Professional Documents
Culture Documents
can be non .
linear function
• y is a scalar measurement
Marco Lovera
The output-error method
Measurement model:
• Measurement equation:
From
deterministic value Is affected
( only
the expected value by error )
=
-
•
mean variance
• at different time
ewicorrelodeol
instant
one
random number Gowmoin
Joan be a function of K
Marco Lovera
The output-error method
A
Y ym
:
Ym
,
• Therefore
this must
xxx
be proven
Marco Lovera
The output-error method
/ ¥
www.t.mudemt from Vol
It
• Therefore =o?
}
eevysjiaf
H
they are uncorrelated
Marco Lovera
The output-error method
• Block diagram:
Marco Lovera
The output-error method
Marco Lovera
The output-error method
Kent linear
if it in put of non system
compute min
it is not possible to
need to do it
in closed form ,
we
numerically
Marco Lovera
The output-error method
we have that
& t
measurement between true and model
error
discrepancy system
• Therefore if then
and the cost converges to
initially
Consider a starting value for the parameter and a
perturbation
we get
vector to
matrix & to
vector
Marco Lovera
An optimization scheme for the OE method
Marco Lovera
An optimization scheme for the OE method
is reached.
Marco Lovera
An optimization scheme for the OE method
Marco Lovera
An optimization scheme for the OE method
Recall that
and therefore
problem to
compute
0
Marco Lovera
An optimization scheme for the OE method
. to
Marco Lovera
An optimization scheme for the OE method
Marco Lovera
An optimization scheme for the OE method
£9
'
( r ÷ 5 %)
Marco Lovera
An optimization scheme for the OE method
Marco Lovera
An optimization scheme for the OE method
linear model
to more useful for
The analytical approach, on the other hand, starts from the
model equations:
ni
no condition if we want
include I. C.
to
.
parameters
into the
estimated
to be
is function
and note that
.
given
-
Marco Lovera
An optimization scheme for the OE method
Marco Lovera
Local and global minima
an
parameters.
←hfi•V
o¥'i→V←
0*0
' =/ GLOBAL MINIMUM LOCAL MINIMA
point
'
! ,
,
.
Oo
Marco Lovera
10/10/17
where
Crowner Rae bound
to
function of logl
for Gaumoin
Marco Lovera
Asymptotic variance of the OE estimates
.
MY
doll approximation
|g=g*
this quantity
•
in
given for free from our IAMTWE SCHEME ALGORITHM
•
Jloie Joy +
Yoel a. so +sotffIy*so
do
conditioning !!
:
Marco Lovera M
Asymptotic variance of the OE estimates
Marco Lovera
Confidence intervals for the estimates
• Therefore, asymptotically
*
Marco Lovera
Confidence intervals for the estimates
m *
an *
Marco Lovera
Multiple output case
k
R matrix
pxp
Marco Lovera
Multiple output case
Yp
different sensors)
.int#FEHt*E.H
measurements (subvectors of the output provided by
→ a .
,wI
→
3Yn
Yz ( ) Q accelerometer
vector of seampeneuts
→
yq
Marco Lovera
Multiple output case
Marco Lovera
Multiple output case
Marco Lovera
Multiple output case
where
↳ Rii
J ÷i
÷1 e. ÷r → .
yn
→
-3
÷ to
Yz →
- ' 2
ez÷
-6
-6 → is
J3÷ro
÷ eo
y , he you
J=Jn+@
-
don't
we want to minimise care
he
of J3
N .B .
variance
Marco Lovera lmegbgiblejn )
becomes
532=0032
\ YJ =
CYs ⇐
10+6
{ t.tt#geuenPampaterghnY.oEa
no not .
this may lotnnfnskityd
llowlta
loss of
Multiple output case
• Finally, the gradient and the hessian of the cost ans the
Fischer information matrix can be generalised as
Marco Lovera
MATLAB FILE : oe .
example .m
a= . a b= -2
S
ftp.axotxbm
S e Mlo )
,
O=[ F)
Ts =
goes nowupluig interval
with 99,7%
µH= senlt ) + sentst ) + senlst )
to the words
? We have to estimate a ,b
^)
Is a well posed problem ? -
structural uibntifrability Is
guaranteed because of its features
otherwise Gcsk
¥ →
identifiable
-
look at the input also
( use 2000-3000-4000
for deval samples nomore
)
y=ao)x+Dlo)n force
Fade
DI
=H9s¥oj +
°ff0÷x + 3Bo÷Pn because Tfg=o ( u applied externally Admit )
(¥¥=° depend O on
mafn
guitars go that onbe amputee *
A
.# :] →
FF 't : :]
'
H÷=aaEgts¥x+so÷u
Now these model we need to solve to compute wuntivitis Is linear
mmulaton
mutinies
nommalx
Mo + L
in
for LH
£ to get
tout