Abstract: Aiming at the short.comings of the fruit fly optimization algorithm,such as slow convergence speed,low convergence accuracy and only positive values of candidate solutions,an  improved fruit fly optimization algorithm based on double strategies co-evolution was proposed.One of the two carefully constructed evolutionary strategies was randomly selected as the olfactory search operator of the current individual according to the probability.Thus the olfactory search mechanism of the hybrid coevolution with two strategies was formed,which could reasonably balance the global exploration and local exploitation of the algorithm.Through the introduction of the real-time visual updating strategy and the initializing population method with good point set,the initial swarm had better diversity,and the convergence rate of the algorithm was also effectively accelerated.The feasibility and effectiveness of the proposed algorithm were verified by using the classical benchmark functions and the inverse kinematics of the planar redundant manipulator.The simulation results indicated that the proposed algorithm was outperformed with superior convergence rate,convergence accuracy and results stability.

Key words: fruit fly optimization algorithm, good point set, double strategies, co-evolutionary, manipulator, inverse kinematics

摘要： 针对果蝇优化算法收敛速度慢、收敛精度低以及候选解只能取正值等不足,提出一种基于双策略协同进化的改进果蝇优化算法,该算法按概率从两个精心构造的进化策略中随机选择其中一个策略,作为当前果蝇个体的嗅觉搜索操作算子,进而形成两个策略混合协同进化的嗅觉搜索机制,达到合理兼顾算法全局探索与局部开发的目的,大幅度提升算法的收敛质量。此外,通过引入佳点集初始化种群方法以及实时视觉更新策略,使初始种群具有较好的多样性,同时加快了算法的收敛速度。借助经典的基准测试函数和平面冗余机械臂的逆运动学求解验证了所提算法的可行性与有效性。结果表明;该算法在寻优速度、精度以及结果稳定性等方面明显优于对比算法。

关键词: 果蝇优化算法, 佳点集, 双策略, 协同进化, 机械臂, 逆运动学