|






     

| 
 |

Mr. VIDYA BHASKAR a Kunwar Pratap Singh Rana
SHUKLA a Surendra Kumar
a Dharmesh Verma
a Kapil Verma
a Jitendra Kumar
 |   
Ñ ›he aim of this project is to design a plant
using Genetic Algorithm.
Ñ ›he objective of this project is to show that by
employing the GA method of tuning a plant,
an optimization can be achieved.
 !
Ñ PID controller consists of Proportional Action,
Integral Action and Derivative Action. It is
commonly refer to Ziegler-Nichols PID tuning
parameters. It is by far the most common
control algorithm
Ñ PID controllers algorithm are mostly used in
feedback loops.
 rhat is genetic algorithm
Ñ Genetic Algorithms (GA.s) are a stochastic global search
method that mimics the process of natural evolution. It is
one of the methods used for optimization
Ñ ›here are three main stages of a genetic algorithm, these
are known as R
R
R R

 
Ñ During the R
R

 

 
 



R

assessed. ›his value is used in the selection
process to provide bias towards fitter individuals. Just like
in natural evolution, a fit chromosome has a higher
probability of being selected for reproduction.
Ñ mnce the selection process is complete, the
R R
R

  
›he crossover
operations swaps certain parts of the two
selected strings in a bid to capture the good
parts of old chromosomes and create better
new ones
Ñ GA. 2 


  
R 

 R 


 


string position.
 mverview
Î PID controller
Î Genetic Algorithms
å A solution of reduction computation time
Î Summary of work
Î Conclusions

6
 PID controller
Î Controller structure

Î Control law
 r ù l ‰  ‰
‰

ù l ‰  ‰  ù‰  ‰ 
 

 r


Î 6 variables to tune 
ÿ  ÿ  r ÿ ÿ  ÿ

7
 rhy Genetic Algorithms?
 




 


0
 0  

 0  0  
 
 
 
  
 

      


u







 ‰ 


 
‰ 


  l |    ÿ r
ÿ 
ÿ 
ÿ 

ÿ

$
Lmr CHAR›
 Direct the GA
Î GA optimisation problem

  l | l |`    rÿ ` G
Î Penalty factors on gain and phase
margins
R R

 

 
|`

|u

R
R

  R
R R R R
R R R
u
r  `

r   

>
 Summary of work

Î A solution to speed up the GA optimisation

Î ›he two degree of freedom controller well
performs for systems such as: stable, inverse
unstable, non-minimum phase, integrating
long time-delay.
Î Model uncertainty has not been discussed.

>>
 Conclusions
Î None of the proposed methods performs
significantly better.
Î ›he fourth design directly penalises the
impact of the high frequency measurement
noise on the closed-loop system.
Î ›he GA with look up table significantly
reduced the computation time.

>

›