中文摘要：

为了改进基本遗传算法的早熟收敛、随机漫游，验证改进后的算法在七木工程中的应用效果，提出4点改进措施，形成自适应遗传算法。利用混沌序列的“遍历性、随机性、规律性”的特点生成初始种群：引入适应度的指数尺度变换；提出自适应的交叉、变异概率公式：幅度系数调节交叉率、变异率。改进后的优化结果与基本遗传算法进行了对比，在进化时间、收敛精度上得到提高。通过土木工程中桁架结构非对称受荷的数值算例，证明白适应改进遗传算法是现实可行的。

英文摘要：

In order to improve basic genetic algorithm＇s premature convergence and random roam and verify improved algorithm＇s application effect in civil engineering, the article brings forward four improved measures, with which adaptive and improved genetic algorithm came into being. By the use of the chaos serial＇s properties of ＂ergodicity, randomness, regularity＂, original population is generated. Fitness index scaling is adopted. Adaptive crossover and mutation rate formula are presented. Crossover rate and mutation rate are adjusted by extent coefficient. Improved optimal result is compared with basic genetic algorithm. Evolution time and convergence precision are increased. By a numerical example of bar truss structure with unsymmetrical loads in civil engineering, adaptive and improved genetic algorithm is feasible.