将遗传算法（GA）和模拟退火（SA）应用于飞机方案优化设计，给出了算法实现过程。对同一算例进行了优化实验，对二者进行了对比分析。实验结果表明SA达到收敛所需迭代次数及方案分析次数远较GA为多，但其优化结果要好于GA。这两类非数值优化方法应用于实际的飞机方案优化问题，必须首先解决由于所需方案分析次数太多而导致的计算效率低下问题。相对而言GA较SA在实际飞机方案设计中有更好的应用前景。

Two non-numerical optimization algorithms, genetic algorithm (GA) and simulated annealing (SA), were applied to aircraft conceptual optimization design. The implementation details of these two algorithms were discussed. Optimization experiments were conducted for the same design example comprising simple aircraft scheme analysis models, through which the two algorithms were compared. The experimental results show that both the iteration number and the scheme analysis number required by SA are much greater than GA, while the optimal result of SA is better than that of GA. The issue of low computational efficiency due to large scheme analysis numbers must be settled firstly otherwise these two non-numerical algorithms will be inapplicable to prartical aircraft conceptual optimization problems. Comparatively, GA has better application foreground than SA in practical aircraft conceptual optimization.