Académique Documents
Professionnel Documents
Culture Documents
Neural Networks
Lecture 9: Designing Controller Using
Neural Networks
H.A. Talebi
Farzaneh Abdollahi
Neural Networks
Lecture 9
1/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Neural Networks
Lecture 9
2/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Considering reference
signal r
y = f 1 fr = r
Neural Networks
Lecture 9
3/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
NN in Control Feedback
BP can
1
e = r y , E = e2
2
E
4wij =
wij
I
Neural Networks
Lecture 9
4/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
y
u
Lecture 9
5/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
NN in Control Feedback
I
I
y
u
is not available!!
y
Then apply
instead of y
.
u
u
This method is so-called Gradient Through The Model of The Plant
y
2. Approximate y
u with sign{ u } which is usually available without knowing
the dynamics
I
Neural Networks
Lecture 9
y
u
can be
6/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
i
Ci dv
j=1 g (f (v )) vi .
dt = vi
Neural Networks
Lecture 9
7/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
x R n, u R p
(N+1)n+p ,
Define
v = (x0 , x1 , ..., xN , u) R
A I
0 0 . . . 0 0 B
0 ... 0
0
0 A I
0
.
.
.
0
0
0
B
.
.
.
0
0
0
0 A I . . . 0 0 0
0 ... 0
0
= .
.
.
.
.
.
..
.
.
.
.
.
..
..
.. . .
..
..
..
..
..
..
..
.
0
0
0 0 ... I
0 0
0 . . . B
0
0
0
0 0 . . . A I
0
0 . . . 0 B
The problem can be defined as minv J s.t. v = 0
Neural Networks
Lecture 9
8/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
c
ij
j
i
j=1
i=1
i=1
Our problem can be presented as
P(N+1)n+p
minv J subject to f (vi ) = j=1
aij vj 0 for i = 1, ..., Nn + 1
A
I
0 A
0
0
..
..
.
.
0
0
0
0
T
0
I
A
..
.
0
0
I
..
.
...
...
...
..
.
0
0
0
..
.
0
0
0
..
.
B
0
0
..
.
0
B
0
..
.
...
...
...
..
.
0
0
0
..
.
0 ...
I
0
0
0
. . . B
0 . . . A I
0
0
...
0
. . . 1 T T . . . T
P
Pn
Pn
T
I = (T 1), = ( n ai1 ,
ai2 , ..., i=1
i=1
i=1
P
P
Pan in ) , T
n
n
T
1 = (1, 1, . . . , 1) , = ( i=1 bi1 ,
i=1 bi2 , ...,
i=1 bin )
0
0
Neural Networks
Lecture 9
0
0
0
..
.
B
T
9/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
fi
vi
= aij
Pn
i = ln + 1, ..., (l + 1)n,
l = 0, ..., N 1
J
Pn
vi =
s
v
i
=
Nn
+ 1, ..., (N + 1)n
iNn,j
Nn+j
Pn j=1
r
v
i
=
(N
+
1)n
+ 1, ..., (N + 1)n + p
i(N+1)n,j
(N+1)n+j
j=1
qij , sij , rij are elements of Q, S, R respectively
Neural Networks
Lecture 9
10/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Neural Networks
Lecture 9
11/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
The model of the plant is identified first and the parameters of the controller
is defined based on identified model
Neural Networks
Lecture 9
12/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Neural Networks
Lecture 9
13/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example [2]
f (.) is unknown
r (k) = sin( 2k
25 ): a bounded reference input
Neural Networks
Lecture 9
14/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example Contd
Since the plant is unknown, assuming the unforced system is stable, f (.)
is estimated by series parallel NN identifier as f(.)
Hence u(k) = f[yp (k), yp (k 1)] + 0.6yp (k) + 0.2yp (k 1) + r (k)
Neural Networks
Lecture 9
15/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example Contd
I
The time interval Ti and Tc for updating the identification and control
parameters should be chosen wisely.
Neural Networks
Lecture 9
16/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example Contd
I
Ti = Tc = 1
Neural Networks
Lecture 9
17/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example Contd
I
Choose Ti = Tc = 10
Neural Networks
Lecture 9
18/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 2 [2]
I
Reference model:
ym (k + 1) = 0.32ym (k) + 0.64ym (k 1) 0.5ym (k 2) + r (k)
r (k) = sin( 2k
25 ): a bounded reference input
Neural Networks
Lecture 9
19/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 2 Contd
I
The control signal is: u(k) = 1 [fk [yp (k), yp (k 1), yp (k 2)]
0
Choose Ti = Tc = 10
Neural Networks
Lecture 9
20/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 3 [2]
The system is nonminimum phase (it has zero out of unit circle)
Neural Networks
Lecture 9
21/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 3 Contd
I
Neural Networks
Lecture 9
22/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
I
I
uc = (
ya ) + K1 (y r y a ) + K0 (yr ya ) is conventional FB controller
un = f (x, x)
Neural Networks
un = f
Lecture 9
23/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
f
The learning rule is w = w
uc
Neural Networks
Lecture 9
24/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 [3]
Consider
one-link
flexible arm:
, )
+ F1 + fc
h1 (,
u
M() +
=
h2 (, ) + K + F2
I
I
I
I
I
I
I
: hub angle
: deflection variable
h1 and h2 are Coriolis and Centrifugal forces, respectively
M(): P.D. inertia matrix
u: torque
F1 : viscus damping; F2 damping matrix;
fc hub friction; K stiffness matrix
Neural Networks
Lecture 9
25/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 Contd
I
I
I
I
I
m()
1.0703 0.0282
1.6235 0.4241 ;
M() = 1.0703
0.0282 0.4241
2.592
2
2
m() = 0.9929 + 0.12(1 + 2 ) 0.241 2
17.4561
0
K=
0
685.5706
, )
= 0.24[(
1 2 )1 (1 2 )2 ]
h1 (,
0.122 (1 2 )
h2 (, ) =
0.122 (2 1 )
4.74 > 0
fc = Ccoul ( 1+e210 1); Ccoul =
4.77 < 0
Neural Networks
Lecture 9
26/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 Contd
The NN structure:
I
K0 = 1; K1 = 2
Neural Networks
Lecture 9
27/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 Contd
Neural Networks
Lecture 9
28/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 Contd
Neural Networks
Lecture 9
29/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
Example 4 Contd
Neural Networks
Lecture 9
30/31
Outline Open-Loop Inverse Dynamics NN in Control Feedback Optimal Control Using Hopfield Adaptive Control Using Neural Ne
References
Neural Networks
Lecture 9
31/31