m
s,
e
lec
tri
c
a
l
m
a
c
h
in
e
s,
a
n
d
b
a
tt
e
ry
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
in
EV.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
i
m
a
las
rik
a
n
tap
p
a
@g
m
a
il
.
c
o
m
.
Dr
.
S
e
sha
c
h
a
la
m
De
v
a
r
a
k
o
n
d
a
is
a
p
r
o
fe
ss
o
r
a
n
d
Vic
e
P
rin
c
i
p
a
l
a
t
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
B
M
S
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
,
I
n
d
ia.
He
h
o
ld
s
a
P
h
.
D.
d
e
g
re
e
i
n
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
-
Co
n
tr
o
l
E
n
g
i
n
e
e
rin
g
,
a
n
d
P
o
we
r
El
e
c
tro
n
ics
,
M
o
ti
lal
Ne
h
ru
Na
ti
o
n
a
l
In
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
,
Alla
h
a
b
a
d
,
U.P
Hi
s
Re
se
a
rc
h
In
tere
sts
a
re
M
o
d
e
l
o
rd
e
r
re
d
u
c
ti
o
n
,
P
o
we
r
El
e
c
tr
o
n
ics
,
N
o
n
-
Li
n
e
a
r
c
o
n
tr
o
l
e
n
g
in
e
e
rin
g
,
a
n
d
b
a
tt
e
r
y
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
in
EHV.
He
h
a
s
p
lay
e
d
a
m
a
jo
r
r
o
le
i
n
e
sta
b
li
sh
in
g
a
Ce
n
tre
o
f
E
x
c
e
ll
e
n
c
e
a
lo
n
g
wit
h
t
h
e
S
k
il
l
S
e
c
to
r
Co
u
n
c
il
o
f
I
n
d
ia
(ES
S
CI)
in
VLS
I
d
e
si
g
n
.
M
e
m
b
e
r
o
f
se
v
e
ra
l
b
o
a
rd
s
o
f
stu
d
ies
(BOS)
su
c
h
a
s Da
y
a
n
a
n
d
a
S
a
g
a
r
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Ne
w
H
o
rizo
n
C
o
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
,
Dr
AIT
Ba
n
g
a
lo
re
,
Ko
n
g
u
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
Er
o
d
e
,
A
d
h
iam
m
a
n
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
Ho
su
r
,
a
n
d
p
ro
p
o
se
d
i
n
n
o
v
a
ti
v
e
c
u
rricu
la.
He
a
lso
p
la
y
e
d
a
k
e
y
r
o
le
in
sta
rti
n
g
a
t
h
ir
d
P
G
p
ro
g
ra
m
,
M
.
Tec
h
.
i
n
VLS
I
De
sig
n
a
n
d
Emb
e
d
d
e
d
S
y
ste
m
s,
in
2
0
1
4
,
wh
ich
is su
c
c
e
ss
fu
ll
y
ru
n
n
i
n
g
i
n
t
h
e
d
e
p
a
rtme
n
t
n
o
w
.
He
is a
m
e
m
b
e
r
o
f
th
e
e
v
a
lu
a
ti
o
n
c
o
m
m
it
tee
fo
r
th
e
Na
ti
o
n
a
l
B
o
a
rd
o
f
Ac
c
re
d
it
a
ti
o
n
a
n
d
AICT
E.
He
ha
s
re
c
e
iv
e
d
fu
n
d
s
u
n
d
e
r
t
h
e
M
OD
ROBS
sc
h
e
m
e
fro
m
AICTE
&
h
a
s
c
o
n
d
u
c
ted
se
v
e
ra
l
wo
rk
sh
o
p
s
o
n
o
u
tc
o
m
e
-
b
a
se
d
e
d
u
c
a
ti
o
n
(OBE).
A
m
e
m
b
e
r
o
f
p
r
o
fe
ss
io
n
a
l
so
c
ieties
su
c
h
a
s
IEE
E
a
n
d
IS
TE
.
Ha
s
su
p
e
r
v
ise
d
fo
u
r
P
h
.
D.
sc
h
o
lars
a
n
d
se
v
e
ra
l
M
.
Tec
h
.
st
u
d
e
n
ts
a
n
d
n
o
w
g
u
i
d
in
g
t
h
re
e
re
se
a
rc
h
sc
h
o
lars
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
sc
h
a
lam
.
e
c
e
@b
m
sc
e
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.