Univ aixfr abstract this paper shows that small

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: zation, in this case, the IT grades. A chromosome vector, vi = [IT1, IT2,. . . , ITn] or a binary string can be used as codes. Then, crossover is allowed between IT grades or segments of binary string for same process in different genes at certain probability. Random mutation produces spontaneous random changes in various chromosomes by changing some binary bits from ‘0’ to ‘1’ or reversely. This allows the algorithm to overcome local maxima. Selection based on cost function should direct the search toward promising regions. The fitness for every chromosome is evaluated with the assumption that the lower the manufacturing cost, the higher the fitness. Penalty functions are applied to any infeasible assignment plans. Figure 2 depicts this entire process. Generate population Evaluate fitness Crossover, mutation Determine and record elite chromosome Reach last generation? Y Output the best chromosome N Figure 2; Flowchart of Genetic Algorithm.. 5.3. Implementation and case study Genetic algorithm parameters such as number o...
View Full Document

Ask a homework question - tutors are online