Scribd
Upload
7 views

Genetic Algorithm

genetic algorithm of

Uploaded by

Abesha Kassie
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views

Genetic Algorithm

genetic algorithm of

Uploaded by

Abesha Kassie
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Genetic algorithm

The Darwinian evolutionary theory's natural evolution process is imitated by the genetic
algorithm and it is an optimization engine. University of Michigan Professor John Holland first
came up with the idea of genetic algorithm (H. N. Ghafil and K. Jármai, 2020).
DNA, which refers to the same idea in biological individuals, is the mathematical representation
of the individual process parameter values in the algorithm. DNAs store each individual’s unique
information, which provide the output features. Solution space refers to the collection of all
feasible solutions (DNAs) to an optimization issue. Multiple chromosomes can be found in each
DNA to present various properties. The chromosome is thought of as a mathematical expression
where each number represents a gene. The objective of optimization is to provide an output with
a gene composition that will maximize their performance. Initialization, Evaluation, Selection,
Crossover and Mutation or Recombination are the five main GA phases.
Initialization is the first step in the procedure. The initialized population [1] is produced during
this stage. The performance response parameters of each string are assessed. The individual is
assigned a fitness score and a chance of survival based on their performance. Then, selection is
carried out depending on each outputs chance of surviving. After the selection process, some of
the population can join the mating pool. The individuals in this mating pool then exchange traits
with one another, which results in crossover, which creates offspring P' with a mixture of
features from the mating pool. The following generation [𝑘+1] after the 𝑘𝑡ℎ generation is made
up of this group of kids along with additional freshly generated random outputs. The loop repeats
in this trend. To complete the optimization a stopping requirement should be met, by either the
maximum number of iterations is reached or the convergence of the results.
Using genetic algorithm to optimize the problem in hand, each individual i.e., rotational speed,
welding speed, tilt angle, axial force, tool rotational speed, tool traverse speed, depth tool tip, tool pin
profile are coded mathematically. This GA method was implemented using computer MATLAB
programming. The GA optimization is done for all outputs with the following MATLAB
programming generated code and solver, and it is presented as follow:

You might also like