/
Tariq Ahamed Tariq Ahamed

Tariq Ahamed - PowerPoint Presentation

myesha-ticknor
myesha-ticknor . @myesha-ticknor
Follow
391 views
Uploaded On 2016-06-11

Tariq Ahamed - PPT Presentation

Wavelet Neural Control Of Cascaded Continuous Stirred Tank Reactors AIM The main objective of the project is to control the concentration of reactant in the CSTR The tank is controlled by manipulating the coolant flow rate ID: 358101

rate sec load time sec rate time load settling network neural reactor flow coolant wnn imc concentration peak energy

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "Tariq Ahamed" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Slide1

Tariq Ahamed

Wavelet Neural Control Of Cascaded Continuous Stirred Tank ReactorsSlide2

AIM

The main objective of the project is to control the concentration of reactant in the CSTR.

The tank is controlled by manipulating the coolant flow rate.

The system is subjected to step changes and load disturbances and the responses by different controllers are noted.Slide3

CSTR- Model

C

A0

Input= Coolant Flow rate (L/min) : q

c

= u;

States: Concentration of A in Reactor #1 (mol/L) : C

a1

= y(1);

Temperature of Reactor #1 (K) : T

1

= y(2);

Concentration of A in Reactor #2 (mol/L) : C

a2

= y(3);

Temperature of Reactor #2 (K) : T

2

= y(4);Slide4

The component balance

Rate of flow of

‘A’ in

Rate of flow of

‘A’ out

Rate of change

of ‘A’ caused by

chemical

reaction

Rate of change

of ‘A’ inside the

tank

Where, q= inlet feed rate

C

af

= feed concentration of A

V

1

= volume of reactor 1

= pre exponential factor for A->B

E/R= Activation energy Slide5

The energy balance

Rate of flow of

energy into

CSTR

Heat removal through energy jacket

Rate at which

energy is

generated due

to chemical

reaction

Rate of change

of liquid energy

Where, Feed Temperature (K) :

T

f

Coolant Temperature (K) :

T

cf

Overall Heat Transfer Coefficient : U

A1

Heat of Reaction: dH Density of Fluid (g/L): rho

Density of Coolant Fluid (g/L): rhoc Heat Capacity of Fluid (J/g-K): Cp Heat Capacity of Coolant Fluid (J/g-K): C

pcSlide6

Controller Design

PID controller

Direct Inverse Controller

Internal Model Controller

The neural controllers are also modeled in Wavelet Network.Slide7

PID control

The differential form of PID control is given as:

e= C

req

- C

a

(t)

And e

k-1

and e

k-2 are past values of error.

Steady state initial conditions are given.Required concentration of A in reactor 2 is givenSlide8

Parameters

Cohen Coon method was used to arrive at the following values of

K

p

,

K

i and Kd

.

K

i

= 304.9508 sec-1Kp= 10.628

mol/L/secKd= 0.0005907 secSlide9

Graph for multiple set point tracking.

Rise Time (sec)

Peak Overshoot

Settling Time (sec)

Offset

Values

23

0

74

0Slide10

Neural Network Training

A chirp signal (coolant flow rate) is given as input to the Continuous Stirred Tank Reactor and output (concentration of A) is taken.

This pattern is divided in the columns of past inputs, past outputs, present output and required output.

The training of the network is done by feeding the feed forward net with the pattern and adjusting the weights until the error is reduced.

The training uses Levenberg Marquardt algorithm.Slide11

ANN based DIC

The neural network consisted of 3 layers with 9 sigmoidal neurons in the hidden layer. The learning rate was 0.3.

Activation function- tansigSlide12

Rise Time (sec)

Peak Overshoot

Settling Time (sec)

Offset

Load disturbance settling (Load given for 150 sec)

Values

5

0.00004

25

0

171Slide13

ANN based IMC

The inverse network was same as the Direct Inverse Controller network.

The forward network had 1 input, 1 hidden layer with 4 neurons and 1 output.

The learning rate was 0.01.

Activation function- tansigSlide14

Rise Time (sec)

Peak Overshoot

Settling Time (sec)

Offset

Load disturbance settling (Load given for 150 sec)

Values

14

0

24

0

16Slide15

Training the neural controllers using Wavelet Neural Network

Shannon Filter

whereSlide16

WNN based DIC

The inverse neural model here consisted of 5 inputs, 1 hidden layer with 7

shannon

neurons and 1 output. The learning rate was 0.064.

Rise Time (sec)

Peak Overshoot

Settling Time (sec)

Offset

Load disturbance settling (Load given for 150 sec)

Values

3

0.000136

24

0

167Slide17

WNN based IMC

The forward model had 3 inputs, 1 output and 1 hidden layer with 5

shannon

neurons with the learning rate of 0.01.

Rise Time (sec)

Peak Overshoot

Settling Time (sec)

Offset

Load disturbance settling (Load given for 150 sec)

Values

14

0

22

0

14Slide18

Results

Controller

Rise Time (sec)

Peak Overshoot

Settling time (sec)

Offset (mol/L)

Load disturbance settling (Load given for 150 sec)

PID

23

0

74

0

-

DIC50.00004

250171

IMC140240

16DIC-WNN3

0.000136240167

IMC-WNN140

22014Slide19

ANN- DIC

WNN- DIC

ANN- IMC

WNN- IMC