论文部分内容阅读
在机械或结构的优化设计中 ,普遍存在约束的作用 ,且最优解往往位于可行域的边界上。由于外界环境的变化或人为因素造成设计变量扰动 ,可能使设计成为不可行。本文提出了一种的基于设计变量敏感性的健壮性设计方法 ,并提出了一种用 Pareto遗传算法来实施的带约束的多目标优化方法以求解健壮性问题。 Pareto遗传算法可得到 Pareto最优解集 ,从中可选出满足设计需要的解。本文提出的算法包括 5个基本算子 :选择、变异、交叉、小生境技术、Pareto集合过滤器。文中用算例说明该方法的应用
In the optimization of mechanical or structural design, there is a universal constraint, and the optimal solution is often located in the border of feasible region. Due to changes in the external environment or human factors caused by design variables perturbation, may make the design becomes not feasible. This paper presents a robust design method based on the sensitivity of design variables and proposes a constrained multi-objective optimization method using Pareto genetic algorithm to solve the robustness problem. Pareto genetic algorithm can be Pareto optimal solution set, which can be selected to meet the design needs of the solution. The proposed algorithm includes five basic operators: selection, mutation, crossover, niche technology, Pareto set filter. An example is given to illustrate the application of this method