Flight schedule design and fleet assignment are the main sub problems of the airline schedule planning which have the most effect on the costs and profit of the airline. In this paper, integrated flight schedule design and fleet assignment problem is described and genetic algorithm has been developed to solve this problem. It has numbers of constraints and multi-layer permutation chromosomes with variable length. So, creating the initial population randomly and use of customary operators of evolutionary algorithms will not be efficient since the probability of feasibility is very low. For this purpose, a new function based on loop concept to create an initial population and new crossover and mutation operators have been developed. A genetic algorithm has been used within the main loop to optimize the redirection of the passengers. Four models with different numbers of airports and fleets are created as an input for the problem which have been solved by two and three islands genetic algorithms. Results show that in each iteration of the main loop, feasible answers are obtained and finally there was a proper improvement in the costs. In larger models, there is a better Improvement in the costs and more difference between two and three islands algorithms. Three islands mode results in a better solution within a longer time. The developed algorithm can successfully find feasible optimal solution and it can be used for high-dimensional problems in which there is no possibility to find the optimal solution by using conventional methods such as MILP.