I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
,
p
p
.
83
~
9
1
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
1
4
.i
1
.
p
p
83
-
91
83
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Im
pro
v
ing
lit
hiu
m
-
i
o
n batt
ery reli
a
bility throug
h ne
ura
l
network
rema
ini
ng
useful
li
fe
pre
diction
B
ra
him
Z
ra
ibi
,
M
o
ha
m
ed
M
a
ns
o
uri
La
b
o
r
a
t
o
r
y
LA
M
S
A
D
,
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
o
f
B
e
r
r
e
c
h
i
d
,
H
a
ssan
F
i
r
st
U
n
i
v
e
r
si
t
y
o
f
S
e
t
t
a
t
,
B
e
r
r
e
c
h
i
d
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
31
,
2
0
2
4
R
ev
is
ed
J
u
l
1
,
2
0
2
4
Acc
ep
ted
J
u
l
26
,
2
0
2
4
Th
e
re
li
a
b
le
p
e
rfo
rm
a
n
c
e
o
f
l
it
h
i
u
m
-
io
n
b
a
tt
e
ries
is
c
ru
c
ial
f
o
r
th
e
sa
fe
a
n
d
e
fficie
n
t
o
p
e
ra
ti
o
n
o
f
e
lec
tri
c
a
l
sy
ste
m
s,
p
a
rti
c
u
larly
in
e
lec
tri
c
v
e
h
icle
s.
To
m
it
ig
a
te
th
e
r
isk
o
f
b
a
tt
e
ry
fa
il
u
re
d
u
e
to
d
e
g
ra
d
a
t
io
n
,
a
c
c
u
ra
te
fo
re
c
a
stin
g
o
f
th
e
re
m
a
in
in
g
u
s
e
fu
l
li
fe
(RUL)
is
imp
e
ra
ti
v
e
.
I
n
t
h
is
stu
d
y
,
w
e
p
ro
p
o
se
e
m
p
lo
y
i
n
g
v
a
ri
o
u
s
re
c
u
rre
n
t
n
e
u
r
a
l
n
e
two
rk
(RNN
)
m
e
th
o
d
s,
i
n
c
lu
d
in
g
RNN
,
g
a
ted
re
c
u
rre
n
t
u
n
i
t
(G
RU),
a
n
d
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(L
S
TM
),
to
e
n
h
a
n
c
e
RUL
p
re
d
ictio
n
a
c
c
u
ra
c
y
fo
r
li
t
h
iu
m
-
io
n
b
a
tt
e
ries
.
O
u
r
a
p
p
ro
a
c
h
a
ims
to
p
ro
v
id
e
re
li
a
b
le,
a
c
c
u
ra
te,
a
n
d
s
imp
le
e
stim
a
tes
o
f
re
m
a
in
in
g
b
a
tt
e
ry
li
fe
,
fa
c
il
it
a
ti
n
g
e
ffe
c
ti
v
e
m
a
n
a
g
e
m
e
n
t
o
f
e
lec
tri
c
v
e
h
icle
p
o
we
r
sy
ste
m
s
a
n
d
m
in
imiz
in
g
t
h
e
risk
o
f
fa
il
u
re
.
P
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
m
e
tri
c
s
su
c
h
a
s
m
e
a
n
a
b
so
lu
te
e
rr
o
r
(M
AE)
,
R
-
sq
u
a
r
e
d
(R²
),
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
t
a
g
e
e
rro
r
(M
APE
),
a
n
d
r
o
o
t
m
e
a
n
sq
u
a
r
e
d
e
rro
r
(
RM
S
E)
a
re
u
ti
li
z
e
d
to
a
ss
e
ss
p
re
d
ictio
n
a
c
c
u
ra
c
y
.
E
x
p
e
rime
n
t
a
l
v
a
li
d
a
ti
o
n
c
o
n
d
u
c
ted
u
si
n
g
t
h
e
NA
S
A
li
th
i
u
m
-
io
n
b
a
tt
e
r
y
d
a
tas
e
t
d
e
m
o
n
stra
tes
th
e
su
p
e
ri
o
rit
y
o
f
LS
T
M
in
re
d
u
c
i
n
g
p
re
d
ictio
n
e
rro
r
a
n
d
e
n
h
a
n
c
in
g
RUL
p
re
d
ictio
n
p
e
rfo
rm
a
n
c
e
c
o
m
p
a
re
d
to
a
lt
e
rn
a
ti
v
e
a
p
p
r
o
a
c
h
e
s.
T
h
e
se
fin
d
i
n
g
s
u
n
d
e
rsc
o
re
th
e
p
o
ten
t
ial
o
f
n
e
u
ra
l
n
e
two
rk
m
e
th
o
d
o
lo
g
ies
in
a
d
v
a
n
c
in
g
b
a
t
tery
m
a
n
a
g
e
m
e
n
t
p
ra
c
ti
c
e
s
a
n
d
e
n
su
rin
g
t
h
e
lo
n
g
e
v
it
y
a
n
d
re
l
ia
b
i
li
ty
o
f
li
t
h
i
u
m
-
io
n
b
a
tt
e
ry
sy
ste
m
s.
K
ey
w
o
r
d
s
:
Gate
d
r
ec
u
r
r
e
n
t u
n
it
L
ith
iu
m
-
io
n
b
atter
ies
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
M
ac
h
in
e
lear
n
in
g
R
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
R
em
ain
in
g
u
s
ef
u
l lif
e
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
:
B
r
ah
im
Z
r
aib
i
L
ab
o
r
ato
r
y
L
AM
SAD,
Natio
n
al
Sch
o
o
l o
f
A
p
p
lied
Scien
ce
s
o
f
B
er
r
ec
h
id
,
Hass
an
First Un
iv
er
s
ity
o
f
Settat
B
er
r
ec
h
id
,
Mo
r
o
cc
o
E
m
ail: b
.
zr
aib
i@
u
h
p
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ic
v
eh
icles
p
o
wer
ed
b
y
lith
iu
m
-
io
n
b
atter
ies
h
av
e
em
er
g
ed
as
a
p
r
o
m
is
in
g
s
o
l
u
tio
n
to
co
m
b
at
th
e
escalatin
g
th
r
ea
t
o
f
air
p
o
llu
tio
n
an
d
r
ed
u
ce
C
O
2
em
is
s
i
o
n
s
s
tem
m
in
g
f
r
o
m
g
lo
b
al
tr
an
s
p
o
r
tatio
n
s
y
s
tem
s
[
1
]
.
T
h
ese
v
e
h
icles,
h
er
ald
ed
f
o
r
th
eir
e
n
v
ir
o
n
m
en
tal
b
e
n
ef
its
,
r
ely
o
n
in
tr
icate
b
atter
y
p
ac
k
s
to
o
p
er
ate
ef
f
icien
tly
.
Ho
wev
er
,
as
th
es
e
b
atter
ies
u
n
d
er
g
o
co
n
tin
u
o
u
s
u
s
e,
th
eir
p
er
f
o
r
m
an
ce
u
n
d
er
g
o
es
ch
an
g
e
s
,
m
an
if
esti
n
g
as
ca
p
ac
ity
lo
s
s
an
d
in
cr
ea
s
ed
r
esis
tan
ce
[
2
]
,
[
3
]
.
T
h
e
r
ep
e
r
cu
s
s
io
n
s
o
f
s
u
c
h
alter
atio
n
s
ex
ten
d
b
ey
o
n
d
m
e
r
e
e
f
f
icien
cy
co
n
ce
r
n
s
,
o
f
ten
c
u
lm
in
atin
g
in
s
ev
e
r
e
ca
tast
r
o
p
h
es
s
u
ch
as
co
m
b
u
s
tio
n
o
r
ex
p
l
o
s
io
n
s
with
in
en
er
g
y
s
to
r
ag
e
s
y
s
tem
s
.
T
h
ese
ca
tast
r
o
p
h
ic
ev
en
ts
ar
e
lar
g
ely
p
r
ec
ip
itated
b
y
th
e
h
ei
g
h
ten
ed
r
esis
tan
ce
with
in
d
eg
r
ad
e
d
b
atter
ies,
wh
ich
g
en
er
ates
ex
ce
s
s
iv
e
h
ea
t.
C
o
n
s
eq
u
en
tly
,
th
e
ac
cu
r
ate
esti
m
atio
n
o
f
b
atter
y
life
s
p
an
ass
u
m
es
p
ar
am
o
u
n
t
im
p
o
r
tan
ce
,
s
er
v
in
g
as
a
p
iv
o
tal
in
d
icato
r
o
f
b
atter
y
ag
in
g
an
d
d
am
ag
e
s
tatu
s
.
Su
ch
in
s
ig
h
ts
ar
e
in
d
is
p
en
s
ab
l
e
f
o
r
en
s
u
r
in
g
th
e
s
af
ety
an
d
r
e
liab
ilit
y
o
f
elec
tr
if
ied
v
e
h
icles
an
d
en
er
g
y
s
to
r
ag
e
s
y
s
tem
s
alik
e.
T
o
n
av
ig
ate
th
e
co
m
p
lex
ities
in
h
er
e
n
t
in
u
ti
lizin
g
th
ese
b
atter
ies
s
af
e
ly
an
d
ef
f
ec
tiv
el
y
,
th
e
im
p
lem
en
tatio
n
o
f
r
o
b
u
s
t
b
att
er
y
m
a
n
ag
em
en
t
s
y
s
tem
s
(
B
MS)
[
4
]
b
ec
o
m
es
im
p
er
ativ
e.
R
ec
en
t
y
ea
r
s
h
av
e
witn
ess
ed
a
s
u
r
g
e
in
r
esear
ch
en
d
ea
v
o
r
s
aim
ed
at
r
ef
in
in
g
b
atter
y
tech
n
o
l
o
g
ies,
with
a
p
ar
ticu
lar
f
o
c
u
s
o
n
em
p
o
wer
in
g
B
MS
to
p
r
o
f
icie
n
tly
esti
m
ate
b
atter
y
p
ar
am
ete
r
s
.
Mo
n
ito
r
in
g
f
ac
to
r
s
s
u
ch
as
s
t
ate
o
f
ch
ar
g
e
(
SOC
)
[
5
]
,
s
tate
o
f
h
ea
lth
(
SOH)
[
6
]
,
r
em
ain
in
g
u
s
ef
u
l
life
(
R
UL
)
,
c
h
ar
g
e
ca
p
ac
ity
,
an
d
in
ter
n
al
r
e
s
is
tan
ce
em
er
g
es
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
83
-
91
84
q
u
in
tess
en
tial
p
r
ac
tices
to
u
p
h
o
ld
th
e
ef
f
icien
t
a
n
d
s
ec
u
r
e
u
ti
lizatio
n
o
f
lith
iu
m
-
io
n
b
atter
ie
s
[
7
]
.
Am
o
n
g
th
ese,
R
UL
em
er
g
es
as
a
p
iv
o
tal
p
ar
am
eter
,
p
iv
o
tal
f
o
r
f
a
u
lt
d
iag
n
o
s
es
an
d
ea
r
ly
s
af
ety
war
n
in
g
s
th
r
o
u
g
h
o
u
t
th
e
life
cy
cle
o
f
lith
iu
m
-
io
n
b
atter
ies
in
elec
tr
if
ied
v
eh
icles.
Mo
r
e
o
v
er
,
th
e
ac
cu
r
ate
p
r
ed
ictio
n
o
f
R
UL
p
lay
s
an
in
s
tr
u
m
en
tal
r
o
le
in
q
u
an
tify
i
n
g
b
atter
y
life
an
d
f
o
r
ec
asti
n
g
th
e
r
em
ain
in
g
m
ileag
e
o
f
e
lectr
ic
v
eh
icles
[
8
]
.
L
ith
iu
m
-
io
n
b
atter
ies,
r
en
o
wn
ed
f
o
r
th
eir
h
ig
h
e
n
er
g
y
d
en
s
ity
,
p
o
wer
d
en
s
ity
,
lo
w
s
elf
-
d
is
ch
ar
g
e
r
ate,
an
d
ex
ten
d
ed
life
s
p
a
n
,
s
tan
d
o
u
t
as f
av
o
r
e
d
ch
o
ices a
cr
o
s
s
d
iv
er
s
e
ap
p
licatio
n
s
.
T
h
e
co
n
ce
p
t
o
f
R
UL
,
d
elin
ea
t
ed
as th
e
r
em
ai
n
in
g
n
u
m
b
er
o
f
cy
cles to
r
ea
ch
th
e
f
ailu
r
e
th
r
esh
o
ld
,
h
as
s
p
u
r
r
ed
th
e
d
ev
elo
p
m
en
t
o
f
f
o
u
r
d
is
tin
ct
p
r
ed
ictio
n
m
eth
o
d
s
:
d
ir
ec
t
m
ea
s
u
r
e
m
en
t,
m
o
d
el
-
b
ased
,
d
ata
-
d
r
iv
en
,
an
d
h
y
b
r
id
m
et
h
o
d
o
lo
g
ies
[
9
]
.
T
h
e
d
ir
ec
t
m
ea
s
u
r
em
e
n
t
ap
p
r
o
ac
h
u
ti
lizes
o
p
en
-
c
ir
cu
it
v
o
ltag
e
an
d
elec
tr
o
ch
em
ical
im
p
ed
a
n
ce
s
p
ec
tr
o
s
co
p
y
to
ass
ess
th
e
ca
p
ac
ity
an
d
im
p
e
d
an
ce
o
f
b
atter
y
c
ells
.
I
n
co
n
tr
ast,
th
e
m
o
d
el
-
b
ased
m
eth
o
d
lev
e
r
ag
e
s
v
ar
io
u
s
m
o
d
els,
in
clu
d
in
g
e
lectr
o
ch
em
ical,
eq
u
iv
alen
t
ci
r
cu
it,
an
d
em
p
ir
ical
m
o
d
els
s
u
ch
as
u
n
s
ce
n
ted
Kalm
an
f
ilter
(
UKF)
an
d
p
ar
ticle
f
ilter
(
PF
)
.
Data
-
d
r
iv
en
p
r
ed
i
ctio
n
m
eth
o
d
s
,
lik
e
g
au
s
s
ian
p
r
o
ce
s
s
es
(
GP)
[
1
0
]
,
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
s
(
R
NN)
,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
n
etwo
r
k
s
(
L
STM
)
[
1
1
]
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
[
1
2
]
,
g
r
ey
m
o
d
els
(
G
M)
,
r
elev
a
n
ce
v
ec
t
o
r
m
ac
h
in
e
s
(
R
VM
)
[
1
3
]
,
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
[
1
4
]
,
ar
e
g
ain
in
g
in
c
r
ea
s
in
g
atten
tio
n
d
u
e
to
th
e
ab
u
n
d
a
n
ce
o
f
d
ata
av
ailab
le
f
r
o
m
L
i
-
io
n
b
atter
ies.
T
h
ese
d
ata
-
d
r
iv
e
n
m
eth
o
d
s
d
o
n
o
t
d
ep
en
d
o
n
co
m
p
lex
ch
e
m
ical,
p
h
y
s
ical,
o
r
m
ath
em
atica
l
m
o
d
els
o
f
b
atter
y
ca
p
ac
ity
d
eg
r
a
d
atio
n
,
m
ak
in
g
th
em
h
ig
h
l
y
attr
ac
tiv
e
f
o
r
b
atter
y
h
ea
lth
p
r
ed
ictio
n
.
I
n
r
ec
e
n
t
tim
es,
th
e
p
r
o
wess
o
f
n
e
u
r
al
n
etwo
r
k
s
,
p
ar
ticu
lar
ly
R
NNs,
h
as
g
ar
n
e
r
ed
atten
tio
n
f
o
r
its
p
o
ten
tial
to
en
h
an
ce
p
r
ed
icti
o
n
ac
cu
r
ac
y
.
L
ev
er
a
g
in
g
th
ei
r
in
n
ate
ca
p
ac
ity
f
o
r
s
elf
-
lear
n
in
g
,
R
NNs
h
o
ld
p
r
o
m
is
e
in
r
e
v
o
lu
tio
n
izin
g
R
UL
p
r
ed
ictio
n
m
eth
o
d
o
lo
g
ies
[
1
5
]
,
[
1
6
]
.
Dee
p
lea
r
n
in
g
m
et
h
o
d
s
,
alr
ea
d
y
lau
d
e
d
f
o
r
th
eir
s
u
cc
ess
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
o
f
f
e
r
f
u
r
th
er
cr
e
d
i
b
ilit
y
to
th
is
ap
p
r
o
ac
h
,
p
a
r
ticu
lar
ly
in
tim
e
-
s
er
ies
p
r
ed
ictio
n
task
s
.
Pro
p
o
s
in
g
th
e
u
tili
za
tio
n
o
f
d
iv
er
s
e
R
NN
m
eth
o
d
s
in
o
u
r
s
tu
d
y
r
ep
r
esen
ts
a
co
n
ce
r
ted
ef
f
o
r
t
to
au
g
m
en
t
th
e
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
lith
iu
m
-
i
o
n
b
atter
y
R
UL
,
th
er
eb
y
ad
v
an
cin
g
th
e
f
r
o
n
tier
o
f
b
atter
y
m
an
ag
em
en
t
in
elec
tr
if
ie
d
v
e
h
icles.
T
h
e
p
r
im
ar
y
ch
allen
g
e
s
f
ac
ed
in
th
e
c
o
n
tex
t
o
f
R
UL
p
r
ed
ictio
n
in
th
is
s
tu
d
y
ar
e
m
u
ltifa
ce
ted
.
Fo
r
e
m
o
s
t a
m
o
n
g
t
h
ese
ch
allen
g
es is
th
e
im
p
er
ativ
e
t
o
en
h
a
n
ce
th
e
p
r
ed
ictio
n
ac
c
u
r
ac
y
o
f
R
UL
,
s
tr
iv
in
g
f
o
r
h
ig
h
p
r
ec
is
io
n
an
d
m
in
im
izin
g
p
r
ed
i
ctio
n
er
r
o
r
s
to
en
s
u
r
e
r
eliab
l
e
p
r
o
g
n
o
s
ticatio
n
s
.
Ad
d
itio
n
ally
,
t
h
e
s
tu
d
y
g
r
a
p
p
l
es
with
th
e
n
ee
d
to
cu
r
b
co
m
p
u
tatio
n
al
co
s
ts
an
d
r
ed
u
ce
len
g
th
y
tr
ain
in
g
tim
es
ass
o
ciate
d
with
co
m
p
lex
p
r
e
d
i
ctio
n
m
o
d
els,
aim
in
g
to
s
tr
ea
m
lin
e
p
r
o
ce
s
s
es a
n
d
im
p
r
o
v
e
ef
f
icien
cy
.
Fu
r
th
er
m
o
r
e
,
th
e
p
u
r
s
u
it
o
f
a
n
o
p
tim
al
s
o
lu
tio
n
p
r
esen
ts
ch
alle
n
g
es
o
f
its
o
wn
,
d
em
a
n
d
in
g
h
i
g
h
s
tab
ilit
y
,
r
ap
id
co
n
v
er
g
en
ce
s
p
ee
d
,
f
lex
ib
ilit
y
,
an
d
s
ea
m
l
ess
im
p
lem
en
tatio
n
to
ef
f
ec
tiv
ely
ad
d
r
ess
th
e
in
tr
icac
ies
o
f
R
UL
p
r
ed
ictio
n
in
p
r
ac
tical
ap
p
licatio
n
s
.
Ad
d
r
e
s
s
in
g
th
ese
ch
allen
g
es
is
p
ar
a
m
o
u
n
t
to
ad
v
an
cin
g
th
e
s
tate
-
of
-
th
e
-
ar
t
in
R
UL
p
r
ed
ictio
n
m
eth
o
d
o
lo
g
ies
an
d
e
n
s
u
r
in
g
th
eir
p
r
ac
tical
v
iab
ilit
y
an
d
ef
f
icac
y
.
T
h
e
k
ey
co
n
tr
ib
u
tio
n
s
o
f
th
is
p
ap
e
r
r
ev
o
lv
e
ar
o
u
n
d
th
e
d
ev
elo
p
m
en
t
o
f
a
p
r
e
d
ictiv
e
m
o
d
el
f
o
r
lith
iu
m
-
io
n
b
atter
y
R
UL
p
r
ed
ictio
n
u
s
in
g
a
s
im
p
l
e
y
et
ef
f
ec
tiv
e
te
ch
n
iq
u
e
b
ased
o
n
v
ar
io
u
s
R
NN
m
eth
o
d
s
a
p
p
lied
t
o
u
n
iv
ar
iate
tim
e
s
er
ies
d
ata.
Fu
r
th
er
m
o
r
e,
th
is
wo
r
k
o
f
f
er
s
v
alu
a
b
le
in
s
ig
h
ts
in
to
th
e
ef
f
icac
y
o
f
s
im
p
le
R
NN
m
eth
o
d
s
in
R
UL
p
r
ed
ictio
n
f
o
r
lith
iu
m
-
io
n
b
atter
ies
th
r
o
u
g
h
co
m
p
r
e
h
en
s
iv
e
co
m
p
ar
is
o
n
s
with
o
t
h
er
m
e
th
o
d
o
lo
g
ies,
in
clu
d
in
g
R
NN,
g
ated
r
ec
u
r
r
e
n
t
u
n
it
(
GR
U)
,
an
d
L
STM
tech
n
iq
u
es
em
p
lo
y
e
d
in
p
r
ev
io
u
s
s
tu
d
ies.
No
tab
ly
,
o
u
r
p
r
o
p
o
s
ed
L
STM
m
eth
o
d
d
em
o
n
s
tr
ates o
u
ts
tan
d
in
g
p
er
f
o
r
m
an
ce
,
ac
h
iev
in
g
e
x
ce
p
tio
n
al
p
r
ed
ictiv
e
ac
cu
r
ac
y
in
R
UL
esti
m
atio
n
an
d
f
ac
ilit
atin
g
t
im
ely
p
r
e
d
ictio
n
s
b
ase
d
o
n
p
r
ev
io
u
s
ly
esti
m
ated
in
f
o
r
m
atio
n
.
T
h
ese
ad
v
an
ce
m
e
n
ts
h
o
ld
p
r
o
m
is
e
f
o
r
en
h
an
cin
g
b
atter
y
life
tim
e
co
n
tr
o
l
s
tr
ateg
ies
an
d
s
af
ety
m
o
n
ito
r
in
g
f
u
n
ctio
n
s
,
th
er
eb
y
r
ed
u
cin
g
th
e
r
is
k
o
f
ca
tast
r
o
p
h
ic
ev
en
ts
.
T
h
e
s
u
b
s
eq
u
en
t
s
ec
tio
n
s
o
f
th
i
s
p
ap
er
ar
e
s
tr
u
ctu
r
ed
as
f
o
llo
ws
.
Sectio
n
2
o
u
tlin
es
t
h
e
f
r
a
m
ewo
r
k
o
f
o
u
r
m
eth
o
d
an
d
elu
cid
ates
th
e
p
r
o
ce
s
s
o
f
p
r
ed
ictin
g
th
e
R
UL
an
d
in
tr
o
d
u
ce
s
th
e
to
o
ls
an
d
m
eth
o
d
o
lo
g
y
em
p
lo
y
ed
f
o
r
p
r
ed
ictin
g
th
e
R
UL
o
f
lith
iu
m
-
io
n
b
atter
ies
u
s
in
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
.
I
n
s
ec
tio
n
3
,
we
p
r
esen
t
th
e
R
UL
p
r
ed
ictio
n
r
esu
lts
an
d
co
m
p
a
r
e
th
em
with
e
x
is
tin
g
p
r
ed
ictio
n
m
eth
o
d
s
.
L
astl
y
,
t
h
e
p
ap
er
co
n
clu
d
es
with
a
s
u
m
m
ar
y
o
f
f
in
d
in
g
s
.
2.
M
E
T
H
O
D
2
.
1
.
T
he
re
curr
ent
ne
ura
l net
wo
rk
m
e
t
ho
ds
Pre
d
ictin
g
th
e
r
em
ain
in
g
life
o
f
lith
iu
m
-
io
n
b
atter
ies
r
ep
r
esen
ts
a
m
u
ltifa
ce
ted
an
d
cr
u
cia
l
en
d
ea
v
o
r
,
p
ar
ticu
lar
ly
in
d
o
m
ain
s
lik
e
el
ec
tr
ic
v
eh
icles
an
d
p
o
r
tab
le
ele
ctr
o
n
ics.
I
n
tack
lin
g
th
is
ch
alle
n
g
e,
v
ar
io
u
s
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
s
em
er
g
e
as
p
r
o
m
is
in
g
s
o
lu
tio
n
s
,
ea
c
h
o
f
f
er
in
g
d
is
tin
ct
ad
v
an
ta
g
es
co
n
ti
n
g
en
t
u
p
o
n
f
ac
t
o
r
s
s
u
ch
as
d
ata
n
atu
r
e,
r
eso
u
r
ce
a
v
ailab
ilit
y
,
an
d
s
p
ec
if
ic
r
eq
u
ir
em
en
ts
.
Am
o
n
g
th
e
ar
r
ay
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
,
R
NNs,
G
R
Us,
an
d
L
STM
s
n
et
wo
r
k
s
,
r
ep
r
esen
te
d
in
F
ig
u
r
es
1
to
3
,
s
tan
d
o
u
t
p
r
o
m
i
n
en
tly
.
R
NNs
ex
ce
l
in
ca
p
tu
r
in
g
tem
p
o
r
al
f
ea
tu
r
es
b
y
lev
e
r
ag
in
g
c
o
r
r
elatio
n
s
b
etwe
en
c
u
r
r
en
t
ca
p
ac
ity
an
d
p
r
ev
io
u
s
in
p
u
ts
,
f
ac
ilit
atin
g
r
e
alis
tic
e
s
tim
atio
n
s
f
o
r
f
u
tu
r
e
p
r
ed
ictio
n
s
.
Ho
wev
er
,
th
ey
e
n
co
u
n
ter
c
h
allen
g
es
with
lo
n
g
-
d
is
tan
ce
d
ep
en
d
en
ci
es,
lead
in
g
to
is
s
u
es
lik
e
v
a
n
is
h
in
g
g
r
ad
ien
ts
.
I
n
co
n
tr
ast,
L
STM
ad
d
r
ess
es
th
ese
co
n
ce
r
n
s
b
y
r
e
g
u
latin
g
g
r
a
d
ie
n
t
p
r
o
p
ag
ati
o
n
an
d
m
ain
tain
i
n
g
p
ar
am
eter
m
em
o
r
y
ac
r
o
s
s
tim
e
iter
atio
n
s
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
mp
r
o
vin
g
lith
iu
m
-
io
n
b
a
tter
y
r
elia
b
ilit
y
th
r
o
u
g
h
n
eu
r
a
l
n
etw
o
r
k
r
ema
in
in
g
u
s
efu
l life
…
(
B
r
a
h
im
Zr
a
ib
i
)
85
L
STM
ar
ch
itectu
r
e
co
m
p
r
is
e
s
lo
n
g
-
ter
m
an
d
s
h
o
r
t
-
ter
m
s
tates,
h
ar
n
ess
in
g
in
p
u
t
an
d
a
ctiv
atio
n
v
alu
es
to
co
m
p
u
te
h
i
d
d
en
la
y
er
n
o
d
es
ef
f
ec
tiv
ely
.
On
t
h
e
o
th
er
h
an
d
,
GR
U
[
1
7
]
,
ch
ar
ac
ter
ize
d
b
y
its
s
im
p
lifie
d
ar
ch
itectu
r
e
f
ea
tu
r
in
g
two
g
at
es
—
u
p
d
ate
an
d
r
eset
—
o
f
f
er
s
co
m
p
ar
ab
le
p
er
f
o
r
m
an
ce
to
L
STM
with
f
ewe
r
p
ar
am
eter
s
[
9
]
,
[
1
8
]
,
[
1
9
]
.
F
i
g
u
r
e
1
.
T
h
e
R
N
N
a
r
c
h
it
e
c
t
u
r
e
Fig
u
r
e
2
.
T
h
e
GR
U
ar
ch
itectu
r
e
Fig
u
r
e
3
.
T
h
e
L
STM
ar
ch
itect
u
r
e
T
h
e
s
elec
tio
n
o
f
th
e
m
o
s
t
s
u
itab
le
alg
o
r
ith
m
h
in
g
es
o
n
d
ataset
ch
ar
ac
ter
is
tics
,
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
an
d
d
esire
d
ac
c
u
r
ac
y
lev
els.
L
e
v
er
ag
in
g
th
e
s
tr
en
g
th
s
o
f
ea
ch
alg
o
r
ith
m
,
o
u
r
m
e
th
o
d
,
as d
ep
icted
in
Fig
u
r
e
4
,
is
m
eticu
lo
u
s
ly
cr
a
f
ted
to
ca
p
italize
o
n
th
ese
d
i
v
er
s
e
b
en
ef
its
,
en
s
u
r
i
n
g
o
p
ti
m
al
p
er
f
o
r
m
an
ce
i
n
p
r
ed
ictin
g
lith
iu
m
-
i
o
n
b
atter
y
R
UL
.
T
o
ac
h
iev
e
o
p
tim
al
p
er
f
o
r
m
a
n
ce
in
p
r
ed
ictin
g
th
e
R
UL
o
f
lith
iu
m
-
io
n
b
atter
ies.
T
o
f
u
r
th
e
r
en
h
a
n
ce
ac
cu
r
ac
y
,
we
ad
h
er
ed
t
o
a
we
ll
-
d
ef
in
ed
p
r
o
ce
s
s
f
o
r
R
UL
p
r
ed
ictio
n
,
wh
ich
is
d
etailed
in
Fig
u
r
e
5
.
T
h
is
s
y
s
tem
atic
ap
p
r
o
ac
h
en
s
u
r
es a
r
o
b
u
s
t a
n
d
ef
f
icien
t
p
r
ed
ictio
n
m
o
d
el.
Fig
u
r
e
4
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
t
o
p
r
ed
ict
R
UL
o
f
b
atter
y
lith
iu
m
-
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
83
-
91
86
Fig
u
r
e
5
.
T
h
e
p
r
o
ce
s
s
f
o
r
p
r
ed
ict
in
g
R
UL
o
f
b
atter
y
lith
iu
m
-
io
n
2
.
2
.
B
a
t
t
er
y
da
t
a
s
et
T
h
e
s
tu
d
y
v
alid
ates
its
f
in
d
in
g
s
u
s
in
g
ex
p
er
im
e
n
tal
d
ata
s
o
u
r
ce
d
f
r
o
m
th
e
NASA
[
2
0
]
o
f
e
x
ce
llen
ce
,
f
o
cu
s
in
g
o
n
a
g
in
g
d
ata
f
o
r
1
8
6
5
0
lith
iu
m
-
io
n
b
atter
ies
.
T
h
e
d
ataset
in
clu
d
es
th
r
ee
d
is
tin
c
t
m
o
d
es:
ch
ar
g
in
g
,
wh
er
e
th
e
b
atter
y
is
ch
ar
g
ed
with
a
co
n
s
tan
t
cu
r
r
en
t
u
n
til
r
ea
ch
in
g
4
.
2
V,
f
o
llo
wed
b
y
a
co
n
s
tan
t
v
o
ltag
e
p
h
ase;
d
is
ch
ar
g
e,
w
h
er
e
th
e
b
atter
y
is
d
is
ch
ar
g
ed
with
a
c
o
n
s
tan
t
cu
r
r
e
n
t
u
n
til
r
ea
ch
i
n
g
2
.
5
V
;
an
d
ter
m
in
atio
n
,
o
cc
u
r
r
in
g
wh
en
th
e
b
atter
y
'
s
ac
tu
al
ca
p
ac
ity
d
r
o
p
s
b
elo
w
7
0
%
o
f
its
r
ated
ca
p
ac
ity
(
2
Ah
)
.
A
n
aly
s
is
is
co
n
d
u
cte
d
u
s
in
g
th
e
d
ataset
f
o
r
th
e
B
0
0
0
6
b
atter
y
s
h
o
win
g
i
n
F
ig
u
r
e
6
.
Fig
u
r
e
6
.
C
ap
ac
ity
d
eg
r
ad
atio
n
cu
r
v
e
o
f
B
0
0
0
6
b
atter
y
2
.
3
.
Sy
s
t
em
co
nfig
ura
t
io
n
a
nd
ev
a
lua
t
io
n c
rit
er
ia
o
f
perf
o
rma
nce
T
h
e
h
ar
d
war
e
an
d
s
o
f
twar
e
en
v
ir
o
n
m
en
t
an
d
h
y
p
er
-
p
ar
a
m
eter
s
s
h
o
wn
in
T
a
b
le
1
w
as
u
s
ed
to
im
p
lem
en
t
th
e
th
r
ee
m
eth
o
d
s
,
i.e
.
R
NN,
GR
U,
an
d
L
STM
,
r
esp
ec
tiv
ely
.
T
h
e
Ad
a
m
o
p
tim
izer
an
d
Hu
b
er
lo
s
s
ar
e
u
tili
ze
d
,
as
well
as
th
e
r
e
ctif
ied
lin
ea
r
u
n
it
(
R
eL
U)
ac
ti
v
atio
n
f
u
n
ctio
n
.
I
n
ad
d
itio
n
,
we
u
tili
ze
th
e
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
[
2
1
]
,
r
o
o
t
m
ea
n
s
q
u
a
r
e
er
r
o
r
(
R
MSE
)
,
R
s
q
u
ar
e
(
R
²)
[
2
2
]
,
a
n
d
m
ea
n
ab
s
o
lu
te
p
er
ce
n
ta
g
e
er
r
o
r
(
MA
PE)
[
2
3
]
to
ev
al
u
ate
th
e
m
eth
o
d
s
o
f
R
UL
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
.
=
1
∑
|
−
̂
|
=
1
(
1
)
=
√
1
∑
(
−
̂
)
²
=
1
(
2
)
²
=
1
−
∑
(
−
̂
)
2
=
1
∑
(
−
̅
̅
̅
̅
̂
)
2
=
1
(
3
)
=
1
∑
|
−
̂
|
=
1
×
100%
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
mp
r
o
vin
g
lith
iu
m
-
io
n
b
a
tter
y
r
elia
b
ilit
y
th
r
o
u
g
h
n
eu
r
a
l
n
etw
o
r
k
r
ema
in
in
g
u
s
efu
l life
…
(
B
r
a
h
im
Zr
a
ib
i
)
87
W
h
er
e
s
tan
d
s
f
o
r
th
e
g
en
u
in
e
ca
p
ac
ity
o
f
th
e
b
atter
y
,
̂
f
o
r
t
h
e
esti
m
ated
ca
p
ac
ity
,
an
d
̅
̅
̅
f
o
r
th
e
ac
tu
al
ca
p
ac
ity
av
er
ag
e.
T
h
e
ca
p
ac
it
y
f
o
r
ec
ast
ac
cu
r
ac
y
is
g
r
ea
ter
wh
en
th
e
MA
E
,
MA
PE,
an
d
R
MSE
ar
e
n
ea
r
to
ze
r
o
.
W
h
en
it
co
m
es
to
R
²,
a
n
u
m
b
er
n
ea
r
to
o
n
e
m
ea
n
s
m
o
r
e
ac
cu
r
ate
R
UL
p
r
ed
ictio
n
s
.
T
h
e
Deta
iled
f
lo
wch
ar
t
s
tep
s
f
o
r
p
r
ed
ictin
g
R
UL
b
ased
o
n
th
e
p
r
o
p
o
s
ed
m
o
d
el
ar
e
illu
s
tr
ated
in
Fig
u
r
e
7
.
T
h
e
m
o
d
el
f
r
am
ewo
r
k
d
ep
e
n
d
as
m
o
d
el
in
p
u
ts
a
r
e
th
e
cu
r
r
e
n
t
an
d
p
r
ev
io
u
s
ca
p
ac
ity
v
ec
to
r
[
C
(
t
−
i)
,
.
.
.
,
C
(
t)
]
.
W
h
ile
m
o
d
el
o
u
tp
u
ts
ar
e
C
(
t
+
1
)
,
wh
i
ch
ca
n
b
e
p
r
ed
icted
af
ter
em
p
lo
y
in
g
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
.
W
e
u
s
e
a
r
ec
u
r
s
iv
e
p
r
ed
ictio
n
p
r
o
ce
d
u
r
e
wh
er
e
th
e
p
r
ev
io
u
s
ly
f
o
r
ec
ast
ca
p
ac
ity
as
th
e
n
ex
t
in
p
u
t
o
f
th
e
m
o
d
el
to
p
r
ed
ict
n
ew
ca
p
a
city
v
alu
e
u
n
til th
e
b
atter
y
'
s
E
OL
is
ar
r
iv
ed
,
th
e
n
n
ew
R
UL
ca
n
esti
m
ated
.
T
ab
le
1
.
E
n
v
ir
o
n
m
en
t o
f
h
ar
d
war
e
an
d
s
o
f
twar
e
a
n
d
b
est v
a
lu
es o
f
h
y
p
er
-
p
a
r
am
eter
s
H
a
r
d
w
a
r
e
EN
V
I
R
O
N
M
EN
T
S
o
f
t
w
a
r
e
EN
V
I
R
O
N
M
EN
T
h
y
p
e
r
p
a
r
a
me
t
e
r
s (
si
z
e
)
h
y
p
e
r
p
a
r
a
me
t
e
r
s
R
A
M
8
G
P
y
t
h
o
n
w
i
t
h
T
e
n
so
r
f
l
o
w
W
i
n
d
o
w
:
8
Ep
o
c
h
s:
1
5
0
0
1
.
8
0
G
H
z
C
P
U
W
i
n
d
o
w
s 1
0
p
r
o
f
e
ssi
o
n
a
l
e
d
i
t
i
o
n
B
a
t
c
h
:
8
l
e
a
r
n
i
n
g
_
r
a
t
e
:
8e
-
4
I
n
t
e
l
(
R
)
H
D
G
r
a
p
h
i
c
s Fam
i
l
y
sh
u
f
f
l
e
_
b
u
f
f
e
r
:
1
0
0
0
R
e
g
u
l
a
r
i
z
a
t
i
o
n
:
w
i
t
h
o
u
t
Fig
u
r
e
7
.
Flo
wch
ar
t
s
tep
s
f
o
r
p
r
ed
ictin
g
R
UL
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
R
em
a
ini
ng
us
ef
ul life
predic
t
io
n
wit
h t
he
v
a
rio
us
m
et
ho
d
s
I
n
th
is
s
ec
tio
n
,
we
p
r
esen
t
th
e
r
esu
lts
o
f
o
u
r
ex
p
er
im
en
tatio
n
o
n
p
r
ed
ictin
g
R
UL
u
s
in
g
th
r
ee
d
is
tin
ct
m
eth
o
d
s
R
NN,
GR
U,
an
d
L
STM
.
E
ac
h
m
eth
o
d
co
m
p
r
is
es
f
o
u
r
k
e
y
s
tep
s
:
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
,
tr
ai
n
in
g
o
v
er
8
0
cy
cles,
v
alid
atio
n
p
r
ed
ictio
n
o
v
er
8
8
c
y
cles,
an
d
4
0
n
ew
p
r
ed
ictio
n
cy
cles
(
f
r
o
m
1
6
9
to
2
0
8
)
.
T
h
e
R
UL
p
r
ed
ictio
n
r
esu
lts
f
o
r
ea
c
h
m
eth
o
d
a
r
e
d
elin
ea
ted
,
with
r
ea
l
v
alu
es
d
ep
icted
i
n
y
ello
w,
p
r
ed
ictio
n
s
in
g
r
ee
n
(
b
eg
in
n
i
n
g
at
c
y
cle
8
0
)
,
a
n
d
n
e
w
p
r
ed
i
ctio
n
s
in
r
ed
.
First,
em
p
lo
y
in
g
th
e
R
NN
m
eth
o
d
f
o
r
li
th
iu
m
-
io
n
b
atter
ies
R
UL
p
r
ed
ictio
n
r
ev
ea
ls
cl
o
s
e
alig
n
m
en
t
b
etwe
en
v
alid
atio
n
an
d
tr
u
e
v
alu
es
as
s
h
o
wn
i
n
Fi
g
u
r
e
8
(
a)
,
in
d
icativ
e
o
f
ef
f
ec
tiv
e
lear
n
i
n
g
.
H
o
wev
er
,
its
p
er
f
o
r
m
an
ce
in
n
ew
p
r
e
d
ic
tio
n
s
is
s
u
b
o
p
tim
al.
C
o
n
v
er
s
ely
,
th
e
GR
U
m
eth
o
d
as
s
h
o
wn
in
Fig
u
r
e
8
(
b
)
ex
h
ib
its
im
p
r
o
v
ed
ac
cu
r
ac
y
d
u
r
in
g
th
e
v
alid
atio
n
p
h
ase,
y
et
n
ew
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
r
em
ain
s
i
n
ad
eq
u
ate.
T
h
e
L
STM
m
et
h
o
d
,
o
n
th
e
o
th
er
h
a
n
d
,
n
o
t
o
n
ly
en
h
a
n
c
es
R
UL
p
r
ed
ictio
n
ac
cu
r
ac
y
f
o
r
lith
iu
m
-
io
n
b
att
er
ies
b
u
t
n
o
tab
ly
ac
h
iev
es
s
a
tis
f
ac
to
r
y
p
er
f
o
r
m
a
n
c
e
in
n
e
w
p
r
ed
ictio
n
s
.
T
h
e
co
n
s
is
ten
cy
b
etwe
en
esti
m
ates
an
d
tr
u
e
v
alu
es
is
ev
id
en
t
as
s
h
o
wn
in
Fig
u
r
e
8
(
c
)
,
with
s
ig
n
i
f
ican
t
im
p
r
o
v
em
en
t
in
n
ew
p
r
e
d
ictio
n
ac
cu
r
ac
y
.
F
u
r
th
er
m
o
r
e,
th
e
l
o
s
s
cu
r
v
e
o
f
th
e
L
STM
m
eth
o
d
c
o
n
s
is
ten
tly
co
n
v
er
g
es
to
war
d
s
ze
r
o
,
d
em
o
n
s
t
r
atin
g
co
n
tin
u
al
lear
n
in
g
an
d
r
ed
u
ce
d
p
er
t
u
r
b
atio
n
co
m
p
ar
ed
to
R
NN
an
d
GR
U
m
eth
o
d
s
as
s
h
o
wn
in
Fig
u
r
e
s
9
(a
)
to
9
(
c)
.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
s
co
r
e
th
e
s
u
p
er
io
r
ity
o
f
L
STM
in
ac
h
iev
in
g
h
ig
h
esti
m
atio
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
in
p
r
ed
ictin
g
n
ew
R
UL
,
th
u
s
s
o
lid
if
y
in
g
its
s
tatu
s
a
s
th
e
m
o
s
t
ac
cu
r
ate
m
eth
o
d
f
o
r
lith
iu
m
-
io
n
b
atter
ies
R
UL
p
r
ed
ictio
n
.
T
h
e
s
u
b
s
eq
u
e
n
t
s
ec
tio
n
p
r
o
v
id
es
a
s
u
m
m
a
r
y
o
f
n
u
m
e
r
ic
R
UL
p
r
ed
ictio
n
e
r
r
o
r
s
an
d
co
n
tex
tu
alize
s
th
em
ag
ain
s
t o
th
er
lead
i
n
g
m
eth
o
d
s
in
th
e
liter
atu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
83
-
91
88
(
a)
(
b
)
(
c)
Fig
u
r
e
8
.
R
UL
p
r
e
d
ictio
n
r
esu
lts
u
s
in
g
: (
a)
R
NN,
(
b
)
GR
U,
an
d
(
c)
L
STM
(
a)
(
b
)
(
c)
Fig
u
r
e
9
.
R
UL
tr
ain
in
g
p
er
f
o
r
m
an
ce
: (
a)
R
NN,
(
b
)
GR
U,
an
d
(
c)
L
STM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
mp
r
o
vin
g
lith
iu
m
-
io
n
b
a
tter
y
r
elia
b
ilit
y
th
r
o
u
g
h
n
eu
r
a
l
n
etw
o
r
k
r
ema
in
in
g
u
s
efu
l life
…
(
B
r
a
h
im
Zr
a
ib
i
)
89
3
.
2
.
Co
m
pa
ra
t
iv
e
re
s
ults a
na
ly
s
is
3
.
2
.
1
.
R
em
a
ini
ng
us
ef
ul life
v
a
lid
a
t
io
n a
nd
t
he
ev
a
lua
t
io
n c
rit
er
ia
I
n
t
h
e
p
r
e
c
e
d
i
n
g
s
e
c
t
i
o
n
,
o
u
r
f
o
c
u
s
w
a
s
o
n
e
v
a
l
u
a
t
i
n
g
t
h
e
e
x
t
r
a
p
o
l
a
t
i
o
n
c
a
p
a
b
i
l
i
ti
e
s
o
f
t
h
e
L
ST
M
m
o
d
e
l
t
h
r
o
u
g
h
R
U
L
p
r
e
d
i
c
t
i
o
n
t
e
s
ts
co
n
d
u
c
t
e
d
o
n
t
h
e
B
0
0
0
6
b
a
t
t
e
r
y
c
a
s
e
.
S
u
b
s
e
q
u
e
n
tl
y
,
t
h
e
p
r
e
d
i
c
t
i
o
n
r
e
s
u
l
ts
f
o
r
t
h
i
s
b
a
t
t
e
r
y
w
e
r
e
p
l
o
t
te
d
,
a
c
c
o
m
p
a
n
i
e
d
b
y
t
h
e
p
r
e
s
e
n
t
a
t
i
o
n
o
f
a
c
c
u
r
a
c
y
i
n
d
i
c
a
t
o
r
s
.
T
o
e
n
s
u
r
e
c
o
m
p
r
e
h
e
n
s
i
v
e
c
a
p
a
c
it
y
i
n
f
o
r
m
a
t
i
o
n
i
n
c
l
u
s
i
o
n
d
u
r
i
n
g
th
e
t
r
a
i
n
i
n
g
p
r
o
c
e
s
s
,
t
h
e
i
n
it
i
a
l
8
0
d
a
t
a
p
o
i
n
t
s
f
r
o
m
t
h
e
c
a
p
a
ci
ty
d
e
g
r
a
d
a
t
i
o
n
c
u
r
v
e
,
c
o
n
s
t
i
t
u
t
i
n
g
a
n
e
a
r
-
e
v
e
n
s
p
li
t
,
w
e
r
e
u
t
il
i
z
e
d
a
s
t
h
e
t
r
ai
n
i
n
g
s
e
ts
.
S
u
b
s
e
q
u
e
n
t
t
o
m
o
d
el
t
r
ai
n
i
n
g
,
p
r
e
d
i
c
t
i
o
n
s
o
f
f
u
t
u
r
e
c
a
p
a
c
i
t
y
a
c
r
o
s
s
r
e
m
ai
n
i
n
g
c
y
cl
e
s
we
r
e
m
a
d
e
,
e
m
p
h
a
s
i
z
i
n
g
th
e
s
i
g
n
i
f
i
c
a
n
ce
o
f
e
a
r
l
y
-
c
y
c
l
e
R
U
L
p
r
e
d
i
ct
i
o
n
f
o
r
b
a
t
t
e
r
y
m
a
n
a
g
e
m
e
n
t
.
I
n
t
h
i
s
s
e
ct
i
o
n
,
o
u
r
a
t
t
e
n
t
i
o
n
s
h
i
f
t
s
t
o
wa
r
d
s
s
c
r
u
t
i
n
iz
i
n
g
t
h
e
r
e
c
u
r
s
i
v
e
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
a
n
d
t
h
e
r
o
b
u
s
t
n
e
s
s
o
f
o
u
r
p
r
o
p
o
s
e
d
m
e
t
h
o
d
.
T
h
e
e
x
p
e
r
i
m
e
n
t
s
c
o
n
d
u
c
t
e
d
a
f
f
i
r
m
t
h
e
a
b
i
l
i
t
y
o
f
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
t
o
e
f
f
e
c
t
i
v
e
l
y
c
a
p
t
u
r
e
t
h
e
d
y
n
a
m
i
c
n
a
t
u
r
e
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
.
E
v
a
l
u
at
i
o
n
o
f
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
w
a
s
c
o
n
d
u
c
t
e
d
u
s
i
n
g
f
o
u
r
k
e
y
i
n
d
i
c
a
t
o
r
s
:
MA
E
,
R
²
,
M
AP
E
,
a
n
d
R
M
S
E
,
wi
t
h
d
e
t
a
il
e
d
r
e
s
u
l
ts
p
r
e
s
e
n
t
e
d
i
n
T
a
b
l
e
2
.
T
ab
le
2
,
alo
n
g
with
Fig
u
r
es
8
an
d
9
,
p
r
o
v
id
e
a
co
m
p
r
e
h
en
s
iv
e
in
s
ig
h
t
in
to
th
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
i
es,
all
b
ased
o
n
th
e
B
0
0
0
6
b
atter
y
'
s
tes
tin
g
s
et
with
id
en
tical
s
tar
tin
g
p
o
in
ts
.
No
tab
ly
,
MA
E
,
MA
PE,
a
n
d
R
MSE
v
alu
es
ass
o
ciate
d
with
th
e
L
STM
m
eth
o
d
ar
e
n
o
ta
b
ly
lo
wer
co
m
p
a
r
ed
t
o
th
o
s
e
o
f
t
h
e
R
NN
an
d
GR
U
m
eth
o
d
s
,
w
h
ile
th
e
R
²
v
al
u
es
ar
e
co
r
r
esp
o
n
d
in
g
ly
h
ig
h
e
r
.
T
h
ese
f
i
n
d
in
g
s
u
n
d
er
s
co
r
e
th
e
co
n
s
id
er
ab
le
en
h
an
ce
m
en
t
in
R
UL
p
r
ed
ictio
n
f
ac
ilit
ated
b
y
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
.
Par
ticu
lar
ly
n
o
tewo
r
th
y
a
r
e
th
e
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
o
b
s
er
v
ed
in
M
AE
an
d
R
MSE
m
etr
ics
as
s
h
o
wn
in
Fig
u
r
e
1
0
wh
e
n
tr
an
s
itio
n
i
n
g
f
r
o
m
L
STM
to
GR
U,
in
d
icatin
g
im
p
r
o
v
e
m
en
ts
o
f
2
9
.
2
%
an
d
1
0
.
8
%,
r
esp
ec
tiv
ely
.
Su
ch
o
u
tc
o
m
es
h
ig
h
lig
h
t
th
e
ef
f
icac
y
a
n
d
s
u
p
er
io
r
ity
o
f
th
e
p
r
o
p
o
s
ed
L
STM
m
eth
o
d
in
en
h
a
n
cin
g
p
r
ed
i
ctiv
e
ac
cu
r
ac
y
a
n
d
p
r
ec
is
io
n
f
o
r
lith
iu
m
-
io
n
b
atte
r
y
R
UL
p
r
ed
ictio
n
.
T
ab
le
2
.
R
UL
p
r
e
d
ictio
n
r
esu
l
ts
f
o
r
B
0
0
0
6
M
e
t
h
o
d
s
S
t
a
r
t
p
o
i
n
t
M
A
E
R
²
(
%
)
R
M
S
E
M
A
P
E
R
N
N
80
0
.
0
1
2
8
7
9
4
.
7
0
0
.
0
2
3
2
1
0
.
9
8
1
0
G
R
U
80
0
.
0
1
2
0
6
9
4
.
8
6
0
.
0
2
2
8
6
0
.
9
4
7
3
LSTM
80
0
.
0
0
8
5
4
9
5
.
9
1
0
.
0
2
0
3
8
0
.
7
8
6
1
Fig
u
r
e
1
0
.
C
o
m
p
ar
in
g
R
UL
esti
m
atio
n
r
esu
lts
b
y
MA
E
an
d
R
MSE
3
.
2
.
2
.
Resul
t
s
a
na
ly
s
is
a
nd
c
o
m
pa
riso
n
T
h
is
s
ec
tio
n
co
m
p
a
r
es
th
e
ac
cu
r
ac
y
o
f
R
UL
esti
m
ates
ac
r
o
s
s
v
ar
io
u
s
m
eth
o
d
o
lo
g
ies
f
r
o
m
ex
is
tin
g
liter
atu
r
e.
s
in
g
le
m
eth
o
d
s
em
er
g
e
as
s
u
f
f
icien
t
f
o
r
h
a
n
d
lin
g
tim
e
s
er
ies
d
ata,
as
s
u
p
p
o
r
t
ed
b
y
th
e
r
esu
lts
in
T
ab
le
3
an
d
th
e
ac
co
m
p
an
y
in
g
an
aly
s
is
.
Ad
d
itio
n
all
y
,
to
o
f
f
er
a
b
r
o
ad
e
r
co
m
p
a
r
is
o
n
en
c
o
m
p
ass
in
g
v
ar
io
u
s
n
eu
r
al
n
etwo
r
k
p
r
ed
ictio
n
m
eth
o
d
o
lo
g
ies,
we
co
llate
p
er
f
o
r
m
an
ce
r
esu
lts
f
r
o
m
o
th
er
s
tu
d
i
es
u
tili
zin
g
th
e
s
am
e
NASA
d
ataset
an
d
p
er
f
o
r
m
an
ce
m
etr
ics,
alo
n
g
s
id
e
co
m
m
e
n
cin
g
p
r
e
d
ictio
n
s
f
r
o
m
id
e
n
tical
s
tar
ti
n
g
p
o
in
ts
.
As
d
elin
ea
ted
in
T
a
b
le
3
,
th
e
L
S
T
M
m
eth
o
d
n
o
ta
b
ly
o
u
tp
er
f
o
r
m
s
its
s
in
g
le
co
u
n
ter
p
ar
ts
in
ter
m
s
o
f
ac
c
u
r
ac
y
,
af
f
ir
m
in
g
t
h
e
ef
f
icien
c
y
an
d
e
f
f
icac
y
o
f
L
STM
as
ev
id
en
ce
d
in
th
is
ar
ticle.
Sp
ec
if
ically
,
th
e
L
STM
m
eth
o
d
d
em
o
n
s
tr
ates
a
d
em
o
n
s
tr
ab
le
r
ed
u
ctio
n
i
n
MA
E
an
d
R
MSE
.
T
h
e
cu
m
u
lativ
e
f
i
n
d
i
n
g
s
u
n
d
e
r
s
co
r
e
th
e
0
0.0
1
0.0
2
0.0
3
M
A
E
R
M
S
E
e
r
r
o
r
v
al
ue
M
e
t
ho
ds
R
N
N
G
R
U
LST
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
83
-
91
90
h
ig
h
-
ac
cu
r
ac
y
esti
m
atio
n
ca
p
ab
ilit
ies
o
f
th
e
p
r
o
p
o
s
ed
L
STM
R
UL
p
r
ed
ictio
n
m
eth
o
d
,
p
o
s
itio
n
in
g
it
as
a
s
u
p
er
io
r
ch
o
ice
in
th
e
r
ea
lm
o
f
p
r
ed
ictiv
e
m
o
d
elin
g
.
T
ab
le
3
.
R
UL
p
r
e
d
ictio
n
r
esu
l
ts
o
f
B
0
0
0
6
f
o
r
v
ar
io
u
s
p
a
p
er
s
M
e
t
h
o
d
s
S
t
a
r
t
p
o
i
n
t
M
A
E
R
M
S
E
R
N
N
LSTM
[
2
4
]
78
0
.
1
1
3
1
0
.
0
7
8
4
U
K
F
A
U
K
F
[
2
2
]
80
0
.
0
9
9
4
0
.
0
3
7
1
0
.
1
2
7
5
0
.
0
4
8
9
R
V
M
G
M
[
1
3
]
80
0
.
0
6
6
7
0
.
0
6
3
4
S
V
R
[
1
2
]
80
0
.
0
4
7
7
LSTM
R
N
N
[
2
5
]
R
V
M
70
0
.
0
3
1
1
0
.
0
7
9
9
0
.
0
6
8
2
R
N
N
G
R
U
LSTM
80
0
.
0
1
2
8
7
0
.
0
1
2
0
6
0
.
0
0
8
5
4
0
.
0
2
3
2
1
0
.
0
2
2
8
6
0
.
0
2
0
3
8
4.
CO
NCLU
SI
O
N
I
n
co
n
cl
u
s
io
n
,
th
is
s
tu
d
y
in
tr
o
d
u
ce
s
th
e
L
STM
m
eth
o
d
as
a
n
o
v
el
ap
p
r
o
ac
h
f
o
r
p
r
ed
ictin
g
th
e
R
UL
o
f
lith
iu
m
-
io
n
b
atter
ies,
o
f
f
e
r
in
g
s
ig
n
if
ican
t
ad
v
an
ce
m
en
ts
o
v
er
estab
lis
h
ed
m
eth
o
d
o
lo
g
ies
s
u
ch
as
R
NN
s
an
d
GR
U.
L
ev
er
ag
in
g
a
d
ataset
s
o
u
r
ce
d
f
r
o
m
NASA,
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
u
n
d
e
r
g
o
es
r
i
g
o
r
o
u
s
ex
p
er
im
en
tal
v
alid
atio
n
,
a
f
f
ir
m
in
g
its
ex
ce
p
tio
n
al
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
f
o
r
lith
iu
m
-
io
n
b
atter
y
R
UL
.
E
m
p
ir
ical
f
in
d
in
g
s
u
n
eq
u
i
v
o
ca
lly
d
em
o
n
s
tr
ate
th
e
s
u
p
er
io
r
ac
cu
r
a
cy
o
f
th
e
L
STM
m
eth
o
d
co
m
p
a
r
ed
to
alter
n
ativ
e
ap
p
r
o
ac
h
es.
T
h
r
o
u
g
h
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
u
s
in
g
f
o
u
r
p
er
f
o
r
m
a
n
ce
in
d
ices,
L
STM
em
e
r
g
es
as
th
e
clea
r
f
r
o
n
tr
u
n
n
er
,
s
u
r
p
ass
in
g
R
NN,
G
R
U,
an
d
o
th
er
co
n
tem
p
o
r
ar
y
m
eth
o
d
o
lo
g
ies
in
p
r
e
d
ictiv
e
ac
cu
r
ac
y
.
T
h
ese
r
esu
lt
s
u
n
d
er
s
co
r
e
t
h
e
s
ig
n
if
ican
ce
o
f
o
u
r
p
r
o
p
o
s
ed
L
STM
-
b
ased
ap
p
r
o
ac
h
in
ad
v
a
n
cin
g
R
UL
p
r
ed
ictio
n
m
eth
o
d
o
l
o
g
ies
f
o
r
lith
iu
m
-
i
o
n
b
atter
ies,
with
p
r
o
m
is
in
g
i
m
p
licatio
n
s
f
o
r
en
h
a
n
cin
g
b
atter
y
m
an
ag
em
e
n
t
p
r
ac
tices a
n
d
en
s
u
r
i
n
g
o
p
er
ati
o
n
al
ef
f
icien
c
y
an
d
r
eliab
ilit
y
in
v
ar
io
u
s
a
p
p
licatio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
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
me
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
,
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
]
B
.
Zr
a
i
b
i
,
M
.
M
a
n
so
u
r
i
,
S
.
E
.
L
o
u
k
i
l
i
,
a
n
d
S
.
B
.
A
l
l
a
,
“
H
y
b
r
i
d
n
e
u
r
a
l
n
e
t
w
o
r
k
m
e
t
h
o
d
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
S
O
H
a
n
d
R
U
L
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s,”
A
d
v
a
n
c
e
s
i
n
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
S
y
st
e
m
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
1
9
3
–
1
9
8
,
2
0
2
2
,
d
o
i
:
1
0
.
2
5
0
4
6
/
a
j
0
7
0
5
2
0
.
[
3
]
J.
Z
h
u
,
T.
Ta
n
,
L
.
W
u
,
a
n
d
H
.
Y
u
a
n
,
“
R
U
L
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
y
b
a
se
d
o
n
i
m
p
r
o
v
e
d
D
G
W
O
-
EL
M
me
t
h
o
d
i
n
a
r
a
n
d
o
m
d
i
s
c
h
a
r
g
e
r
a
t
e
s
e
n
v
i
r
o
n
me
n
t
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
2
5
1
7
6
–
1
2
5
1
8
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
6
8
2
2
.
[
4
]
Y
.
Zh
a
n
g
a
n
d
Y
.
-
F
.
Li
,
“
P
r
o
g
n
o
st
i
c
s
a
n
d
h
e
a
l
t
h
ma
n
a
g
e
me
n
t
o
f
Li
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s
:
a
r
e
v
i
e
w
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
6
1
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
s
e
r
.
2
0
2
2
.
1
1
2
2
8
2
.
[
5
]
F
.
A
y
a
d
i
,
M
.
La
h
i
a
n
i
,
a
n
d
N
.
D
e
r
b
e
l
,
“
K
a
l
ma
n
f
i
l
t
e
r
o
b
ser
v
e
r
f
o
r
S
o
C
p
r
e
d
i
c
t
i
o
n
o
f
Li
t
h
i
u
m
c
e
l
l
s,
”
A
d
v
a
n
c
e
s
i
n
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
a
n
d
En
g
i
n
e
e
ri
n
g
S
y
s
t
e
m
s
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
1
8
0
–
1
8
8
,
2
0
1
7
,
d
o
i
:
1
0
.
2
5
0
4
6
/
a
j
0
2
0
4
2
4
.
[
6
]
J.
Ji
a
,
J.
Li
a
n
g
,
Y
.
S
h
i
,
J.
W
e
n
,
X
.
P
a
n
g
,
a
n
d
J.
Ze
n
g
,
“
S
O
H
a
n
d
R
U
L
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
b
a
se
d
o
n
g
a
u
ssi
a
n
p
r
o
c
e
s
s
r
e
g
r
e
ss
i
o
n
w
i
t
h
i
n
d
i
r
e
c
t
h
e
a
l
t
h
i
n
d
i
c
a
t
o
r
s,”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
3
,
n
o
.
2
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
0
2
0
3
7
5
.
[
7
]
M
.
E
l
ma
h
a
l
l
a
w
y
,
T
.
El
f
o
u
l
y
,
A
.
A
l
o
u
a
n
i
,
a
n
d
A
.
M
.
M
a
ss
o
u
d
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
Li
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
m
o
d
e
l
i
n
g
,
a
n
d
st
a
t
e
o
f
h
e
a
l
t
h
a
n
d
r
e
ma
i
n
i
n
g
u
sef
u
l
l
i
f
e
t
i
me
p
r
e
d
i
c
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
1
9
0
4
0
–
1
1
9
0
7
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
2
1
1
3
7
.
[
8
]
R
.
X
i
o
n
g
,
B
a
t
t
e
ry
m
a
n
a
g
e
m
e
n
t
a
l
g
o
r
i
t
h
m
f
o
r e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
.
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
15
-
0
2
4
8
-
4.
[
9
]
B
.
Zr
a
i
b
i
,
C
.
O
k
a
r
,
H
.
C
h
a
o
u
i
,
a
n
d
M
.
M
a
n
so
u
r
i
,
“
R
e
m
a
i
n
i
n
g
u
sef
u
l
l
i
f
e
a
s
sessme
n
t
f
o
r
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
u
s
i
n
g
C
N
N
-
LST
M
-
D
N
N
h
y
b
r
i
d
m
e
t
h
o
d
,
”
I
EEE
T
r
a
n
sa
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
.
7
0
,
n
o
.
5
,
p
p
.
4
2
5
2
–
4
2
6
1
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
2
1
.
3
0
7
1
6
2
2
.
[
1
0
]
R
.
R
.
R
i
c
h
a
r
d
s
o
n
,
M
.
A
.
O
sb
o
r
n
e
,
a
n
d
D
.
A
.
H
o
w
e
y
,
“
G
a
u
ss
i
a
n
p
r
o
c
e
ss re
g
r
e
ssi
o
n
f
o
r
f
o
r
e
c
a
st
i
n
g
b
a
t
t
e
r
y
st
a
t
e
o
f
h
e
a
l
t
h
,
”
J
o
u
rn
a
l
o
f
Po
w
e
r
S
o
u
rc
e
s
,
v
o
l
.
3
5
7
,
p
p
.
2
0
9
–
2
1
9
,
J
u
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
p
o
w
s
o
u
r
.
2
0
1
7
.
0
5
.
0
0
4
.
[
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
,
“
L
o
n
g
sh
o
r
t
-
t
e
r
m
m
e
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
m
a
i
n
i
n
g
u
s
e
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,”
I
E
EE
T
r
a
n
s
a
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
.
7
,
p
p
.
5
6
9
5
–
5
7
0
5
,
Ju
l
.
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
]
Z.
W
a
n
g
,
S
.
Ze
n
g
,
J.
G
u
o
,
a
n
d
T
.
Q
i
n
,
“
R
e
ma
i
n
i
n
g
c
a
p
a
c
i
t
y
e
s
t
i
m
a
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
b
a
s
e
d
o
n
t
h
e
c
o
n
st
a
n
t
v
o
l
t
a
g
e
c
h
a
r
g
i
n
g
p
r
o
f
i
l
e
,
”
PLO
S
O
N
E
,
v
o
l
.
1
3
,
n
o
.
7
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
0
0
1
6
9
.
[
1
3
]
L.
Zh
a
o
,
Y
.
W
a
n
g
,
a
n
d
J.
C
h
e
n
g
,
“
A
h
y
b
r
i
d
me
t
h
o
d
f
o
r
r
e
m
a
i
n
i
n
g
u
s
e
f
u
l
l
i
f
e
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
w
i
t
h
r
e
g
e
n
e
r
a
t
i
o
n
p
h
e
n
o
m
e
n
a
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
9
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
9
0
9
1
8
9
0
.
[
1
4
]
J.
Z
h
o
u
,
D
.
Li
u
,
Y
.
P
e
n
g
,
a
n
d
X
.
P
e
n
g
,
“
D
y
n
a
mi
c
b
a
t
t
e
r
y
r
e
ma
i
n
i
n
g
u
s
e
f
u
l
l
i
f
e
e
st
i
m
a
t
i
o
n
:
a
n
o
n
-
l
i
n
e
d
a
t
a
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
,
”
i
n
2
0
1
2
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
I
n
st
r
u
m
e
n
t
a
t
i
o
n
a
n
d
M
e
a
s
u
rem
e
n
t
T
e
c
h
n
o
l
o
g
y
C
o
n
f
e
re
n
c
e
Pro
c
e
e
d
i
n
g
s
,
M
a
y
2
0
1
2
,
p
p
.
2
1
9
6
–
2
1
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
2
M
T
C
.
2
0
1
2
.
6
2
2
9
2
8
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
mp
r
o
vin
g
lith
iu
m
-
io
n
b
a
tter
y
r
elia
b
ilit
y
th
r
o
u
g
h
n
eu
r
a
l
n
etw
o
r
k
r
ema
in
in
g
u
s
efu
l life
…
(
B
r
a
h
im
Zr
a
ib
i
)
91
[
1
5
]
Y
.
Zh
a
n
g
,
R
.
X
i
o
n
g
,
H
.
H
e
,
a
n
d
Z.
L
i
u
,
“
A
LST
M
-
R
N
N
m
e
t
h
o
d
f
o
r
t
h
e
l
i
t
h
u
i
m
-
i
o
n
b
a
t
t
e
r
y
r
e
ma
i
n
i
n
g
u
s
e
f
u
l
l
i
f
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
1
7
Pr
o
g
n
o
s
t
i
c
s
a
n
d
S
y
st
e
m
H
e
a
l
t
h
M
a
n
a
g
e
m
e
n
t
C
o
n
f
e
re
n
c
e
(
PH
M
-
H
a
r
b
i
n
)
,
Ju
l
.
2
0
1
7
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
P
H
M
.
2
0
1
7
.
8
0
7
9
3
1
6
.
[
1
6
]
F
.
Zh
a
o
,
Y
.
L
i
,
X
.
W
a
n
g
,
L
.
B
a
i
,
a
n
d
T.
Li
u
,
“
L
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
s
t
a
t
e
o
f
c
h
a
r
g
e
p
r
e
d
i
c
t
i
o
n
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
u
s
i
n
g
R
N
N
s
-
C
N
N
s n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
9
8
1
6
8
–
9
8
1
8
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
6
2
2
5
.
[
1
7
]
M.
S
a
j
j
a
d
e
t
a
l
.
,
“
A
n
o
v
e
l
C
N
N
-
G
R
U
-
b
a
se
d
h
y
b
r
i
d
a
p
p
r
o
a
c
h
f
o
r
s
h
o
r
t
-
t
e
r
m
r
e
si
d
e
n
t
i
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
4
3
7
5
9
–
1
4
3
7
6
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
9
5
3
7
.
[
1
8
]
Z.
W
a
n
g
,
N
.
L
i
u
,
C
.
C
h
e
n
,
a
n
d
Y
.
G
u
o
,
“
A
d
a
p
t
i
v
e
se
l
f
-
a
t
t
e
n
t
i
o
n
LST
M
f
o
r
R
U
L
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
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
3
5
,
p
p
.
3
9
8
–
4
1
3
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
2
3
.
0
1
.
1
0
0
.
[
1
9
]
X
.
S
o
n
g
,
F
.
Y
a
n
g
,
D
.
W
a
n
g
,
a
n
d
K
.
-
L.
Ts
u
i
,
“
C
o
m
b
i
n
e
d
C
N
N
-
LST
M
n
e
t
w
o
r
k
f
o
r
st
a
t
e
-
of
-
c
h
a
r
g
e
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
i
e
s
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
8
8
9
4
–
8
8
9
0
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
6
5
1
7
.
[
2
0
]
A
.
S
a
x
e
n
a
,
B
.
B
o
l
e
,
M
.
D
a
i
g
l
e
,
a
n
d
K
.
G
o
e
b
e
l
,
“
P
r
o
g
n
o
s
t
i
c
s
f
o
r
b
a
t
t
e
r
i
e
s
--
a
g
i
n
g
e
x
p
e
r
i
m
e
n
t
s
a
n
d
mo
d
e
l
i
n
g
,
”
N
A
S
A
B
a
t
t
e
r
y
Wo
r
k
sh
o
p
,
2
0
1
2
.
[
2
1
]
D
.
Li
u
,
Y
.
L
u
o
,
Y
.
P
e
n
g
,
X
.
P
e
n
g
,
a
n
d
M
.
P
e
c
h
t
,
“
L
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
r
e
ma
i
n
i
n
g
u
sef
u
l
l
i
f
e
e
s
t
i
m
a
t
i
o
n
b
a
s
e
d
o
n
n
o
n
l
i
n
e
a
r
A
R
m
o
d
e
l
c
o
m
b
i
n
e
d
w
i
t
h
d
e
g
r
a
d
a
t
i
o
n
f
e
a
t
u
r
e
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
A
n
n
u
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
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
S
o
c
i
e
t
y
2
0
1
2
,
S
e
p
.
2
0
1
2
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
3
3
6
–
342
,
d
o
i
:
1
0
.
3
6
0
0
1
/
p
h
mc
o
n
f
.
2
0
1
2
.
v
4
i
1
.
2
1
6
5
.
[
2
2
]
Z.
X
u
e
,
Y
.
Zh
a
n
g
,
C
.
C
h
e
n
g
,
a
n
d
G
.
M
a
,
“
R
e
m
a
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
w
i
t
h
a
d
a
p
t
i
v
e
u
n
s
c
e
n
t
e
d
k
a
l
ma
n
f
i
l
t
e
r
a
n
d
o
p
t
i
m
i
z
e
d
s
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ssi
o
n
,
”
N
e
u
ro
c
o
m
p
u
t
i
ng
,
v
o
l
.
3
7
6
,
p
p
.
9
5
–
1
0
2
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
9
.
0
9
.
0
7
4
.
[
2
3
]
X
.
Zh
e
n
g
a
n
d
H
.
F
a
n
g
,
“
A
n
i
n
t
e
g
r
a
t
e
d
u
n
s
c
e
n
t
e
d
k
a
l
m
a
n
f
i
l
t
e
r
a
n
d
r
e
l
e
v
a
n
c
e
v
e
c
t
o
r
r
e
g
r
e
ssi
o
n
a
p
p
r
o
a
c
h
f
o
r
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
r
e
mai
n
i
n
g
u
sef
u
l
l
i
f
e
a
n
d
s
h
o
r
t
-
t
e
r
m
c
a
p
a
c
i
t
y
p
r
e
d
i
c
t
i
o
n
,
”
Re
l
i
a
b
i
l
i
t
y
E
n
g
i
n
e
e
ri
n
g
&
S
y
s
t
e
m
S
a
f
e
t
y
,
v
o
l
.
1
4
4
,
p
p
.
7
4
–
8
2
,
D
e
c
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
s
s.
2
0
1
5
.
0
7
.
0
1
3
.
[
2
4
]
J.
F
a
n
,
J.
F
a
n
,
F
.
Li
u
,
J
.
Q
u
,
a
n
d
R
.
L
i
,
“
A
n
o
v
e
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
l
i
-
i
o
n
b
a
t
t
e
r
y
p
r
o
g
n
o
s
t
i
c
a
n
d
h
e
a
l
t
h
man
a
g
e
me
n
t
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
6
0
0
4
3
–
1
6
0
0
6
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
4
7
8
4
3
.
[
2
5
]
J.
Q
u
,
F
.
Li
u
,
Y
.
M
a
,
a
n
d
J.
F
a
n
,
“
A
n
e
u
r
a
l
-
n
e
t
w
o
r
k
-
b
a
se
d
me
t
h
o
d
f
o
r
R
U
L
p
r
e
d
i
c
t
i
o
n
a
n
d
S
O
H
mo
n
i
t
o
r
i
n
g
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
7
1
7
8
–
8
7
1
9
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
5
4
6
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Br
a
h
im
Zr
a
i
b
i
re
c
e
iv
e
d
th
e
Li
c
e
n
se
'
s
D
e
g
re
e
in
e
lec
tro
n
ics
a
n
d
t
h
e
M
a
ste
r’s
De
g
re
e
in
El
e
c
tro
n
ics
,
El
e
c
tro
tec
h
n
ics
,
Au
t
o
m
a
ti
c
s,
a
n
d
In
d
u
strial
C
o
m
p
u
ti
n
g
fro
m
th
e
F
a
c
u
l
ty
o
f
S
c
ien
c
e
s
Ain
c
h
o
c
k
,
Ha
ss
a
n
II
Un
iv
e
rsity
,
Ca
sa
b
lan
c
a
,
M
o
ro
c
c
o
,
in
2
0
1
6
a
n
d
2
0
1
9
,
re
sp
e
c
ti
v
e
ly
.
He
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
in
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
e
x
a
c
tl
y
i
n
En
e
r
g
y
sto
ra
g
e
m
a
n
a
g
e
m
e
n
t
a
n
d
li
fe
sp
a
n
e
stim
a
ti
o
n
o
f
li
t
h
iu
m
-
i
o
n
b
a
tt
e
ries
b
y
m
a
c
h
in
e
lea
rn
i
n
g
(wi
th
Ho
n
s.)
fr
o
m
t
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
in
Be
rre
c
h
id
,
Ha
ss
a
n
F
irst
Un
iv
e
rsity
,
M
o
ro
c
c
o
,
in
2
0
2
3
.
His
re
se
a
rc
h
in
tere
sts
fo
c
u
s
o
n
t
h
e
li
fe
ti
m
e
e
stim
a
ti
o
n
o
f
li
t
h
iu
m
-
i
o
n
b
a
tt
e
ries
,
m
a
c
h
in
e
lea
rn
in
g
,
e
n
e
rg
y
c
o
n
v
e
rsi
o
n
,
a
n
d
e
n
e
rg
y
st
o
ra
g
e
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
.
z
ra
ib
i@u
h
p
.
a
c
.
m
a
.
Mo
h
a
m
e
d
Ma
n
so
u
r
i
re
c
e
iv
e
d
t
h
e
P
h
.
D.
d
e
g
re
e
in
M
e
c
h
a
n
ica
l
En
g
in
e
e
ri
n
g
a
n
d
En
g
i
n
e
e
rin
g
S
c
ien
c
e
s
fro
m
th
e
fa
c
u
lt
y
o
f
sc
ien
c
e
a
n
d
tec
h
n
o
lo
g
y
,
Ha
ss
a
n
F
irst
Un
iv
e
rsity
,
S
e
tt
a
t,
M
o
r
o
c
c
o
,
a
n
d
fr
o
m
L’I
NS
A,
Ro
u
e
n
,
F
ra
n
c
e
,
in
2
0
1
3
.
He
is
c
u
rre
n
tl
y
a
p
r
o
fe
ss
o
r
a
n
d
re
se
a
rc
h
e
r
a
t
th
e
N
a
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
in
Be
rre
c
h
id
,
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
Re
n
e
wa
b
le
En
e
rg
ies
,
Re
se
a
rc
h
Lab
o
ra
t
o
ry
o
f
An
a
ly
sis
a
n
d
M
o
d
e
li
n
g
o
f
S
y
ste
m
s
a
n
d
De
c
isio
n
S
u
p
p
o
rt,
a
n
d
h
e
a
d
o
f
t
h
e
re
se
a
rc
h
tea
m
o
f
M
o
d
e
li
n
g
a
n
d
sim
u
latio
n
o
f
M
u
lt
i
p
h
y
s
ics
sy
ste
m
s.
His
sc
h
o
la
rly
wo
r
k
h
a
s
p
ro
d
u
c
e
d
m
o
re
th
a
n
3
0
jo
u
rn
a
l
a
n
d
c
o
n
fe
re
n
c
e
p
u
b
li
c
a
ti
o
n
s.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
m
e
c
h
a
n
o
-
re
li
a
b
i
li
ty
st
u
d
y
,
i
n
d
u
strial
e
n
g
i
n
e
e
rin
g
,
o
p
ti
m
iza
ti
o
n
o
f
sh
a
p
e
a
n
d
re
li
a
b
il
it
y
o
p
t
imiz
a
ti
o
n
o
f
c
o
u
p
led
fl
u
id
-
str
u
c
tu
re
s
y
ste
m
s,
a
n
d
e
n
e
rg
y
st
o
ra
g
e
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
e
d
.
m
a
n
so
u
ri@
u
h
p
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.