In order to balance the convergence rate and the global searching ability and overcome the premature convergence of the differential evolution algorithm, a modified differential evolution algorithm based on Gauss mutation (GMDE) was proposed. The paper provided a detailed a-nalysis of population diversity descent and individual stagnant evolution and then incorporated the Gauss mutation into differential evolution. The optimization performance of GMDE was evaluated and the results of numerical simulation and two engineering optimization design examples show that the proposed algorithm can overcome the premature convergence efficiently and can obtain a better balance of convergence rate and the global searching ability.%为平衡算法收敛速度和全局搜索能力,克服差分进化算法易“早熟”的缺陷,在分析引起种群多样性下降及个体进化停滞原因的基础上,通过引入高斯变异操作,提出了基于高斯变异改进的差分进化算法(modified differential evolution base on Gauss mutation,GMDE).数值仿真及2个工程优化问题的求解结果表明本文算法能有效避免“早熟”收敛,且在算法收敛速度和全局搜索能力上取得了较好的平衡.
展开▼
