关键词: 智能计算, 果蝇算法, 分群策略, 非线性函数

Abstract: For the traditional fruit flies optimization algorithm has the disadvantage of low optimization accuracy and easily
falls into local minimum point, this paper proposes a group search strategy which has different radii of flight to greatly
increase the population diversity of fruit flies in the search region. In the fruit flies individual flight distance and step function, it introduces different functions into different fruit fliessubgroups. Those functions have cycle oscillation properties.
It can well avoid flies group into local minimum point to get the optimal solution. Through the simulation experiment for
the eight test functions, it verifies these strategies can effectively improve the search precision, convergence speed and
stability.

Key words: intelligent computing, fruit flies algorithm, group search strategy, nonlinear function