关键词: 人工智能, 平滑函数, 全局优化, 进化算法, 全局收敛性

Abstract: In order to make the evolutionary algorithms escape from local minima in solving global optimization problems, a smooth function was introduced. This function can eliminate all such local optimal which are worse than the optimal solutions found so far. Taking the properties of the smooth function into consideration, a crossover operator was designed which can find the descent direction of the real function by using the relationship between the smooth function and the population. A mutation operator was constructed to increase the diversity of the population. Finally, an evolutionary algorithm for global optimization problems was proposed. The global convergence of the proposed algorithm is theoretically verified and its effectiveness is demonstrated by numerical simulations for all test functions.

Key words: artificial intelligence, smooth function, global optimization, evolutionary algorithm, global convergence