Mutation

Two kinds of mutation strategies are applied. First mutation strategy is to exchange two operations selected randomly in a chromosome. The probability of applying Mutation

Strategy is explained as Pm₁. After applying Mutation strategy, the constraint adjustment algorithm has to be applied to function on the created populations to adjust them to the feasible domain. The second mutation strategy is first randomly to find out an operation in a chromosome. From the candidate lists, a set of machine, TAD and tool is then randomly selected to replace the set of machine, TAD and the tool being utilized in the operation. The possibility of applying this strategy is explained as Pm₂.

For m generations, steps (2-5) are repeated.

The pseudo-code of genetic algorithm for implementing this, in specified process planning problem is given in Programme no.3.

Step 1: Parameter setting      

 1.1:   Number of generations: max_gen

1.2:      Population size: pop_size

1.3:   crossover possibility: pc

1.4:      Mutation possibility: pm

1.5:   recent generation: gen = 0

Step 2: Coding of all solution

An integer coding of all solution set is complete

Step 3: Selection mechanism

Step 3.1: A roulette wheel selection is completed for selecting best candidates.

// it will happen as per to Programme no.2

Step 3.2: Generate initial solution and determine initial fitness for each set of chromosomes

Step 3.3: get the minimum fitness in between the set of chromosomes and assign best = fitness.

Step 4: Genetic exchange over

Step 4.1: Crossover implementation  // as illustrated in Programme no.2

Step 4.2: Mutation implementation

Step 4.3: Satisfy the constraints and penalize the infeasible one.

Step 5: determine the fitness of each chromosom of the population set.

Step 5.1: choose the best set of chromosomes of that generation and carry them for next generation. Now allocate

best = fitness

Step 6: Updation :

Step 6.1: Replace the existing chromosomes together with the chromosomes of best fitness generated

Step 6.2: gen = gen + 1

Step 7: Check

if (gen < max_gen)

goto Step 3. else

Output the best solution or greatest and desired objectives.

Programme no.3: Algorithmic Steps in Perspective to the Problem