Information Technology Reference
In-Depth Information
Fig. 3.3
Pilot plant of the department of system engineering and automatic control of University
of Seville
dC
A
dt
F
f
V
(
k
0
e
−
E
/(
RT
)
C
A
=
C
A
,
in
−
C
A
)
−
(3.42)
where
T
is the temperature into the reactor,
T
j
,
in
the inlet temperature of the cooling
jacket fluid,
C
A
denotes the reactant concentration in the reactor. The other variables
and parameters can be seen in Table
3.1
.
Using real data, the system can be modeled by a Neurofuzzy System. Being it
a discrete model, in order to capture the dynamics of the system, two input vari-
ables have been chosen: The valve position (
V
(
−
)
k
1
) and the previous sampled
Temperature (
T
). In Fig.
3.5
,the
membership functions are depicted. Using a training learning method, we obtain the
following rules:
(
k
−
1
)
). The output is the actual temperature (
T
(
k
)
•
if
T
(
k
−
1
)
is LOW and
V
(
k
−
1
)
is LOW
then
T
(
k
)
=
1
.
0045
T
(
k
−
1
)
+
0
.
0005
V
(
k
−
1
)
−
0
.
0898
•
if
T
(
k
−
1
)
is LOW and
V
(
k
−
1
)
is HIGH
then
T
(
k
)
=
1
.
0006
T
(
k
−
1
)
+
0
.
0005
V
(
k
−
1
)
−
0
.
0571
Search WWH ::
Custom Search