自适应遗传算法在桁架结构优化设计中的应用

交叉算子与变异算子是遗传算法中产生新个体的主要手段。针对简单遗传算法中交叉概率与变异概率随进化过程恒定不变的缺点，采用自适应的交叉、变异概率研究了针对离散变量结构优化设计的遗传算法。以在应力约束条件下的静定桁架与超静定桁架结构为算例，比较了改进交叉、变异算子前后的优化结果，并将计算结果与满应力设计方法所得结果进行了比较。结果表明，自适应遗传算法对离散变量结构优化是有效的、可行的。

Application of Adaptive Genetic Algorithms on Optimization Design of Truss Structure

Crossover operator and mutation operator are the main methods that generate new individuals in genetic algorithms. Because of the simple GA's shortcomings, that are,crossover probability and mutation probability keep constant, adaptive crossover probability and mutation probability in the research of GA for discrete variables optimization design is presented in this paper. The optimal results are compared with the solutions that are obtained by the fully stress method by examples on optimum design for a statically determinate truss structure and a statically indeterminate one with discrete variables. The results indicate that the algorithm proposed in this paper is effective and feasible.