中文摘要：

针对进化规划在进化搜索过程中存在较多非法个体这一问题，提出一种新的自适应进化规划算法。该算法根据混沌序列的特性，将混沌序列引入到进化规划的变异算子中。理论分析和实验表明，与基于Guassian变异的进化规划相比，该算法不仅具有良好的快速收敛性和鲁棒性，而且能够有效地消除非法解，计算简单、容易实现。

英文摘要：

Some of the mutation individuals fell outside of the defined space in evolutionary search process. To solve the problem, a novel self-adaptive evolution programming algorithm was proposed. According to chaos sequence characteristic, this algorithm introduced the chaos sequence in the mutation operator of evolution programming. Theory analysis and experiment show that the proposed scheme has good fast astringency and robustness compared with evolution programming based on Guassian mutation. Furthermore, it eliminates all illegal individuals effectively as soon as they appear,