论文部分内容阅读
交叉操作和变异操作是遗传算法的两种基本操作,遗传算法的收敛速度在很大程度上与交叉概率和变异概率的选取以及交叉个体的配对策略有关。本文提出一种基于距离测度的改进自适应遗传退火算法,根据个体的距离密集度自适应地确定其交叉概率和变异概率。算法采用非等概率交叉配对策略,根据两个个体之间的距离自适应地确定交叉配对概率。此外,算法引入模拟退火机制,在遗传进化过程中的每一代,对最优个体进行邻域局部寻优,利用模拟退火进一步改善算法的收敛性能。对带边界约束函数优化问题进行了仿真计算,结果表明了该算法的有效性。
The crossover operation and mutation operation are two basic operations of genetic algorithm. The convergence speed of genetic algorithm is largely related to the selection of crossover probability and mutation probability and the crossover individual mating strategy. In this paper, an improved adaptive genetic annealing algorithm based on distance measure is proposed, whose crossover probability and mutation probability are adaptively determined according to individual distance density. The algorithm uses non-equal-probability cross-matching strategy to adaptively determine the cross-matching probability according to the distance between two individuals. In addition, the algorithm introduces a simulated annealing mechanism. During each generation in the process of genetic evolution, the local optimum of the individual is optimized. Simulated annealing is used to further improve the convergence performance of the algorithm. The simulation of the optimization problem with boundary constraint function is carried out. The results show the effectiveness of the algorithm.