Dynamic Neural Network Control DNNC: A NonConventional Neural Network Model

1
Dynamic Neural Network Control (DNNC) A
Non-Conventional Neural Network Model
Masoud Nikravesh EECS
Department, CS Division
BISC Program University of
California Berkeley,
California Abstract In this study, Dynamic
Neural Network Control methodology for model
identification and control of nonlinear processes
is presented. The methodology uses
several techniques Dynamic Neural Network
Control (DNNC) network structure, neuro-statistica
l (neural network non-parametric statistical
technique such as ACE Alternative Conditional
Expectation) techniques, model-based
control strategy, and stability analysis
techniques such as Liapunov theory. In
this study, the DNNC model is used because it is
much easier to update and adapt the network
on-line. In addition, this technique in
conjunction with Levenberge-Marquardt algorithm
can be used as a more robust technique for
network training and optimization purposes. The
ACE technique is used for scaling the networks
input-output data and can be used to find the
input structure of the network. The result from
Liapunov theory is used to find the optimal
neural network structure. In addition, a special
neural network structure is used to insure the
stability of the network for long-term
prediction. In this model, the current
information from the input layer is presented
into a pseudo hidden layer. This model minimizes
not only the conventional error in the output
layer but also minimizes the filtered value of
the output. This technique is a tradeoff
between the accuracy of the actual and filtered
prediction, which will result in the stability of
the long-term prediction of the network model.
Even though, it is clear that DNNC will perform
better than PID control, it is useful to compare
PID with DNNC to illustrate the extreme range of
the non linearity of the processes were used in
this study. The integration of the DNNC and
the shortest-prediction-horizon nonlinear
model-predictive control is a great candidate for
control of highly nonlinear processes including
biochemical reactors.
References 1. M. Nikravesh, A. E. Farell, T. G.
Stanford, Control of Nonisothermal CSTR
with time varying parameters via dynamic neural
nework control (DNNC), Chemical Engineering
Journal, vol. 76, 2000, pp. 1-16. 2. M.
Nikravesh, Artificial neural networks for
nonlinear control of industrial processes, "
Nonlinear Model Based Process Control", Book
edited by Ridvan Berber and Costas Karavaris,
NATO Advanced Science Institute Series, Vol 353,
1998 Kluwer Academic Publishers, pp. 831-870 3.
S. Valluri, M. Soroush, and M. Nikravesh,
Shortest-prediction-horizon nonlinear model-predic
tive control, Chemical Engineering science, Vol
53, No2, pp. 273-292, 1998.
2
Dynamic Neural Network Control (DNNC) A
Non-Conventional Neural Network Model Masoud
Nikravesh EECS Department, CS Division BISC
Program University of California Berkeley,
California
3
Dynamic Neural Network Control (DNNC)

• Introduction
• Theory
• Applications and Results
• Conclusions
• Future Works

4
(No Transcript)
5
IMC
d
ysp

u
y
w
e

P
Q

-
d

-
P
y
6
Modified IMC, Zheng et al. (1994)
d
ysp

u
y
w1
e

w

P
Q1

-
-
w2
d

-
P
Q2
y
To address integral windup.
7
Non-linear model state-feedback control structure
d
ysp

u
y
w1
e

w

P
Q1

-
-
w2
d
P

-
Q2
x
h(x(t-?)
xf(x)g(x) u
y
8
On-Line Adaptation
9
(No Transcript)
10
Controller
CA
CA
Trajectory
Trajectory
qc
CA
Model
Setpoint
Setpoint
Filter
Filter
11
Model Predictive Control
Y
ai
Time
i
12
  k discrete time y(k)
model output u(k) change in the
input (manipulated variable) defined as u(k)-
u(k-1) d(k) unmodelled
disturbance effects on the output ai
unit step response coefficients N
number of time intervals needed to describe the
process dynamics (Note ) ym(k)
current feedback measurement y (kj)
predicted output at kj due to input moves up
to k. In the absence of any
additional information, it is assumed that  
13
(No Transcript)
14
The Backpropagation Neural Network
15
Comparing DMC with the neural network, the
following analogy may be drawn,  
16
The DNNC Process Model
17
The DNNC Process Model
18
State-Space Representation of DNNC
19
State-Space Representation of DNNC
20
State-Space Representation of DNNC
21
Stability of the DNNC Process Model
22
DNNC Controller
23
Stability of the DNNC Process Model
24
Stability of the DNNC Process Model
25
Extension of the DNNC Model to the MIMO Case in
IMC Framework
26
Neuro-Statistical Model
27

28
 

29
Upper
Mean
Actual
MPV
Lower
30


31
(No Transcript)
32
(No Transcript)
33
Typical multi-layer DNNC process model.

34
Alternative Conditional Expectation
Y
X
?(Y)
?(X)
35
NN Prediction


No. Epochs 5 No. Hidden Nodes 1  
No. Epochs 200 No. Hidden Nodes 10  
36
(No Transcript)
37
Typical multi-layer DNNC process model.

38
Controller
CA
CA
Trajectory
Trajectory
qc
CA
Model
Setpoint
Setpoint
Filter
Filter
39
Process Model
?c (t) exp ( - ? t ).
?h(t) Fouling coefficient ?c(t) Deactivation
coefficient CA effluent concentration, the
controlled variable qc coolant flow rate, the
manipulated variable q feed flow rate,
disturbance CAf feed concentration Tf feed
temperatures Tcf coolant inlet temperature
40
(No Transcript)
41
(No Transcript)
42
(No Transcript)
43
(No Transcript)
44
(No Transcript)
45
(No Transcript)
46
(No Transcript)
47
(No Transcript)
48
(No Transcript)
49
(No Transcript)
50
(No Transcript)
51
(No Transcript)
52
(No Transcript)
53
(No Transcript)
54
(No Transcript)
55
(No Transcript)
56
(No Transcript)
57
Conclusions

• The DNNC strategy differs from previous neural
  network controllers because the network structure
  is very simple, having limited nodes in the input
  and hidden layers.
• As a result of its simplicity, the DNNC design
  and implementation are easier than other control
  strategies such as conventional and hybrid neural
  networks.
• In addition to offering a better initialization
  of network weights, the inverse of the process is
  exact and does not involve approximation error.
• DNNCs ability to model nonlinear process
  behavior does not appear to suffer as a result of
  its simplicity.
• For the nonlinear, time varying case, the
  performance of DNNC was compared to the PID
  control strategy.
• In comparison with PID control, DNNC showed
  significant improvement with faster response time
  toward the setpoint for the servo problem.
• The DNNC strategy is also able to reject
  unmodeled disturbances more effectively.
• DNNC showed excellent performance in controlling
  the complex processes in the region where the PID
  controller failed.
• It has been shown that the DNNC controller
  strategy is robust enough to perform well over a
  wide range of operating conditions.

58
IMC
d
ysp

u
y
w
e

P
Q

-
d

-
P
y
59
Modified IMC, Zheng et al. (1994)
d
ysp

u
y
w1
e

w

P
Q1

-
-
w2
d

-
P
Q2
y
To address integral windup.
60
Non-linear model state-feedback control structure
d
ysp

u
y
w1
e

w

P
Q1

-
-
w2
d
P

-
Q2
x
h(x(t-?)
xf(x)g(x) u
y
61
Future Works

• The integration of the DNNC and the
  shortest-prediction-horizon nonlinear
  model-predictive
• No assumption regarding the uncertainty in input
  and output
• Use of fuzzy logic techniques.