Beruflich Dokumente
Kultur Dokumente
Thomas F. Edgar
Department of Chemical Engineering
University of Texas
Austin, TX 78712
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 1
Outline
Static model, sequential estimation
Multivariate sequential estimation
Example
Dynamic discrete-time model
Closed-loop estimation
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 2
Least Squares Parameter Estimation
k
min
a ax
i 1
y
i i
* 2
(1)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 3
Simple Example
1
k
2 k
*
ak xi xi yi (2)
14
i 1
2 43 14i 1
2 43
pk bk
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 4
Sequential or Recursive Form
To update ak based on a new data pt. (yi , xi), in Eq. (2) let
k
pk 1
xi 2 pk 11 xk 2 (3)
i 1
and k
bk xi y i * bk 1 xk y k * (4)
i 1
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 5
Recursive Form for Parameter Estimation
ak ak 1 K k xk ak 1 y k * (5)
1 44 2 4 43
estimation error
where
1
K k pk 1xk 1 pk 1xk 2
(6)
1
pk pk 1 p k 1
2
xk 1 pk 1xk
2 2
(7)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 6
Estimating Multiple Parameters
(Steady State Model)
T
y x a a1x1 a2 x2 L an x n (8)
2
min k
i
a i 1
xT
a y i
*
(non-sequential solution requires
n x n inverse)
1 1 T
Pk P k 1 x k x k (9)
B k B k 1 x k y k * (10)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 7
Recursive Solution
1
T T
a k a k 1 P k 1 x k 1 x k P k 1 x k x k a k 1 y k * (11)
1 4 4 4 4 2 4 4 4 43 1 4 4 2 4 43
Kk estimation
error
1
P k P k 1 P k 1 x k 1 x k P k 1 x k
T T
x k P k 1 (12)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 8
Simple Example (Estimate Slope & Intercept)
Linear parametric model
input, u 0 1 2 3 4 10 12 18
output, y 5.71 9 15 19 20 45 55 78
y = a1 + a2 u
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 9
Sequential vs. Non-sequential Covariance Matrix vs. Number
Estimation of a2 Only (a1 = 0) of Samples Using Eq. (12)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 10
Sequential Estimation of a1 and a2 Using Eq. (11)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 11
Application to Digital Model and Feedback Control
y (t ) a1y (t 1) a2 y (t 2) L an y (t n )
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 12
Recursive Least Squares Solution
y (t ) T (t 1) (t 1) (t ) (14)
where
T (t 1) [ y (t 1), y (t 2),. . . y(t n ),
u(t 1 N ),. . . u(t r N ), 1]
T (t 1) [a1, a2 ,. . . an , b1, b2, . . . br , d ].
min t 2
14 (4i 441)2(i4) 4y4(i )43
T
(15)
i 1
"least squares"
(predicted value of y)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 14
Recursive Least Squares Solution
T (t 1)P (t 1) (17)
P (t 1) (t 1)
K (t ) (18)
1 T (t 1)P (t 1) (t 1)
P (t ) [I K (t ) T (t 1)]P (t 1) (19)
(t ) (t 1) K (t )[ y (t ) y (t )] (20)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 15
Closed-Loop RLS Estimation
- covariance resetting
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 16
Enhance sensitivity of least squares estimation algorithms
with forgetting factor
t 2
J ( (t )) t i T (i 1) (i ) y (i ) (21)
i 1
1
P (t ) [P (t 1) P (t 1) (t 1)[ T (t 1)P (t 1) (t 1) ] 1.
T (t 1)P (t 1)] (22)
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 17
Closed-Loop Estimation (RLS)
Perturbation signal is added to process input (via set point)
to excite process dynamics
large signal: good parameter estimates
but large errors in process output
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 18
3. use PRBS perturbation signal only when
estimation error is large and P is not small.
Vary PRBS amplitude with size of elements
proportional to tr (P).
4. P(0) = 104 I
Thomas F. Edgar (UT-Austin) RLS Linear Models Virtual Control Book 12/06 19