智能优化算法在飞机总体设计中的应用

Application of Intelligent Optimization Algorithm on Aircraft Configuration Design

飞机总体设计在飞机的整个设计过程中是非常关键的步骤,在这个过程中,飞机的总体布局和许多重要参数都被确定下来。但是,飞机的总体设计又是一个复杂和艰难的过程,因为涉及到大型系统的有约束的非线性优化问题,用传统优化方法很难得到满意的结果。本文采用了近年来发展很快的几种智能优化算法——遗传算法、模拟退火算法、禁忌搜索算法、Hopfield神经网络算法解决飞机总体设计优化问题,阐述了各算法的关键步骤及运行过程,并编写了相应的计算程序。通过对各种算法的结果进行比较和讨论,最后的结论是:模拟退火算法最适合求解这类复杂的约束非线性优化问题,禁忌搜索算法和遗传算法次之,Hopfield神经网络算法效果最差,容易陷入局部最优解。

Aircraft configuration design is a very important part in overall aircraft design,because the general layout and many crucial parameters of the aircraft will be determined in the process.However,it is so complex and difficult that achieving an optimal solution is almost impossible with traditional optimization approaches for the nonlinear optimization of a large system.In this article,several intelligent optimization algorithms that have been developing rapidly in recent years are introduced to solve the problem of aircraft configuration design,namely,the genetic algorithm（GA）,simulated annealing（SA）,tabu search（TS） and Hopfield neural network（HNN）.The key approaches and their operation are elaborated and their corresponding computer codes are programmed.By comparing and analyzing the results of these methods,it is shown that simulated annealing is most appropriate for solving these complicated nonlinear optimization problems.Tabu search and genetic algorithm come next,while the result of Hopfield neural network is least ideal owing to its tendency to fall easily into local optimization.