Abstract: Aiming at the weakness premature convergence and slow convergence velocity of evolutionary programming algorithm，combining the improved random search method with evolutionary programming，a self-adjusting evolutionary programming algorithm is proposed.In this algorithm，the mutation is carried out using the Gaussian mutation operator.Using the improved random search method to make the mutation of individual self-adjusting，enhance the individual capacity of evolution in the direction of high fitness，increase the diversity among individual differences，and then improve the performance of the algorithm.Simulations based on benchmarks confirm that this algorithm is better than classical evolutionary programming algorithm in the aspects of global optimization，convergence speed and the robustness.

Key words: evolutionary programming, premature convergence, improved random search method, self-adjusting

摘要： 针对进化规划算法收敛速度慢和早熟收敛的缺点，将改进的随机搜索方法和进化规划算法相结合，提出了一种自调整的进化规划算法。在该算法中，使用高斯变异算子对个体进行变异，利用改进的随机搜索方法对个体变异进行自调整，提升了个体向适应度高的方向进化的能力，提高了个体间的多样性差异，从而改善算法的性能。对该算法性能进行典型算例的数字仿真证明该算法具有良好的性能。

关键词: 进化规划, 早熟收敛, 改进的随机搜索方法, 自调整