论文部分内容阅读
【目的】针对引力搜索算法在求解优化问题时易陷入局部极值问题,提出了一种自适应混合变异的引力搜索算法。【方法】采用动态调整粒子速度和位置的更新公式,提高算法搜索精度。引入变异算子,对最优粒子进行高斯变异,对非最优粒子进行自适应t分布变异。【结果】提高算法在求解函数优化问题时的全局探索能力和局部开发能力。【结论】用9个标准测试函数的仿真实验,与标准GSA及改进算法进行比较,结果表明所提出算法具有较强的收敛精度和鲁棒性。
【Objective】 Aimed at the problem of gravitational search algorithm falling into local extreme when solving optimization problems, a gravitation search algorithm based on adaptive hybrid mutation is proposed. 【Method】 The updating formula of particle velocity and position was dynamically adjusted to improve the searching accuracy of the algorithm. The mutation operator is introduced to perform Gaussian mutation on the optimal particle and the adaptive t distribution variation on the non-optimal particle. 【Result】 The global exploration ability and local development ability of the algorithm in solving the function optimization problem are improved. 【Conclusion】 Compared with the standard GSA and the improved algorithm, the simulation results of nine standard test functions show that the proposed algorithm has better convergence accuracy and robustness.