改进的遗传算法在Logistic曲线拟合中的应用

Application of the Improved Genetic Algorithm in Logistic Curve Fitting

针对简单GA在拟合Logistic曲线中存在的易产生早熟收敛、得到的结果可能为非全局最优收敛解以及在进化后期搜索效率降低的缺陷,引入动态自适应策略调整交叉概率和变异概率,对简单GA进行改进,从而在提高收敛速度的同时,又能使得拟合曲线的均方误差减小。数值实验表明,改进的遗传算法的拟合精度有了明显的提高。

According to the shortage of simple genetic algorithm in solving Logistic curve fitting ： easy to produce premature conver- gence, easy to fall into local optimal equilibrium states, poor efficiency at evolutionary late stage, an dynamic adaptive strategy was introduced to adjust the crossing probability and mutating probability and to improve GA. Numerical experiments illustrate that the improved algorithm is feasible and effective, which improves convergence speed and reduces square error sum of curve fitting.