带有顶端增强算子的遗传算法

二进制编码遗传算法是基于演化和自然选择模型的全局优算法,加速算法的寻优速度具有重要价值,受生物界“王者”现象启发,结合内插外推理论,设计了一种加速遗传算法的顶端增强算子,该算子着眼最优个体群,以赋予适应值最大的个体群更多的操作,顶端加强算子的引入,加强了遗传寻优算法的方向性,有效地防止了算法陷入伪极值点,从而大大提高了算法的收敛速度,该算法不要求被寻优函数连续可微,不增加求解系统的次数,其增加的计算量极小,给出使用该算法对两个遗传法测试函数寻优和一个小规模的神经网络系统训练的算例,并与基本遗传算法进行了比较,仿真结果验证了该算法的有效性。

Genetic algorithm with top enhanced operator

A binary-coded genetic algorithm is a global optimizing method based on a model of evolution and natural selection, and search speed is very important to it. From the "King" phenomenon, and the theory of interpolation and extrapolation, a top enhanced operator was designed, which emphasizes on the importance of the best sub-group, and enables them to do more work. The operator improves the orientation and prevents the algorithm from falling into the pseudo-extremum, thereby improving the convergence speed. The operator does not require that the function to be optimized is continuous or differentiable. Because it is very simple and does not increase the times of system processing, the increased computation demand is very little. Some examples using Top Enhancement GA(TEGA) are given. Two are optimization of test functions, the other is a simple neural network training problem. These examples are compared with those using general GA to verify the efficiency of TEGA.