论文部分内容阅读
针对遗传算法在处理多峰优化问题时容易发生早熟现象的问题,采用了动态调整交叉概率值和变异概率值的方法,引入爬山法在迭代过程中进行局部寻优,仿真实验对比分析了标准遗传算法和改进遗传算法的性能.研究结果表明:改进后遗传算法的收敛速度较快,得到结果误差值比较小.研究结论证明在相应的进化阶段采用合理的概率值,利用爬山法对遗传算法局部寻优,可以避免早熟现象,提高遗传算法收敛速度和精度.
Aiming at the problem that genetic algorithm is prone to premature phenomenon when dealing with multi-peak optimization problem, the method of dynamically adjusting crossover probability and mutation probability is adopted. The method of hill-climbing is introduced to find the optimal solution during the iterative process. Simulations are performed to compare the standard genetic Algorithm and improved genetic algorithm.The results show that the improved genetic algorithm has a faster convergence rate and a smaller error result.Research conclusions show that using reasonable probability value in the corresponding evolutionary stages and using the hill-climbing method to localize the genetic algorithm Optimized, you can avoid premature phenomenon, improve the convergence speed and accuracy of genetic algorithm.