关键词: 果蝇优化算法, 多目标搜索, 背包问题

Abstract: In the practical engineering optimization problems, most of the problems are multi-objective optimization problem, multi-objective optimization problem is a research hotspot for a long time. This paper proposes a new fruit fly optimization algorithm, and successfully uses the algorithm to solve a multi-objective knapsack problem. The improved fruit fly algorithm uses clustering strategy and dynamic radius. In group A, a new feasible solution is explored from the position of population in the dynamic radius. In group B, it uses the crossover operation between the non dominated individuals. The initial location of the fly population is selected by random in the non dominated solutions. The convergence speed of the algorithm is improved greatly. By testing in multiple data sets with PSO and NSGA-2, the final results show that using the proposed algorithm under certain conditions can take the better search result, which proves the feasibility of using fruit fly optimization algorithm to solve the multi-objective problem.

Key words: Fruit Fly Optimization Algorithm（FFOA）, multiple objective search, knapsack problem