一种求解数值优化问题的快速进化规划算法

步长变量(自适应参数)是影响进化规划算法性能的一个重要参数，但该参数往往减小较快导致搜索速度下降或早熟收敛。针对这一问题，对变异算子进行了改进，对成功的变异进行适当延伸，当个体变异失败时，对变异量实施Gauss或Cauchy扰动，从而使精细化搜索和大范围搜索有机结合起来。对若干经典算例的仿真实验表明该算法的有效性。

An Improved Fast Evolutionary Programming for Numerical Optimization Problems

The adaptive parameters play a significant role in Evolutionary Programming (EP), which control the progress rate of the objective function in the evolutionary process. However, they are frequently lost and then make the search stagnate early or premature converge. A new mutation operator is proposed aiming at solving these problems. An extension operation is performed in order to make full use of the good mutation direction if the offspring is better than its parent. Otherwise, a Gaussian or Cauchy perturbation is superimposed on the mutation vector based on the parents performance. So the fine-tuning search ability of the Gaussian mutation and the coarse-grained search ability of the Cauchy mutation are combined efficiently. The experimental results show that the improved algorithm performs better than the classical EP for many benchmark problems.