欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出了一种基于正交交叉算子的元胞差分进化算法.进化初期采用反学习初始化方法获得初始候选种群,利用元胞结构的局部搜索方法替代控制参数调节差分进化算法的选择压力,从而平衡差分进化算法的探索能力和开发能力,利用元胞自动机的并行演化机制保持种群的多样性,从而避免陷入局部最优.该算法利用无交叉因子的正交交叉算子,通过多元素重复试验加速种群收敛速度.对多个典型测试函数的仿真实验结果表明,所提出的算法相较于多个差分进化改进算法具有更快的收敛速度和更好的计算精度.
英文摘要：
A cellular differential evolution （cDE）algorithm based on orthogonal crossover is presented. The opposition-based learning initialization is used to search better solution in the initial stage, the local search within cellular neighbourhood structure is presented to tune the selection pressure instead of the control parameters. And the parallel evolution mechanism of cellular automata is given to ensure the diversity of the evolution population. In addition, the orthogonal crossover is adopted to accelerate the convergence speed with multi-element repeated trials. The performance of the cDE algorithm is evaluated on a suite of classic benchmark functions and compared favorably with the canonical DE and several DE variants. Simulation shows the proposed algorithm has better convergence performance and higher calculation accuracy.
同期刊论文项目
同项目期刊论文
期刊信息
位置：